Feeds:
Posts
Comments

Archive for the ‘Artificial Intelligence in CANCER’ Category

Live Notes from JP Morgan Healthcare Conference Virtual Endpoints Preview: January 8-9 2024

Reporter: Stephen J. Williams, Ph.D.

Endpoints at #JPM24 | Primed to unlock biopharma’s next dealmaking wave
Endpoints at JP Morgan Healthcare Conference
January 8-9 | San Francisco, CA80 Mission St, San Francisco, CA

An oasis has emerged in the biopharma money desert as backers look to replenish capital — still, uncertainty remains on whether it’s a mirage or the much needed dealmaking bump the industry needs. Yet spirits run high as JPM24 marks the triumphant return of inking strategic alliances and peering into the industry crystal ball — while keeping an eye out for some major M&A.

We’re back live from San Francisco for JPM Monday and Tuesday — our calendar of can’t-miss panels and fireside chats will feature prominent biopharma leaders to watch. The Endpoints Hub provides the ultimate coworking space with everything you need — 1:1 and group meeting spots plus guest pass capabilities and more. Join us in-person at the Endpoints Hub or watch online to stay plugged into all the action.

8 JAN
Welcome remarks
8:05 AM – 8:25 AM PST
Pfizer vet Mikael Dolsten has some thoughts on Big Pharma R&D

Endpoints News founding editor John Carroll will sit down with longtime Pfizer CSO Mikael Dolsten to talk about Pfizer’s pipeline, what he’s learned on the job about preclinical research and development and what’s ahead for the pharma giant in drug development and deals.

Mikael Dolsten

Chief Scientific Officer, President, Pfizer Research & Development

Pfizer

Pfizer Mikael Dolsten: Pfizer produced a series of AI generated molecules with new properties. Sees rapid adoption of AI in the area of drug discovery and molecular design.

 
 
8:25 AM – 9:05 AM PST
What pharma wants: The industry’s dealmakers look ahead at 2024

The drug industry’s appetite for new assets hasn’t slowed down. Top business development execs will give their outlook on the year, what they’re looking for and how they see the market.

Glenn Hunzinger

Pharmaceutical & Life Sciences Consulting Solutions Leader

PwC US

Rachna Khosla

SVP, Head of Business Development

Amgen

James Sabry

Global Head of Pharma Partnering

Roche

Devang Bhuva

SVP, Corporate Development

Gilead Sciences, Inc.

Endpoints News

Dealmaking panel

Glenn Hunzinger: if you do not have a GLP1 will have a tough time getting a good market price for your company; capital markets are not where they want to be; sees a tough deal making climate like last year.  The problem with many biotech companies are they are coming earlier to the venture capital because of greater funding needs and so it is imperative that they articulate the potential of their company in scientific detail

Rachna Khosla:  Make sure your investors are not just CAPITAL PARTNERS but use their expertise and involve them in development issues you may have, especially ones that a young firm will face.  The problem is most investments assume what the future looks like (for example how antibody drug conjugates, once a field left for dead, has been rejuvenated because of advances in chemistry). 

James Sabry: noted that cardiac and metabolic drugs are now at the focus of many investors, especially with the new anti-obesity drugs on market

Devang Bhuva: Most deals we see start as collaborations or partnerships.  You want to involve an alliance management team early in the deal making process.  This process could take years.

 
9:05 AM – 9:20 AM PST
The IPO: How Apogee Therapeutics went public in the most challenging market in years

Not many biotechs went public in 2023. And of those that did, not many have had a great time of it. Apogee is the exception and our panel will offer a behind-the-scenes look at their decision to enter the market and what life is like as a young public company.

Michael Henderson

CEO

Apogee Therapeutics

Kyle LaHucik

MODERATOR

Senior Reporter

Endpoints News

Michael Henderson:  Not many biotech IPOs deals happened in 2023.  Michael feels it is because too many biotechs focused on building platforms, which was a hard sell in 2023.  He felt not many biotechs had clear milestones and investors wanted a clear primary validated target.  He said many biotech startups are in a funding crunch and most need at least $440M on their balance sheet to get to 2026.

9:50 AM – 10:10 AM PST
Top predictions for biotech in 2024

Catalent CEO Alessandro Maselli will be back at the big JPM healthcare confab to talk with Endpoints News founder John Carroll about their top predictions of what’s coming up for the biotech industry in 2024. The stakes couldn’t be higher as the industry grapples with headwinds and new opportunities in a gale of market forces. Two top observers share their thoughts on the year ahead.

Alessandro Maselli

President & CEO

Catalent

10:15 AM – 10:35 AM PST
Innovation at a crossroads: Keys to unlocking the value of science and technology

The industry has long discussed the promise of technology and the acceleration it provides in scientific advancement and across the industry value chain. However, the promise of its impact has yet to fully be realized. This discussion will outline the keys to unleashing this promise and the implications and actions to be taken by the biopharmaceutical companies across the industry.

Ray Pressburger

North America Life Sciences Industry Lead & Global Life Sciences Strategy Lead

Accenture

SPONSORED BY

10:35 AM – 11:05 AM PST
Activism and Investing: In conversation with Elliott Investment Management’s Marc Steinberg

Elliott has been behind many of 2023’s highest-profile healthcare investments, including multiple activist engagements and taking Syneos Health private. What has made large healthcare companies such interesting investment opportunities for firms like Elliott? What’s Elliott’s investing strategy in healthcare? And what should companies expect when an activist calls?

Marc Steinberg

Senior Portfolio Manager

Elliott Investment Management

Andrew Dunn

MODERATOR

Biopharma Correspondent

Endpoints News

11:05 AM – 11:35 AM PST
Creating ROI from AI

AI is predicted to transform the way drugs are made, from discovery to clinical trials to market. But beyond the initial hype and early adoption, where has AI made meaningful contributions to R&D? How does it help drug developers advance science? Endpoints publisher Arsalan Arif is convening a panel of leading experts to discuss the state of AI in the pharmaceutical landscape and the outlook for 2024. How does AI impact the drug pipeline, from the early steps of discovery to reducing trial failure rate?

Thomas Clozel

Co-Founder & CEO

Owkin

Venkat Sethuraman

SVP, Global Biometrics & Data Sciences

Bristol Myers Squibb

Frank O. Nestle

Global Head of Research & Chief Scientific Officer

Sanofi

Matthias Evers

Chief Business Officer

Evotec

Arsalan Arif

MODERATOR

Founder & Publisher

Endpoints News

SPONSORED BY

11:35 AM – 12:00 PM PST
Biopharma’s dealmaker: Behind the scenes with Centerview Partners co-president Eric Tokat

Almost every major biopharma deal in 2023 had Centerview’s name attached to it. And much of the time, Eric Tokat was the banker making those deals happen. Hear his outlook for 2024, how transactions are getting done and what’s placed his firm at the center of so much action.

E. Eric Tokat

Co-President, Investment Banking

Centerview Partners

CenterView Partners Eric Tokat feels dealmaking will improve in 2024, given the recent flurry of dealmaking at end of last year and right before main JPM Healthcare Conference.  He says Centerview wants to help the biotechs they invest in on their strategic path.  This may translate into buyers more actively involved (more than startups want) and buyers now are in the drivers seat as far as the timeline of deals and development.

Is the megamerger dead for this year?  He says it is very hard to see two major mergers happening but there will be many smaller and mid size biotech deals happening, but these deals will be more speculative in nature..  The focus for large pharma is top line growth.  Most of the buyers have an infrastructure and value is more of buying and dropping it in their business so there is now a huge emphasis on due diligence on whether synergies exist or not

 
12:00 PM – 12:30 PM PST
Founder, legend, leader: In conversation with Nobel laureate Carolyn Bertozzi

Carolyn Bertozzi’s discoveries around bioorthogonal chemistry won the Nobel Prize in Chemistry in 2022 and are at the heart of new therapies being tested in patients. Join us as we discuss what inspires her and where she sees the next big advances.

Carolyn Bertozzi

Prof. of Chemistry, Stanford University and Baker Family Director of Sarafan ChEM-H

Stanford University

Nicole DeFeudis

MODERATOR

Editor

Endpoints News

Bioorthogonal chemistry: class of high yielding chemical reactions that proceed rapidly and selectively in biological environments without side reactions toward endogenous functions.  This is also a type of ‘click chemistry’ in biological system where only specifically alter the biomolecule of interest.

Orthogonal: two chemicals not interacting with each other

Dr. Bertozzi noted she has started a new Antibody-Drug-Conjugate (ADC) company which involves designing with biorthogonal chemistry to make new functional molecules with varying properties

She noted hardly any biologists knew anything about glycobiology when she first started.  However now she feels pharma and academia are working very well with each other

Bioorthogonal and Click Chemistry
Curated by Prof. Carolyn R. Bertozzi, 2022 winner of the Nobel Prize in Chemistry

Source: https://pubs.acs.org/page/vi/bioorthogonal-click-chemistry

The 2022 Nobel Prize in Chemistry has been awarded jointly to ACS Central Science Editor-in-Chief, Carolyn R. Bertozzi of Stanford University, Morten Meldal of the University of Copenhagen, and K. Barry Sharpless of Scripps Research, for the development of click chemistry and bioorthogonal chemistry.

To celebrate this remarkable achievement, 2022 Nobel Prize winner Professor Carolyn R. Bertozzi has curated this Bioorthogonal and Click Chemistry Virtual Issue, highlighting papers published across ACS journals that have built upon the foundational work in this exciting area of chemistry.

From Mechanism to Mouse: A Tale of Two Bioorthogonal Reactions

Ellen M. Sletten and Carolyn R. Bertozzi* Acc. Chem. Res. 2011, 44, 9, 666-676 August 15, 2011

Abstract

Bioorthogonal reactions are chemical reactions that neither interact with nor interfere with a biological system. The participating functional groups must be inert to biological moieties, must selectively reactive with each other under biocompatible conditions, and, for in vivo applications, must be nontoxic to cells and organisms. Additionally, it is helpful if one reactive group is small and therefore minimally perturbing of a biomolecule into which it has been introduced either chemically or biosynthetically. Examples from the past decade suggest that a promising strategy for bioorthogonal reaction development begins with an analysis of functional group and reactivity space outside those defined by nature. Issues such as stability of reactants and products (particularly in water), kinetics, and unwanted side reactivity with biofunctionalities must be addressed, ideally guided by detailed mechanistic studies. Finally, the reaction must be tested in a variety of environments, escalating from aqueous media to biomolecule solutions to cultured cells and, for the most optimized transformations, to live organisms.

9 JAN

9:40 AM – 10:10 AM PST

Biotech downturn survival school

Our panelists have seen the worst, and made it through to the other side. Join us for downturn survival school as our panelists talk about what sets apart the ones who make it through tough times.

These panalists think it will be specialist capital year to shine while the general capital is still sitting on the sidelines

JJ Kang

CEO

Appia Bio

“2023 was a tough year while 2020 was a boon year to start a company.  We will continue to see these cycles; many of these new CEOs have never seen a biotech downturn yet and may not know how to preserve capital for the downturn”.

“Doing a partnership with Kite Pharmaceuticals early in our startp allowed us to get work done without risking a lot of capital, even if it means equity and asset dilution.  That makes sense. However even if you are small insist on being an equal partner.”

“There are many investors we talk to who do not want to invest in cell therapy.  Too risky now”

Carl Gordon

Managing Partner

OrbiMed Advisors

There are many macroeconomic factors affecting investment and capital today which will carry on through 2024.   Not raising money when you do not need money is a bad philosophy.  Always bbe raising captial.  This is especially true when you have to rely on hedge funds.  Parnerships howeve are sometimes the only way for small biotechs to leverage their strengths.

Joshua Boger

Executive Chair

Alkeus Pharmaceuticals, Inc.

Boger: Expect volatility for 2024.  This environment feels very different than past downturns.

Even in downturns there is still lots of capital; remember access to human capital is better in a downturn and is easier to access;  however it has become harder to get drug approvals

The panelists agree that access to capital and funding will be as tricky in 2024 than 2023.  They did

suggest that a new funding avenue, private credit, may be a source of capital.  This is discussed below:

When thinking about a private alternative investment asset class, the first thing that springs to mind is private equity. But there’s one more asset class with the word private in its name that has recently gained much attention. We’re talking about private credit

Indeed, this once little-known investment strategy is now growing rapidly in popularity, offering private investors worldwide an exciting opportunity to diversify their portfolio with, in theory, less risky investments that yield significant returns. 

  • Private credit investments refer to investors lending money to companies who then repay the loan at a given interest rate within the predetermined period.
  • The private credit market has grown significantly over the past years, rising from $875 million in 2020 to $1.4 trillion at the beginning of 2023. 

Please WATCH VIDEO BY GOLDMAN SACHS ON PRIVATE CREDIT

 

 

 

 

10:50 AM – 11:20 AM PST

The New Molecule: How breakthrough technologies are actually changing pharma R&D

Join us for a look at how AI, machine learning and generative technologies are actually being applied inside drugmakers’ labs. We’ll explore how new technologies are being used, their implications, how they intersect with regulatory and IP issues and how this fast-changing field is likely to evolve.

Kailash Swarna

Managing Director & Global Life Sciences Clinical Development Lead

Accenture

Artificial Intelligence is making impact in a grand way on biology in three aspects:

  1. Speeding up target validation: now we can get through 300 molecules a day
  2. Predicition like AlphaFold is doing; molecular simulations
  3. Document submission especially with regulatory and IND submissions

Pamela Carroll

COO

Isomorphic Labs formerly of AlphaFold

We were first with Novartis at last year JPM and was one year old but parnering with them in that initial year was very important for sealing the deal.

They are looking now at neurologic diseases like ALS.  She wondered whether ALS is actually multiple diseases and we need to stratify patients like we do in oncology trials.  Their main competion is the whole tech world like Amazon, Google and other Machine Learning companies so being a tech player in the biotech world means you are not just competing with other biotechs but large tech companies as well.

Jorge Conde

General Partner

Andreessen Horowitz

Need is still great for drug discovery; early adopters show AI tools can be used in big pharma. There are lots of applications of AI in managing care; a lot of back office applications including patient triaging.  He does not see big AI mergers with pharma companies –  this will be mainly partnerships not M&A deals

Alicyn Campbell

Chief Scientific Officer

Evinova, a Healthtech Subsidiary of the AstraZeneca Group

There is a need to turn AI for real world example.  For example AI tools were used in clinical trials to determine patient cohorts with pneumonitis.  At Evinova they are determining how AI can hel[p show clinical benefit with respect to efficacy and safety

Joshua Boger at #JPM24 (Brian Benton Photography)

  January 12, 2024 09:06 AM ESTUpdated 10:00 AM PeopleStartups

Vertex founder Joshua Boger on surviving downturns, ‘painful’ partnerships, and the importance of culture: #JPM24

Andrew Dunn

Biopharma Correspondent

Source: https://endpts.com/jpm24-vertex-founder-joshua-boger-on-surviving-downturns-painful-partnerships-and-the-importance-of-culture/

While the JP Morgan Healthcare Conference was full of voices of measured optimism, rooting for the market to bounce back in 2024, one longtime biotech leader warned against setting any firm expectations.

Instead of predicting when the downturn may end, Vertex Pharmaceuticals founder Joshua Boger said he advises biotech leaders to expect — and plan for — volatility. Speaking Tuesday on an Endpoints News panel alongside OrbiMed’s Carl Gordon and Appia Bio CEO JJ Kang, Boger shared lessons learned on surviving downturns, striking pharma deals, and the importance of keeping a company’s culture based on his two decades of founding and leading Vertex as CEO from 1989 to 2009. The 72-year-old is now serving as executive chairman of Alkeus Pharmaceuticals, a startup developing a rare disease drug.

“I never experienced a straight line up,” Boger said. “Everything had its cycles, and it was how you respond to the cycle, not by predicting when the end is going to be, but just by responding to the present situation.”

At Boger’s first appearance at the JP Morgan conference in 1991, he said the conference’s theme was the end of biotech financing. Just a few months later, Regeneron successfully went public, rapidly changing the outlook for the whole field.

“We had no idea we were ever going to take public money,” he said. “When Regeneron did their IPO, we went, ‘Whoa, there’s something happening here,’ and we pivoted quickly.”

Vertex went public later that year. Throughout his 20-year tenure, Boger said no pharma company ever made an acquisition offer for Vertex, which now commands a market value of $110 billion and recently won the first FDA approval for a CRISPR gene editing therapy.

“We had an uber corporate policy to always make ourselves more expensive than anyone would stomach,” Boger said.

However, Vertex did strike a range of partnerships with Big Pharmas, which Boger described as a painful but necessary part of running a biotech startup.

“It’s impossible for a partnership not to slow you down,” he said. “You can and should try as hard as you can not to do that, but just count on it. They’ll slow you down.”

Boger said startups should insist on being equal partners in pharma deals, at least making sure they have a seat at a partner’s development meetings.

“Realize they’re going to be painful, it’s going to be horrible, and you need to do it,” Boger said.

While Vertex suffered through layoffs, stock price plunges, and trial failures, Boger credited a focus on culture as key to its long-term success.

“It’s the most important ingredient for a successful company,” he said. “Technology is acquirable. Culture is not acquirable. There are 10 companies that will fail because of culture for every one that succeeds, and the successful companies in retrospect will almost always have special cultural aspects that kept them through those downtimes.”

JPM24 opens with ADCs the hottest ticket in San Francisco

By Annalee ArmstrongJan 8, 2024 6:30am

Source: https://www.fiercebiotech.com/biotech/jpm24-opens-adcs-hottest-ticket-san-francisco

The overall deal flow in biopharma tapered off in 2023 but the big companies sure know what they want (what they really, really want), according to a new report from J.P. Morgan.

And that’s antibody-drug conjugates, which drove a fourth-quarter spike in licensing deal proceeds and provided a glimmer of hope to an industry battered by outside forces and grim financing prospects.

J.P. Morgan’s annual 2023 Biopharma Licensing and Venture Report arrived on the eve of the firm’s famous conference, which is set to welcome thousands of attendees in San Francisco today—East Coast weather permitting.

2023 was tough, but clinical biotechs still had a lot of opportunities to wheel and deal, according to J.P. Morgan. While licensing deals, venture investments, M&A and IPOs were down overall in the fourth quarter, deal values stayed fairly high thanks to a flurry of late-stage tie ups.

Follow the Fierce team’s coverage of the 2024 J.P. Morgan Healthcare Conference here

Biopharma licensing partnerships accounted for $63 billion in total value during the fourth quarter from 108 deals. Just one deal—Merck’s ADC partnership with Daiichi Sankyo—accounted for $22 billion of that. Another huge one was another ADC bet, with Bristol Myers Squibb signing on to work with SystImmune for a total value of $8.4 billion. If you exclude the Merck deal, the total value of these partnerships is still higher than the previous quarter, which ended with $32.1 billion.

The total number of licensing deals compares to 149 in the same quarter a year earlier, 195 for Q4 2021 and 223 for Q4 2022.

As for venture investments, the year closed out with $17 billion total across 250 rounds, thanks to $3.5 billion earned through 79 rounds in the last quarter. Aiolos Bio snagged the title of largest venture round of the quarter with $245 million, which also proved to be the largest series A, too.

There was just one IPO in all of the fourth quarter—Cargo Therapeutics making the plunge for $300 million—and 13 overall for the year. It’s a far cry from the heyday of 2021 and experts are still unsure what 2024 will hold. J.P. Morgan reported $2.5 billion raised from 12 completed biopharma IPOs for the year on Nasdaq and NYSE. Nine out of the 12 companies had clinical programs when they took the leap to the public markets. As of December 13, five of the companies were trading above their IPO price.

As for M&A, December saw a rush of Big Pharmas snapping up companies around Christmas. J.P. Morgan tallied the fourth quarter at $37.6 billion and $128.8 billion across 112 total acquisitions for all of 2023.

AbbVie was the top buyer of the quarter with the two largest acquisitions thanks to the $10 billion outlay for ImmunoGen and $8.7 billion buy of Cerevel Therapeutics.

All of this adds up to 270 total deals in the fourth quarter total, which is lower than the third quarter which exceeded 300.

J.P. Morgan sees some big potential for smaller biopharmas looking for licensing partners, as Big Pharmas have been handing out larger upfront payments for the deals they really want.

Cancer was once again the most in-demand therapeutic areas, reaching a new height of $86.1 billion in 2023. Followed by $21.1 billion for neurological disorders.

For More Articles on Real Time Conference Coverage in this Open Access Scientific Journal see:

Part One: The Process of Real Time Coverage using Social Media

Part Two: List of BioTech Conferences 2013 to Present

https://worldmedicalinnovation.org/

https://pharmaceuticalintelligence.com/2022/05/01/2022-world-medical-innovation-forum-gene-cell-therapy-may-2-4-2022-boston-in-person/

 

https://event.technologyreview.com/emtech-digital-2022/agenda-overview

 

Read Full Post »

The Continued Impact and Possibilities of AI in Medical and Pharmaceutical Industry Practices

Reporter: Adam P. Tubman, MSc Biotechnology, Research Associate 3, Computer Graphics and AI in Drug Discovery

 

Researchers have been able to discover many ways to incorporate AI into the practices of healthcare, both in terms of medical healthcare and also in pharmaceutical drug development. For example, given the situation where a doctor provides an inaccurate diagnosis to a patient because the doctor had an incomplete or inaccurate medical record/history, AI presents a solution that has the potential to rapidly and correctly account for human error and predict the correct diagnosis based on the patterns identified in other patient’s medical history to disease diagnosis indication. In the pharmaceutical industry, companies are changing and expanding approaches to drug discovery and development given the possibilities that AI can offer. One company, Reverie Labs, located in Cambridge, MA, is a pharmaceutical company utilizing AI for application of machine learning and computational chemistry to discover new possible compounds to be used in the development of cancer treatments.

Today, AI uses have had many other applications in medicine including managing healthcare data and performing robotic surgery, both of which transform the in-person patient and doctor experience. AI has even been used to change in-person cancer patient experiences. For example, Freenome, a company in San Francisco, CA uses AI in initial screenings, blood tests and diagnostic tests when a patient is being initially tested for cancer. The hope is that this technology will aide in speeding up cancer diagnoses and lead to new treatment developments.

The future will continue to bring many possibilities of AI, provided an acceptable level of accuracy is still maintained by AI technologies and that the technology remains beneficial. If research continues to focus on diagnosing diseases at a faster rate given the potential human errors in having an inaccurate or incomplete medical record upon diagnosis, AI could provide an improved experience for patients given the quicker diagnosis and treatment combined with less time spent either treating the wrong underlying condition or not knowing what condition to treat when accounting for an incomplete medical record. If this technology is proven to be successful not just in theory, but in practice, technology would then be available and could be beneficially applied to all diagnoses and treatment plans, across the world.

However, the reality regarding AI development is that its evolution depends on how much human effort is involved in its development. Therefore, the world won’t know or see the full benefits of AI until it is developed and actively applied. Similarly, the impact that AI will have in medical and pharmaceutical practices won’t be known until scientists fully develop and apply the technologies. Many possibilities, including a possible drastic lowering of the cost for pharmaceutical drugs across the board once drugs are much more readily discovered and produced, may carry a profound benefit to patients who currently struggle to afford their own treatment plans. Additionally, unforeseen advances in the medicinal and pharmaceutical fields because of AI development will lead to unforeseen effects on the global economy and many other life changing variables for the entire world.

For more information on this topic, please check out the article below.

SOURCE

Daley, S. (2018). Artificial Intelligence in healthcare: 39 examples Improving the Future of Medicine. Built In. https://builtin.com/artificial-intelligence/artificial-intelligence-healthcare

Read Full Post »

The Use of ChatGPT in the World of BioInformatics and Cancer Research and Development of BioGPT by MIT

Curator: Stephen J. Williams, Ph.D.

Chatbots are being used in multiple interdisciplanary areas in research and medicine and so it was a natural progression to incorporate artificial intelligence (AI), natural language processing (NLP), and chatbot technology like ChatGPT into bioinformatic analysis.

“In domains like informatics, management and marketing, media and communication science, languages and philosophy, psychology and sociology, engineering, design, and human-computer interaction, the fast expanding body of chatbot study is clearly interdisciplinary.

The field of bioinformatics is a natural fit for incorporting this technology.  The curated information below shows some use examples of this technology in bioinformatics related to cancer research.

The text in this reference source was actually generated by ChatGPT (https://chat.openai.com/chat)

Source: https://omicstutorials.com/using-chatgpt-in-bioinformatics-and-biomedical-research/

How ChatGPT can be used in bioinformatics research?
ChatGPT is a variant of the GPT (Generative Pre-trained Transformer) language model that was designed to generate human-like text in a conversational setting. It is not directly related to bioinformatics, which is the field of study that deals with the storage, retrieval, and analysis of biological data, particularly in the context of genetics and genomics. However, ChatGPT could potentially be used in a bioinformatics context as a tool for generating natural language descriptions of genetic or genomic data, or for generating responses to queries about such data.

For example, a researcher could use ChatGPT to generate descriptions of genetic variants or gene expression patterns based on input data. This could be useful for generating summaries of results for reports or papers, or for generating explanations of complex concepts for non-expert audiences. ChatGPT could also be used to generate responses to queries about genetic or genomic data, such as “What is the function of gene X?” or “What are the potential consequences of variant Y?”

It’s worth noting that ChatGPT is just one of many tools and techniques that can be used in bioinformatics, and it is unlikely to be the most suitable or effective option in every situation. There are many specialized tools and resources available for working with biological data, and it is often necessary to use a combination of these tools to fully analyze and understand the data.

Generating descriptions of genetic or genomic data: ChatGPT could be used to generate natural language descriptions of genetic or genomic data based on input data. For example, suppose a researcher has a dataset containing information about gene expression levels in different tissues. The researcher could use ChatGPT to generate a description of the data, such as:
“Gene X is highly expressed in the liver and kidney, with moderate expression in the brain and heart. Gene Y, on the other hand, shows low expression in all tissues except for the lung, where it is highly expressed.”

 

Thereby ChatGPT, at its simplest level, could be used to ask general questions like “What is the function of gene product X?” and a ChatGPT could give a reasonable response without the scientist having to browse through even highly curated databases lie GeneCards or UniProt or GenBank.  Or even “What are potential interactors of Gene X, validated by yeast two hybrid?” without even going to the curated InterActome databases or using expensive software like Genie.

Summarizing results: ChatGPT could be used to generate summaries of results from genetic or genomic studies. For example, a researcher might use ChatGPT to generate a summary of a study that found a association between a particular genetic variant and a particular disease. The summary might look something like this:
“Our study found that individuals with the variant form of gene X are more likely to develop disease Y. Further analysis revealed that this variant is associated with changes in gene expression that may contribute to the development of the disease.”

It’s worth noting that ChatGPT is just one tool that could potentially be used in these types of applications, and it is likely to be most effective when used in combination with other bioinformatics tools and resources. For example, a researcher might use ChatGPT to generate a summary of results, but would also need to use other tools to analyze the data and confirm the findings.

ChatGPT is a variant of the GPT (Generative Pre-training Transformer) language model that is designed for open-domain conversation. It is not specifically designed for generating descriptions of genetic variants or gene expression patterns, but it can potentially be used for this purpose if you provide it with a sufficient amount of relevant training data and fine-tune it appropriately.

To use ChatGPT to generate descriptions of genetic variants or gene expression patterns, you would first need to obtain a large dataset of examples of descriptions of genetic variants or gene expression patterns. You could use this dataset to fine-tune the ChatGPT model on the task of generating descriptions of genetic variants or gene expression patterns.

Here’s an example of how you might use ChatGPT to generate a description of a genetic variant:

First, you would need to pre-process your dataset of descriptions of genetic variants to prepare it for use with ChatGPT. This might involve splitting the descriptions into individual sentences or phrases, and encoding them using a suitable natural language processing (NLP) library or tool.

Next, you would need to fine-tune the ChatGPT model on the task of generating descriptions of genetic variants. This could involve using a tool like Hugging Face’s Transformers library to load the ChatGPT model and your pre-processed dataset, and then training the model on the task of generating descriptions of genetic variants using an appropriate optimization algorithm.

Once the model has been fine-tuned, you can use it to generate descriptions of genetic variants by providing it with a prompt or seed text and asking it to generate a response. For example, you might provide the model with the prompt “Generate a description of a genetic variant associated with increased risk of breast cancer,” and ask it to generate a response. The model should then generate a description of a genetic variant that is associated with increased risk of breast cancer.

It’s worth noting that generating high-quality descriptions of genetic variants or gene expression patterns is a challenging task, and it may be difficult to achieve good results using a language model like ChatGPT without a large amount of relevant training data and careful fine-tuning.

 

To train a language model like chatGPT to extract information about specific genes or diseases from research papers, you would need to follow these steps:

Gather a large dataset of research papers that contain information about the specific genes or diseases you are interested in. This dataset should be diverse and representative of the types of papers you want the model to be able to extract information from.

Preprocess the text data in the research papers by tokenizing the text and creating a vocabulary. You may also want to consider lemmatizing or stemming the text to reduce the dimensionality of the dataset.

Train the language model on the preprocessed text data. You may want to fine-tune a pre-trained model such as chatGPT on your specific dataset, or you can train a new model from scratch.

ChatGPT could also be useful for sequence analysis

A few examples of sequence analysis a ChatGPT could be useful include:

  1. Protein structure
  2. Identifying functional regions of a protein
  3. Predicting protein-protein interactions
  4. Identifying protein homologs
  5. Generating Protein alignments

All this could be done without having access to UNIX servers or proprietary software or knowing GCG coding

ChatGPT in biomedical research
There are several potential ways that ChatGPT or other natural language processing (NLP) models could be applied in biomedical research:

Text summarization: ChatGPT or other NLP models could be used to summarize large amounts of text, such as research papers or clinical notes, in order to extract key information and insights more quickly.

Data extraction: ChatGPT or other NLP models could be used to extract structured data from unstructured text sources, such as research papers or clinical notes. For example, the model could be trained to extract information about specific genes or diseases from research papers, and then used to create a database of this information for further analysis.

Literature review: ChatGPT or other NLP models could be used to assist with literature review tasks, such as identifying relevant papers, extracting key information from papers, or summarizing the main findings of a group of papers.

Predictive modeling: ChatGPT or other NLP models could be used to build predictive models based on large amounts of text data, such as electronic health records or research papers. For example, the model could be trained to predict the likelihood of a patient developing a particular disease based on their medical history and other factors.

It’s worth noting that while NLP models like ChatGPT have the potential to be useful tools in biomedical research, they are only as good as the data they are trained on, and it is important to carefully evaluate the quality and reliability of any results generated by these models.

 

ChatGPT in text mining of biomedical data
ChatGPT could potentially be used for text mining in the biomedical field in a number of ways. Here are a few examples:

Extracting information from scientific papers: ChatGPT could be trained on a large dataset of scientific papers in the biomedical field, and then used to extract specific pieces of information from these papers, such as the names of compounds, their structures, and their potential uses.

Generating summaries of scientific papers: ChatGPT could be used to generate concise summaries of scientific papers in the biomedical field, highlighting the main findings and implications of the research.

Identifying trends and patterns in scientific literature: ChatGPT could be used to analyze large datasets of scientific papers in the biomedical field and identify trends and patterns in the data, such as emerging areas of research or common themes among different papers.

Generating questions for further research: ChatGPT could be used to suggest questions for further research in the biomedical field based on existing scientific literature, by identifying gaps in current knowledge or areas where further investigation is needed.

Generating hypotheses for scientific experiments: ChatGPT could be used to generate hypotheses for scientific experiments in the biomedical field based on existing scientific literature and data, by identifying potential relationships or associations that could be tested in future research.

 

PLEASE WATCH VIDEO

 

In this video, a bioinformatician describes the ways he uses ChatGPT to increase his productivity in writing bioinformatic code and conducting bioinformatic analyses.

He describes a series of uses of ChatGPT in his day to day work as a bioinformatian:

  1. Using ChatGPT as a search engine: He finds more useful and relevant search results than a standard Google or Yahoo search.  This saves time as one does not have to pour through multiple pages to find information.  However, a caveat is ChatGPT does NOT return sources, as highlighted in previous postings on this page.  This feature of ChatGPT is probably why Microsoft bought OpenAI in order to incorporate ChatGPT in their Bing search engine, as well as Office Suite programs

 

  1. ChatGPT to help with coding projects: Bioinformaticians will spend multiple hours searching for and altering open access available code in order to run certain function like determining the G/C content of DNA (although there are many UNIX based code that has already been established for these purposes). One can use ChatGPT to find such a code and then assist in debugging that code for any flaws

 

  1. ChatGPT to document and add coding comments: When writing code it is useful to add comments periodically to assist other users to determine how the code works and also how the program flow works as well, including returned variables.

 

One of the comments was interesting and directed one to use BIOGPT instead of ChatGPT

 

@tzvi7989

1 month ago (edited)

0:54 oh dear. You cannot use chatgpt like that in Bioinformatics as it is rn without double checking the info from it. You should be using biogpt instead for paper summarisation. ChatGPT goes for human-like responses over precise information recal. It is quite good for debugging though and automating boring awkward scripts

So what is BIOGPT?

BioGPT https://github.com/microsoft/BioGPT

 

The BioGPT model was proposed in BioGPT: generative pre-trained transformer for biomedical text generation and mining by Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon and Tie-Yan Liu. BioGPT is a domain-specific generative pre-trained Transformer language model for biomedical text generation and mining. BioGPT follows the Transformer language model backbone, and is pre-trained on 15M PubMed abstracts from scratch.

The abstract from the paper is the following:

Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Among the two main branches of pre-trained language models in the general language domain, i.e. BERT (and its variants) and GPT (and its variants), the first one has been extensively studied in the biomedical domain, such as BioBERT and PubMedBERT. While they have achieved great success on a variety of discriminative downstream biomedical tasks, the lack of generation ability constrains their application scope. In this paper, we propose BioGPT, a domain-specific generative Transformer language model pre-trained on large-scale biomedical literature. We evaluate BioGPT on six biomedical natural language processing tasks and demonstrate that our model outperforms previous models on most tasks. Especially, we get 44.98%, 38.42% and 40.76% F1 score on BC5CDR, KD-DTI and DDI end-to-end relation extraction tasks, respectively, and 78.2% accuracy on PubMedQA, creating a new record. Our case study on text generation further demonstrates the advantage of BioGPT on biomedical literature to generate fluent descriptions for biomedical terms.

Tips:

  • BioGPT is a model with absolute position embeddings so it’s usually advised to pad the inputs on the right rather than the left.
  • BioGPT was trained with a causal language modeling (CLM) objective and is therefore powerful at predicting the next token in a sequence. Leveraging this feature allows BioGPT to generate syntactically coherent text as it can be observed in the run_generation.py example script.
  • The model can take the past_key_values (for PyTorch) as input, which is the previously computed key/value attention pairs. Using this (past_key_values or past) value prevents the model from re-computing pre-computed values in the context of text generation. For PyTorch, see past_key_values argument of the BioGptForCausalLM.forward() method for more information on its usage.

This model was contributed by kamalkraj. The original code can be found here.

 

This repository contains the implementation of BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining, by Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon and Tie-Yan Liu. BioGPT is a github which is being developed by MIT in collaboration with Microsoft. It is based on Python.

License

BioGPT is MIT-licensed. The license applies to the pre-trained models as well.

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

As of right now this does not seem Open Access, however a sign up is required!

We provide our pre-trained BioGPT model checkpoints along with fine-tuned checkpoints for downstream tasks, available both through URL download as well as through the Hugging Face 🤗 Hub.

Model Description URL 🤗 Hub
BioGPT Pre-trained BioGPT model checkpoint link link
BioGPT-Large Pre-trained BioGPT-Large model checkpoint link link
BioGPT-QA-PubMedQA-BioGPT Fine-tuned BioGPT for question answering task on PubMedQA link
BioGPT-QA-PubMedQA-BioGPT-Large Fine-tuned BioGPT-Large for question answering task on PubMedQA link
BioGPT-RE-BC5CDR Fine-tuned BioGPT for relation extraction task on BC5CDR link
BioGPT-RE-DDI Fine-tuned BioGPT for relation extraction task on DDI link
BioGPT-RE-DTI Fine-tuned BioGPT for relation extraction task on KD-DTI link
BioGPT-DC-HoC Fine-tuned BioGPT for document classification task on HoC link

 

So far as to date (6/12/2023) there are three papers referencing BioGPT on PubMed (abstracts and links below)

 

BioGPT: generative pre-trained transformer for biomedical text generation and mining.

Luo R, Sun L, Xia Y, Qin T, Zhang S, Poon H, Liu TY.Brief Bioinform. 2022 Nov 19;23(6):bbac409. doi: 10.1093/bib/bbac409.PMID: 36156661

We evaluate BioGPT on six biomedical natural language processing tasks and demonstrate that our model outperforms previous models on most tasks. …Our case study on text generation further demonstrates the advantage of BioGPT on biomedical literature to generate fl …

Here they show the advantages of BioGPT over BioBERT and ChatGPT in an example of text extraction and question answer

Table 7. Example of generated text

Input                                           Model                 Text

Bicalutamide                               GPT-2                 Bicalutamide, a synthetic bicalutamide derivative, was found to increase the cellular proliferation

of C. elegans cells. This effect was not observed with the other synthetic bicalutamide derivatives. This is in line with our previous work which showed that bicalutamide increases the proliferation of C. elegans cells but not in the presence of synthetic bicalutamide.

BioGPT             Bicalutamide (Casodex) is an androgen receptor (AR) antagonist approved for the treatment of metastatic castration-resistant prostate cancer (mCRPC) in patients who have progressed on or are ineligible for docetaxel chemotherapy, as well as for the treatment of early-stage prostate cancer in men who have not progressed on or are ineligible for docetaxel chemotherapy, as well as for the treatment of metastatic castration-sensitive prostate cancer (mCSPC) in men who have not progressed on or are ineligible for docetaxel chemotherapy.

Janus kinase 3 (JAK-3)                 GPT-2               Janus kinase 3 (JAK-3) mediates the conversion of glucose to glycogen in skeletal muscle. The
increase in glucose uptake by skeletal muscle is believed to be associated with a reduction in muscle protein breakdown and with the release of ketone bodies, which contribute to the metabolism of glucose.

BioGPT             Janus kinase 3 (JAK-3) is a member of the Janus kinase (JAK) family of non-receptor tyrosine kinases and plays an important role in the regulation of cell proliferation, differentiation, survival, migration and angiogenesis.

Apricitabine                                 GPT-2               Apricitabine, duloxetine and citalopram) were investigated in patients with a history of
treatment-resistant depression (n = 10). We found that treatment with the three drugs significantly decreased depressive symptoms, but not depressive symptoms over the next 12 weeks. We conclude that antidepressant drugs that reduce depressive symptoms and reduce depressive symptoms over time may be beneficial in patients with recurrent depression.

BioGPT             Apricitabine is an oral prodrug of 5-aza-2 ’-deoxycytidine (5-aza-CdR), a DNA methyltransferase (DNMT) inhibitor, which has been approved by the US Food and Drug Administration (FDA) for the treatment of myelodysplastic syndrome (MDS) and acute myeloid leukemia (AML) in combination with low-dose cytarabine (Ara-C) and granulocyte colony-stimulating factor (G-CSF) for patients with intermediate-2 or high-risk MDS or AML.

Xylazine                                      GPT-2               Xylazine, the ‘active ingredient’ in ‘bath salts’ (see above) has been linked to numerous deaths,
including those of former University of California, Berkeley, professor Andrew Anglin, who posted

a video of himself having a bath filled with it.

BioGPT             Xylazine is an alpha 2-adrenoceptor agonist which has been used as a sedative and analgesic in veterinary medicine for many years, but its effects on the cardiovascular system have not been extensively studied in the dog, and its effects on the central nervous system (CNS) have not been well characterized in the dog, despite the fact that xylazine has been widely used as a sedative and analgesic in veterinary medicine for more than 30 years.

Psoralen                                      GPT-2               Psoralen, the city of the spiritualist, and had been given to him by God, who wished to show him
the way of salvation, and to draw him back to the true life of Christ, and to bring him into communion with his fellow-man.

BioGPT             Psoralen photochemotherapy (PUVA) is a well-established treatment for psoriasis, but its use is limited by the risk of skin cancer, particularly squamous cell carcinoma (SCC) of the head and neck (H & N), which is the most common site of skin cancer in the United States (US)

CP-673451                                  GPT-2                 CP-673451) and 4-5-6-3-1-2-3-4-6-7-8-9-10-11-12-13-14-15-16-17-18-19-20-21-22-23-24-25-26-27-

28-29-30-31-32-33-34-35-36-37-38-39-40-41-42-43-44-45-46-47-48-49-50…

BioGPT             CP-673451 is a potent, selective, and orally active inhibitor of human neutrophil elastase (HNE) and human cathepsin G (CatG) with in vitro and in vivo anti-inflammatory activity in a variety of animal models of inflammation and in a model of acute lung injury (ALI) in the rat induced by intratracheal instillation of lipopolysaccharide (LPS) and tumor necrosis factor-alpha (TNF-alpha), a model of acute lung injury (ALI) in which neutrophils play an important role.

BIIB-021                                     GPT-2               BIIB-021A-2-1.pdf. Wright, C. (2002). ‘The War on Terror: A Legal Theory of Terrorist Attacks,’ in
L.E.R. Wright, S.R. Warrick and J.H. Rothman (Eds.), The War on Terror: Essays in Honor of Michael T. Klare (New York: Oxford University Press), 143-57.

BioGPT             BIIB-021 is a novel, orally active, non-peptide bradykinin B2 receptor antagonist with potent and long-lasting anti-inflammatory activity in animal models of acute and chronic inflammation and in a rat model of adjuvant-induced arthritis (AIA), an animal model of rheumatoid arthritis (RA) and in a rat model of collagen-induced arthritis (CIA), an animal model of collagen-induced arthritis (CIA), in which arthritis is induced by immunization with bovine type II collagen (CII).

Note how BioGPT is more descriptive and accurate!

EGFI: drug-drug interaction extraction and generation with fusion of enriched entity and sentence information.

Huang L, Lin J, Li X, Song L, Zheng Z, Wong KC.Brief Bioinform. 2022 Jan 17;23(1):bbab451. doi: 10.1093/bib/bbab451.PMID: 34791012

The rapid growth in literature accumulates diverse and yet comprehensive biomedical knowledge hidden to be mined such as drug interactions. However, it is difficult to extract the heterogeneous knowledge to retrieve or even discover the latest and novel knowledge in an efficient manner. To address such a problem, we propose EGFI for extracting and consolidating drug interactions from large-scale medical literature text data. Specifically, EGFI consists of two parts: classification and generation. In the classification part, EGFI encompasses the language model BioBERT which has been comprehensively pretrained on biomedical corpus. In particular, we propose the multihead self-attention mechanism and packed BiGRU to fuse multiple semantic information for rigorous context modeling. In the generation part, EGFI utilizes another pretrained language model BioGPT-2 where the generation sentences are selected based on filtering rules.

Results: We evaluated the classification part on ‘DDIs 2013’ dataset and ‘DTIs’ dataset, achieving the F1 scores of 0.842 and 0.720 respectively. Moreover, we applied the classification part to distinguish high-quality generated sentences and verified with the existing growth truth to confirm the filtered sentences. The generated sentences that are not recorded in DrugBank and DDIs 2013 dataset demonstrated the potential of EGFI to identify novel drug relationships.

Availability: Source code are publicly available at https://github.com/Layne-Huang/EGFI.

 

GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information.

Jin Q, Yang Y, Chen Q, Lu Z.ArXiv. 2023 May 16:arXiv:2304.09667v3. Preprint.PMID: 37131884 Free PMC article.

While large language models (LLMs) have been successfully applied to various tasks, they still face challenges with hallucinations. Augmenting LLMs with domain-specific tools such as database utilities can facilitate easier and more precise access to specialized knowledge. In this paper, we present GeneGPT, a novel method for teaching LLMs to use the Web APIs of the National Center for Biotechnology Information (NCBI) for answering genomics questions. Specifically, we prompt Codex to solve the GeneTuring tests with NCBI Web APIs by in-context learning and an augmented decoding algorithm that can detect and execute API calls. Experimental results show that GeneGPT achieves state-of-the-art performance on eight tasks in the GeneTuring benchmark with an average score of 0.83, largely surpassing retrieval-augmented LLMs such as the new Bing (0.44), biomedical LLMs such as BioMedLM (0.08) and BioGPT (0.04), as well as GPT-3 (0.16) and ChatGPT (0.12). Our further analyses suggest that: (1) API demonstrations have good cross-task generalizability and are more useful than documentations for in-context learning; (2) GeneGPT can generalize to longer chains of API calls and answer multi-hop questions in GeneHop, a novel dataset introduced in this work; (3) Different types of errors are enriched in different tasks, providing valuable insights for future improvements.

PLEASE WATCH THE FOLLOWING VIDEOS ON BIOGPT

This one entitled

Microsoft’s BioGPT Shows Promise as the Best Biomedical NLP

 

gives a good general description of this new MIT/Microsoft project and its usefullness in scanning 15 million articles on PubMed while returning ChatGPT like answers.

 

Please note one of the comments which is VERY IMPORTANT


@rufus9322

2 months ago

bioGPT is difficult for non-developers to use, and Microsoft researchers seem to default that all users are proficient in Python and ML.

 

Much like Microsoft Azure it seems this BioGPT is meant for developers who have advanced programming skill.  Seems odd then to be paying programmers multiK salaries when one or two Key Opinion Leaders from the medical field might suffice but I would be sure Microsoft will figure this out.

 

ALSO VIEW VIDEO

 

 

This is a talk from Microsoft on BioGPT

 

Other Relevant Articles on Natural Language Processing in BioInformatics, Healthcare and ChatGPT for Medicine on this Open Access Scientific Journal Include

Medicine with GPT-4 & ChatGPT
Explanation on “Results of Medical Text Analysis with Natural Language Processing (NLP) presented in LPBI Group’s NEW GENRE Edition: NLP” on Genomics content, standalone volume in Series B and NLP on Cancer content as Part B New Genre Volume 1 in Series C

Proposal for New e-Book Architecture: Bi-Lingual eTOCs, English & Spanish with NLP and Deep Learning results of Medical Text Analysis – Phase 1: six volumes

From High-Throughput Assay to Systems Biology: New Tools for Drug Discovery

Machine Learning (ML) in cancer prognosis prediction helps the researcher to identify multiple known as well as candidate cancer diver genes

 

20 articles in Natural Language Processing

142 articles in BioIT: BioInformatics

111 articles in BioIT: BioInformatics, NGS, Clinical & Translational, Pharmaceutical R&D Informatics, Clinical Genomics, Cancer Informatics

 

Read Full Post »

Use of Systems Biology for Design of inhibitor of Galectins as Cancer Therapeutic – Strategy and Software

 

 

Curator: Stephen J. Williams, Ph.D.

Below is a slide representation of the overall mission 4 to produce a PROTAC to inhibit Galectins 1, 3, and 9.

 

Using A Priori Knowledge of Galectin Receptor Interaction to Create a BioModel of Galectin 3 Binding

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Now after collecting literature from PubMed on “galectin-3” AND “binding” to determine literature containing kinetic data we generate a WordCloud on the articles.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

This following file contains the articles needed for BioModels generation.

https://pharmaceuticalintelligence.com/wp-content/uploads/2022/12/Curating-Galectin-articles-for-Biomodels.docx

 

From the WordCloud we can see that these corpus of articles describe galectin binding to the CRD (carbohydrate recognition domain).  Interestingly there are many articles which describe van Der Waals interactions as well as electrostatic interactions.  Certain carbohydrate modifictions like Lac NAc and Gal 1,4 may be important.  Many articles describe the bonding as well as surface  interactions.  Many studies have been performed with galectin inhibitors like TDGs (thio-digalactosides) like TAZ TDG (3-deoxy-3-(4-[m-fluorophenyl]-1H-1,2,3-triazol-1-yl)-thio-digalactoside).  This led to an interesting article

Dual thio-digalactoside-binding modes of human galectins as the structural basis for the design of potent and selective inhibitors

Affiliations 2016 Jul 15;6:29457.
 doi: 10.1038/srep29457. Free PMC article

Abstract

Human galectins are promising targets for cancer immunotherapeutic and fibrotic disease-related drugs. We report herein the binding interactions of three thio-digalactosides (TDGs) including TDG itself, TD139 (3,3′-deoxy-3,3′-bis-(4-[m-fluorophenyl]-1H-1,2,3-triazol-1-yl)-thio-digalactoside, recently approved for the treatment of idiopathic pulmonary fibrosis), and TAZTDG (3-deoxy-3-(4-[m-fluorophenyl]-1H-1,2,3-triazol-1-yl)-thio-digalactoside) with human galectins-1, -3 and -7 as assessed by X-ray crystallography, isothermal titration calorimetry and NMR spectroscopy. Five binding subsites (A-E) make up the carbohydrate-recognition domains of these galectins. We identified novel interactions between an arginine within subsite E of the galectins and an arene group in the ligands. In addition to the interactions contributed by the galactosyl sugar residues bound at subsites C and D, the fluorophenyl group of TAZTDG preferentially bound to subsite B in galectin-3, whereas the same group favored binding at subsite E in galectins-1 and -7. The characterised dual binding modes demonstrate how binding potency, reported as decreased Kd values of the TDG inhibitors from μM to nM, is improved and also offer insights to development of selective inhibitors for individual galectins.

Figures

Figure 1
 
Figure 2
 
Figure 3

 

 

Read Full Post »

 

Medical Startups – Artificial Intelligence (AI) Startups in Healthcare

Reporters: Stephen J. Williams, PhD and Aviva Lev-Ari, PhD, RN and Shraga Rottem, MD, DSc,

The motivation for this post is two fold:

First, we are presenting an application of AI, NLP, DL to our own medical text in the Genomics space. Here we present the first section of Part 1 in the following book. Part 1 has six subsections that yielded 12 plots. The entire Book is represented by 38 x 2 = 76 plots.

Second, we bring to the attention of the e-Reader the list of 276 Medical Startups – Artificial Intelligence (AI) Startups in Healthcare as a hot universe of R&D activity in Human Health.

Third, to highlight one academic center with an AI focus

ETH Logo
 
ETH AI Center - Header Image
 
 
Dear friends of the ETH AI Center,

We would like to provide you with some exciting updates from the ETH AI Center and its growing community.

We would like to provide you with some exciting updates from the ETH AI Center and its growing community. The ETH AI Center now comprises 110 research groups in the faculty, 20 corporate partners and has led to nine AI startups.

As the Covid-19 restrictions in Switzerland have recently been lifted, we would like to hear from you what kind of events you would like to see in 2022! Participate in the survey to suggest event formats and topics that you would enjoy being a part of. We are already excited to learn what we can achieve together this year.

We already have many interesting events coming up, we look forward to seeing you at our main and community events!

SOURCE

https://news.ethz.ch/html_mail.jsp?params=%2FUnFXUQJ%2FmiOP6akBq8eHxaXG%2BRdNmeoVa9gX5ArpTr6mX74xp5d78HhuIHTd9V6AHtAfRahyx%2BfRGrzVL1G8Jy5e3zykvr1WDtMoUC%2B7vILoHCGQ5p1rxaPzOsF94ID

 

 

LPBI Group is applying AI for Medical Text Analysis with Machine Learning and Natural Language Processing: Statistical and Deep Learning

Our Book 

Latest in Genomics Methodologies for Therapeutics: Gene Editing, NGS & BioInformatics, Simulations and the Genome Ontology

Medical Text Analysis of this Books shows the following results obtained by Madison Davis by applying Wolfram NLP for Biological Languages on our own Text. See below an Example:

Part 1: Next Generation Sequencing (NGS)

 

1.1 The NGS Science

1.1.1 BioIT Aspect

 

Hypergraph Plot #1 and Tree Diagram Plot #1

for 1.1.1 based on 16 articles & on 12 keywords

protein, cancer, dna, genes, rna, survival, immune, tumor, patients, human, genome, expression

(more…)

Read Full Post »

The Vibrant Philly Biotech Scene: Proteovant Therapeutics Using Artificial Intelligence and Machine Learning to Develop PROTACs

Reporter: Stephen J. Williams, Ph.D.

It has been a while since I have added to this series but there have been a plethora of exciting biotech startups in the Philadelphia area, and many new startups combining technology, biotech, and machine learning. One such exciting biotech is Proteovant Therapeutics, which is combining the new PROTAC (Proteolysis-Targeting Chimera) technology with their in house ability to utilize machine learning and artificial intelligence to design these types of compounds to multiple intracellular targets.

PROTACs (which actually is under a trademark name of Arvinus Operations, but is also refered to as Protein Degraders. These PROTACs take advantage of the cell protein homeostatic mechanism of ubiquitin-mediated protein degradation, which is a very specific targeted process which regulates protein levels of various transcription factors, protooncogenes, and receptors. In essence this regulated proteolyic process is needed for normal cellular function, and alterations in this process may lead to oncogenesis, or a proteotoxic crisis leading to mitophagy, autophagy and cellular death. The key to this technology is using chemical linkers to associate an E3 ligase with a protein target of interest. E3 ligases are the rate limiting step in marking the proteins bound for degradation by the proteosome with ubiquitin chains.

Model of PROTAC Ternarary Complex

A review of this process as well as PROTACs can be found elsewhere in articles (and future articles) on this Open Access Journal.

Protevant have made two important collaborations:

  1. Oncopia Therapeutics: came out of University of Michigan Innovation Hub and lab of Shaomeng Wang, who developed a library of BET and MDM2 based protein degraders. In 2020 was aquired by Riovant Sciences.
  2. Riovant Sciences: uses computer aided design of protein degraders

Proteovant Company Description:

Proteovant is a newly launched development-stage biotech company focusing on discovery and development of disease-modifying therapies by harnessing natural protein homeostasis processes. We have recently acquired numerous assets at discovery and development stages from Oncopia, a protein degradation company. Our lead program is on track to enter IND in 2021. Proteovant is building a strong drug discovery engine by combining deep drugging expertise with innovative platforms including Roivant’s AI capabilities to accelerate discovery and development of protein degraders to address unmet needs across all therapeutic areas. The company has recently secured $200M funding from SK Holdings in addition to investment from Roivant Sciences. Our current therapeutic focus includes but is not limited to oncology, immunology and neurology. We remain agnostic to therapeutic area and will expand therapeutic focus based on opportunity. Proteovant is expanding its discovery and development teams and has multiple positions in biology, chemistry, biochemistry, DMPK, bioinformatics and CMC at many levels. Our R&D organization is located close to major pharmaceutical companies in Eastern Pennsylvania with a second site close to biotech companies in Boston area.

Protein degradation

Source: Protevant

The ubiquitin proteasome system (UPS) is responsible for maintaining protein homeostasis. Targeted protein degradation by the UPS is a cellular process that involves marking proteins and guiding them to the proteasome for destruction. We leverage this physiological cellular machinery to target and destroy disease-causing proteins.

Unlike traditional small molecule inhibitors, our approach is not limited by the classic “active site” requirements. For example, we can target transcription factors and scaffold proteins that lack a catalytic pocket. These classes of proteins, historically, have been very difficult to drug. Further, we selectively degrade target proteins, rather than isozymes or paralogous proteins with high homology. Because of the catalytic nature of the interactions,  it is possible to achieve efficacy at lower doses with prolonged duration while decreasing dose-limiting toxicities.

Biological targets once deemed “undruggable” are now within reach.

About Riovant Sciences: from PRNewsWire https://www.prnewswire.com/news-releases/roivant-unveils-targeted-protein-degradation-platform-301186928.html

Roivant develops transformative medicines faster by building technologies and developing talent in creative ways, leveraging the Roivant platform to launch “Vants” – nimble and focused biopharmaceutical and health technology companies. These Vants include Proteovant but also Dermovant, ImmunoVant,as well as others.

Roivant’s drug discovery capabilities include the leading computational physics-based platform for in silico drug design and optimization as well as machine learning-based models for protein degradation.

The integration of our computational and experimental engines enables the rapid design of molecules with high precision and fidelity to address challenging targets for diseases with high unmet need.

Our current modalities include small molecules, heterobifunctionals and molecular glues.

Roivant Unveils Targeted Protein Degradation Platform

– First therapeutic candidate on track to enter clinical studies in 2021

– Computationally-designed degraders for six targets currently in preclinical development

– Acquisition of Oncopia Therapeutics and research collaboration with lab of Dr. Shaomeng Wang at the University of Michigan to add diverse pipeline of current and future compounds

Clinical-stage degraders will provide foundation for multiple new Vants in distinct disease areas

– Platform supported by $200 million strategic investment from SK Holdings

Other articles in this Vibrant Philly Biotech Scene on this Online Open Access Journal include:

The Vibrant Philly Biotech Scene: PCCI Meeting Announcement, BioDetego Presents Colon Cancer Diagnostic Tool

The Vibrant Philly Biotech Scene: Focus on KannaLife Sciences and the Discipline and Potential of Pharmacognosy

The Vibrant Philly Biotech Scene: Focus on Vaccines and Philimmune, LLC

The Vibrant Philly Biotech Scene: Focus on Computer-Aided Drug Design and Gfree Bio, LLC

Philly Biotech Scene: Biobots and 3D BioPrinting (Now called Allevi)

Philly Biotech Scene: November 2015 PCCI Meeting Showcasing ViFant (Penn Center For Innovation)

Spark Therapeutics’ $4.8Billion deal Confirmed as Biggest VC-backed Exit in Philadelphia

Read Full Post »

The Map of human proteins drawn by artificial intelligence and PROTAC (proteolysis targeting chimeras) Technology for Drug Discovery

Curators: Dr. Stephen J. Williams and Aviva Lev-Ari, PhD, RN

UPDATED on 11/5/2021

Introducing Isomorphic Labs

I believe we are on the cusp of an incredible new era of biological and medical research. Last year DeepMind’s breakthrough AI system AlphaFold2 was recognised as a solution to the 50-year-old grand challenge of protein folding, capable of predicting the 3D structure of a protein directly from its amino acid sequence to atomic-level accuracy. This has been a watershed moment for computational and AI methods for biology.
Building on this advance, today, I’m thrilled to announce the creation of a new Alphabet company –  Isomorphic Labs – a commercial venture with the mission to reimagine the entire drug discovery process from the ground up with an AI-first approach and, ultimately, to model and understand some of the fundamental mechanisms of life.

For over a decade DeepMind has been in the vanguard of advancing the state-of-the-art in AI, often using games as a proving ground for developing general purpose learning systems, like AlphaGo, our program that beat the world champion at the complex game of Go. We are at an exciting moment in history now where these techniques and methods are becoming powerful and sophisticated enough to be applied to real-world problems including scientific discovery itself. One of the most important applications of AI that I can think of is in the field of biological and medical research, and it is an area I have been passionate about addressing for many years. Now the time is right to push this forward at pace, and with the dedicated focus and resources that Isomorphic Labs will bring.

An AI-first approach to drug discovery and biology
The pandemic has brought to the fore the vital work that brilliant scientists and clinicians do every day to understand and combat disease. We believe that the foundational use of cutting edge computational and AI methods can help scientists take their work to the next level, and massively accelerate the drug discovery process. AI methods will increasingly be used not just for analysing data, but to also build powerful predictive and generative models of complex biological phenomena. AlphaFold2 is an important first proof point of this, but there is so much more to come. 
At its most fundamental level, I think biology can be thought of as an information processing system, albeit an extraordinarily complex and dynamic one. Taking this perspective implies there may be a common underlying structure between biology and information science – an isomorphic mapping between the two – hence the name of the company. Biology is likely far too complex and messy to ever be encapsulated as a simple set of neat mathematical equations. But just as mathematics turned out to be the right description language for physics, biology may turn out to be the perfect type of regime for the application of AI.

What’s next for Isomorphic Labs
This is just the beginning of what we hope will become a radical new approach to drug discovery, and I’m incredibly excited to get this ambitious new commercial venture off the ground and to partner with pharmaceutical and biomedical companies. I will serve as CEO for Isomorphic’s initial phase, while remaining as DeepMind CEO, partially to help facilitate collaboration between the two companies where relevant, and to set out the strategy, vision and culture of the new company. This will of course include the building of a world-class multidisciplinary team, with deep expertise in areas such as AI, biology, medicinal chemistry, biophysics, and engineering, brought together in a highly collaborative and innovative environment. (We are hiring!
As pioneers in the emerging field of ‘digital biology’, we look forward to helping usher in an amazingly productive new age of biomedical breakthroughs. Isomorphic’s mission could not be a more important one: to use AI to accelerate drug discovery, and ultimately, find cures for some of humanity’s most devastating diseases.

SOURCE

https://www.isomorphiclabs.com/blog

DeepMind creates ‘transformative’ map of human proteins drawn by artificial intelligence

DeepMind plans to release hundreds of millions of protein structures for free

James Vincent July 22, 2021 11:00 am

AI research lab DeepMind has created the most comprehensive map of human proteins to date using artificial intelligence. The company, a subsidiary of Google-parent Alphabet, is releasing the data for free, with some scientists comparing the potential impact of the work to that of the Human Genome Project, an international effort to map every human gene.

Proteins are long, complex molecules that perform numerous tasks in the body, from building tissue to fighting disease. Their purpose is dictated by their structure, which folds like origami into complex and irregular shapes. Understanding how a protein folds helps explain its function, which in turn helps scientists with a range of tasks — from pursuing fundamental research on how the body works, to designing new medicines and treatments.
 “the culmination of the entire 10-year-plus lifetime of DeepMind” 
Previously, determining the structure of a protein relied on expensive and time-consuming experiments. But last year DeepMind showed it can produce accurate predictions of a protein’s structure using AI software called AlphaFold. Now, the company is releasing hundreds of thousands of predictions made by the program to the public.
“I see this as the culmination of the entire 10-year-plus lifetime of DeepMind,” company CEO and co-founder Demis Hassabis told The Verge. “From the beginning, this is what we set out to do: to make breakthroughs in AI, test that on games like Go and Atari, [and] apply that to real-world problems, to see if we can accelerate scientific breakthroughs and use those to benefit humanity.”



Two examples of protein structures predicted by AlphaFold (in blue) compared with experimental results (in green). 
Image: DeepMind


There are currently around 180,000 protein structures available in the public domain, each produced by experimental methods and accessible through the Protein Data Bank. DeepMind is releasing predictions for the structure of some 350,000 proteins across 20 different organisms, including animals like mice and fruit flies, and bacteria like 
E. coli. (There is some overlap between DeepMind’s data and pre-existing protein structures, but exactly how much is difficult to quantify because of the nature of the models.) Most significantly, the release includes predictions for 98 percent of all human proteins, around 20,000 different structures, which are collectively known as the human proteome. It isn’t the first public dataset of human proteins, but it is the most comprehensive and accurate.

If they want, scientists can download the entire human proteome for themselves, says AlphaFold’s technical lead John Jumper. “There is a HumanProteome.zip effectively, I think it’s about 50 gigabytes in size,” Jumper tells The Verge. “You can put it on a flash drive if you want, though it wouldn’t do you much good without a computer for analysis!”
 “anyone can use it for anything” 
After launching this first tranche of data, DeepMind plans to keep adding to the store of proteins, which will be maintained by Europe’s flagship life sciences lab, the European Molecular Biology Laboratory (EMBL). By the end of the year, DeepMind hopes to release predictions for 100 million protein structures, a dataset that will be “transformative for our understanding of how life works,” according to Edith Heard, director general of the EMBL.
The data will be free in perpetuity for both scientific and commercial researchers, says Hassabis. “Anyone can use it for anything,” the DeepMind CEO noted at a press briefing. “They just need to credit the people involved in the citation.”

The benefits of protein folding


Understanding a protein’s structure is useful for scientists across a range of fields. The information can help design new medicines, synthesize novel enzymes that break down waste materials, and create crops that are resistant to viruses or extreme weather. Already, DeepMind’s protein predictions are being used for medical research, including studying the workings of SARS-CoV-2, the virus that causes COVID-19.
 “it will definitely have a huge impact for the scientific community” 
New data will speed these efforts, but scientists note it will still take a lot of time to turn this information into real-world results. “I don’t think it’s going to be something that changes the way patients are treated within the year, but it will definitely have a huge impact for the scientific community,” Marcelo C. Sousa, a professor at the University of Colorado’s biochemistry department, told The Verge.
Scientists will have to get used to having such information at their fingertips, says DeepMind senior research scientist Kathryn Tunyasuvunakool. “As a biologist, I can confirm we have no playbook for looking at even 20,000 structures, so this [amount of data] is hugely unexpected,” Tunyasuvunakool told The Verge. “To be analyzing hundreds of thousands of structures — it’s crazy.”

Notably, though, DeepMind’s software produces predictions of protein structures rather than experimentally determined models, which means that in some cases further work will be needed to verify the structure. DeepMind says it spent a lot of time building accuracy metrics into its AlphaFold software, which ranks how confident it is for each prediction.

Example protein structures predicted by AlphaFold.
Image: DeepMind
Predictions of protein structures are still hugely useful, though. Determining a protein’s structure through experimental methods is expensive, time-consuming, and relies on a lot of trial and error. That means even a low-confidence prediction can save scientists years of work by pointing them in the right direction for research.
Helen Walden, a professor of structural biology at the University of Glasgow, tells The Verge that DeepMind’s data will “significantly ease” research bottlenecks, but that “the laborious, resource-draining work of doing the biochemistry and biological evaluation of, for example, drug functions” will remain.
Sousa, who has previously used data from AlphaFold in his work, says for scientists the impact will be felt immediately. “In our collaboration we had with DeepMind, we had a dataset with a protein sample we’d had for 10 years, and we’d never got to the point of developing a model that fit,” he says. “DeepMind agreed to provide us with a structure, and they were able to solve the problem in 15 minutes after we’d been sitting on it for 10 years.”

Why protein folding is so difficult

Proteins are constructed from chains of amino acids, which come in 20 different varieties in the human body. As any individual protein can be comprised of hundreds of individual amino acids, each of which can fold and twist in different directions, it means a molecule’s final structure has an incredibly large number of possible configurations. One estimate is that the typical protein can be folded in 10^300 ways — that’s a 1 followed by 300 zeroes.

 Protein folding has been a “grand challenge” of biology for decades 

Because proteins are too small to examine with microscopes, scientists have had to indirectly determine their structure using expensive and complicated methods like nuclear magnetic resonance and X-ray crystallography. The idea of determining the structure of a protein simply by reading a list of its constituent amino acids has been long theorized but difficult to achieve, leading many to describe it as a “grand challenge” of biology.
In recent years, though, computational methods — particularly those using artificial intelligence — have suggested such analysis is possible. With these techniques, AI systems are trained on datasets of known protein structures and use this information to create their own predictions.

DeepMind’s AlphaFold software has significantly increased the accuracy of computational protein-folding, as shown by its performance in the CASP competition. 
Image: DeepMind
Many groups have been working on this problem for years, but DeepMind’s deep bench of AI talent and access to computing resources allowed it to accelerate progress dramatically. Last year, the company competed in an international protein-folding competition known as CASP and blew away the competition. Its results were so accurate that computational biologist John Moult, one of CASP’s co-founders, said that “in some sense the problem [of protein folding] is solved.”

DeepMind’s AlphaFold program has been upgraded since last year’s CASP competition and is now 16 times faster. “We can fold an average protein in a matter of minutes, most cases seconds,” says Hassabis.

@@@@@@@

The company also released the underlying code for AlphaFold last week as open-source, allowing others to build on its work in the future.

@@@@@@@

Liam McGuffin, a professor at Reading University who developed some of the UK’s leading protein-folding software, praised the technical brilliance of AlphaFold, but also noted that the program’s success relied on decades of prior research and public data. “DeepMind has vast resources to keep this database up to date and they are better placed to do this than any single academic group,” McGuffin told The Verge. “I think academics would have got there in the end, but it would have been slower because we’re not as well resourced.”

Why does DeepMind care?

Many scientists The Verge spoke to noted the generosity of DeepMind in releasing this data for free. After all, the lab is owned by Google-parent Alphabet, which has been pouring huge amounts of resources into commercial healthcare projects. DeepMind itself loses a lot of money each year, and there have been numerous reports of tensions between the company and its parent firm over issues like research autonomy and commercial viability.

Hassabis, though, tells The Verge that the company always planned to make this information freely available, and that doing so is a fulfillment of DeepMind’s founding ethos. He stresses that DeepMind’s work is used in lots of places at Google — “almost anything you use, there’s some of our technology that’s part of that under the hood” — but that the company’s primary goal has always been fundamental research.
 “There’s many ways value can be attained.” 

“The agreement when we got acquired is that we are here primarily to advance the state of AGI and AI technologies and then use that to accelerate scientific breakthroughs,” says Hassabis. “[Alphabet] has plenty of divisions focused on making money,” he adds, noting that DeepMind’s focus on research “brings all sorts of benefits, in terms of prestige and goodwill for the scientific community. There’s many ways value can be attained.”
Hassabis predicts that AlphaFold is a sign of things to come — a project that shows the huge potential of artificial intelligence to handle messy problems like human biology.

“I think we’re at a really exciting moment,” he says. “In the next decade, we, and others in the AI field, are hoping to produce amazing breakthroughs that will genuinely accelerate solutions to the really big problems we have here on Earth.”


SOURCE

https://www.theverge.com/platform/amp/2021/7/22/22586578/deepmind-alphafold-ai-protein-folding-human-proteome-released-for-free?__twitter_impression=true

Potential Use of Protein Folding Predictions for Drug Discovery

PROTAC Technology: Opportunities and Challenges

  • Hongying Gao
  • Xiuyun Sun
  • Yu Rao*

Cite this: ACS Med. Chem. Lett. 2020, 11, 3, 237–240Publication Date:March 12, 2020https://doi.org/10.1021/acsmedchemlett.9b00597Copyright © 2020 American Chemical Society

Abstract

PROTACs-induced targeted protein degradation has emerged as a novel therapeutic strategy in drug development and attracted the favor of academic institutions, large pharmaceutical enterprises (e.g., AstraZeneca, Bayer, Novartis, Amgen, Pfizer, GlaxoSmithKline, Merck, and Boehringer Ingelheim, etc.), and biotechnology companies. PROTACs opened a new chapter for novel drug development. However, any new technology will face many new problems and challenges. Perspectives on the potential opportunities and challenges of PROTACs will contribute to the research and development of new protein degradation drugs and degrader tools.

Although PROTAC technology has a bright future in drug development, it also has many challenges as follows:
(1)
Until now, there is only one example of PROTAC reported for an “undruggable” target; (18) more cases are needed to prove the advantages of PROTAC in “undruggable” targets in the future.
(2)
“Molecular glue”, existing in nature, represents the mechanism of stabilized protein–protein interactions through small molecule modulators of E3 ligases. For instance, auxin, the plant hormone, binds to the ligase SCF-TIR1 to drive recruitment of Aux/IAA proteins and subsequently triggers its degradation. In addition, some small molecules that induce targeted protein degradation through “molecular glue” mode of action have been reported. (21,22) Furthermore, it has been recently reported that some PROTACs may actually achieve target protein degradation via a mechanism that includes “molecular glue” or via “molecular glue” alone. (23) How to distinguish between these two mechanisms and how to combine them to work together is one of the challenges for future research.
(3)
Since PROTAC acts in a catalytic mode, traditional methods cannot accurately evaluate the pharmacokinetics (PK) and pharmacodynamics (PD) properties of PROTACs. Thus, more studies are urgently needed to establish PK and PD evaluation systems for PROTACs.
(4)
How to quickly and effectively screen for target protein ligands that can be used in PROTACs, especially those targeting protein–protein interactions, is another challenge.
(5)
How to understand the degradation activity, selectivity, and possible off-target effects (based on different targets, different cell lines, and different animal models) and how to rationally design PROTACs etc. are still unclear.
(6)
The human genome encodes more than 600 E3 ubiquitin ligases. However, there are only very few E3 ligases (VHL, CRBN, cIAPs, and MDM2) used in the design of PROTACs. How to expand E3 ubiquitin ligase scope is another challenge faced in this area.

PROTAC technology is rapidly developing, and with the joint efforts of the vast number of scientists in both academia and industry, these problems shall be solved in the near future.

PROTACs have opened a new chapter for the development of new drugs and novel chemical knockdown tools and brought unprecedented opportunities to the industry and academia, which are mainly reflected in the following aspects:
(1)
Overcoming drug resistance of cancer. In addition to traditional chemotherapy, kinase inhibitors have been developing rapidly in the past 20 years. (12) Although kinase inhibitors are very effective in cancer therapy, patients often develop drug resistance and disease recurrence, consequently. PROTACs showed greater advantages in drug resistant cancers through degrading the whole target protein. For example, ARCC-4 targeting androgen receptor could overcome enzalutamide-resistant prostate cancer (13) and L18I targeting BTK could overcome C481S mutation. (14)
(2)
Eliminating both the enzymatic and nonenzymatic functions of kinase. Traditional small molecule inhibitors usually inhibit the enzymatic activity of the target, while PROTACs affect not only the enzymatic activity of the protein but also nonenzymatic activity by degrading the entire protein. For example, FAK possesses the kinase dependent enzymatic functions and kinase independent scaffold functions, but regulating the kinase activity does not successfully inhibit all FAK function. In 2018, a highly effective and selective FAK PROTAC reported by Craig M. Crews’ group showed a far superior activity to clinical candidate drug in cell migration and invasion. (15) Therefore, PROTAC can expand the druggable space of the existing targets and regulate proteins that are difficult to control by traditional small molecule inhibitors.
(3)
Degrade the “undruggable” protein target. At present, only 20–25% of the known protein targets (include kinases, G protein-coupled receptors (GPCRs), nuclear hormone receptors, and iron channels) can be targeted by using conventional drug discovery technologies. (16,17) The proteins that lack catalytic activity and/or have catalytic independent functions are still regarded as “undruggable” targets. The involvement of Signal Transducer and Activator of Transcription 3 (STAT3) in the multiple signaling pathway makes it an attractive therapeutic target; however, the lack of an obviously druggable site on the surface of STAT3 limited the development of STAT3 inhibitors. Thus, there are still no effective drugs directly targeting STAT3 approved by the Food and Drug Administration (FDA). In November 2019, Shaomeng Wang’s group first reported a potent PROTAC targeting STAT3 with potent biological activities in vitro and in vivo. (18) This successful case confirms the key potential of PROTAC technology, especially in the field of “undruggable” targets, such as K-Ras, a tricky tumor target activated by multiple mutations as G12A, G12C, G12D, G12S, G12 V, G13C, and G13D in the clinic. (19)
(4)
Fast and reversible chemical knockdown strategy in vivo. Traditional genetic protein knockout technologies, zinc-finger nuclease (ZFN), transcription activator-like effector nuclease (TALEN), or CRISPR-Cas9, usually have a long cycle, irreversible mode of action, and high cost, which brings a lot of inconvenience for research, especially in nonhuman primates. In addition, these genetic animal models sometimes produce phenotypic misunderstanding due to potential gene compensation or gene mutation. More importantly, the traditional genetic method cannot be used to study the function of embryonic-lethal genes in vivo. Unlike DNA-based protein knockout technology, PROTACs knock down target proteins directly, rather than acting at the genome level, and are suitable for the functional study of embryonic-lethal proteins in adult organisms. In addition, PROTACs provide exquisite temporal control, allowing the knockdown of a target protein at specific time points and enabling the recovery of the target protein after withdrawal of drug treatment. As a new, rapid and reversible chemical knockdown method, PROTAC can be used as an effective supplement to the existing genetic tools. (20)

SOURCE

PROTAC Technology: Opportunities and Challenges
  • Hongying Gao
  • Xiuyun Sun
  • Yu Rao*

Cite this: ACS Med. Chem. Lett. 2020, 11, 3, 237–240

Goal in Drug Design: Eliminating both the enzymatic and nonenzymatic functions of kinase.

Work-in-Progress

Induction and Inhibition of Protein in Galectins Drug Design

Work-in-Progress

Screening Proteins in DeepMind’s AlphaFold DataBase

The company also released the underlying code for AlphaFold last week as open-source, allowing others to build on its work in the future.

Work-in-Progress

Other related research published in this Open Access Online Journal include the following:

Synthetic Biology in Drug Discovery

Peroxisome proliferator-activated receptor (PPAR-gamma) Receptors Activation: PPARγ transrepression  for Angiogenesis in Cardiovascular Disease and PPARγ transactivation for Treatment of Diabetes

Read Full Post »

Al is on the way to lead critical ED decisions on CT

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc

Artificial intelligence (AI) has infiltrated many organizational processes, raising concerns that robotic systems will eventually replace many humans in decision-making. The advent of AI as a tool for improving health care provides new prospects to improve patient and clinical team’s performance, reduce costs, and impact public health. Examples include, but are not limited to, automation; information synthesis for patients, “fRamily” (friends and family unpaid caregivers), and health care professionals; and suggestions and visualization of information for collaborative decision making.

In the emergency department (ED), patients with Crohn’s disease (CD) are routinely subjected to Abdomino-Pelvic Computed Tomography (APCT). It is necessary to diagnose clinically actionable findings (CAF) since they may require immediate intervention, which is typically surgical. Repeated APCTs, on the other hand, results in higher ionizing radiation exposure. The majority of APCT performance guidance is clinical and empiric. Emergency surgeons struggle to identify Crohn’s disease patients who actually require a CT scan to determine the source of acute abdominal distress.

Image Courtesy: Jim Coote via Pixabay https://www.aiin.healthcare/media/49446

Aid seems to be on the way. Researchers employed machine learning to accurately distinguish these sufferers from Crohn’s patients who appear with the same complaint but may safely avoid the recurrent exposure to contrast materials and ionizing radiation that CT would otherwise wreak on them.

The study entitled “Machine learning for selecting patients with Crohn’s disease for abdominopelvic computed tomography in the emergency department” was published on July 9 in Digestive and Liver Disease by gastroenterologists and radiologists at Tel Aviv University in Israel.

Retrospectively, Jacob Ollech and his fellow researcher have analyzed 101 emergency treatments of patients with Crohn’s who underwent abdominopelvic CT.

They were looking for examples where a scan revealed clinically actionable results. These were classified as intestinal blockage, perforation, intra-abdominal abscess, or complex fistula by the researchers.

On CT, 44 (43.5 %) of the 101 cases reviewed had such findings.

Ollech and colleagues utilized a machine-learning technique to design a decision-support tool that required only four basic clinical factors to test an AI approach for making the call.

The approach was successful in categorizing patients into low- and high-risk groupings. The researchers were able to risk-stratify patients based on the likelihood of clinically actionable findings on abdominopelvic CT as a result of their success.

Ollech and co-authors admit that their limited sample size, retrospective strategy, and lack of external validation are shortcomings.

Moreover, several patients fell into an intermediate risk category, implying that a standard workup would have been required to guide CT decision-making in a real-world situation anyhow.

Consequently, they generate the following conclusion:

We believe this study shows that a machine learning-based tool is a sound approach for better-selecting patients with Crohn’s disease admitted to the ED with acute gastrointestinal complaints about abdominopelvic CT: reducing the number of CTs performed while ensuring that patients with high risk for clinically actionable findings undergo abdominopelvic CT appropriately.

Main Source:

Konikoff, Tom, Idan Goren, Marianna Yalon, Shlomit Tamir, Irit Avni-Biron, Henit Yanai, Iris Dotan, and Jacob E. Ollech. “Machine learning for selecting patients with Crohn’s disease for abdominopelvic computed tomography in the emergency department.” Digestive and Liver Disease (2021). https://www.sciencedirect.com/science/article/abs/pii/S1590865821003340

Other Related Articles published in this Open Access Online Scientific Journal include the following:

Al App for People with Digestive Disorders

Reporter: Irina Robu, Ph.D.

https://pharmaceuticalintelligence.com/2019/06/24/ai-app-for-people-with-digestive-disorders/

Machine Learning (ML) in cancer prognosis prediction helps the researcher to identify multiple known as well as candidate cancer diver genes

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc

https://pharmaceuticalintelligence.com/2021/05/04/machine-learning-ml-in-cancer-prognosis-prediction-helps-the-researcher-to-identify-multiple-known-as-well-as-candidate-cancer-diver-genes/

Al System Used to Detect Lung Cancer

Reporter: Irina Robu, Ph.D.

https://pharmaceuticalintelligence.com/2019/06/28/ai-system-used-to-detect-lung-cancer/

Artificial Intelligence: Genomics & Cancer

https://pharmaceuticalintelligence.com/ai-in-genomics-cancer/

Yet another Success Story: Machine Learning to predict immunotherapy response

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc

https://pharmaceuticalintelligence.com/2021/07/06/yet-another-success-story-machine-learning-to-predict-immunotherapy-response/

Systemic Inflammatory Diseases as Crohn’s disease, Rheumatoid Arthritis and Longer Psoriasis Duration May Mean Higher CVD Risk

Reporter: Aviva Lev-Ari, PhD, RN

https://pharmaceuticalintelligence.com/2017/10/09/systemic-inflammatory-diseases-as-crohns-disease-rheumatoid-arthritis-and-longer-psoriasis-duration-may-mean-higher-cvd-risk/

Autoimmune Inflammatory Bowel Diseases: Crohn’s Disease & Ulcerative Colitis: Potential Roles for Modulation of Interleukins 17 and 23 Signaling for Therapeutics

Curators: Larry H Bernstein, MD FCAP and Aviva Lev-Ari, PhD, RN https://pharmaceuticalintelligence.com/2016/01/23/autoimmune-inflammtory-bowl-diseases-crohns-disease-ulcerative-colitis-potential-roles-for-modulation-of-interleukins-17-and-23-signaling-for-therapeutics/

Inflammatory Disorders: Inflammatory Bowel Diseases (IBD) – Crohn’s and Ulcerative Colitis (UC) and Others

Curators: Larry H. Bernstein, MD, FCAP and Aviva Lev-Ari, PhD, RN

https://pharmaceuticalintelligence.com/gama-delta-epsilon-gde-is-a-global-holding-company-absorbing-lpbi/subsidiary-5-joint-ventures-for-ip-development-jvip/drug-discovery-with-3d-bioprinting/ibd-inflammatory-bowl-diseases-crohns-and-ulcerative-colitis/

Read Full Post »

From High-Throughput Assay to Systems Biology: New Tools for Drug Discovery

Curator: Stephen J. Williams, PhD

Marc W. Kirschner*

Department of Systems Biology
Harvard Medical School

Boston, Massachusetts 02115

With the new excitement about systems biology, there is understandable interest in a definition. This has proven somewhat difficult. Scientific fields, like spe­cies, arise by descent with modification, so in their ear­liest forms even the founders of great dynasties are only marginally different than their sister fields and spe­cies. It is only in retrospect that we can recognize the significant founding events. Before embarking on a def­inition of systems biology, it may be worth remember­ing that confusion and controversy surrounded the in­troduction of the term “molecular biology,” with claims that it hardly differed from biochemistry. Yet in retro­spect molecular biology was new and different. It intro­duced both new subject matter and new technological approaches, in addition to a new style.

As a point of departure for systems biology, consider the quintessential experiment in the founding of molec­ular biology, the one gene one enzyme hypothesis of Beadle and Tatum. This experiment first connected the genotype directly to the phenotype on a molecular level, although efforts in that direction can certainly be found in the work of Archibald Garrod, Sewell Wright, and others. Here a protein (in this case an enzyme) is seen to be a product of a single gene, and a single function; the completion of a specific step in amino acid biosynthesis is the direct result. It took the next 30 years to fill in the gaps in this process. Yet the one gene one enzyme hypothesis looks very different to us today. What is the function of tubulin, of PI-3 kinase or of rac? Could we accurately predict the phenotype of a nonle­thal mutation in these genes in a multicellular organ­ism? Although we can connect structure to the gene, we can no longer infer its larger purpose in the cell or in the organism. There are too many purposes; what the protein does is defined by context. The context also includes a history, either developmental or physiologi­cal. Thus the behavior of the Wnt signaling pathway depends on the previous lineage, the “where and when” questions of embryonic development. Similarly the behavior of the immune system depends on previ­ous experience in a variable environment. All of these features stress how inadequate an explanation for function we can achieve solely by trying to identify genes (by annotating them!) and characterizing their transcriptional control circuits.

That we are at a crossroads in how to explore biology is not at all clear to many. Biology is hardly in its dotage; the process of discovery seems to have been per­fected, accelerated, and made universally applicable to all fields of biology. With the completion of the human genome and the genomes of other species, we have a glimpse of many more genes than we ever had before to study. We are like naturalists discovering a new con­tinent, enthralled with the diversity itself. But we have also at the same time glimpsed the finiteness of this list of genes, a disturbingly small list. We have seen that the diversity of genes cannot approximate the diversity of functions within an organism. In response, we have argued that combinatorial use of small numbers of components can generate all the diversity that is needed. This has had its recent incarnation in the sim­plistic view that the rules of cis-regulatory control on DNA can directly lead to an understanding of organ­isms and their evolution. Yet this assumes that the gene products can be linked together in arbitrary combina­tions, something that is not assured in chemistry. It also downplays the significant regulatory features that in­volve interactions between gene products, their local­ization, binding, posttranslational modification, degra­dation, etc. The big question to understand in biology is not regulatory linkage but the nature of biological systems that allows them to be linked together in many nonlethal and even useful combinations. More and more we come to realize that understanding the con­served genes and their conserved circuits will require an understanding of their special properties that allow them to function together to generate different pheno­types in different tissues of metazoan organisms. These circuits may have certain robustness, but more impor­tant they have adaptability and versatility. The ease of putting conserved processes under regulatory control is an inherent design feature of the processes them­selves. Among other things it loads the deck in evolu­tionary variation and makes it more feasible to generate useful phenotypes upon which selection can act.

Systems biology offers an opportunity to study how the phenotype is generated from the genotype and with it a glimpse of how evolution has crafted the pheno­type. One aspect of systems biology is the develop­ment of techniques to examine broadly the level of pro­tein, RNA, and DNA on a gene by gene basis and even the posttranslational modification and localization of proteins. In a very short time we have witnessed the development of high-throughput biology, forcing us to consider cellular processes in toto. Even though much of the data is noisy and today partially inconsistent and incomplete, this has been a radical shift in the way we tear apart problems one interaction at a time. When coupled with gene deletions by RNAi and classical methods, and with the use of chemical tools tailored to proteins and protein domains, these high-throughput techniques become still more powerful.

High-throughput biology has opened up another im­portant area of systems biology: it has brought us out into the field again or at least made us aware that there is a world outside our laboratories. Our model systems have been chosen intentionally to be of limited genetic diversity and examined in a highly controlled and repro­ducible environment. The real world of ecology, evolu­tion, and human disease is a very different place. When genetics separated from the rest of biology in the early part of the 20th century, most geneticists sought to understand heredity and chose to study traits in the organism that could be easily scored and could be used to reveal genetic mechanisms. This was later ex­tended to powerful effect to use genetics to study cell biological and developmental mechanisms. Some ge­neticists, including a large school in Russia in the early 20th century, continued to study the genetics of natural populations, focusing on traits important for survival. That branch of genetics is coming back strongly with the power of phenotypic assays on the RNA and pro­tein level. As human beings we are most concerned not with using our genetic misfortunes to unravel biology’s complexity (important as that is) but with the role of our genetics in our individual survival. The context for understanding this is still not available, even though the data are now coming in torrents, for many of the genes that will contribute to our survival will have small quan­titative effects, partially masked or accentuated by other genetic and environmental conditions. To under­stand the genetic basis of disease will require not just mapping these genes but an understanding of how the phenotype is created in the first place and the messy interactions between genetic variation and environ­mental variation.

Extracts and explants are relatively accessible to syn­thetic manipulation. Next there is the explicit recon­struction of circuits within cells or the deliberate modifi­cation of those circuits. This has occurred for a while in biology, but the difference is that now we wish to construct or intervene with the explicit purpose of de­scribing the dynamical features of these synthetic or partially synthetic systems. There are more and more tools to intervene and more and more tools to measure. Although these fall short of total descriptions of cells and organisms, the detailed information will give us a sense of the special life-like processes of circuits, pro­teins, cells in tissues, and whole organisms in their en­vironment. This meso-scale systems biology will help establish the correspondence between molecules and large-scale physiology.

You are probably running out of patience for some definition of systems biology. In any case, I do not think the explicit definition of systems biology should come from me but should await the words of the first great modern systems biologist. She or he is probably among us now. However, if forced to provide some kind of label for systems biology, I would simply say that systems biology is the study of the behavior of complex biologi­cal organization and processes in terms of the molecu­lar constituents. It is built on molecular biology in its special concern for information transfer, on physiology for its special concern with adaptive states of the cell and organism, on developmental biology for the impor­tance of defining a succession of physiological states in that process, and on evolutionary biology and ecol­ogy for the appreciation that all aspects of the organ­ism are products of selection, a selection we rarely understand on a molecular level. Systems biology attempts all of this through quantitative measurement, modeling, reconstruction, and theory. Systems biology is not a branch of physics but differs from physics in that the primary task is to understand how biology gen­erates variation. No such imperative to create variation exists in the physical world. It is a new principle that Darwin understood and upon which all of life hinges. That sounds different enough for me to justify a new field and a new name. Furthermore, the success of sys­tems biology is essential if we are to understand life; its success is far from assured—a good field for those seeking risk and adventure.

Source: “Meaning of Systems Biology” Cell, Vol. 121, 503–504, May 20, 2005, DOI 10.1016/j.cell.2005.05.005

Old High-throughput Screening, Once the Gold Standard in Drug Development, Gets a Systems Biology Facelift

From Phenotypic Hit to Chemical Probe: Chemical Biology Approaches to Elucidate Small Molecule Action in Complex Biological Systems

Quentin T. L. Pasquer, Ioannis A. Tsakoumagkos and Sascha Hoogendoorn 

Molecules 202025(23), 5702; https://doi.org/10.3390/molecules25235702

Abstract

Biologically active small molecules have a central role in drug development, and as chemical probes and tool compounds to perturb and elucidate biological processes. Small molecules can be rationally designed for a given target, or a library of molecules can be screened against a target or phenotype of interest. Especially in the case of phenotypic screening approaches, a major challenge is to translate the compound-induced phenotype into a well-defined cellular target and mode of action of the hit compound. There is no “one size fits all” approach, and recent years have seen an increase in available target deconvolution strategies, rooted in organic chemistry, proteomics, and genetics. This review provides an overview of advances in target identification and mechanism of action studies, describes the strengths and weaknesses of the different approaches, and illustrates the need for chemical biologists to integrate and expand the existing tools to increase the probability of evolving screen hits to robust chemical probes.

5.1.5. Large-Scale Proteomics

While FITExP is based on protein expression regulation during apoptosis, a study of Ruprecht et al. showed that proteomic changes are induced both by cytotoxic and non-cytotoxic compounds, which can be detected by mass spectrometry to give information on a compound’s mechanism of action. They developed a large-scale proteome-wide mass spectrometry analysis platform for MOA studies, profiling five lung cancer cell lines with over 50 drugs. Aggregation analysis over the different cell lines and the different compounds showed that one-quarter of the drugs changed the abundance of their protein target. This approach allowed target confirmation of molecular degraders such as PROTACs or molecular glues. Finally, this method yielded unexpected off-target mechanisms for the MAP2K1/2 inhibitor PD184352 and the ALK inhibitor ceritinib [97]. While such a mapping approach clearly provides a wealth of information, it might not be easily attainable for groups that are not equipped for high-throughput endeavors.

All-in-all, mass spectrometry methods have gained a lot of traction in recent years and have been successfully applied for target deconvolution and MOA studies of small molecules. As with all high-throughput methods, challenges lie in the accessibility of the instruments (both from a time and cost perspective) and data analysis of complex and extensive data sets.

5.2. Genetic Approaches

Both label-based and mass spectrometry proteomic approaches are based on the physical interaction between a small molecule and a protein target, and focus on the proteome for target deconvolution. It has been long realized that genetics provides an alternative avenue to understand a compound’s action, either through precise modification of protein levels, or by inducing protein mutations. First realized in yeast as a genetically tractable organism over 20 years ago, recent advances in genetic manipulation of mammalian cells have opened up important opportunities for target identification and MOA studies through genetic screening in relevant cell types [98]. Genetic approaches can be roughly divided into two main areas, with the first centering on the identification of mutations that confer compound resistance (Figure 3a), and the second on genome-wide perturbation of gene function and the concomitant changes in sensitivity to the compound (Figure 3b). While both methods can be used to identify or confirm drug targets, the latter category often provides many additional insights in the compound’s mode of action.

Figure 3. Genetic methods for target identification and mode of action studies. Schematic representations of (a) resistance cloning, and (b) chemogenetic interaction screens.

5.2.1. Resistance Cloning

The “gold standard” in drug target confirmation is to identify mutations in the presumed target protein that render it insensitive to drug treatment. Conversely, different groups have sought to use this principle as a target identification method based on the concept that cells grown in the presence of a cytotoxic drug will either die or develop mutations that will make them resistant to the compound. With recent advances in deep sequencing it is now possible to then scan the transcriptome [99] or genome [100] of the cells for resistance-inducing mutations. Genes that are mutated are then hypothesized to encode the protein target. For this approach to be successful, there are two initial requirements: (1) the compound needs to be cytotoxic for resistant clones to arise, and (2) the cell line needs to be genetically unstable for mutations to occur in a reasonable timeframe.

In 2012, the Kapoor group demonstrated in a proof-of-concept study that resistance cloning in mammalian cells, coupled to transcriptome sequencing (RNA-seq), yields the known polo-like kinase 1 (PLK1) target of the small molecule BI 2536. For this, they used the cancer cell line HCT-116, which is deficient in mismatch repair and consequently prone to mutations. They generated and sequenced multiple resistant clones, and clustered the clones based on similarity. PLK1 was the only gene that was mutated in multiple groups. Of note, one of the groups did not contain PLK1 mutations, but rather developed resistance through upregulation of ABCBA1, a drug efflux transporter, which is a general and non-specific resistance mechanism [101]. In a following study, they optimized their pipeline “DrugTargetSeqR”, by counter-screening for these types of multidrug resistance mechanisms so that these clones were excluded from further analysis (Figure 3a). Furthermore, they used CRISPR/Cas9-mediated gene editing to determine which mutations were sufficient to confer drug resistance, and as independent validation of the biochemical relevance of the obtained hits [102].

While HCT-116 cells are a useful model cell line for resistance cloning because of their genomic instability, they may not always be the cell line of choice, depending on the compound and process that is studied. Povedana et al. used CRISPR/Cas9 to engineer mismatch repair deficiencies in Ewing sarcoma cells and small cell lung cancer cells. They found that deletion of MSH2 results in hypermutations in these normally mutationally silent cells, resulting in the formation of resistant clones in the presence of bortezomib, MLN4924, and CD437, which are all cytotoxic compounds [103]. Recently, Neggers et al. reasoned that CRISPR/Cas9-induced non-homologous end-joining repair could be a viable strategy to create a wide variety of functional mutants of essential genes through in-frame mutations. Using a tiled sgRNA library targeting 75 target genes of investigational neoplastic drugs in HAP1 and K562 cells, they generated several KPT-9274 (an anticancer agent with unknown target)-resistant clones, and subsequent deep sequencing showed that the resistant clones were enriched in NAMPT sgRNAs. Direct target engagement was confirmed by co-crystallizing the compound with NAMPT [104]. In addition to these genetic mutation strategies, an alternative method is to grow the cells in the presence of a mutagenic chemical to induce higher mutagenesis rates [105,106].

When there is already a hypothesis on the pathway involved in compound action, the resistance cloning methodology can be extended to non-cytotoxic compounds. Sekine et al. developed a fluorescent reporter model for the integrated stress response, and used this cell line for target deconvolution of a small molecule inhibitor towards this pathway (ISRIB). Reporter cells were chemically mutagenized, and ISRIB-resistant clones were isolated by flow cytometry, yielding clones with various mutations in the delta subunit of guanine nucleotide exchange factor eIF2B [107].

While there are certainly successful examples of resistance cloning yielding a compound’s direct target as discussed above, resistance could also be caused by mutations or copy number alterations in downstream components of a signaling pathway. This is illustrated by clinical examples of acquired resistance to small molecules, nature’s way of “resistance cloning”. For example, resistance mechanisms in Hedgehog pathway-driven cancers towards the Smoothened inhibitor vismodegib include compound-resistant mutations in Smoothened, but also copy number changes in downstream activators SUFU and GLI2 [108]. It is, therefore, essential to conduct follow-up studies to confirm a direct interaction between a compound and the hit protein, as well as a lack of interaction with the mutated protein.

5.2.3. “Chemogenomics”: Examples of Gene-Drug Interaction Screens

When genetic perturbations are combined with small molecule drugs in a chemogenetic interaction screen, the effect of a gene’s perturbation on compound action is studied. Gene perturbation can render the cells resistant to the compound (suppressor interaction), or conversely, result in hypersensitivity and enhanced compound potency (synergistic interaction) [5,117,121]. Typically, cells are treated with the compound at a sublethal dose, to ascertain that both types of interactions can be found in the final dataset, and often it is necessary to use a variety of compound doses (i.e., LD20, LD30, LD50) and timepoints to obtain reliable insights (Figure 3b).

An early example of successful coupling of a phenotypic screen and downstream genetic screening for target identification is the study of Matheny et al. They identified STF-118804 as a compound with antileukemic properties. Treatment of MV411 cells, stably transduced with a high complexity, genome-wide shRNA library, with STF-118804 (4 rounds of increasing concentration) or DMSO control resulted in a marked depletion of cells containing shRNAs against nicotinamide phosphoribosyl transferase (NAMPT) [122].

The Bassik lab subsequently directly compared the performance of shRNA-mediated knockdown versus CRISPR/Cas9-knockout screens for the target elucidation of the antiviral drug GSK983. The data coming out of both screens were complementary, with the shRNA screen resulting in hits leading to the direct compound target and the CRISPR screen giving information on cellular mechanisms of action of the compound. A reason for this is likely the level of protein depletion that is reached by these methods: shRNAs lead to decreased protein levels, which is advantageous when studying essential genes. However, knockdown may not result in a phenotype for non-essential genes, in which case a full CRISPR-mediated knockout is necessary to observe effects [123].

Another NAMPT inhibitor was identified in a CRISPR/Cas9 “haplo-insufficiency (HIP)”-like approach [124]. Haploinsuffiency profiling is a well-established system in yeast which is performed in a ~50% protein background by heterozygous deletions [125]. As there is no control over CRISPR-mediated loss of alleles, compound treatment was performed at several timepoints after addition of the sgRNA library to HCT116 cells stably expressing Cas9, in the hope that editing would be incomplete at early timepoints, resulting in residual protein levels. Indeed, NAMPT was found to be the target of phenotypic hit LB-60-OF61, especially at earlier timepoints, confirming the hypothesis that some level of protein needs to be present to identify a compound’s direct target [124]. This approach was confirmed in another study, thereby showing that direct target identification through CRISPR-knockout screens is indeed possible [126].

An alternative strategy was employed by the Weissman lab, where they combined genome-wide CRISPR-interference and -activation screens to identify the target of the phase 3 drug rigosertib. They focused on hits that had opposite action in both screens, as in sensitizing in one but protective in the other, which were related to microtubule stability. In a next step, they created chemical-genetic profiles of a variety of microtubule destabilizing agents, rationalizing that compounds with the same target will have similar drug-gene interactions. For this, they made a focused library of sgRNAs, based on the most high-ranking hits in the rigosertib genome-wide CRISPRi screen, and compared the focused screen results of the different compounds. The profile for rigosertib clustered well with that of ABT-571, and rigorous target validation studies confirmed rigosertib binding to the colchicine binding site of tubulin—the same site as occupied by ABT-571 [127].

From the above examples, it is clear that genetic screens hold a lot of promise for target identification and MOA studies for small molecules. The CRISPR screening field is rapidly evolving, sgRNA libraries are continuously improving and increasingly commercially available, and new tools for data analysis are being developed [128]. The challenge lies in applying these screens to study compounds that are not cytotoxic, where finding the right dosage regimen will not be trivial.

SYSTEMS BIOLOGY AND CANCER RESEARCH & DRUG DISCOVERY

Integrative Analysis of Next-Generation Sequencing for Next-Generation Cancer Research toward Artificial Intelligence

Youngjun Park, Dominik Heider and Anne-Christin Hauschild. Cancers 202113(13), 3148; https://doi.org/10.3390/cancers13133148

Abstract

The rapid improvement of next-generation sequencing (NGS) technologies and their application in large-scale cohorts in cancer research led to common challenges of big data. It opened a new research area incorporating systems biology and machine learning. As large-scale NGS data accumulated, sophisticated data analysis methods became indispensable. In addition, NGS data have been integrated with systems biology to build better predictive models to determine the characteristics of tumors and tumor subtypes. Therefore, various machine learning algorithms were introduced to identify underlying biological mechanisms. In this work, we review novel technologies developed for NGS data analysis, and we describe how these computational methodologies integrate systems biology and omics data. Subsequently, we discuss how deep neural networks outperform other approaches, the potential of graph neural networks (GNN) in systems biology, and the limitations in NGS biomedical research. To reflect on the various challenges and corresponding computational solutions, we will discuss the following three topics: (i) molecular characteristics, (ii) tumor heterogeneity, and (iii) drug discovery. We conclude that machine learning and network-based approaches can add valuable insights and build highly accurate models. However, a well-informed choice of learning algorithm and biological network information is crucial for the success of each specific research question

1. Introduction

The development and widespread use of high-throughput technologies founded the era of big data in biology and medicine. In particular, it led to an accumulation of large-scale data sets that opened a vast amount of possible applications for data-driven methodologies. In cancer, these applications range from fundamental research to clinical applications: molecular characteristics of tumors, tumor heterogeneity, drug discovery and potential treatments strategy. Therefore, data-driven bioinformatics research areas have tailored data mining technologies such as systems biology, machine learning, and deep learning, elaborated in this review paper (see Figure 1 and Figure 2). For example, in systems biology, data-driven approaches are applied to identify vital signaling pathways [1]. This pathway-centric analysis is particularly crucial in cancer research to understand the characteristics and heterogeneity of the tumor and tumor subtypes. Consequently, this high-throughput data-based analysis enables us to explore characteristics of cancers with a systems biology and a systems medicine point of view [2].Combining high-throughput techniques, especially next-generation sequencing (NGS), with appropriate analytical tools has allowed researchers to gain a deeper systematic understanding of cancer at various biological levels, most importantly genomics, transcriptomics, and epigenetics [3,4]. Furthermore, more sophisticated analysis tools based on computational modeling are introduced to decipher underlying molecular mechanisms in various cancer types. The increasing size and complexity of the data required the adaptation of bioinformatics processing pipelines for higher efficiency and sophisticated data mining methodologies, particularly for large-scale, NGS datasets [5]. Nowadays, more and more NGS studies integrate a systems biology approach and combine sequencing data with other types of information, for instance, protein family information, pathway, or protein–protein interaction (PPI) networks, in an integrative analysis. Experimentally validated knowledge in systems biology may enhance analysis models and guides them to uncover novel findings. Such integrated analyses have been useful to extract essential information from high-dimensional NGS data [6,7]. In order to deal with the increasing size and complexity, the application of machine learning, and specifically deep learning methodologies, have become state-of-the-art in NGS data analysis.

Figure 1. Next-generation sequencing data can originate from various experimental and technological conditions. Depending on the purpose of the experiment, one or more of the depicted omics types (Genomics, Transcriptomics, Epigenomics, or Single-Cell Omics) are analyzed. These approaches led to an accumulation of large-scale NGS datasets to solve various challenges of cancer research, molecular characterization, tumor heterogeneity, and drug target discovery. For instance, The Cancer Genome Atlas (TCGA) dataset contains multi-omics data from ten-thousands of patients. This dataset facilitates a variety of cancer researches for decades. Additionally, there are also independent tumor datasets, and, frequently, they are analyzed and compared with the TCGA dataset. As the large scale of omics data accumulated, various machine learning techniques are applied, e.g., graph algorithms and deep neural networks, for dimensionality reduction, clustering, or classification. (Created with BioRender.com.)

Figure 2. (a) A multitude of different types of data is produced by next-generation sequencing, for instance, in the fields of genomics, transcriptomics, and epigenomics. (b) Biological networks for biomarker validation: The in vivo or in vitro experiment results are considered ground truth. Statistical analysis on next-generation sequencing data produces candidate genes. Biological networks can validate these candidate genes and highlight the underlying biological mechanisms (Section 2.1). (c) De novo construction of Biological Networks: Machine learning models that aim to reconstruct biological networks can incorporate prior knowledge from different omics data. Subsequently, the model will predict new unknown interactions based on new omics information (Section 2.2). (d) Network-based machine learning: Machine learning models integrating biological networks as prior knowledge to improve predictive performance when applied to different NGS data (Section 2.3). (Created with BioRender.com).

Therefore, a large number of studies integrate NGS data with machine learning and propose a novel data-driven methodology in systems biology [8]. In particular, many network-based machine learning models have been developed to analyze cancer data and help to understand novel mechanisms in cancer development [9,10]. Moreover, deep neural networks (DNN) applied for large-scale data analysis improved the accuracy of computational models for mutation prediction [11,12], molecular subtyping [13,14], and drug repurposing [15,16]. 

2. Systems Biology in Cancer Research

Genes and their functions have been classified into gene sets based on experimental data. Our understandings of cancer concentrated into cancer hallmarks that define the characteristics of a tumor. This collective knowledge is used for the functional analysis of unseen data.. Furthermore, the regulatory relationships among genes were investigated, and, based on that, a pathway can be composed. In this manner, the accumulation of public high-throughput sequencing data raised many big-data challenges and opened new opportunities and areas of application for computer science. Two of the most vibrantly evolving areas are systems biology and machine learning which tackle different tasks such as understanding the cancer pathways [9], finding crucial genes in pathways [22,53], or predicting functions of unidentified or understudied genes [54]. Essentially, those models include prior knowledge to develop an analysis and enhance interpretability for high-dimensional data [2]. In addition to understanding cancer pathways with in silico analysis, pathway activity analysis incorporating two different types of data, pathways and omics data, is developed to understand heterogeneous characteristics of the tumor and cancer molecular subtyping. Due to its advantage in interpretability, various pathway-oriented methods are introduced and become a useful tool to understand a complex diseases such as cancer [55,56,57].

In this section, we will discuss how two related research fields, namely, systems biology and machine learning, can be integrated with three different approaches (see Figure 2), namely, biological network analysis for biomarker validation, the use of machine learning with systems biology, and network-based models.

2.1. Biological Network Analysis for Biomarker Validation

The detection of potential biomarkers indicative of specific cancer types or subtypes is a frequent goal of NGS data analysis in cancer research. For instance, a variety of bioinformatics tools and machine learning models aim at identify lists of genes that are significantly altered on a genomic, transcriptomic, or epigenomic level in cancer cells. Typically, statistical and machine learning methods are employed to find an optimal set of biomarkers, such as single nucleotide polymorphisms (SNPs), mutations, or differentially expressed genes crucial in cancer progression. Traditionally, resource-intensive in vitro analysis was required to discover or validate those markers. Therefore, systems biology offers in silico solutions to validate such findings using biological pathways or gene ontology information (Figure 2b) [58]. Subsequently, gene set enrichment analysis (GSEA) [50] or gene set analysis (GSA) [59] can be used to evaluate whether these lists of genes are significantly associated with cancer types and their specific characteristics. GSA, for instance, is available via web services like DAVID [60] and g:Profiler [61]. Moreover, other applications use gene ontology directly [62,63]. In addition to gene-set-based analysis, there are other methods that focuse on the topology of biological networks. These approaches evaluate various network structure parameters and analyze the connectivity of two genes or the size and interconnection of their neighbors [64,65]. According to the underlying idea, the mutated gene will show dysfunction and can affect its neighboring genes. Thus, the goal is to find abnormalities in a specific set of genes linked with an edge in a biological network. For instance, KeyPathwayMiner can extract informative network modules in various omics data [66]. In summary, these approaches aim at predicting the effect of dysfunctional genes among neighbors according to their connectivity or distances from specific genes such as hubs [67,68]. During the past few decades, the focus of cancer systems biology extended towards the analysis of cancer-related pathways since those pathways tend to carry more information than a gene set. Such analysis is called Pathway Enrichment Analysis (PEA) [69,70]. The use of PEA incorporates the topology of biological networks. However, simultaneously, the lack of coverage issue in pathway data needs to be considered. Because pathway data does not cover all known genes yet, an integration analysis on omics data can significantly drop in genes when incorporated with pathways. Genes that can not be mapped to any pathway are called ‘pathway orphan.’ In this manner, Rahmati et al. introduced a possible solution to overcome the ‘pathway orphan’ issue [71]. At the bottom line, regardless of whether researchers consider gene-set or pathway-based enrichment analysis, the performance and accuracy of both methods are highly dependent on the quality of the external gene-set and pathway data [72].

2.2. De Novo Construction of Biological Networks

While the known fraction of existing biological networks barely scratches the surface of the whole system of mechanisms occurring in each organism, machine learning models can improve on known network structures and can guide potential new findings [73,74]. This area of research is called de novo network construction (Figure 2c), and its predictive models can accelerate experimental validation by lowering time costs [75,76]. This interplay between in silico biological networks building and mining contributes to expanding our knowledge in a biological system. For instance, a gene co-expression network helps discover gene modules having similar functions [77]. Because gene co-expression networks are based on expressional changes under specific conditions, commonly, inferring a co-expression network requires many samples. The WGCNA package implements a representative model using weighted correlation for network construction that leads the development of the network biology field [78]. Due to NGS developments, the analysis of gene co-expression networks subsequently moved from microarray-based to RNA-seq based experimental data [79]. However, integration of these two types of data remains tricky. Ballouz et al. compared microarray and NGS-based co-expression networks and found the existence of a bias originating from batch effects between the two technologies [80]. Nevertheless, such approaches are suited to find disease-specific co-expressional gene modules. Thus, various studies based on the TCGA cancer co-expression network discovered characteristics of prognostic genes in the network [81]. Accordingly, a gene co-expression network is a condition-specific network rather than a general network for an organism. Gene regulatory networks can be inferred from the gene co-expression network when various data from different conditions in the same organism are available. Additionally, with various NGS applications, we can obtain multi-modal datasets about regulatory elements and their effects, such as epigenomic mechanisms on transcription and chromatin structure. Consequently, a gene regulatory network can consist of solely protein-coding genes or different regulatory node types such as transcription factors, inhibitors, promoter interactions, DNA methylations, and histone modifications affecting the gene expression system [82,83]. More recently, researchers were able to build networks based on a particular experimental setup. For instance, functional genomics or CRISPR technology enables the high-resolution regulatory networks in an organism [84]. Other than gene co-expression or regulatory networks, drug target, and drug repurposing studies are active research areas focusing on the de novo construction of drug-to-target networks to allow the potential repurposing of drugs [76,85].

2.3. Network Based Machine Learning

A network-based machine learning model directly integrates the insights of biological networks within the algorithm (Figure 2d) to ultimately improve predictive performance concerning cancer subtyping or susceptibility to therapy. Following the establishment of high-quality biological networks based on NGS technologies, these biological networks were suited to be integrated into advanced predictive models. In this manner, Zhang et al., categorized network-based machine learning approaches upon their usage into three groups: (i) model-based integration, (ii) pre-processing integration, and (iii) post-analysis integration [7]. Network-based models map the omics data onto a biological network, and proper algorithms travel the network while considering both values of nodes and edges and network topology. In the pre-processing integration, pathway or other network information is commonly processed based on its topological importance. Meanwhile, in the post-analysis integration, omics data is processed solely before integration with a network. Subsequently, omics data and networks are merged and interpreted. The network-based model has advantages in multi-omics integrative analysis. Due to the different sensitivity and coverage of various omics data types, a multi-omics integrative analysis is challenging. However, focusing on gene-level or protein-level information enables a straightforward integration [86,87]. Consequently, when different machine learning approaches tried to integrate two or more different data types to find novel biological insights, one of the solutions is reducing the search space to gene or protein level and integrated heterogeneous datatypes [25,88].

In summary, using network information opens new possibilities for interpretation. However, as mentioned earlier, several challenges remain, such as the coverage issue. Current databases for biological networks do not cover the entire set of genes, transcripts, and interactions. Therefore, the use of networks can lead to loss of information for gene or transcript orphans. The following section will focus on network-based machine learning models and their application in cancer genomics. We will put network-based machine learning into the perspective of the three main areas of application, namely, molecular characterization, tumor heterogeneity analysis, and cancer drug discovery.

3. Network-Based Learning in Cancer Research

As introduced previously, the integration of machine learning with the insights of biological networks (Figure 2d) ultimately aims at improving predictive performance and interpretability concerning cancer subtyping or treatment susceptibility.

3.1. Molecular Characterization with Network Information

Various network-based algorithms are used in genomics and focus on quantifying the impact of genomic alteration. By employing prior knowledge in biological network algorithms, performance compared to non-network models can be improved. A prominent example is HotNet. The algorithm uses a thermodynamics model on a biological network and identifies driver genes, or prognostic genes, in pan-cancer data [89]. Another study introduced a network-based stratification method to integrate somatic alterations and expression signatures with network information [90]. These approaches use network topology and network-propagation-like algorithms. Network propagation presumes that genomic alterations can affect the function of neighboring genes. Two genes will show an exclusive pattern if two genes complement each other, and the function carried by those two genes is essential to an organism [91]. This unique exclusive pattern among genomic alteration is further investigated in cancer-related pathways. Recently, Ku et al. developed network-centric approaches and tackled robustness issues while studying synthetic lethality [92]. Although synthetic lethality was initially discovered in model organisms of genetics, it helps us to understand cancer-specific mutations and their functions in tumor characteristics [91].

Furthermore, in transcriptome research, network information is used to measure pathway activity and its application in cancer subtyping. For instance, when comparing the data of two or more conditions such as cancer types, GSEA as introduced in Section 2 is a useful approach to get an overview of systematic changes [50]. It is typically used at the beginning of a data evaluation [93]. An experimentally validated gene set can provide information about how different conditions affect molecular systems in an organism. In addition to the gene sets, different approaches integrate complex interaction information into GSEA and build network-based models [70]. In contrast to GSEA, pathway activity analysis considers transcriptome data and other omics data and structural information of a biological network. For example, PARADIGM uses pathway topology and integrates various omics in the analysis to infer a patient-specific status of pathways [94]. A benchmark study with pan-cancer data recently reveals that using network structure can show better performance [57]. In conclusion, while the loss of data is due to the incompleteness of biological networks, their integration improved performance and increased interpretability in many cases.

3.2. Tumor Heterogeneity Study with Network Information

The tumor heterogeneity can originate from two directions, clonal heterogeneity and tumor impurity. Clonal heterogeneity covers genomic alterations within the tumor [95]. While de novo mutations accumulate, the tumor obtains genomic alterations with an exclusive pattern. When these genomic alterations are projected on the pathway, it is possible to observe exclusive relationships among disease-related genes. For instance, the CoMEt and MEMo algorithms examine mutual exclusivity on protein–protein interaction networks [96,97]. Moreover, the relationship between genes can be essential for an organism. Therefore, models analyzing such alterations integrate network-based analysis [98].

In contrast, tumor purity is dependent on the tumor microenvironment, including immune-cell infiltration and stromal cells [99]. In tumor microenvironment studies, network-based models are applied, for instance, to find immune-related gene modules. Although the importance of the interaction between tumors and immune cells is well known, detailed mechanisms are still unclear. Thus, many recent NGS studies employ network-based models to investigate the underlying mechanism in tumor and immune reactions. For example, McGrail et al. identified a relationship between the DNA damage response protein and immune cell infiltration in cancer. The analysis is based on curated interaction pairs in a protein–protein interaction network [100]. Most recently, Darzi et al. discovered a prognostic gene module related to immune cell infiltration by using network-centric approaches [101]. Tu et al. presented a network-centric model for mining subnetworks of genes other than immune cell infiltration by considering tumor purity [102].

3.3. Drug Target Identification with Network Information

In drug target studies, network biology is integrated into pharmacology [103]. For instance, Yamanishi et al. developed novel computational methods to investigate the pharmacological space by integrating a drug-target protein network with genomics and chemical information. The proposed approaches investigated such drug-target network information to identify potential novel drug targets [104]. Since then, the field has continued to develop methods to study drug target and drug response integrating networks with chemical and multi-omic datasets. In a recent survey study by Chen et al., the authors compared 13 computational methods for drug response prediction. It turned out that gene expression profiles are crucial information for drug response prediction [105].

Moreover, drug-target studies are often extended to drug-repurposing studies. In cancer research, drug-repurposing studies aim to find novel interactions between non-cancer drugs and molecular features in cancer. Drug-repurposing (or repositioning) studies apply computational approaches and pathway-based models and aim at discovering potential new cancer drugs with a higher probability than de novo drug design [16,106]. Specifically, drug-repurposing studies can consider various areas of cancer research, such as tumor heterogeneity and synthetic lethality. As an example, Lee et al. found clinically relevant synthetic lethality interactions by integrating multiple screening NGS datasets [107]. This synthetic lethality and related-drug datasets can be integrated for an effective combination of anticancer therapeutic strategy with non-cancer drug repurposing.

4. Deep Learning in Cancer Research

DNN models develop rapidly and become more sophisticated. They have been frequently used in all areas of biomedical research. Initially, its development was facilitated by large-scale imaging and video data. While most data sets in the biomedical field would not typically be considered big data, the rapid data accumulation enabled by NGS made it suitable for the application of DNN models requiring a large amount of training data [108]. For instance, in 2019, Samiei et al. used TCGA-based large-scale cancer data as benchmark datasets for bioinformatics machine learning research such as Image-Net in the computer vision field [109]. Subsequently, large-scale public cancer data sets such as TCGA encouraged the wide usage of DNNs in the cancer domain [110]. Over the last decade, these state-of-the-art machine learning methods have been incorporated in many different biological questions [111].

In addition to public cancer databases such as TCGA, the genetic information of normal tissues is stored in well-curated databases such as GTEx [112] and 1000Genomes [113]. These databases are frequently used as control or baseline training data for deep learning [114]. Moreover, other non-curated large-scale data sources such as GEO (https://www.ncbi.nlm.nih.gov/geo/, accessed on 20 May 2021) can be leveraged to tackle critical aspects in cancer research. They store a large-scale of biological data produced under various experimental setups (Figure 1). Therefore, an integration of GEO data and other data requires careful preprocessing. Overall, an increasing amount of datasets facilitate the development of current deep learning in bioinformatics research [115].

4.1. Challenges for Deep Learning in Cancer Research

Many studies in biology and medicine used NGS and produced large amounts of data during the past few decades, moving the field to the big data era. Nevertheless, researchers still face a lack of data in particular when investigating rare diseases or disease states. Researchers have developed a manifold of potential solutions to overcome this lack of data challenges, such as imputation, augmentation, and transfer learning (Figure 3b). Data imputation aims at handling data sets with missing values [116]. It has been studied on various NGS omics data types to recover missing information [117]. It is known that gene expression levels can be altered by different regulatory elements, such as DNA-binding proteins, epigenomic modifications, and post-transcriptional modifications. Therefore, various models integrating such regulatory schemes have been introduced to impute missing omics data [118,119]. Some DNN-based models aim to predict gene expression changes based on genomics or epigenomics alteration. For instance, TDimpute aims at generating missing RNA-seq data by training a DNN on methylation data. They used TCGA and TARGET (https://ocg.cancer.gov/programs/target/data-matrix, accessed on 20 May 2021) data as proof of concept of the applicability of DNN for data imputation in a multi-omics integration study [120]. Because this integrative model can exploit information in different levels of regulatory mechanisms, it can build a more detailed model and achieve better performance than a model build on a single-omics dataset [117,121]. The generative adversarial network (GAN) is a DNN structure for generating simulated data that is different from the original data but shows the same characteristics [122]. GANs can impute missing omics data from other multi-omics sources. Recently, the GAN algorithm is getting more attention in single-cell transcriptomics because it has been recognized as a complementary technique to overcome the limitation of scRNA-seq [123]. In contrast to data imputation and generation, other machine learning approaches aim to cope with a limited dataset in different ways. Transfer learning or few-shot learning, for instance, aims to reduce the search space with similar but unrelated datasets and guide the model to solve a specific set of problems [124]. These approaches train models with data of similar characteristics and types but different data to the problem set. After pre-training the model, it can be fine-tuned with the dataset of interest [125,126]. Thus, researchers are trying to introduce few-shot learning models and meta-learning approaches to omics and translational medicine. For example, Select-ProtoNet applied the ProtoTypical Network [127] model to TCGA transcriptome data and classified patients into two groups according to their clinical status [128]. AffinityNet predicts kidney and uterus cancer subtypes with gene expression profiles [129].

Figure 3. (a) In various studies, NGS data transformed into different forms. The 2-D transformed form is for the convolution layer. Omics data is transformed into pathway level, GO enrichment score, or Functional spectra. (b) DNN application on different ways to handle lack of data. Imputation for missing data in multi-omics datasets. GAN for data imputation and in silico data simulation. Transfer learning pre-trained the model with other datasets and fine-tune. (c) Various types of information in biology. (d) Graph neural network examples. GCN is applied to aggregate neighbor information. (Created with BioRender.com).

4.2. Molecular Charactization with Network and DNN Model

DNNs have been applied in multiple areas of cancer research. For instance, a DNN model trained on TCGA cancer data can aid molecular characterization by identifying cancer driver genes. At the very early stage, Yuan et al. build DeepGene, a cancer-type classifier. They implemented data sparsity reduction methods and trained the DNN model with somatic point mutations [130]. Lyu et al. [131] and DeepGx [132] embedded a 1-D gene expression profile to a 2-D array by chromosome order to implement the convolution layer (Figure 3a). Other algorithms, such as the deepDriver, use k-nearest neighbors for the convolution layer. A predefined number of neighboring gene mutation profiles was the input for the convolution layer. It employed this convolution layer in a DNN by aggregating mutation information of the k-nearest neighboring genes [11]. Instead of embedding to a 2-D image, DeepCC transformed gene expression data into functional spectra. The resulting model was able to capture molecular characteristics by training cancer subtypes [14].

Another DNN model was trained to infer the origin of tissue from single-nucleotide variant (SNV) information of metastatic tumor. The authors built a model by using the TCGA/ICGC data and analyzed SNV patterns and corresponding pathways to predict the origin of cancer. They discovered that metastatic tumors retained their original cancer’s signature mutation pattern. In this context, their DNN model obtained even better accuracy than a random forest model [133] and, even more important, better accuracy than human pathologists [12].

4.3. Tumor Heterogeneity with Network and DNN Model

As described in Section 4.1, there are several issues because of cancer heterogeneity, e.g., tumor microenvironment. Thus, there are only a few applications of DNN in intratumoral heterogeneity research. For instance, Menden et al. developed ’Scaden’ to deconvolve cell types in bulk-cell sequencing data. ’Scaden’ is a DNN model for the investigation of intratumor heterogeneity. To overcome the lack of training datasets, researchers need to generate in silico simulated bulk-cell sequencing data based on single-cell sequencing data [134]. It is presumed that deconvolving cell types can be achieved by knowing all possible expressional profiles of the cell [36]. However, this information is typically not available. Recently, to tackle this problem, single-cell sequencing-based studies were conducted. Because of technical limitations, we need to handle lots of missing data, noises, and batch effects in single-cell sequencing data [135]. Thus, various machine learning methods were developed to process single-cell sequencing data. They aim at mapping single-cell data onto the latent space. For example, scDeepCluster implemented an autoencoder and trained it on gene-expression levels from single-cell sequencing. During the training phase, the encoder and decoder work as denoiser. At the same time, they can embed high-dimensional gene-expression profiles to lower-dimensional vectors [136]. This autoencoder-based method can produce biologically meaningful feature vectors in various contexts, from tissue cell types [137] to different cancer types [138,139].

4.4. Drug Target Identification with Networks and DNN Models

In addition to NGS datasets, large-scale anticancer drug assays enabled the training train of DNNs. Moreover, non-cancer drug response assay datasets can also be incorporated with cancer genomic data. In cancer research, a multidisciplinary approach was widely applied for repurposing non-oncology drugs to cancer treatment. This drug repurposing is faster than de novo drug discovery. Furthermore, combination therapy with a non-oncology drug can be beneficial to overcome the heterogeneous properties of tumors [85]. The deepDR algorithm integrated ten drug-related networks and trained deep autoencoders. It used a random-walk-based algorithm to represent graph information into feature vectors. This approach integrated network analysis with a DNN model validated with an independent drug-disease dataset [15].

The authors of CDRscan did an integrative analysis of cell-line-based assay datasets and other drug and genomics datasets. It shows that DNN models can enhance the computational model for improved drug sensitivity predictions [140]. Additionally, similar to previous network-based models, the multi-omics application of drug-targeted DNN studies can show higher prediction accuracy than the single-omics method. MOLI integrated genomic data and transcriptomic data to predict the drug responses of TCGA patients [141].

4.5. Graph Neural Network Model

In general, the advantage of using a biological network is that it can produce more comprehensive and interpretable results from high-dimensional omics data. Furthermore, in an integrative multi-omics data analysis, network-based integration can improve interpretability over traditional approaches. Instead of pre-/post-integration of a network, recently developed graph neural networks use biological networks as the base structure for the learning network itself. For instance, various pathways or interactome information can be integrated as a learning structure of a DNN and can be aggregated as heterogeneous information. In a GNN study, a convolution process can be done on the provided network structure of data. Therefore, the convolution on a biological network made it possible for the GNN to focus on the relationship among neighbor genes. In the graph convolution layer, the convolution process integrates information of neighbor genes and learns topological information (Figure 3d). Consequently, this model can aggregate information from far-distant neighbors, and thus can outperform other machine learning models [142].

In the context of the inference problem of gene expression, the main question is whether the gene expression level can be explained by aggregating the neighboring genes. A single gene inference study by Dutil et al. showed that the GNN model outperformed other DNN models [143]. Moreover, in cancer research, such GNN models can identify cancer-related genes with better performance than other network-based models, such as HotNet2 and MutSigCV [144]. A recent GNN study with a multi-omics integrative analysis identified 165 new cancer genes as an interactive partner for known cancer genes [145]. Additionally, in the synthetic lethality area, dual-dropout GNN outperformed previous bioinformatics tools for predicting synthetic lethality in tumors [146]. GNNs were also able to classify cancer subtypes based on pathway activity measures with RNA-seq data. Lee et al. implemented a GNN for cancer subtyping and tested five cancer types. Thus, the informative pathway was selected and used for subtype classification [147]. Furthermore, GNNs are also getting more attention in drug repositioning studies. As described in Section 3.3, drug discovery requires integrating various networks in both chemical and genomic spaces (Figure 3d). Chemical structures, protein structures, pathways, and other multi-omics data were used in drug-target identification and repurposing studies (Figure 3c). Each of the proposed applications has a specialty in the different purposes of drug-related tasks. Sun et al. summarized GNN-based drug discovery studies and categorized them into four classes: molecular property and activity prediction, interaction prediction, synthesis prediction, and de novo drug design. The authors also point out four challenges in the GNN-mediated drug discovery. At first, as we described before, there is a lack of drug-related datasets. Secondly, the current GNN models can not fully represent 3-D structures of chemical molecules and protein structures. The third challenge is integrating heterogeneous network information. Drug discovery usually requires a multi-modal integrative analysis with various networks, and GNNs can improve this integrative analysis. Lastly, although GNNs use graphs, stacked layers still make it hard to interpret the model [148].

4.6. Shortcomings in AI and Revisiting Validity of Biological Networks as Prior Knowledge

The previous sections reviewed a variety of DNN-based approaches that present a good performance on numerous applications. However, it is hardly a panacea for all research questions. In the following, we will discuss potential limitations of the DNN models. In general, DNN models with NGS data have two significant issues: (i) data requirements and (ii) interpretability. Usually, deep learning needs a large proportion of training data for reasonable performance which is more difficult to achieve in biomedical omics data compared to, for instance, image data. Today, there are not many NGS datasets that are well-curated and -annotated for deep learning. This can be an answer to the question of why most DNN studies are in cancer research [110,149]. Moreover, the deep learning models are hard to interpret and are typically considered as black-boxes. Highly stacked layers in the deep learning model make it hard to interpret its decision-making rationale. Although the methodology to understand and interpret deep learning models has been improved, the ambiguity in the DNN models’ decision-making hindered the transition between the deep learning model and translational medicine [149,150].

As described before, biological networks are employed in various computational analyses for cancer research. The studies applying DNNs demonstrated many different approaches to use prior knowledge for systematic analyses. Before discussing GNN application, the validity of biological networks in a DNN model needs to be shown. The LINCS program analyzed data of ’The Connectivity Map (CMap) project’ to understand the regulatory mechanism in gene expression by inferring the whole gene expression profiles from a small set of genes (https://lincsproject.org/, accessed on 20 May 2021) [151,152]. This LINCS program found that the gene expression level is inferrable with only nearly 1000 genes. They called this gene list ’landmark genes’. Subsequently, Chen et al. started with these 978 landmark genes and tried to predict other gene expression levels with DNN models. Integrating public large-scale NGS data showed better performance than the linear regression model. The authors conclude that the performance advantage originates from the DNN’s ability to model non-linear relationships between genes [153].

Following this study, Beltin et al. extensively investigated various biological networks in the same context of the inference of gene expression level. They set up a simplified representation of gene expression status and tried to solve a binary classification task. To show the relevance of a biological network, they compared various gene expression levels inferred from a different set of genes, neighboring genes in PPI, random genes, and all genes. However, in the study incorporating TCGA and GTEx datasets, the random network model outperformed the model build on a known biological network, such as StringDB [154]. While network-based approaches can add valuable insights to analysis, this study shows that it cannot be seen as the panacea, and a careful evaluation is required for each data set and task. In particular, this result may not represent biological complexity because of the oversimplified problem setup, which did not consider the relative gene-expressional changes. Additionally, the incorporated biological networks may not be suitable for inferring gene expression profiles because they consist of expression-regulating interactions, non-expression-regulating interactions, and various in vivo and in vitro interactions.

“ However, although recently sophisticated applications of deep learning showed improved accuracy, it does not reflect a general advancement. Depending on the type of NGS data, the experimental design, and the question to be answered, a proper approach and specific deep learning algorithms need to be considered. Deep learning is not a panacea. In general, to employ machine learning and systems biology methodology for a specific type of NGS data, a certain experimental design, a particular research question, the technology, and network data have to be chosen carefully.”

References

  1. Janes, K.A.; Yaffe, M.B. Data-driven modelling of signal-transduction networks. Nat. Rev. Mol. Cell Biol. 20067, 820–828. [Google Scholar] [CrossRef] [PubMed]
  2. Kreeger, P.K.; Lauffenburger, D.A. Cancer systems biology: A network modeling perspective. Carcinogenesis 201031, 2–8. [Google Scholar] [CrossRef] [PubMed]
  3. Vucic, E.A.; Thu, K.L.; Robison, K.; Rybaczyk, L.A.; Chari, R.; Alvarez, C.E.; Lam, W.L. Translating cancer ‘omics’ to improved outcomes. Genome Res. 201222, 188–195. [Google Scholar] [CrossRef]
  4. Hoadley, K.A.; Yau, C.; Wolf, D.M.; Cherniack, A.D.; Tamborero, D.; Ng, S.; Leiserson, M.D.; Niu, B.; McLellan, M.D.; Uzunangelov, V.; et al. Multiplatform analysis of 12 cancer types reveals molecular classification within and across tissues of origin. Cell 2014158, 929–944. [Google Scholar] [CrossRef] [PubMed]
  5. Hutter, C.; Zenklusen, J.C. The cancer genome atlas: Creating lasting value beyond its data. Cell 2018173, 283–285. [Google Scholar] [CrossRef]
  6. Chuang, H.Y.; Lee, E.; Liu, Y.T.; Lee, D.; Ideker, T. Network-based classification of breast cancer metastasis. Mol. Syst. Biol. 20073, 140. [Google Scholar] [CrossRef]
  7. Zhang, W.; Chien, J.; Yong, J.; Kuang, R. Network-based machine learning and graph theory algorithms for precision oncology. NPJ Precis. Oncol. 20171, 25. [Google Scholar] [CrossRef] [PubMed]
  8. Ngiam, K.Y.; Khor, W. Big data and machine learning algorithms for health-care delivery. Lancet Oncol. 201920, e262–e273. [Google Scholar] [CrossRef]
  9. Creixell, P.; Reimand, J.; Haider, S.; Wu, G.; Shibata, T.; Vazquez, M.; Mustonen, V.; Gonzalez-Perez, A.; Pearson, J.; Sander, C.; et al. Pathway and network analysis of cancer genomes. Nat. Methods 201512, 615. [Google Scholar]
  10. Reyna, M.A.; Haan, D.; Paczkowska, M.; Verbeke, L.P.; Vazquez, M.; Kahraman, A.; Pulido-Tamayo, S.; Barenboim, J.; Wadi, L.; Dhingra, P.; et al. Pathway and network analysis of more than 2500 whole cancer genomes. Nat. Commun. 202011, 729. [Google Scholar] [CrossRef]
  11. Luo, P.; Ding, Y.; Lei, X.; Wu, F.X. deepDriver: Predicting cancer driver genes based on somatic mutations using deep convolutional neural networks. Front. Genet. 201910, 13. [Google Scholar] [CrossRef]
  12. Jiao, W.; Atwal, G.; Polak, P.; Karlic, R.; Cuppen, E.; Danyi, A.; De Ridder, J.; van Herpen, C.; Lolkema, M.P.; Steeghs, N.; et al. A deep learning system accurately classifies primary and metastatic cancers using passenger mutation patterns. Nat. Commun. 202011, 728. [Google Scholar] [CrossRef]
  13. Chaudhary, K.; Poirion, O.B.; Lu, L.; Garmire, L.X. Deep learning–based multi-omics integration robustly predicts survival in liver cancer. Clin. Cancer Res. 201824, 1248–1259. [Google Scholar] [CrossRef]
  14. Gao, F.; Wang, W.; Tan, M.; Zhu, L.; Zhang, Y.; Fessler, E.; Vermeulen, L.; Wang, X. DeepCC: A novel deep learning-based framework for cancer molecular subtype classification. Oncogenesis 20198, 44. [Google Scholar] [CrossRef]
  15. Zeng, X.; Zhu, S.; Liu, X.; Zhou, Y.; Nussinov, R.; Cheng, F. deepDR: A network-based deep learning approach to in silico drug repositioning. Bioinformatics 201935, 5191–5198. [Google Scholar] [CrossRef]
  16. Issa, N.T.; Stathias, V.; Schürer, S.; Dakshanamurthy, S. Machine and deep learning approaches for cancer drug repurposing. In Seminars in Cancer Biology; Elsevier: Amsterdam, The Netherlands, 2020. [Google Scholar]
  17. Weinstein, J.N.; Collisson, E.A.; Mills, G.B.; Shaw, K.R.M.; Ozenberger, B.A.; Ellrott, K.; Shmulevich, I.; Sander, C.; Stuart, J.M.; Network, C.G.A.R.; et al. The cancer genome atlas pan-cancer analysis project. Nat. Genet. 201345, 1113. [Google Scholar] [CrossRef]
  18. The ICGC/TCGA Pan-Cancer Analysis of Whole Genomes Consortium. Pan-cancer analysis of whole genomes. Nature 2020578, 82. [Google Scholar] [CrossRef] [PubMed]
  19. King, M.C.; Marks, J.H.; Mandell, J.B. Breast and ovarian cancer risks due to inherited mutations in BRCA1 and BRCA2. Science 2003302, 643–646. [Google Scholar] [CrossRef] [PubMed]
  20. Courtney, K.D.; Corcoran, R.B.; Engelman, J.A. The PI3K pathway as drug target in human cancer. J. Clin. Oncol. 201028, 1075. [Google Scholar] [CrossRef] [PubMed]
  21. Parker, J.S.; Mullins, M.; Cheang, M.C.; Leung, S.; Voduc, D.; Vickery, T.; Davies, S.; Fauron, C.; He, X.; Hu, Z.; et al. Supervised risk predictor of breast cancer based on intrinsic subtypes. J. Clin. Oncol. 200927, 1160. [Google Scholar] [CrossRef]
  22. Yersal, O.; Barutca, S. Biological subtypes of breast cancer: Prognostic and therapeutic implications. World J. Clin. Oncol. 20145, 412. [Google Scholar] [CrossRef] [PubMed]
  23. Zhao, L.; Lee, V.H.; Ng, M.K.; Yan, H.; Bijlsma, M.F. Molecular subtyping of cancer: Current status and moving toward clinical applications. Brief. Bioinform. 201920, 572–584. [Google Scholar] [CrossRef] [PubMed]
  24. Jones, P.A.; Issa, J.P.J.; Baylin, S. Targeting the cancer epigenome for therapy. Nat. Rev. Genet. 201617, 630. [Google Scholar] [CrossRef] [PubMed]
  25. Huang, S.; Chaudhary, K.; Garmire, L.X. More is better: Recent progress in multi-omics data integration methods. Front. Genet. 20178, 84. [Google Scholar] [CrossRef]
  26. Chin, L.; Andersen, J.N.; Futreal, P.A. Cancer genomics: From discovery science to personalized medicine. Nat. Med. 201117, 297. [Google Scholar] [CrossRef] [PubMed]

Use of Systems Biology in Anti-Microbial Drug Development

Genomics, Computational Biology and Drug Discovery for Mycobacterial Infections: Fighting the Emergence of Resistance. Asma Munir, Sundeep Chaitanya Vedithi, Amanda K. Chaplin and Tom L. Blundell. Front. Genet., 04 September 2020 | https://doi.org/10.3389/fgene.2020.00965

In an earlier review article (Waman et al., 2019), we discussed various computational approaches and experimental strategies for drug target identification and structure-guided drug discovery. In this review we discuss the impact of the era of precision medicine, where the genome sequences of pathogens can give clues about the choice of existing drugs, and repurposing of others. Our focus is directed toward combatting antimicrobial drug resistance with emphasis on tuberculosis and leprosy. We describe structure-guided approaches to understanding the impacts of mutations that give rise to antimycobacterial resistance and the use of this information in the design of new medicines.

Genome Sequences and Proteomic Structural Databases

In recent years, there have been many focused efforts to define the amino-acid sequences of the M. tuberculosis pan-genome and then to define the three-dimensional structures and functional interactions of these gene products. This work has led to essential genes of the bacteria being revealed and to a better understanding of the genetic diversity in different strains that might lead to a selective advantage (Coll et al., 2018). This will help with our understanding of the mode of antibiotic resistance within these strains and aid structure-guided drug discovery. However, only ∼10% of the ∼4128 proteins have structures determined experimentally.

Several databases have been developed to integrate the genomic and/or structural information linked to drug resistance in Mycobacteria (Table 1). These invaluable resources can contribute to better understanding of molecular mechanisms involved in drug resistance and improvement in the selection of potential drug targets.

There is a dearth of information related to structural aspects of proteins from M. leprae and their oligomeric and hetero-oligomeric organization, which has limited the understanding of physiological processes of the bacillus. The structures of only 12 proteins have been solved and deposited in the protein data bank (PDB). However, the high sequence similarity in protein coding genes between M. leprae and M. tuberculosis allows computational methods to be used for comparative modeling of the proteins of M. leprae. Mainly monomeric models using single template modeling have been defined and deposited in the Swiss Model repository (Bienert et al., 2017), in Modbase (Pieper et al., 2014), and in a collection with other infectious disease agents (Sosa et al., 2018). There is a need for multi-template modeling and building homo- and hetero-oligomeric complexes to better understand the interfaces, druggability and impacts of mutations.

We are now exploiting Vivace, a multi-template modeling pipeline developed in our lab for modeling the proteomes of M. tuberculosis (CHOPIN, see above) and M. abscessus [Mabellini Database (Skwark et al., 2019)], to model the proteome of M. leprae. We emphasize the need for understanding the protein interfaces that are critical to function. An example of this is that of the RNA-polymerase holoenzyme complex from M. leprae. We first modeled the structure of this hetero-hexamer complex and later deciphered the binding patterns of rifampin (Vedithi et al., 2018Figures 1A,B). Rifampin is a known drug to treat tuberculosis and leprosy. Owing to high rifampin resistance in tuberculosis and emerging resistance in leprosy, we used an approach known as “Computational Saturation Mutagenesis”, to identify sites on the protein that are less impacted by mutations. In this study, we were able to understand the association between predicted impacts of mutations on the structure and phenotypic rifampin-resistance outcomes in leprosy.

FIGURE 2

Figure 2. (A) Stability changes predicted by mCSM for systematic mutations in the ß-subunit of RNA polymerase in M. leprae. The maximum destabilizing effect from among all 19 possible mutations at each residue position is considered as a weighting factor for the color map that gradients from red (high destabilizing effects) to white (neutral to stabilizing effects) (Vedithi et al., 2020). (B) One of the known mutations in the ß-subunit of RNA polymerase, the S437H substitution which resulted in a maximum destabilizing effect [-1.701 kcal/mol (mCSM)] among all 19 possibilities this position. In the mutant, histidine (residue in green) forms hydrogen bonds with S434 and Q438, aromatic interactions with F431, and other ring-ring and π interactions with the surrounding residues which can impact the shape of the rifampin binding pocket and rifampin affinity to the ß-subunit [-0.826 log(affinity fold change) (mCSM-lig)]. Orange dotted lines represent weak hydrogen bond interactions. Ring-ring and intergroup interactions are depicted in cyan. Aromatic interactions are represented in sky-blue and carbonyl interactions in pink dotted lines. Green dotted lines represent hydrophobic interactions (Vedithi et al., 2020).

Examples of Understanding and Combatting Resistance

The availability of whole genome sequences in the present era has greatly enhanced the understanding of emergence of drug resistance in infectious diseases like tuberculosis. The data generated by the whole genome sequencing of clinical isolates can be screened for the presence of drug-resistant mutations. A preliminary in silico analysis of mutations can then be used to prioritize experimental work to identify the nature of these mutations.

FIGURE 3

Figure 3. (A) Mechanism of isoniazid activation and INH-NAD adduct formation. (B) Mutations mapped (Munir et al., 2019) on the structure of KatG (PDB ID:1SJ2; Bertrand et al., 2004).

Other articles related to Computational Biology, Systems Biology, and Bioinformatics on this online journal include:

20th Anniversary and the Evolution of Computational Biology – International Society for Computational Biology

Featuring Computational and Systems Biology Program at Memorial Sloan Kettering Cancer Center, Sloan Kettering Institute (SKI), The Dana Pe’er Lab

Quantum Biology And Computational Medicine

Systems Biology Analysis of Transcription Networks, Artificial Intelligence, and High-End Computing Coming to Fruition in Personalized Oncology

Read Full Post »

Yet another Success Story: Machine Learning to predict immunotherapy response

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc

Immune-checkpoint blockers (ICBs) immunotherapy appears promising for various cancer types, offering a durable therapeutic advantage. Only a number of cases with cancer respond to this therapy. Biomarkers are required to adequately predict the responses of patients. This article evaluates this issue utilizing a system method to characterize the immune response of the anti-tumor based on the entire tumor environment. Researchers build mechanical biomarkers and cancer-specific response models using interpretable machine learning that predict the response of patients to ICB.

The lymphatic and immunological systems help the body defend itself by combating. The immune system functions as the body’s own personal police force, hunting down and eliminating pathogenic baddies.

According to Federica Eduati, Department of Biomedical Engineering at TU/e, “The immune system of the body is quite adept at detecting abnormally behaving cells. Cells that potentially grow into tumors or cancer in the future are included in this category. Once identified, the immune system attacks and destroys the cells.”

Immunotherapy and machine learning are combining to assist the immune system solve one of its most vexing problems: detecting hidden tumorous cells in the human body.

It is the fundamental responsibility of our immune system to identify and remove alien invaders like bacteria or viruses, but also to identify risks within the body, such as cancer. However, cancer cells have sophisticated ways of escaping death by shutting off immune cells. Immunotherapy can reverse the process, but not for all patients and types of cancer. To unravel the mystery, Eindhoven University of Technology researchers used machine learning. They developed a model to predict whether immunotherapy will be effective for a patient using a simple trick. Even better, the model outperforms conventional clinical approaches.

The outcomes of this research are published on 30th June, 2021 in the journal Patterns in an article entitled “Interpretable systems biomarkers predict response to immune-checkpoint inhibitors”.

The Study

  • Characterization of the tumor microenvironment from RNAseq and prior knowledge
  • Multi-task machine-learning models for predicting antitumor immune responses
  • Identification of cancer-type-specific, interpretable biomarkers of immune responses
  • EaSIeR is a tool to predict biomarker-based immunotherapy response from RNA-seq

“Tumor also contains multiple types of immune and fibroblast cells which can play a role in favor of or anti-tumor, and communicates among themselves,” said Oscar Lapuente-Santana, a researcher doctoral student in the computational biology group. “We had to learn how complicated regulatory mechanisms in the micro-environment of the tumor affect the ICB response. We have used RNA sequencing datasets to depict numerous components of the Tumor Microenvironment (TME) in a high-level illustration.”

Using computational algorithms and datasets from previous clinical patient care, the researchers investigated the TME.

Eduati explained

While RNA-sequencing databases are publically available, information on which patients responded to ICB therapy is only available for a limited group of patients and cancer types. So, to tackle the data problem, we used a trick.

All 100 models learned in the randomized cross-validation were included in the EaSIeR tool. For each validation dataset, we used the corresponding cancer-type-specific model: SKCM for the melanoma Gide, Auslander, Riaz, and Liu cohorts; STAD for the gastric cancer Kim cohort; BLCA for the bladder cancer Mariathasan cohort; and GBM for the glioblastoma Cloughesy cohort. To make predictions for each job, the average of the 100 cancer-type-specific models was employed. The predictions of each dataset’s cancer-type-specific models were also compared to models generated for the remaining 17 cancer types.

From the same datasets, the researchers selected several surrogate immunological responses to be used as a measure of ICB effectiveness.

Lapuente-Santana stated

One of the most difficult aspects of our job was properly training the machine learning models. We were able to fix this by looking at alternative immune responses during the training process.

Some of the researchers employed the machine learning approach given in the paper to participate in the “Anti-PD1 Response Prediction DREAM Challenge.”

DREAM is an organization that carries out crowd-based tasks with biomedical algorithms. “We were the first to compete in one of the sub-challenges under the name cSysImmunoOnco team,” Eduati remarks.

The researchers noted,

We applied machine learning to seek for connections between the obtained system-based attributes and the immune response, estimated using 14 predictors (proxies) derived from previous publications. We treated these proxies as individual tasks to be predicted by our machine learning models, and we employed multi-task learning algorithms to jointly learn all tasks.

The researchers discovered that their machine learning model surpasses biomarkers that are already utilized in clinical settings to evaluate ICB therapies.

But why are Eduati, Lapuente-Santana, and their colleagues using mathematical models to tackle a medical treatment problem? Is this going to take the place of the doctor?

Eduati explains

Mathematical models can provide an overview of the interconnection between individual molecules and cells and at the same time predicting a particular patient’s tumor behavior. This implies that immunotherapy with ICB can be personalized in a patient’s clinical setting. The models can aid physicians with their decisions about optimum therapy, it is vital to note that they will not replace them.

Furthermore, the model aids in determining which biological mechanisms are relevant for the biological response.

The researchers noted

Another advantage of our concept is that it does not need a dataset with known patient responses to immunotherapy for model training.

Further testing is required before these findings may be implemented in clinical settings.

Main Source:

Lapuente-Santana, Ó., van Genderen, M., Hilbers, P. A., Finotello, F., & Eduati, F. (2021). Interpretable systems biomarkers predict response to immune-checkpoint inhibitorsPatterns, 100293. https://www.cell.com/patterns/pdfExtended/S2666-3899(21)00126-4

Other Related Articles published in this Open Access Online Scientific Journal include the following:

Inhibitory CD161 receptor recognized as a potential immunotherapy target in glioma-infiltrating T cells by single-cell analysis

Reporter: Dr. Premalata Pati, Ph.D., Postdoc

https://pharmaceuticalintelligence.com/2021/02/20/inhibitory-cd161-receptor-identified-in-glioma-infiltrating-t-cells-by-single-cell-analysis-2/

Immunotherapy may help in glioblastoma survival

Reporter and Curator: Dr. Sudipta Saha, Ph.D.

https://pharmaceuticalintelligence.com/2019/03/16/immunotherapy-may-help-in-glioblastoma-survival/

Deep Learning for In-silico Drug Discovery and Drug Repurposing: Artificial Intelligence to search for molecules boosting response rates in Cancer Immunotherapy: Insilico Medicine @John Hopkins University

Reporter: Aviva Lev-Ari, PhD, RN

https://pharmaceuticalintelligence.com/2016/07/17/deep-learning-for-in-silico-drug-discovery-and-drug-repurposing-artificial-intelligence-to-search-for-molecules-boosting-response-rates-in-cancer-immunotherapy-insilico-medicine-john-hopkins-univer/

Machine Learning (ML) in cancer prognosis prediction helps the researcher to identify multiple known as well as candidate cancer diver genes

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc

https://pharmaceuticalintelligence.com/2021/05/04/machine-learning-ml-in-cancer-prognosis-prediction-helps-the-researcher-to-identify-multiple-known-as-well-as-candidate-cancer-diver-genes/

AI System Used to Detect Lung Cancer

Reporter: Irina Robu, PhD

https://pharmaceuticalintelligence.com/2019/06/28/ai-system-used-to-detect-lung-cancer/

Cancer detection and therapeutics

Curator: Larry H. Bernstein, MD, FCAP

https://pharmaceuticalintelligence.com/2016/05/02/cancer-detection-and-therapeutics/

Read Full Post »

« Newer Posts - Older Posts »