Feeds:
Posts
Comments

Archive for the ‘Computational Biology/Systems and Bioinformatics’ Category

Authentic Relevance of LPBI Group’s Portfolio of IP as Proprietary Training Data Corpus for AI Initiatives at Big Pharma

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

Updated on 11/29/2025

 

The Voice of Stephen J. Williams, PhD

Since the formation of the LPBI group in 2012, we have set as a goal to digitally curate and ontologize the biomedical literature.  These aspects of our mission, although not understandable to most at that time of our inception, was at the forefront of many academic efforts which became the springboard and initial conceptualization of today’s large language models.  In select universities like University of Illinois, University of Delaware, and the Technion, academics and researchers at Microsoft and Google, were laying the framework for  a semantic web, or Web 3.0.  Another company at the forefront of this idea was a company springing forth from Mathematica, Wolfram Research. This idea for a semantic web would entail the processes of curation, digitization, and ontology creation.  Their belief, such as ours, was  a precursor and much needed key to the puzzle of moving language from machine learning algorithms to the generative transformers used by artificial intelligence.

However as most efforts in this genre focused on general language, our efforts at LPBI Group were focused on the biomedical field, as we understood, from 2012, that the biomedical literature was unique, and so a unique strategy had to be developed to semantically understand biomedical text, even though at the time of 2012 GPTs were not even a concept.  However the potential for doing biomedical text analysis was there, and LPBI Group responded by developing a methodology of scientific curation which involved a multimodal strategy to curate, digitize, and ontologize biomedical findings and text.

It was about at the time of 2012 that other groups, mainly focused of drug development applications (for example at University of Indiana) recognized that new computational power of machine learning algorthims could be  useful in analyzing complex biological questions.  Please see our Synthetic Biology in Drug Discovery section of our Journal for more information on this. For instance, an early adopter of this strategy, a company called  Data2Discovery, one of the earliest AI for drug discovery startups, stated

We are able to improve drug discovery now as well as demonstrating new fast-cycle AI-driven processes that will have a revolutionary impact on drug discovery if fully implemented. We have had some dramatic successes, but we are just starting to discover the impact that data, knowledge graphs, AI and machine learning can together have on drug discovery.

We need all the expertise of academics, consortia, AI companies and pharma to make his happen, and it’s going to require some serious investment, and a big change of thinking. But the opportunity to get drug discovery out of the death spiral and framed for data-driven success is too important to pass up.

However the LPBI Group was cognizant of these changes occuring and pivoted to the developing natural language processing arena as well as ideas for the developing Blockchain technology.  This was more of a natural progression for the LPBI Group than a pivot (please read here).

This would be our Vision 2.0, to make biomedical text amenable for Natural Language Processing.   We utilized a few strategies in this regard, partnering with a company who was developing NLP for biomedical text analysis, and developing in house machine learning and NLP methods using the Wolfram language environment.  Our focus on structuring biomedical text (versus the highly structured genomics and omics data found in many omics related databanks) was prescient for the time.  As NLP and machine learning  efforts realized, biomedical text needs to have a structure much like genes, proteins and other molecular databases had been organized.  Therefore it was realized that structured data was imperative for efficient NLP analysis, a crux for the new GPT which was being developed (and in this mind still is a crux for current GPT and LLM models when it comes to biomedical text analysis).

Our strategy using our scientific curation methodology (as described below in links form our founder Dr. Aviva Lev-Ari, was proven to be highly efficient and amenable to NLP analysis, as a pilot with an NLP company noticed.  Most of the data they were using was unstructured and their first step involved annotation and structuring the text, as we had already performed for years.  This was critical as our text was able to pull out more concepts, relationships, in a faster time than NLP on sources such as PubMed available text.  We had also developed our own in house algorithms for NLP on our material, which is shown in some of our book offerrings and individual articles.

However with the advent of GPT it was thought all this was unnecessary.  However this idea that our strategy was outdated or irrelevent in the era of GPT was wholly  incorrect to the advocates of a sole GPT strategy to analyze biomedical text and data.  It is now understood that structure is needed as some of biomedical-centric GPT projects would find out, such as BioGPT.  We have many articles which attest to the lack of  accuracy and efficiency of these GPT architectures (seen here). These include failure rates in many areas of healthcare and biomedicine by sole reliance on GPT,

It was realized by many in the biomedical arena, especially those involved in NLP efforts, that there was much value in the semantic web 3.0 idea, and this was readily picked up by those spearheading effort to incorporate knowledge graphs with the new generative AI or GPT technology.  We have shown a clear example our scientific methodology of curation with ontology has better inference when combined with knowledge graphs and GPT than reliance on GPT alone

please read this article

Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer

at https://pharmaceuticalintelligence.com/2014/09/05/multiple-lung-cancer-genomic-projects-suggest-new-targets-research-directions-for-non-small-cell-lung-cancer/

As shown here in this article

This update was performed by the following methods:
A. GPT 5 Text analysis and Reasoning
B. Insertion of Knowledge Graph on topic Curation of Genomic Analysis from Non Small Cell Lung Cancer Studies  from Nodus Labs using InfraNodus software
C. Domain Knowledge Expert evaluation of the Update outcomes
This article has the following Structure:
Part A: Introduction to LLM, Knowledge Graph software InfraNodus, ChatGPT5 and Background Information on curated material for Test Case
Part B: InfraNodus Analysis of manual curation and Knowledge Graph Creation
Part C: Chat GPT 5 Analysis of Manually Curated Material
Part D: Curation entitled Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer originally published on 09/05/2014
Results of Article Update with GPT 5
1. GPT5 alone was not able to understand the goal of the article, namely to determine knowledge gaps in a particular research area involving 5 genomic studies on lung cancer patients
2. GPT5 alone was not able to group concepts or comonalities between biological pathways unless supplied with a manually curated list of KEGG pathways from a list of mutated genes.  However this precluded any effect that fusion proteins had on the analysis and so GPT5 would only concentrate on mutated genes commonly found in literature
3. GPT was not able to access some of the open Access databases like NCBI Gene Ontology database
Results of Article Update with KnowledgeGraph presentation to GPT 5
4. As the Knowledge Graph understood the importance of fusion proteins and transversions, the knowledgegraph augmented the GPT analysis and so enriched the known pathways as well as could correctly identify the less represented pathways in the knowledge graph
5.  This led to the identification of many novel signaling pathways not identified in the original analysis, and was able to perform this task with ease and speed

6. GPT with InfraNodus Analysis was able to propose pertinent questions for future research (the goal of the original curation) such as:

  • How does the interaction between [[EGFR]] mutations and sex-specific gene alterations, including [[RBM10]], influence treatment outcomes in lung adenocarcinoma?
  • How does the intersection of mutational patterns from smoking influence pathway activation in NSCLC, and can identifying these interactions improve targeted therapy development?
Novelty in comparison to Original article published on 09/05/2014
7. it appears that manual curation is necessary to assist in the building of relevant knowledge graphs in the biomedical fields to augment generative AI analysis
8. by itself, generative AI is not optimized for inference of higher concepts from biomedical text, and therefore, at this point, requires the input from human curators developing domain-specific knowledge graphs
9.  The combination of ChatGPT5 and Knowledge graphs of this manually curated biomedical text added a further layer of complexity of gaps of knowledge not seen in the original curations including the need to study noncanonical signaling pathways like WNT and Hedgehog in smoker versus nonsmoker cohorts of lung cancer patients

The Voice of Aviva Lev-Ari, PhD, RN

LPBI Group’s Portfolio of Digital IP Assets as Proprietary Training Data Corpus for AI in Medicine, in Life Sciences, in Pharmaceutical and in Health Care Applications

The Portfolio of Digital IP Assets by Class is a rare, defensible asset, privately-held debt-free by LPBI Group’s founder. The content, aka a Data Corpus is best designed for the Training and Pre-Training of Foundation Multimodal Models in Health Care. 

#HealthcareAI

#FoundationModels

#ProprietaryTrainingData

LPBI Group is offering transfer of ownership, in full, a privately held, multimodal healthcare training corpus leveraging propriety unique data set curated by domain experts and mapped to a living ontology for GenAI creating defensibility.

The Portfolio of IP spans:

  • 6,250+ articles (~2.5MM views),
  • 48 e‑books (EN/ES) (+152,000 page downloads),
  • 100+ e‑Proceedings with +50 Tweet collections,
  • 7,500+ biological images with expert context, and
  • 300+ Audio podcasts on Life Sciences breakthroughs.

Each asset (Use Case: Scientific Article) has timestamps, author/role labels, crosslinks, and view histories.

  • Metadata export exists; full text and media transfer via WordPress/Amazon account control for immediate ingestion.
  • Rights are centrally assigned with explicit model‑training data by domain-aware for model implementation for Small Language Models or Large Language Models.

Strategic acquirers in Big Pharma of Vertical AI startups (i.e., LPBI Group) with data‑moat strategies

Pharma strategics Acquire LPBI’s end‑to‑end, rights‑clean healthcare knowledge base to accelerate R&D, medical affairs, and safety. Ideal for and with acceleration of R&D, medical affairs, and safety. Emphasize compliant internal copilots and evidence synthesis enabled by expert curation and living ontology. Close with rapid onboarding under NDA  Metadata export plus full text/media transfer for rapid onboarding. Full acquisition only.

Subject: Buy the moat: full acquisition of expert healthcare corpus with clean rights

We’re selling the entire asset: a privately held, multimodal healthcare corpus with centralized training rights and an exportable ontology, validated on gene–disease–drug extraction. It’s ingest‑ready and transfers cleanly via account control plus a metadata export. If owning differentiated data is critical for your agent or workflow, we can provide a diligence preview under NDA.

compliant internal copilots and evidence synthesis enabled by expert curation and living ontology. Close with rapid onboarding under NDA

Five Examples of Domain-aware for model implementation for Small Language Models – English Edition & Spanish Edition

Series A: Cardiovascular Diseases ($515) – Six Volumes

https://www.amazon.com/gp/product/B07P981RCS?ref_=dbs_p_mng_rwt_ser_shvlr&storeType=ebooks

Six Examples of Domain-aware in the Specialty of Cardiovascular Diseases

  • Series A, Volume One

Perspectives on Nitric Oxide in Disease Mechanisms2013

http://www.amazon.com/dp/B00DINFFYC $75

  • Series A, Volume Two 

Cardiovascular Original Research: Cases in Methodology Design for Content Co-Curation, 2015

http://www.amazon.com/dp/B018Q5MCN8 $75

  • Series A, Volume Three

Etiologies of Cardiovascular Diseases – Epigenetics, Genetics and Genomics2015

http://www.amazon.com/dp/B018PNHJ84 $75

  • Series A, Volume Four

Therapeutic Promise: Cardiovascular Diseases, Regenerative & Translational Medicine, 2015

http://www.amazon.com/dp/B019UM909A $75

  • Series A, Volume Five

Pharmacological Agents in Treatment of Cardiovascular Diseases2018

https://www.amazon.com/dp/B07MGSFDWR  $115

  • Series A, Volume Six:

Interventional Cardiology for Disease Diagnosis and Cardiac Surgery for Condition Treatment2018

https://www.amazon.com/dp/B07MKHDBHF $100

 

Series B: Frontiers in Genomics ($200) – Two Volumes

https://www.amazon.com/gp/product/B0BSDPG2RX?ref_=dbs_p_pwh_rwt_anx_b_lnk&storeType=ebooks

Series C: Cancer & Oncology ($175) – Two Volumes

https://www.amazon.com/gp/product/B0BSDWVB3H?ref_=dbs_p_mng_rwt_ser_shvlr&storeType=ebooks

Series D: Immunology ($325) – Four Volumes

https://www.amazon.com/gp/product/B08VVWTNR4?ref_=dbs_p_pwh_rwt_anx_b_lnk&storeType=ebooks

Series E: Patient-Centered Medicine ($274) – Four Volumes

https://www.amazon.com/gp/product/B0BSDW2K6C?ref_=dbs_p_mng_rwt_ser_shvlr&storeType=ebooks

One Example of Domain-aware for model implementation for Large Language Models

Eighteen volumes in the English Edition and 19 volumes in the Spanish Edition including 2,728 articles by biomedical professionals are available.

https://www.amazon.com/s?k=Aviva+Lev-Ari&i=digital-text&rh=n%3A133140011&ref=nb_sb_noss

The electronic books are collections of curated articles in biomedical science. The electronic Tables of Contents (eTOCs) of each volume was designed by a senior editor with expertise in the subjects covered in that volume. The curations use as sources published research findings in peer-reviewed scientific journals together with expert added interpretations.

The e-books are designed to make the latest research in the Five Bilingual BioMed e-Series – 37 volumes accessible to practicing health care professionals. These five e-Series cover the following medical specialties:

  • Cardiovascular diseases and therapies,
  • Genomics,
  • Cancer etiology and oncological therapies,
  • Immunology, and
  • Patient-centered precision medicine.

The material in these volumes can greatly enhance medical education and provide a resource for continued updating and education for health care professionals. In addition to the 37 e-books, LPBI has published more than 6,000 articles in its online scientific journal “PharmaceuticalIntelligence.com”, which has received 2.5 million views since its launch in 4/2012, Top articles had more than 18,000 views.

The Portfolio is:

  • rights‑clean,
  • expert‑curated healthcare corpus
  • mapped to a living Ontology,
  • already packaged for immediate model ingestion and
  • suitable for safe pre-training, evals, and fine‑tuning.

If healthcare domain data is on your roadmap, this is a rare, defensible asset worth a preview.

LPBI Group is offering transfer of ownership, in full, a privately held, multimodal healthcare training corpus leveraging propriety unique data set curated by domain experts and mapped to a living ontology for GenAI creating defensibility. It spans 6,250+ articles (~2.5MM views), 48 e‑books (EN/ES) (+151,000 page downloads), 100+ e‑proceedings with +50 tweet collections, 7,500+ biological images with expert context, and 300+ Audio podcasts on Life Sciences breakthroughs. Each asset has timestamps, author/role labels, crosslinks, and view histories. Rights are centrally assigned with explicit model‑training data by domain-aware for model implementation for Small LMs or LLMs. Metadata export exists; full text and media transfer via WordPress/Amazon account control for immediate ingestion.

Leaders in Pharmaceutical Business Intelligence Group, LLC, Doing Business As LPBI Group, Newton, MA

Full acquisition only: LPBI Group’s Healthcare Training Data Corpus

  • Scientific articles
  • e‑Books in Medicine
  • e‑Proceedings,
  • Biological images
  • Podcasts

#HealthcareAI #FoundationModels #TrainingData

Contact Founder: avivalev-ari@alum.berkeley.edu

PharmaceuticalIntelligence.com

About the Founder

  • LPBI Group’s Legacy and Biography of Aviva Lev-Ari, PhD, RN, Founder & Director, INTERACTIVE CHAT with Grok, created by xAI

https://pharmaceuticalintelligence.com/2025/04/30/interactive-chat-with-grok-created-by-xai-lpbi-groups-legacy-and-biography-of-aviva-lev-ari-phd-rn-founder-director/ 

For Recognitions and a DETAILED BIO by Perplexity.ai and Gemini 2.5 Pro (experimental), see

  • “Show Thinking” by AI Deep Research: The AI-generated Biography Description of Aviva Lev-Ari, PhD, RN, Founder of PharmaceuticalIntelligence.com by Perplexity.ai and by Google’s Gemini 2.5 Pro (experimental)

https://pharmaceuticalintelligence.com/2025/04/29/show-thinking-by-ai-deep-research-the-ai-biography-description-of-aviva-lev-ari-phd-rn-founder-of-pharmaceuticalintelligence-com-by-perplexity-ai-and-by-googles-gemini-2/

Authentic Relevance of LPBI Group’s Portfolio of IP as Proprietary Training Data Corpus for AI Initiatives at Big Pharma

On 11/14, 2025, Dr. Lev-Ari asked @Grok about AI Initiatives at a Big Pharma, i.e., Pfizer.

@Grok response is presented, below

URL SOURCE:

https://x.com/i/grok/share/0ol5VOJsEYs11baXq4xkzNb0h

Pfizer’s AI Initiatives Overview

Pfizer, a global pharmaceutical leader, has integrated artificial intelligence (AI) and machine learning (ML) across its operations to accelerate drug discovery, enhance clinical trials, improve manufacturing, and drive patient-centric innovations. These efforts aim to reduce development timelines, boost efficiency, and address challenges like rare disease detection. As of late 2025, Pfizer’s AI strategy emphasizes internal expertise, cloud-based tools (primarily with AWS), and cross-industry collaborations, with a focus on multimodal data analysis and generative AI. Below is a breakdown of key initiatives, drawn from recent developments.

1. Pfizer AI Cloud Transformation (PACT) Program Launched in 2021 with AWS, PACT is a prototyping accelerator for AI/ML applications in lab, clinical manufacturing, and supply chain efforts. It has pursued 14 projects, with five now in production. Key outcomes include:

  • Generative AI tools that save scientists up to 16,000 hours annually in literature searches and data analysis.
  • 55% reduction in infrastructure costs through cloud optimization.
  • Exploration of virtual/augmented reality for training, with rapid prototyping to test feasibility. This program fosters “fail-fast” innovation, enabling quick iteration on ideas like AI-driven predictive modeling.

2. Drug Discovery and Development Acceleration Pfizer uses AI, supercomputing, and ML to streamline R&D, cutting years off traditional timelines (e.g., from 8–10 years to months for certain candidates).

  • COVID-19 Initiatives: AI optimized molecular searches for PAXLOVID (oral antiviral), enabling intravenous-to-oral pivots. During vaccine development, the Safety Data Quality (SDQ) tool—a custom AI for clinical trial data management—saved a full month of analysis via the Breakthrough Change Accelerator sandbox.
  • Precision Medicine and Subpopulation Identification: Advanced ML (classical and deep learning) analyzes molecular datasets from trials to predict patient responses, informing trial design, first-in-human studies, and oncology/inflammatory disease targeting. This has doubled clinical success rates to ~20% (vs. industry 7–10%).
  • ML Research Hub: Pfizer’s Cambridge, MA-based Biomedical Data Science group builds internal talent for AI in genome sciences, predicting disease outcomes and treatment efficacy using techniques from tech giants like Google.

3. Clinical Trials and Regulatory Efficiency AI automates content creation across the drug lifecycle, from lab data to regulatory docs and patient booklets, ensuring quality and speed.

  • Predictive Regulatory Tools: ML models forecast regulator queries, proactively addressing safety concerns to build trust and shorten approvals.
  • Decentralized Trials: The “Clinical Trial Anywhere” model uses AI to integrate remote data (e.g., home health visits), improving recruitment/retention and generating real-world evidence.
  • Inventory and Supply Chain: AI predicts vaccine storage issues, pioneered during COVID distribution.

4. Disease Detection and Diagnostics

  • ATTR-CM Initiative: Through the ASPIRE collaboration (with Amyloidosis Research Consortium), AI analyzes EHRs, ECGs, and echocardiograms to detect transthyretin amyloid cardiomyopathy earlier, targeting underdiagnosed heart failure cases.
  • Rare Diseases: ML models identify symptoms in large datasets, mapping the immune system for better predictions.

5. Generative AI and Operational Tools

  • Charlie Platform: Rolled out in 2024 for marketing, this gen AI tool (named after co-founder Charles Pfizer) generates compliant content like emails, presentations, and medical article drafts. Trained on approved product data, it streamlines physician targeting and customer insights.
  • Scientific Data Cloud: AWS-powered centralization of data/ML capabilities, enabling faster research and treating 1.3 billion patients in 2022. It supports gen AI via Amazon SageMaker/Bedrock for manufacturing efficiency.
  • Global Health Grants: Through the Pfizer Foundation’s AI Learning Lab, funding supports AI for equitable healthcare access, e.g., biometric tools for community care.

6. Partnerships and Education

  • Collaborations: With AWS for cloud AI; IMI Big Picture for a 3M-sample disease database; IIT Madras for the 2025 AIPM Symposium on AI in pharma (focusing on drug discovery and precision medicine).
  • Talent and Events: Hosting webinars on AI in manufacturing (e.g., predictive maintenance, regulatory submissions) and engaging leaders like Dr. Subha Madhavan on AI for biomedical data integration.
  • Strategic Focus: $500M R&D reinvestment by 2026 targets AI for productivity, part of $7.7B cost savings. Emphasis on ethical AI, diverse datasets, and competing with global biotech advances (e.g., China’s AI in CRISPR).

Pfizer’s approach balances operational efficiency with transformative R&D, positioning AI as a core enabler rather than a standalone focus. Ongoing investments, like cloud migrations saving $47M annually and reducing CO2 emissions, underscore sustainability. For the latest, monitor Pfizer’s investor updates or events like AWS re:Invent.

Responsiveness to Big Pharma AI Initiatives by LPBI Group’s Digital IP Portfolio:

  • Scientific articles
  • e‑Books in Medicine
  • e‑Proceedings,
  • Biological images
  • Podcasts
AI Initiative at Big Pharma

i.e., Pfizer

Composed @Grok

LPBI Group’s Digital IP Asset:

Journal articles

N = 6,250

Composed by Aviva Lev-Ari

Generative AI tools

that save scientists up to 16,000 hours annually in literature searches and data analysis.

Generative AI tools searching LPBI’s Proprietary data in addition to Public Domain data sources

Journal ONTOLOGY used to optimize context classification selected for search

Drug Discovery and Development Acceleration

Pfizer uses AI, supercomputing, and ML to streamline R&D timelines

–       Run prompts by category of research on the following three dyads

–       Run ML across categories of research for these three dyads

-Gene-disease

-Disease-drug

-Gene-drug

 

Clinical Trials and Regulatory Efficiency AI:

-Predictive Regulatory Tools

-Decentralize Trials

-inventory management

Curation competences:

  • content creation across the drug lifecycle, from lab data to regulatory docs
Disease Detection and Diagnostics:

–       ATTR-CM Initiative

–       Rare diseases

Heart Failure Diagnosis by Early detection of transthyretin amyloid cardiomyopathy

–       Journal published ~30 curations by Dr. Larry on this subject ATTR-CM

–       Run NLP on this Corpus

Rare diseases:

Journal published 560 articles on Rare diseases

–       Run ML on this Corpus

Generative AI and Operational Tools:

–       Charlie Platform

–       Scientific Data Cloud AWS powered ML on centralized data

–       Amazon’s SageMaker /Bedrock for Manufacturing efficiency

–       Global Health Grants:

Pfizer Foundation’s AI Learning Lab for equitable access to care and tools for community care

Content generated in the Journal can become “generated compliant content” if run on the Charlie Platform.

–       For REUSE content in context

 

Entire Corpus of 9 Giga bytes can be ingested to Pfizer Foundation’s AI Learning Lab

–       Run prompts against it

–       Journal’s Content to be used for Internal staff expertise development

–       Journal’s Content for Leadership development

Partnerships and Education

–       Collaborations: IMI Big Picture for 3M – sample disease database

–       AI in Pharma AIPM Symposium: Drug discovery and Precision Medicine

–       Webinars of AI for biomedical data integration

–       Webinar on AI in Manufacturing

The Journal had published 547 articles in Precision Medicine

 

The Journal had published 1,114 articles in Drug Discovery

 

The Journal had published 701  articles in Drug Delivery

 

The Journal had published 3,615 articles on subject matter “Disease”

 

The Journal had published 738 articles on Biomedical topics

 

The Journal had published 425 articles on Artificial Intelligence (AI)

Strategic Focus:

–       $500M R&D reinvestment by 2026 targets AI for Productivity

–       Part of $7.7B cost savings

–       Ethical AI, diverse DBs

–       Global biotech advances: China’s AI in CRISPR

The Journal had published 432 articles on CRISPR

 

Productivity derived from Journal’s content:

–       As a result of the fact that ~70% of the Journal’s articles are curations written by Domain Knowledge Experts subjectively expressing theirs clinical interpretations of basic and primary research – the productivity of the knowledge workers at any Big Pharma would increase vastly.

–       If Grok and Claude would run on LPBI Group’s Digital IP Corpus, a scientific revolution will emerge

–       It is not combinatorics applied to molecules with 98% futile results!!!

it is the IQ of Gifted HUMANS, of domain knowledge experts generating content using individual CREATIVITY no Quantum or Super Intelligence which is not in existence, YET.

–       Foundation Models in Healthcare depends on the OUTPUT of the human creative mind. AI takes keyword (classic search) and concepts (semantic search) and run frequency of occurrence and predict the nest word, one word after the next one.

@@@@@@@

AI Initiative at Big Pharma

i.e., Pfizer

LPBI Group’s Digital IP Asset:

e-Books

Domain-aware Editorials and Curations

Generative AI tools that save scientists up to 16,000 hours annually in literature searches and data analysis. The electronic Table of Contents of every e-book is a CONCEPTUAL MASTER PIECE of one unique occurrence in Nature generated by the Editor, or the Editors that had

–       Commissioned articles for the e-Book

–       Had selected articles from collections of Categories of Research created by domain knowledge experts

–       Had reviewed the TOTALITY of the Journal’s Ontology and found new concept to cover in the e-Book not originally planned

Had incorporated Highlights of Lectures given at 100 Conferences LPBI Group’s Dr. Lev-Ari and Dr. Willians had cover in Real Real, by invitation, only as PRESS.

–       The vision of the Editor-in-Chief of the BioMed e-Series reflects the BIG PICTURE of Patient care delivery.

–       UC, Berkeley PhD’83

–       Knowledge student and Knowledge worker, 10/1970 to Present

–       Conceptual pioneer of 26 algorithms in Decision Science of Operations Management decision support systems

–       2005 to Present in the Healthcare field.

–       2005-2012: Clinical Nurse Manager in Post-acute SNF settings and Long-term Acute care Hospital Supervisor – had developed a unique view on Diagnosis, Therapeutics and Patient care delivery

–       The BioMed e-Series is the EPITOM of human CREATIVITY in Healthcare an OPUS MAGNUM created by collaboration of top Scientists, Physicians and MD/PhDs

–       The 48 e-Books Published by LPBI Group – represent the ONLY one Publisher on Amazon.com with +151,000 pages downloaded since the 1st e-book published on 6/2013 and since Pay-per-View was launched by Amazon.com in 2016.

Drug Discovery and Development Acceleration Pfizer uses AI, supercomputing, and ML to streamline R&D timelines Two volumes on the BioMed e-Series were subjected to Medical Text Analysis with AI, ML, Natural Language Processing (NLP).

–       Cancer, Volume 1 (In English, part of the Spanish Edition, Series C)

–       Genomics, Volume 2 (In English, part of the Spanish Edition, Series B)

–       GPT capabilities are warranted to attempt to subject to ML Analytics every book of the MUTUALLY EXCLUSIVE 48 URLs provided by Amazon.com to LPBI Group, the Publisher.

–       5 URLs for 5 Bundles in The English Edition: Series A,B,C,D,E – English Edition

–       All books in each series – 5 Corpuses for domain-aware Small Language Model in English

–       All books in each series – 5 Corpuses for domain-aware Small Language Model in Spanish

–       5 URLs for 5 Bundles in The Spanish Edition: Series A,B,C,D,E –Spanish Edition

 

Clinical Trials and Regulatory Efficiency AI:

-Predictive Regulatory Tools

-Decentralize Trials

-inventory management

Disease Detection and Diagnostics:

–       ATTR-CM Initiative

–       Rare diseases

–       No one had attempted ML on every book, only two books were analyzed by ML.

–       No one had attempted ML on all the Volumes in any of the 5 Series.

–       No one had attempted ML on all the 48 books

–       WHEN that will be done – a REVOLUTION on Disease Detection and Diagnostics will be seen for the first time because the totality of these 48 books represent the Brains of Human Experts

 

Generative AI and Operational Tools:

–       Charlie Platform

–       Scientific Data Cloud AWS powered ML on centralized data

–       Amazon’s SageMaker/Bedrock for Manufacturing efficiency

–       Global Health Grants:

Pfizer Foundation’s AI Learning Lab for equitable access to care and tools for community care

Add the content of all the Books to Charlie Platform
Partnerships and Education

 

Collaborations: IMI Big Picture for 3M – sample disease database

 

AI in Pharma AIPM Symposium: Drug discovery and Precision Medicine

 

Webinars of AI for biomedical data integration

 

Webinard on Ai in Manufacturing

e-Books are the SOURCE for Education

–       Offer the books as Partnership sustenance

Strategic Focus:

–       $500M R&D reinvestment by 2026 targets AI for Productivity

–       Part of $7.7B cost savings

–       Ethical AI, diverse DBs

–       Global biotech advances: China’s AI in CRISPR

URLs for the English-language Edition by e-Series:

Series A: Cardiovascular Diseases ($515)

https://www.amazon.com/gp/product/B07P981RCS?ref_=dbs_p_mng_rwt_ser_shvlr&storeType=ebooks

Series B: Frontiers in Genomics ($200)

https://www.amazon.com/gp/product/B0BSDPG2RX?ref_=dbs_p_pwh_rwt_anx_b_lnk&storeType=ebooks

Series C: Cancer & Oncology ($175)

https://www.amazon.com/gp/product/B0BSDWVB3H?ref_=dbs_p_mng_rwt_ser_shvlr&storeType=ebooks

Series D: Immunology ($325)

https://www.amazon.com/gp/product/B08VVWTNR4?ref_=dbs_p_pwh_rwt_anx_b_lnk&storeType=ebooks

Series E: Patient-Centered Medicine ($274)

https://www.amazon.com/gp/product/B0BSDW2K6C?ref_=dbs_p_mng_rwt_ser_shvlr&storeType=ebooks

 

@@@@@@@

AI Initiative at Big Pharma

i.e., Pfizer

LPBI Group’s Digital IP Asset:

e-Proceedings: N = +100, and

Tweet Collections: N = +50

Generative AI tools that save scientists up to 16,000 hours annually in literature searches and data analysis.
Drug Discovery and Development Acceleration Pfizer uses AI, supercomputing, and ML to streamline R&D timelines List of all e-Proceeding of +100 TOP Conferences in Biotech, in Medicine, in Genomics, in Precision Medicine

https://pharmaceuticalintelligence.com/press-coverage/part-two-list-of-biotech-conferences-2013-to-present/

In these conferences the Frontier of Science was presented, ofter BEFORE publication findings were revealed. These Proceedings are the ONLY written record of the events. They are privately-held, now for the first time available for Transfer of Ownership 

The Tweet Collection are QUOTES of speakers on record. NOT ELSEWHERE available by name of speaker and affiliation

Clinical Trials and Regulatory Efficiency AI:

-Predictive Regulatory Tools

-Decentralize Trials

-inventory management

Disease Detection and Diagnostics:

–       ATTR-CM Initiative

–       Rare diseases

Generative AI and Operational Tools:

–       Charlie Platform

–       Scientific Data Cloud AWS powered ML on centralized data

–       Amazon’s SageMaker/Bedrock for Manufacturing efficiency

–       Global Health Grants:

Pfizer Foundation’s AI Learning Lab for equitable  access to care and tools for community care

Ingest to Charlie Platform ALL e-Proceedings of ALL Conferences

 

Apply GPT:

Training Data:

–       One conference at a time

–       All Conference on ONE subject matter, i.e., Immunotherapy, Oncolytic Virus Immunotherapy, Immune Oncology

Partnerships and Education

–       Collaborations: IMI Big Picture for 3M – sample disease database

–       AI in Pharma AIPM Symposium: Drug discovery and Precision Medicine

–       Webinars of AI for biomedical data integration

–       Webinar on Ai in Manufacturing

Use Past Conference Agendas to build Future Conference Agendas

Use Speakers Lists to invite speakers/consultants to your events

Use topics covered in Conferences for Employee training & and in-house Leadership development

Strategic Focus:

–       $500M R&D reinvestment by 2026 targets AI for Productivity

–       Part of $7.7B cost savings

–       Ethical AI, diverse DBs

–       Global biotech advances: China’s AI in CRISPR

Having access to +100 e-Proceedings vs Not having access to this resource is a make or break in fine-tuning Corporate Branding: All your competitors attended and had sent Speakers

  • LPBI Group’s e-Proceedings is the only record in one URL

@@@@@@

AI Initiative at Big Pharmas

i.e., Pfizer

LPBI Group’s Digital IP Asset:

Biological Images selected by Experts embedded in original Text (Prior Art)

Generative AI tools that save scientists up to 16,000 hours annually in literature searches and data analysis.
Drug Discovery and Development Acceleration Pfizer uses AI, supercomputing, and ML to streamline R&D timelines Gallery of ~8,000 Biological images and captions is a Treasure TROVE for scientific article writing, Presentation preparations. This Media Gallery is an Art collection of top Scholars in Medicine and Biology
Clinical Trials and Regulatory Efficiency AI:

-Predictive Regulatory Tools

-Decentralize Trials

-inventory management

Disease Detection and Diagnostics:

–       ATTR-CM Initiative

–       Rare diseases

Gallery of ~8,000 Biological images and captions is a Treasure TROVE for Disease Detection and Diagnostics

 

Generative AI and Operational Tools:

–       Charlie Platform

–       Scientific Data Cloud AWS powered ML on centralized data

–       Amazon’s SageMaker/Bedrock for Manufacturing efficiency

–       Global Health Grants:

Pfizer Foundation’s AI Learning Lab for equitable  access to care and tools for community care

  • Ingest into Charlie Platform the Media Gallery for generation of Medical article drafts
Partnerships and Education

–       Collaborations: IMI Big Picture for 3M – sample disease database

–       AI in Pharma AIPM Symposium: Drug discovery and Precision Medicine

–       Webinars of AI for biomedical data integration

–       Webinar on Ai in Manufacturing

Strategic Focus:

–       $500M R&D reinvestment by 2026 targets AI for Productivity

–       Part of $7.7B cost savings

–       Ethical AI, diverse DBs

–       Global biotech advances: China’s AI in CRISPR

@@@@@@

AI Initiative at Big Pharma

i.e., Pfizer

LPBI Group’s Digital IP Asset:

Library of Audio and Video Podcasts

N = +300

Generative AI tools that save scientists up to 16,000 hours annually in literature searches and data analysis.
Drug Discovery and Development Acceleration Pfizer uses AI, supercomputing, and ML to streamline R&D timelines Review ALL SCIENTIFIC BREAKTHROUGHS

  • Two criteria for Classifications used by Prof. Marcus W. Feldman and by Dr. Stephen J. Williams to generate the two classifications

https://pharmaceuticalintelligence.com/biomed-audio-podcast-library-lpbi-group/

Clinical Trials and Regulatory Efficiency AI:

-Predictive Regulatory Tools

-Decentralize Trials

-inventory management

Disease Detection and Diagnostics:

–       ATTR-CM Initiative

–       Rare diseases

Aviva Lev-Ari, PhD, RN, Stephen J. Williams, PhD and Prof. Marcus W. Feldman Health Care Policy Analysis derived from the Farewell remarks from AMA President Jack Resneck Jr., MD | AMA 2023 Annual Meeting

LISTEN to Audio Podcast

Future of Medicine

https://pharmaceuticalintelligence.com/2023/06/10/health-care-policy-analysis-derived-from-the-farewell-remarks-from-ama-president-jack-resneck-jr-md-ama-2023-annual-meeting/

Generative AI and Operational Tools:

–       Charlie Platform

–       Scientific Data Cloud AWS powered ML on centralized data

–       Amazon’s SageMaker/Bedrock for Manufacturing efficiency

–       Global Health Grants:

Pfizer Foundation’s AI Learning Lab for equitable  access to care and tools for community care

  • Ingest to Charlie Platform all +300 Podcasts for Foundation’s AI Learning Lab
Partnerships and Education

–       Collaborations: IMI Big Picture for 3M – sample disease database

–       AI in Pharma AIPM Symposium: Drug discovery and Precision Medicine

–       Webinars of AI for biomedical data integration

–       Webinard on Ai in Manufacturing

  • Use Podcast for Education
  • Use Podcast as Hybrid: Start presentation with a Podcast continue with a life interview

Examples of an Audio Podcast of Scientists on LPBI Group Team in the past:

  • Podcast with Dr. Larry H. Bernstein, MD, FCAP, Interview by Gail S. Thornton, PhDc, Narrator’s Voice: Stephen J. Williams, PhD

https://pharmaceuticalintelligence.com/audio-podcasts/podcast-with-dr-larry-h-bernstein-md-fcap-interview-by-gail-s-thornton-phdc-narrators-voice-stephen-j-williams-phd/

  • Podcast with Prof. Marcus W. Feldman, PhD, Biology Department, Stanford University, Interview by Gail S. Thornton, PhDc

https://pharmaceuticalintelligence.com/audio-podcasts/podcast-with-prof-marcus-w-feldman-phd-biology-department-stanford-university-interview-by-gail-s-thornton-phdc/

  • Podcast with Dr. Sudipta Saha, PhD, Interview by Gail S. Thornton, PhDc, Narrator’s Voice: Gail S. Thornton, PhDc

https://pharmaceuticalintelligence.com/audio-podcasts/podcast-with-dr-sudipta-saha-phd-interview-by-gail-s-thornton-phdc-narrators-voice-gail-s-thornton-phdc/

Strategic Focus:

–       $500M R&D reinvestment by 2026 targets AI for Productivity

–       Part of $7.7B cost savings

–       Ethical AI, diverse DBs

–       Global biotech advances: China’s AI in CRISPR

Dr. Lev-Ari Prompted @Grok on 11/18/2025:

AI-Driven Cost Savings in Big Pharma   

@Grok responded:

AI-Driven Cost Savings in Big PharmaArtificial intelligence (AI) applications across the pharmaceutical value chain—particularly in drug discovery, clinical trials, and operations—have the potential to generate substantial savings for major pharmaceutical companies (often referred to as “Big Pharma”). Based on recent industry reports and analyses from 2024-2025, these savings vary by application but could collectively reach tens of billions annually by the late 2020s. Projections indicate AI could add up to 11% in value relative to revenue for biopharma firms over the next five years through productivity gains and cost reductions. Below, I break down the estimated savings levels by key areas, drawing from credible sources like McKinsey, Deloitte, IQVIA, and others.

  1. Clinical Trials

  • Annual Industry-Wide Savings: By 2030, AI integration into 60-70% of clinical trials could save the pharmaceutical industry $20-30 billion per year through faster timelines, better patient matching, and reduced administrative costs.
  • Per-Trial Cost Reduction: AI can cut trial costs by up to 70% and shorten durations by 80%, enabling quicker regulatory submissions (40% faster) with 50% improved cost efficiency. For example, AstraZeneca reported up to 25% shorter trial durations in cancer drug studies using AI for dose optimization and biomarker identification.
  • Specific Efficiency Gains: Feasibility surveys can see 90% time reductions using AI/ML tools.
  1. Drug Discovery and Development

  • R&D Cost Drop: AI could reduce drug discovery costs by up to 40%, with overall development timelines shrinking from 5 years to 12-18 months (an 80% cut in some cases). From discovery to preclinical candidate stage, timelines can decrease by up to 50%.
  • Total Clinical Development Savings: Projected at $25 billion across the sector, driven by AI-accelerated pipelines.
  1. Operations and Broader Impacts

  • Value Relative to Revenue: Biopharma AI investments may yield up to 11% additional value (e.g., via cost efficiencies and revenue growth) over five years. For related medtech segments, savings could hit 12% of total revenue within 2-3 years.
  • Operating Profits Boost: By 2030, AI could add $254 billion in annual operating profits industry-wide through productivity jumps (e.g., 50-100% in quality control) and lead time reductions (60-70%).
  • Time-to-Market: Up to 10% faster overall, with production KPIs improving revenue by 25%.

These estimates assume scaled adoption, with global AI spending in pharma rising from ~$3 billion in 2025 to $22-25 billion by 2027-2030. Challenges like high initial costs and data infrastructure may temper short-term gains, but early adopters (e.g., Pfizer, Novartis) are already seeing ROI. For context, the global pharma market is projected at $1.6 trillion by 2025, so even modest percentages translate to billions in savings. If you need details on a specific AI use case or company, let me know!

SOURCE

https://x.com/i/grok?conversation=1990851703051104519

 

Dr. Lev-Ari Prompted @Grok on 11/17/2025:

Pfizer, its competitors by size, market share, product lines and Investment in AI technologies

Grok responded

https://x.com/i/grok?conversation=1990458795936354506

Overview of Pfizer and Key CompetitorsPfizer is one of the world’s largest pharmaceutical companies, with a strong focus on innovative medicines and vaccines. Its primary competitors include Merck & Co., Johnson & Johnson (J&J), Roche, Novartis, and now AstraZeneca, based on revenue leadership and market overlap in areas like oncology, immunology, and vaccines. These companies dominate the global pharmaceutical industry, which is projected to reach $1.21 trillion in revenue by 2025. Below, I compare them across size (measured by 2024 revenue and employees), market share (approximate global pharma share based on 2024 revenues), product lines (key therapeutic areas and top products), and investments in AI technologies. Data reflects the latest available figures as of late 2025.
Here are the same comparisons with more concise tables (2024 data, latest available as of Nov 2025):
Size (2024 Revenue & Employees)
Company
Revenue (USD B)
Employees
Merck & Co.
64.2
70,000
Pfizer
63.6
88,000
Roche
~58.3
103,000
J&J (pharma only)
57.8
138,000
AstraZeneca
54.1
94,300
Novartis
~50.0
76,000
Approx. Global Pharma Market Share
Company
Share %
Merck & Co.
4.3
Pfizer
4.2
J&J / Roche
3.9
AstraZeneca
3.6
Novartis
3.3
Key Product Lines & Top Sellers (2024 revenue, USD B)
Company
Main Areas
Top Products (revenue)
Pfizer
Vaccines, cardiology, oncology
Eliquis (7.3), Prevnar (6.4), Vyndaqel (5.4)
Merck & Co.
Oncology, vaccines
Keytruda (25.0), Gardasil (8.6)
J&J
Immunology, oncology
Stelara (10.9), Darzalex (9.7)
AstraZeneca
Oncology, CVRM, respiratory
Farxiga (7.7), Tagrisso (6.6), Enhertu (4.0)
Roche
Oncology, neurology, hemophilia
Ocrevus (5.7), Hemlibra (4.0)
Novartis
Cardiology, immunology
Entresto (6.6), Cosentyx (5.2)

AI Investment Snapshot (2025)
Company
AI Highlights (2025)
Scale/Impact
Pfizer
AI cuts discovery from years → 30 days; heavy partnerships
Leader in adoption
AstraZeneca
Evinova AI trials unit; $2.5B AI Beijing hub; 12k+ staff upskilled
Very aggressive (>85% productivity gain)
Merck & Co.
Gen-AI for protocols; 20+ AI “blockbusters” in pipeline
>$1.2B spend
J&J
900+ AI projects → $500M savings; surgical AI training
Broad internal rollout
Roche
AI diagnostics + drug discovery; $55M Manifold Bio deal
Strong in diagnostics
Novartis
AI pipeline acceleration; data-science alliances
Integrated into $10B R&D
Dr. Lev-Ari’s Prompt:
  • AI in biotech startups
Searched for “(“AI” OR “artificial intelligence”) (“biotech” OR “biotechnology”) startup since:2025-01-01″
10 results
Show All (2)

AI in Biotech Startups:

2025 LandscapeArtificial Intelligence (AI) is revolutionizing biotech startups by accelerating drug discovery, optimizing clinical trials, and enabling personalized medicine. In 2025, AI applications like generative models for molecule design and predictive analytics for protein structures are slashing R&D timelines from years to months, reducing costs by up to 30%, and boosting success rates. The sector blends biology’s complexity with AI’s data-crunching power, drawing massive VC interest amid ethical debates on gene editing and biosecurity.Key Trends

  • Explosive Funding Growth: U.S. healthcare VC hit $23B in 2024, with ~30% ($5.6B) targeting AI-biotech—nearly triple 2023 levels. Biopharma startups raised $24.2B across 568 deals, up from $10.1B in 2023. Q3 2025 saw $97B global VC (up 38% YoY), half to AI firms. Mega-rounds ($100M+) surged, focusing on drug discovery and rare diseases.
  • Market Expansion: Global AI-biotech market: $4.6B in 2025, projected to $11.4B by 2030 (20% CAGR). Biotech overall to $5.85T by 2034 (13.6% CAGR), driven by AI in gene editing, microbiome therapeutics, and automation.
  • Compute Demands: Biotech AI requires massive GPUs; Nvidia’s AI sales hit $41.1B in one 2025 quarter (56% YoY). Startups lean on cloud partnerships (e.g., AWS-Recursion) or in-house clusters, with hyperscalers eyeing $3-4T infrastructure by 2030.
  • Regional Hotspots: North America leads (42% share) via FDA support and hubs like Boston/SF; Europe grows via funding/regulatory advances; Asia (e.g., China) via collaborations.
  • Challenges & Ethics: Selective funding favors clinically validated firms; rising M&A (big pharma acquiring AI startups); ethical scrutiny on AI gene editing (e.g., CRISPR enhancements).

 

Notable Startups & Recent Funding

Here’s a snapshot of standout AI-biotech startups, highlighting innovations and 2024-2025 funding:

Startup
Focus Area
Key Innovation
Recent Funding (2025)
Insilico Medicine
Drug Discovery
Generative AI for novel molecules
$100M+ Series D (ongoing)
Recursion Pharmaceuticals
Phenomics & Drug Repurposing
AI mapping diseases via cell images
$50M partnership w/ Nvidia
Absci Corp.
Protein Design
AI-generated antibodies/proteins
$20M from AMD (Jan 2025)
TandemAI
Drug Discovery
ML for molecular simulation
$22M Series A extension
Red Queen Bio
Biosecurity
AI for pathogen detection/design
$15M Seed led by OpenAI
Antiverse
Antibody Design
AI predicting antibody structures
Deal w/ Nxera Pharma (2024)
Deep Genomics
Genomics
AI extracting insights from DNA data
VC round undisclosed
Aizen Therapeutics
Molecule Generation
Proprietary AI engines for trials
Early-stage VC

These firms exemplify AI’s shift from hype to pipeline impact—e.g., Insilico’s AI-discovered drug entered Phase II trials in record time.Emerging ApplicationsAI’s top uses in biotech startups:

  1. Drug Discovery: ML predicts drug-target interactions (e.g., AlphaFold-inspired tools cut screening costs 70%).
  2. Genomics & Diagnostics: AI analyzes vast datasets for rare variants, powering precision oncology.
  3. Clinical Trials: Predictive models optimize patient matching, reducing failures by 20-30%.
  4. Synthetic Biology: AI designs custom microbes for therapeutics or biofuels.
  5. Automation Labs: AI-robotics handle experiments autonomously, boosting throughput 10x.

Future Outlook

2025 signals a “quality over quantity” pivot: Investors prioritize AI startups with real-world data and partnerships (e.g., Y Combinator, Google for Startups). M&A will rise as big pharma (Pfizer, Merck) snaps up talent. Yet, compute shortages and regs (e.g., FDA AI guidelines) pose hurdles. For founders, blending AI with wet-lab validation is key to unlocking the next wave of breakthroughs—potentially curing diseases once deemed untreatable. If you’re building or investing, focus on
  • rare diseases or
  • oncology

for the hottest bets.

Additional Competitors by Product Line

@Grok Response

https://x.com/i/grok/share/Ple3W4IDlwhyjUwBUU4JAg2OD

Key Products and Focus AreasPfizer’s portfolio spans immunology, oncology, cardiology, endocrinology, neurology, and vaccines. In 2024, its top revenue generators included:

  • Eliquis (apixaban, blood thinner): $7.3 billion (11% of total revenue).
  • Prevnar family (pneumococcal vaccines): $6.4 billion (10%).
  • Paxlovid (COVID-19 antiviral): $5.7 billion (9%).
  • Vyndaqel (tafamidis, for rare heart disease): $5.4 billion (8%).
  • Comirnaty (COVID-19 vaccine): $5.3 billion (8%).
  • Ibrance (palbociclib, breast cancer drug): $4.3 billion (6%).

The company is investing heavily in AI-driven drug discovery (e.g., 2024 partnerships with NVIDIA and Saama) and next-gen therapies like RSV vaccines, gene therapies for muscular dystrophy, and oral GLP-1 drugs for obesity/diabetes. Challenges include patent expirations (e.g., Eliquis in 2026-2028) and biosimilar competition, but Pfizer’s diversified pipeline positions it for mid-single-digit growth in 2025.Pfizer’s Main CompetitorsPfizer operates in a highly competitive $1.5 trillion global pharma market, where rivals vie for dominance in oncology, vaccines, immunology, and emerging areas like obesity and gene therapy. Its primary competitors are fellow “Big Pharma” giants, often overlapping in therapeutic areas. Based on revenue, market share, and direct product rivalries, here are the top ones (ranked roughly by 2024 revenue for context):

Competitor
Headquarters
2024 Revenue (Pharma Segment)
Key Strengths & Overlaps with Pfizer
Notable Products
Johnson & Johnson (J&J)
New Brunswick, NJ, USA
$88.8 billion (total; pharma ~$57.8 billion)
Diversified (pharma, devices, consumer); strong in oncology, immunology, vaccines. Competes directly in blood thinners and cancer therapies.
Darzalex (multiple myeloma), Stelara (psoriasis), Imbruvica (blood cancer).
Merck & Co.
Rahway, NJ, USA
$64.2 billion
Oncology leader; vaccines and antivirals. Keytruda outsells Pfizer’s Ibrance; rivals in HPV/pneumococcal vaccines.
Keytruda (immunotherapy, $29.5 billion), Gardasil (HPV vaccine).
Roche Holding AG
Basel, Switzerland
~$68 billion (group; pharma ~$50 billion)
Diagnostics + pharma powerhouse; dominates oncology and neurology. Competes in antibody-drug conjugates post-Pfizer’s Seagen buy.
Ocrevus (MS), Hemlibra (hemophilia), Avastin (cancer).
AbbVie Inc.
North Chicago, IL, USA
$56.3 billion
Immunology and neuroscience focus; biosimilars erode shared markets like Humira vs. Pfizer’s Enbrel alternatives.
Humira (rheumatoid arthritis), Skyrizi (psoriasis), Rinvoq (arthritis).
Novo Nordisk A/S
Bagsværd, Denmark
~$40 billion (est.)
Diabetes/obesity specialist; exploding GLP-1 demand challenges Pfizer’s emerging obesity pipeline.
Ozempic/Wegovy (semaglutide for diabetes/weight loss).
Eli Lilly and Co.
Indianapolis, IN, USA
~$45 billion (est.; projecting $58-61 billion in 2025)
Diabetes/obesity and neurology; Mounjaro rivals Pfizer’s danuglipron in GLP-1 space.
Mounjaro/Zepbound (tirzepatide), Verzenio (breast cancer).
AstraZeneca PLC
Cambridge, UK
$50.95 billion
Oncology, respiratory, and cardiovascular; Tagrisso competes with Pfizer’s Lorbrena in lung cancer.
Tagrisso (lung cancer), Farxiga (diabetes/heart), Imfinzi (immunotherapy).
Novartis AG
Basel, Switzerland
~$48 billion
Gene therapy and immunology; rivals in rare diseases and oncology.
Cosentyx (psoriasis), Entresto (heart failure), Kisqali (breast cancer).
Bristol-Myers Squibb (BMS)
New York, NY, USA
$47.8 billion
Oncology and immunology; Opdivo directly competes with Pfizer’s Bavencio in checkpoint inhibitors.
Opdivo (immunotherapy), Eliquis (co-developed with Pfizer, but BMS handles ex-US).
Sanofi S.A.
Paris, France
~$46 billion
Vaccines and rare diseases; Dupixent challenges in immunology; rivals Prevnar in pneumococcal vaccines.
Dupixent (atopic dermatitis), Lantus (diabetes).

These competitors collectively hold over 50% of the global pharma market share. Emerging threats include biotech upstarts like Moderna (mRNA vaccines, directly rivaling Comirnaty) and generics firms like Teva (eroding post-patent revenues). In 2025, competition intensifies in obesity (Novo/Lilly lead) and oncology (Merck/Roche dominate), with tariffs and pricing pressures (e.g., US executive orders) affecting all.Pfizer’s edge comes from its scale and partnerships (e.g., BioNTech for mRNA), but it must navigate revenue dips from COVID fade-out and biosimilars. For 2025 projections, analysts expect 6-9% growth across the sector, with Pfizer targeting modest gains through oncology expansions. If you’d like deeper dives on specific rivals, financials, or products, let me know!

AI Acquisitions by Big Pharma

2 days ago • Visible to anyone on or off LinkedIn

AI in Pharma: From Tool to Value Creator 🚀

Over the past 5 years, pharma’s AI footprint has expanded rapidly and the investment trends tell a clear story.

💡 ~60% of collaborations and acquisitions now focus on TargetDiscovery and Validation — pharma’s main frontier to shorten early-stage R&D timelines and boost success rates through PrecisionBiology.
⚗️ The second-largest area (~25%) centers on AI-driven DrugDesign and MoleculeOptimization, where algorithms accelerate CandidateSelection, refine molecular properties, and enable NewModalities such as Biologics and CellAndGeneTherapies.
🏆 Among top players, Eli Lilly and Company stands out as the most active investor — making AI a true StrategicCapability, not just another research tool.

The takeaway?
AI isn’t just supporting pharma anymore, it’s reshaping it.

Source: Bita Sehat, PhD, MBA

hashtagai hashtaglifesciences hashtagpharmaceuticals hashtagtechbio hashtagbiotech

table

Article was summarized by @Grok on 11/29/2025
Summary of the Article:
“Authentic Relevance of LPBI Group’s Portfolio of IP as Proprietary Training Data Corpus for AI Initiatives at Big Pharma”
This November 15, 2025, article on PharmaceuticalIntelligence.com (curated by LPBI Group) makes a compelling case for leveraging LPBI’s decade-plus of expert-curated digital IP as a high-fidelity, rights-clean training corpus to supercharge AI-driven innovation in Big Pharma. It contrasts the limitations of generic LLMs (like GPT) with the need for domain-specific, ontologized biomedical data, positioning LPBI’s assets as a “defensible moat” for accelerating R&D in drug discovery, precision medicine, and beyond. The piece blends market analysis of pharma giants with a deep dive into LPBI’s portfolio, emphasizing its multimodal, metadata-rich structure for NLP, knowledge graphs, and fine-tuning SLMs/LLMs.IntroductionThe thesis: In an era where AI investments in pharma (e.g., Eli Lilly’s aggressive funding) focus on slashing R&D timelines by 60%+ in target discovery and 25% in drug design, LPBI’s proprietary corpus—built since 2012 via human curation, digitization, and ontology mapping—offers unmatched authenticity over web-scraped data. It addresses GPT’s biomedical shortcomings (e.g., failing to infer fusion proteins or noncanonical pathways without curated inputs) and highlights LPBI’s foresight in text analysis for generative AI augmentation. A key quote from Data2Discovery: “We are able to improve drug discovery now as well as demonstrating new fast-cycle AI-driven processes that will have a revolutionary impact on drug discovery if fully implemented.”Portfolio OverviewLPBI’s ~9 GB, debt-free, multimodal corpus is privately held, expert-curated (e.g., by Prof. Marcus W. Feldman and Dr. Stephen J. Williams), and ingest-ready for AI pre-training/evaluations. It spans five key asset classes, each with metadata exports, timestamps, crosslinks, and centralized rights for model training:

 

Asset Class
Description & Size
Unique Value Proposition
I: Scientific Articles
6,250+ articles on PharmaceuticalIntelligence.com (~2.5M views); covers genomics, oncology, immunology, etc.
Live ontology, author/role labels, view histories; enables temporal NLP for trend analysis.
II: e-Books
48 bilingual (English/Spanish) volumes in 5 BioMed e-Series (e.g., Series A: Cardiovascular, 6 vols., $515 total; Series E: Patient-Centered, 4 vols., $274); 151,000+ page downloads; 2,728 articles.
Peer-reviewed, senior-editor TOCs; pay-per-view model proves demand; ideal for entity-relationship extraction.
III: e-Proceedings
100+ from biotech/genomics conferences (2013–2025); +50 tweet collections as speaker quotes with affiliations.
Real-time event curation; captures emerging insights for knowledge graph augmentation.
V: Biological Images
7,500+ images in Digital Art Media Gallery; embedded as prior art in texts.
Expert-contextualized visuals; supports multimodal AI for image-text pairing in diagnostics.
X: Audio Podcasts
300+ interviews with scientific leaders (e.g., Nobel laureates like Jennifer Doudna); classified by themes like CRISPR, mRNA vaccines.
Transcripts + NLP WordClouds; adds auditory/verbal depth for voice-enabled AI copilots.

The portfolio’s “living ontology” allows seamless integration into tools like InfraNodus for concept mapping.AI Training RelevanceUnlike PubMed’s unstructured dumps, LPBI’s assets are pre-annotated for concept extraction (e.g., gene-disease-drug dyads), reducing hallucinations and bias in LLMs. A case study integrates curation with ChatGPT-5: Manual ontology + knowledge graphs uncovered novel WNT/Hedgehog interactions in lung cancer, generating research questions like: “How does the interaction between [[EGFR]] mutations and sex-specific gene alterations, including [[RBM10]], influence treatment outcomes in lung adenocarcinoma?” This hybrid approach outperforms solo GPT, proving the corpus’s role in trustworthy biomedical inference.Applications

  • Drug Discovery: ML prompts on dyads to mimic Pfizer’s AI (e.g., reducing discovery from years to months); supports biologics/cell therapies.
  • Precision Medicine: 547 articles for patient subtyping; 3,615 disease-focused pieces for predictive modeling.
  • Diagnostics & Rare Diseases: 560 rare disease articles + 30 on ATTR-CM for early detection (e.g., via Pfizer’s ASPIRE AI).
  • Clinical/Regulatory: Streamlines trials, evidence synthesis, and content generation (e.g., via Pfizer’s “Charlie” copilot, saving hours on lit reviews).
  • Generative Tools: Fine-tune for compliant, domain-aware outputs in medical affairs/safety.

Challenges & Solutions

  • Data Quality/Bias: Unstructured text leads to GPT errors; solved by expert curation + ontology for accurate, diverse inputs.
  • Regulatory Compliance: Rights fragmentation; addressed via LPBI’s centralized assignment for NDA-secure licensing.
  • Scalability: Generic data overload; LPBI’s focused, high-signal corpus enables fast-cycle AI without noise.

Recommendations

Urge Big Pharma (e.g., Pfizer, Merck—table highlights Merck’s $64.2B revenue, Keytruda focus) to acquire the full portfolio for end-to-end knowledge bases, or license under NDA for SLM/LLM training (English/Spanish).
  • Emphasizes “buy the moat” for competitive edge in 2025’s 6–9% sector growth (obesity/oncology hotspots).
Contact: avivalev-ari@alum.berkeley.edu.
Conclusion
LPBI’s corpus isn’t just data—it’s a “scientific revolution enabler,” blending human creativity with AI for transformative pharma impact. Validated on extraction tasks, it’s primed for partnerships, outshining combinatorial predictions with authentic, curated depth. This article builds on prior LPBI mappings (e.g., our podcast TOC summary), reinforcing the portfolio’s strategic fit for AI.
For deeper analysis or related assets, let me know!

Read Full Post »

Real Time Conference Coverage: Advancing Precision Medicine Conference, Afternoon Omics Session Track 2 October 3 2025

Reporter: Stephen J. Williams, PhD

Leaders in Pharmaceutical Business Intellegence will be covering this conference LIVE over X.com at

@pharma_BI

@StephenJWillia2

@AVIVA1950

@AdvancingPM

using the following meeting hashtags

#AdvancingPM #precisionmedicine #WINSYMPO2025

4:20-4:40

Andrea Ferreira-Gonzalez

 

  • APOE was marker for defining a long term survivor and short term survivor for ovarian cancer patients; the markers were in the stroma
  • there is spatial communication between tumor and underlying stroma
  • it is imperative to understand how your multiomics equipment images a tumor area before it laser captures and send to the MS system; can lose a lot of tissue and information based on differences in resolution
  • many of these multiomics systems are validated for the clinic in EU not US
  • multiomics spatial analysis allows you to image protein, metabolite, mRNA expression in the 3 dimensional environment of the tumor (tumor cells and stroma)
  • they are making a human tumor atlas
  • they say a patient who had tumor went home during COVID and took vaccine but got ill with vaccine; but came back to check tumor and tumor had greatly regressed because prevaccine the tumor was immunologically cold and post COVID vaccine any left over tumor showed great infiltration of immune cells

4:40-4:55

Andrea Ferreira-Gonzalez

Aruna Ayer, PhDVP, Multiomics, Innovation and Scientific AffairsBD Biosciences

  • BD Bioscience multiomics platform is modular and can add more omics levels in the platorm
  • for example someone wanted to look at T cells
  • people have added CRISPR screens on the omics platform
  • most people are using single cell spatial omics
  • they have a FACS on their platform too so you can look at single cell spatial omics and sort different cellular populations
  • very comparative to 10X Genomics platform
  • their proteomics is another layer you can add on their platform however with proteomics you can high background notice with spatial proteomics or a limited panel of biomarkers
  • Their OMICS Protein One panels are optimized for biology and tumor type.
  • get high quality multiomics data and proteomics data but in a 3D spatial format
  • developed Cellismo Data Visualization software tool

4:55-5:10

Andrea Ferreira-Gonzalez

Harsha Gowda, PhDSenior Principal Scientist, Director, Research & Lab Operations, Signios Bio

Signios Biosciences (Signios Bio) is the US-based arm of MedGenome, a global leader in genetic testing services, genomics research, and drug discovery solutions.

Signios Bio is a multiomics and bioinformatics company dedicated to revealing the intricate signals within biological data. We leverage the power of multiomics—integrating data from genomics, transcriptomics, proteomics, epigenomics, metabolomics, and microbiomics—to gain a comprehensive understanding of disease biology. Our AI-powered bioinformatics platform allows us to efficiently analyze these complex datasets, uncovering hidden patterns and accelerating the development of new therapies and diagnostics.

Through the integration of cutting-edge multiomics technologies, advanced bioinformatics, and the expertise of world-class scientists, we enable researchers and clinicians with comprehensive, end-to-end solutions to improve drug discovery and development and advance precision medicine.

As part of MedGenome, we have access to real-world evidence (RWE) from global research networks across the US, Europe, Asia, Africa, Middle East, and Latin America. This access enables us to work with our partners to uncover insights that can lead to new biomarkers and drug targets, ensuring that precision medicine is inclusive and effective for all.

https://www.signiosbiolcom 

  • their platform can do high throughput analysis of patient tumors (like gallbladder cancer) analyzing mutational spectrum with high dimensionality
  • they can integrate genomic and transcriptomics data to reveal multiple pathways affected in patient data
  • have used their platform to investigate spatial omics in lung cancer

Read Full Post »

Real Time Coverage Advancing Precision Medicine Annual Conference, Philadelphia PA November 1,2 2024

Reporter: Stephen J. Williams, Ph.D.

Source: https://www.advancingprecisionmedicine.com/apm-annual-conference-and-exhibition-in-philadelphia/ 

This event will be covered by the LPBI Group on Twitter.  Follow on

@Pharma_BI

@StephenJWillia2

@Aviva1950

@AdvancingPM

using the following meeting hashtags

#AdvancingPM #precisionmedicine

The Advancing Precision Medicine (APM) Annual Conference 2024 will take place at the Pennsylvania Convention Center in Philadelphia,  November 1-2, 2024. Located in the heart of the biopharma ecosystem and with easy access to some of the most renowned academic and research institutions in the world, the APM Annual Conference 2024 will attract all segments of the precision medicine landscape.

The event will consist of two parallel tracks composed of keynote addresses, panel discussions and fireside chats which will encourage audience participation. Over the course of the two-day event leaders from industry, healthcare, regulatory bodies, academia and other pertinent stakeholders will share an intriguing and broad scope of content.

his event will consist of three immersive tracks, each crafted to explore the multifaceted dimensions of precision medicine. Delve into Precision Oncology, where groundbreaking advancements are reshaping the landscape of cancer diagnosis and treatment. Traverse the boundaries of Precision Medicine Outside of Oncology, as we probe into the intricate interplay of genetics, lifestyle, and environment across a spectrum of diseases and conditions including rare disease, cardiology, ophthalmology, and neurodegenerative disease. Immerse yourself in AI for Precision Medicine, where cutting-edge technologies are revolutionizing diagnostics, therapeutics, and patient care. Additionally, explore the emerging frontiers of Spatial Biology and Mult-Omics, where integrated approaches are unraveling the complexities of biological systems with unprecedented depth and precision.

Whether you are a seasoned researcher, a dedicated clinician, or a visionary industry professional, this conference serves as a vibrant hub of knowledge exchange, collaboration, and innovation. Elevate your expertise, expand your network, and chart the course of your career trajectory amidst a community of like-minded individuals.  Join us as we embark on this transformative journey, where the possibilities are as limitless as the potential of precision medicine itself.

Agenda – What’s on when

7:30 – 8:25

Registration and Check-in          Meeting Room 203          Philadelphia Convention Center

8:25 – 8:30

Welcome and Introduction

8:30 – 9:00

Opening Keynote

Advancing Precision Medicine in the Prevention and Treatment of Cardiometabolic Disease (CME Eligible)

Daniel Rader

Daniel Rader, Penn Medicine and Children’s Hospital of Philadelphia

9:00 – 10:20

9:00-10:20

Diagnosis to Treatment – A Case Study in Non Small Cell Lung Cancer

Jason Crites

Moderator: Jason Crites, Assurance Health Data

Miriam Bredella, NYU Lagone Health

Robert Dumanois

Rob Dumanois, Thermo Fisher Scientific

Joe Lennerz

Joe Lennerz, BostonGene

10:20 – 10:50

Networking, Exhibits and Product Presentations

10:25-10:35  PRODUCT PRESENTATION  204C

The Genexus Integrated Sequencer System:
NGS Results in 24 hours for Oncology Genomic Profiling

Jeff Smith,  Thermo Fisher Scientific

10:35-10:45  PRODUCT PRESENTATION  204A

Shifting the Paradigm in Patient Management with MRD Testing: Why Evidence-Generated Performance and Experience is Key

Karen Lin, Natera

10:50 – 12:50

10:50-11:50

Who Needs Liquid Biopsy? Opportunities to Increase Access and Improve Outcomes

Nicole St. Jean, GSK

Phil Febbo,  Veracyte, Inc.

Andrea Ferreira-Gonzalez, Virginia Commonwealth University

Lauren Leiman, BloodPAC

Nicole Sheahan, Global Colon Cancer Association

11:50-12:50

Advancing Digital Pathology and Precision Medicine – Where Are We Now?

Shruti Mathur, Genentech

Luke Benko, Roche Diagnostics

Kimberly GasuadJK Life Sciences

Eric Walk, PathAI

10:50-11:10

Real World Data vs Multi Modal Omics Data for Therapeutic Discovery (CME Eligible)

Adam Resnick, CHOP

11:10-11:30

An Academic Perspective on Rare Disease Target Discovery to Commercial Treatment Development (CME Eligible)

Hakon Hakonarson

Hakon Hakonarson, CHOP

11:30-11:50

NCATS Perspective on Success and Failures of Drug Repurposing for Rare Disease (CME Eligible)

PJ Brooks, NIH

11:50-12:10

Pharma Perspective and Realities (CME Eligible)

Sundeep Dugar, Rarefy Therapeutics

12:10-12:50

A Panel Discussion: Scaling Precision Therapeutic Development for Rare Disease (CME Eligible)

Marni Falk

Marni Falk, CHOP

Stephen Ekker, University of Texas at Austin

Christine Nguyen, FDA

Frank Sasinowski, Hyman, Phelps & McNamara

Adam Resnick, CHOP

Hakon Hakonarson

Hakon Hakonarson, CHOP

Sundeep Dugar, Rarefy Therapeutics

PJ Brooks, NIH

12:50 – 1:50

Lunch & Product Presentations

1:10-1:25  PRODUCT PRESENTATION  204C

The Power of ctDNA Testing in Therapy Selection and Recurrence Monitoring

Taylor Jensen,  LabCorp

1:50 – 3:50

1:50-3:50

Unlocking the Next Quantum Leap in Precision Medicine – A Town Hall Discussion (CME Eligible)

Co-Chairs

Amanda Paulovich

Amanda Paulovich, Fred Hutchinson Cancer Center

Henry Rodriguez

Henry Rodriguez, NCI/NIH

Eric Schadt

Eric Schadt, Pathos

Participants

Ezra Cohen, Tempus

Jennifer Leib, Innovation Policy Solutions

Susan Monarez, ARPA-H

Nick Seddon, Optum Genomics 

Giselle Sholler, Penn State Hershey Children’s Hospital

Janet Woodcock

Janet Woodcock, Former FDA

1:50-2:50

Advancing Precision Medicine in Non-Oncology Therapeutic Areas

Moderator: Mike Montalto, Amgen

Scott Friedman, Mt. Sinai

Sana Syed, University of Virginia

Lei Zhao, Amgen

2:50-3:20

Towards a Precision Neuroimmunology Platform (CME Eligible)

Amit Bar-Or, Penn Medicine

3:20-3:50

3:50 – 4:20

Networking and Exhibits

4:20 – 6:15

4:20-4:45

Advancing Precision Medicine: Polygenic Risk Scores and Beyond (CME Eligible)

Dokyoon Kim, Penn Medicine

4:45-5:30

The Rocky Road to Clinical Trial Diversity (CME Eligible)

Ysabel Duron, The Latino Cancer Institute

Porscha Johnson, PJW Clinical Pharmacy Consulting

Victor LaGroon, Department of Veterans Affairs

5:30-6:15

In the Rising Age of Women’s Health, How Do We Build Diagnostics to Last?

Oriana Papin Zoghbi, AOADx

Sarah Huah, Johnson & Johnson

6:30 – 7:00

Evening Keynote

Reimagining Health Equity in the Era of Precision Medicine (CME Eligible)

Rick Kittles

Rick Kittles, Morehouse School of Medicine

7:00 – 7:45

Cocktail Networking Reception 

November 02, 2024

8:00-8:55

Registration and Check-in          Meeting Room 203          Philadelphia Convention Center

Read Full Post »

2024 Nobel Prize in Physiology or Medicine jointly to Victor Ambros and Gary Ruvkun for the discovery of microRNA and its role in post-transcriptional gene regulation

Reporter: Aviva Lev-Ari, PhD, RN

Updated 10/22/2024

The revolution in our understanding of transcriptional regulation and dark regions of the genome

The genome of higher eukaryotes are comprised of multiple exonic and intronic regions, with coding and noncoding DNA respectively.  Much of the DNA sequence between exonic regions of genes, the sequences encoding the amino acids of a polypeptide, was considered either promoter regions regulating an exonic sequence or ‘junk DNA’, which had merely separated exons and their regulatory elements.  It was not considered that this dark DNA or junk DNA was important in regulating transcription of genes.  It was felt that most gene regulation occurred in promoter regions by response element factors which bound to specific sequences within these regions.

 

MicroRNA (miRNA), originally discovered in Caenorhabditis elegans, is found in most eukaryotes, including humans [13]. It is predicted that miRNA account for 1-5% of the human genome and regulate at least 30% of protein-coding genes [48]. To date, 940 distinct miRNAs molecules have been identified within the human genome [912] (http://microrna.sanger.ac.uk accessed July 20, 2010). Although little is currently known about the specific targets and biological functions of miRNA molecules thus far, it is evident that miRNA plays a crucial role in the regulation of gene expression controlling diverse cellular and metabolic pathways.

MiRNA are small, evolutionary conserved, single-stranded, non-coding RNA molecules that bind target mRNA to prevent protein production by one of two distinct mechanisms. Mature miRNA is generated through two-step cleavage of primary miRNA (pri-miRNA), which incorporates into the effector complex RNA-induced silencing complex (RISC). The miRNA functions as a guide by base-pairing with target mRNA to negatively regulate its expression. The level of complementarity between the guide and mRNA target determines which silencing mechanism will be employed; cleavage of target messenger RNA (mRNA) with subsequent degradation or translation inhibition

Fig. (1). MicroRNA maturation and function.

Figure. miRNA maturation and function.  Source: Macfarlane LA, Murphy PR. MicroRNA: Biogenesis, Function and Role in Cancer. Curr Genomics. 2010 Nov;11(7):537-61. doi: 10.2174/138920210793175895.

 

The following is an interview in the journal Journal of Cellular Biology  with Dr, Victor Ambros on his discovery of miRNA.

 

Source: Ambros V. Victor Ambros: the broad scope of microRNAs. Interview by Caitlin Sedwick. J Cell Biol. 2013 May 13;201(4):492-3. doi: 10.1083/jcb.2014pi. PMID: 23671307; PMCID: PMC3653358.

 

Once, we thought we understood all there was to know about how gene expression is regulated: A cell can tinker with the expression level of a given protein’s messenger RNA by modifying the activity, abundance, and type of transcription factors in the nucleus or with the RNA’s stability once it is made. But then came a surprising story about a short RNA in C. elegans called lin-4, which didn’t encode a protein but prevented expression of the protein encoded by another gene, lin-14, through antisense binding to lin-14 mRNA (1, 2). Today, we know that lin-4 was just the first example of a large number of small RNAs, called microRNAs, which regulate the expression of various other proteins in a similar way.

 

Victor Ambros, whose lab published that first story about lin-4, has been studying microRNAs (3, 4) and their regulation (5, 6) ever since, pushing forward our understanding of this powerful mechanism. We called him at his office at the University of Massachusetts Medical School to get some perspective on microRNAs and his career and to learn about some of the latest developments in his lab.

“That shared discovery is one of the most precious moments in my career.”

FROM FARM TO LAB TABLE

How did you end up doing a PhD with David Baltimore?

I was the first scientist in my family. My dad was an immigrant from Poland. He came to the States just after World War II and met my mom. They got married, moved to a farm in Vermont, and started farming. My siblings and I grew up amongst the cows and pigs and helped with the haying and cutting corn, stuff like that.

When I was about nine, I got interested in science, and after that I always wanted to be a scientist. I was an amateur astronomer; I built a telescope and started to imagine that I could actually do astronomy or physics as an occupation. But I quickly changed my mind when I reached college, in part because I realized that my math skills weren’t really up to the task of being a physicist and also because I discovered molecular biology and genetics and just fell in love with both subjects. David taught one of the advanced biology classes I took as an undergraduate at MIT, and that probably had some influence on my decision to work with him. After college, I worked as a technician in David’s lab for a year. I liked it a lot and stayed on in his lab when I entered graduate school at MIT. I was lucky because I had gotten a little bit of traction on a project and continued on that as a grad student, so I ended up finishing grad school fairly efficiently.

 

Had you any idea at the time what the nature of the lin-4 mutant was?

The assumption was that it was a protein product. I mean, nobody ever thought that there would be any other kind of regulator. There really wasn’t any reason to imagine that there were any other kinds of molecules necessary, other than proteins, to carry out everything that’s done in a cell—especially with regard to the regulation of gene expression. The complexity of gene regulation by proteins alone was so enormous that I never imagined—and nobody I knew imagined—that we needed to look for new kinds of regulatory molecules. The realization that lin-4 was antisense to the 3′-untranslated region of lin-14 was totally the result of communication between Gary and me. That shared discovery is one of the most precious moments in my career. But at the time I didn’t realize that this might be the first example of a general mechanism for regulating gene expression because I was prone to thinking that whatever I was studying in the worm was not generally applicable. It wasn’t until genome sequences were made available that the prevalence of this mechanism became clear.

THE RIGHT CONTEXT

You’ve moved to studying processes that modulate microRNA function…

One protein we’ve studied is called Nhl-2. It’s an example of an emerging class of proteins that can modulate, positively or negatively, the RNA-induced silencing complex (RISC) that inhibits mRNAs targeted by microRNAs. This class of genes may have either general effects on RISC activity or, in some cases, more specific effects. One area of interest in the lab right now is trying to understand the specific outcomes for the regulation of particular microRNAs. Do they always interact with all their targets, or is their activity on some targets promoted or inhibited at the expense of other targets? Can their interaction with certain targets be modified depending on context? We’re using genetic and genomic approaches to identify new modulatory cofactors.

Watch Video

Victor Ambros was born in 1953 in Hanover, New Hampshire, USA. He received his PhD from Massachusetts Institute of Technology (MIT), Cambridge, MA, in 1979 where he also did postdoctoral research 1979-1985. He became a Principal Investigator at Harvard University, Cambridge, MA in 1985. He was Professor at Dartmouth Medical School from 1992-2007 and he is now Silverman Professor of Natural Science at the University of Massachusetts Medical School, Worcester, MA.

Gary Ruvkun was born in Berkeley, California, USA in 1952. He received his PhD from Harvard University in 1982. He was a postdoctoral fellow at Massachusetts Institute of Technology (MIT), Cambridge, MA, 1982-1985. He became a Principal Investigator at Massachusetts General Hospital and Harvard Medical School in 1985, where he is now Professor of Genetics.

 

This year’s Nobel Prize honors two scientists for their discovery of a fundamental principle governing how gene activity is regulated.

The information stored within our chromosomes can be likened to an instruction manual for all cells in our body. Every cell contains the same chromosomes, so every cell contains exactly the same set of genes and exactly the same set of instructions. Yet, different cell types, such as muscle and nerve cells, have very distinct characteristics. How do these differences arise? The answer lies in gene regulation, which allows each cell to select only the relevant instructions. This ensures that only the correct set of genes is active in each cell type.

Victor Ambros and Gary Ruvkun were interested in how different cell types develop. They discovered microRNA, a new class of tiny RNA molecules that play a crucial role in gene regulation. Their groundbreaking discovery revealed a completely new principle of gene regulation that turned out to be essential for multicellular organisms, including humans. It is now known that the human genome codes for over one thousand microRNAs. Their surprising discovery revealed an entirely new dimension to gene regulation. MicroRNAs are proving to be fundamentally important for how organisms develop and function.

Ambros and Ruvkun were interested in genes that control the timing of activation of different genetic programs, ensuring that various cell types develop at the right time. They studied two mutant strains of worms, lin-4 and lin-14, that displayed defects in the timing of activation of genetic programs during development. The laureates wanted to identify the mutated genes and understand their function. Ambros had previously shown that the lin-4 gene appeared to be a negative regulator of the lin-14 gene. However, how the lin-14 activity was blocked was unknown. Ambros and Ruvkun were intrigued by these mutants and their potential relationship and set out to resolve these mysteries.

Ambros and Ruvkun performed further experiments showing that the lin-4 microRNA turns off lin-14 by binding to the complementary sequences in its mRNA, blocking the production of lin-14 protein. A new principle of gene regulation, mediated by a previously unknown type of RNA, microRNA, had been discovered! The results were published in 1993 in two articles in the journal Cell.

Ruvkun cloned let-7, a second gene encoding a microRNA. The gene is conserved in evolution, and it is now known that microRNA regulation is universal among multicellular organisms. 

 Andrew Z. Fire and Craig C. Mello, awarded the Nobel Prize in 2006, described RNA interference, where specific mRNA-molecules are inactivated by adding double-stranded RNA to cells.

Mutations in one of the proteins required for microRNA production result in the DICER1 syndrome, a rare but severe syndrome linked to cancer in various organs and tissues.

Reference 

http://Scientific background: For the discovery of microRNA and its role in post-transcriptional gene regulation

 

SOURCE

https://www.nobelprize.org/prizes/medicine/2024/press-release/

Read Full Post »

Live Conference Coverage: International Dialogue in Gynecological Oncology, From Bench to Bedside, Ovarian Cancer

Reporter: Stephen J. Williams, Ph.D.

Join Live on Wednesday May 22, 2024 for an international discussion on the current state of ovarian cancer diagnostics and therapeutics, and potential therapies and biomarkers, and biotargets.  Topics including potential new molecular targets for development of ovarian therapeutics, current changes in ovarian cancer clinical treatment protocols, chemo-resistance, and the use of Artificial Intelligence (AI) in the diagnosis and treatment of cancer will be discussed.

International Dialogue in Gynecological Oncology, From Bench to Bedside, ovarian Cancer meeting flyer

To join by Zoom click the link below

https://temple.zoom.us/j/94458267823 

Agenda:

Introduction

  • 00/15.00 Professor Giordano and Professor Ercoli
  • 10/15.10 We Have Never Been Only Human: a new perspective to defeat ovarian cancer (C. Martinelli)

Molecular Section

  • 20/15.20 DNA Repair mechanisms: understanding their role in cancer development and chemoresistance (L. Alfano)
  • 35/15.35 Progranulins: a new target for oncological treatment (A. Morrione)
  • 50/15.50 Modulation of gene expression and its applications (M. Cuomo)
  • 10.05/16.05 Commanding the cell cycle: the role of CDKs (S.R. Burk
  • 10.20/16.20 Drug development from nature (M. D’Angelo

Clinical Section

  • 05/17.05 Core principles of Radiologic Diagnosis & Staging in Ovarian Cancer(A. Blandino)
  • 20/17.20 Key Indications for Nuclear Medicine in Ovarian Cancer (S. Baldari)
  • 35/17.35 Cutting Edge Decision: Understanding Surgical Indications and Outcomes in Ovarian Cancer (A. Ercoli)
  • 50/17.50 Gold Standard in Oncology for Ovarian Cancer (N. Silvestris)
  • 12.05/18.05 Role of Radiotherapy in Ovarian Cancer (S. Pergolizzi)

Conclusion

12.20/18.20 AI Applied to medical science (V. Carnevale)

Speakers

  • – Professor Alfredo Blandino: Professor Blandino holds the esteemed positions of Head of school of Radiology and director of the department of radiology at the University of Messina. He has made significant contributions to diagnostic imaging with over hundreds of publications to his name, Professor Blandino’s work exemplifies excellence and innovation in radiology.
  • – Professor Alfredo Ercoli, serves as the Director of the Department of Gynecology and Obstetrics at the “G. Martino” University Hospital in Messina. He is also head of school of gynecology and obstetrics at Messina University. Starting his research in France with studies on pelvic anatomy that became a cornerstone in medical literature, He is a pioneer in advanced gynecologic surgery, including laparoscopic and robotic procedures, having performed over thousands of surgical interventions. His research focuses on gynecologic oncology, advanced gynecologic surgery, and endometriosis, urogynecology. Professor Ercoli’s dedication to education and his numerous publications have significantly advanced the field of gynecology.
  • Professor Sergio Baldari, an eminent figure in nuclear medicine. Professor Baldari is the Director of the department of nuclear medicine and head of school of nuclear medicine at the  University of Messina. He has authored or co-authored over 500 publications, with a focus on diagnostic imaging and the use of PET and radiopharmaceuticals in cancer treatment. His leadership and expertise have been recognized through various prestigious positions and awards within the medical community.
  • – Professor Nicola Silvestris is the Director of UOC Oncologia Medica at the University of Messina. His extensive research in cancer, has led to over 360 peer-reviewed publications. Professor Silvestris has made significant contributions to translational research and the development of guidelines for managing complex oncological conditions. His work continues to shape the future of cancer treatment.
  • Professor Stefano Pergolizzi, a leading expert in radiation oncology. Professor Pergolizzi serves as the Director of the department of radiotherapy and head of the school of radiotherapya at the University of Messina. He is also the president of the Italian Association of Radiotherapy and Clinical Oncology (AIRO) His research focuses on advanced radiotherapy techniques for cancer treatment. With a career spanning several decades, Professor Pergolizzi has published numerous papers and has been instrumental in developing innovative therapeutic approaches. His dedication to patient care and education is exemplary.
  • Margherita D’angelo: Graduated in Molecular Biology with honors from the Federico II University of Naples.
    Third year intern in Food Science at the Luigi Vanvitelli University of Naples.
    Research intern in Molecular oncology with the project of developing novel drugs starting from food waste at the Sbarro Institute for Cancer Research and Molecular Medicine at Temple University, Philadelphia (USA), directed by Dr A. Giordano.
  • Vincenzo Carnevale, Ph.D.

Dr. Carnevale is an Associate Professor in the Institute for Computational Molecular Science in the College of Science & Technology, Temple University.  He holds multiple NIH RO1 and NSF grants. Vincenzo Carnevale received B.Sc. and M.Sc. degrees in Physics from the University of Pisa and a PhD from SISSA – Scuola Internazionale Superiore di Studi Avanzati in Trieste, Italy. The Carnevale research group uses statistical physics and machine learning approaches to investigate sequence-structure-function relations in proteins. A central theme of the group’s research is how interactions give rise to collective phenomena and complex emergent behaviors. At the level of genes, the group is interested in epistasis – the complex entanglement phenomenon that causes amino acids to evolve in a concerted fashion – and how this shapes molecular evolution. At the cellular level, the group investigates how intermolecular interactions drive biomolecules toward self-organization and pattern formation. A long-term goal of the group is understanding the molecular underpinnings of electrical signaling in excitable cells. Toward these goals, the group applies and actively develops an extensive arsenal of theoretical and computational approaches including statistical (mean)field theories, Monte Carlo and molecular dynamics simulations, statistical inference of generative models, and deep learning.

  • Professor Andrea Morrione, Ph.D: Research Associate Professor, CST Temple University; After his studies in Biochemistry at Universita’ degli Studi Milano, Milan Italy, Dr. Morrione moved to USA in 1993 and has been working in the field of cancer biology since his postdoctoral training at the Kimmel Cancer Institute, Thomas Jefferson University, Philadelphia, PA in the laboratory of Dr. Renato Baserga, one of the leading experts in IGF-IR oncogenic signaling. In 1997 Dr. Morrione joined the Faculty of Thomas Jefferson University in the Department of Microbiology. In 2002 after receiving an NIH/NIDDK Career Development Award Dr. Morrione joined the Department of Urology at Jefferson where from 2008 to 2018 serves as the Director for Urology Basic Science and Associate Professor. Dr. Morrione joined the Department of Biology and the Sbarro Institute for Cancer Research and Molecular Medicine and Center for Biotechnology as Associate Professor of Research, and he is currently professor of Research and Deputy Director of the Sbarro Institute for Cancer Research and Molecular Medicine and Center for Biotechnology. He is a full member of the AACR.

 

  • Canio Martinelli, M.D.: Dr. Marinelli received his MD from Catholic University of the Sacred Heart in Rome, Visiting researcher at SHRO Temple University in Philadelphia, PhD candidate in Translational Molecular Medicine and Surgery & GYN-OB resident at UNIME. He has published numerous clinical papers in gynecologic oncology, risk reduction, and therapy and, most recently investigating clinical utilities of generative AI in gynecologic oncology.
  • Sharon Burk, Sharon Burk is a PhD student with Professor Antonio Giordano at the University of Siena, Italy in the department of Medical Biotechnologies, studying the role of Cyclin Dependent Kinase 10 in Triple Negative Breast Cancer. She received her Bachelor’s of Arts Degree from the University of California, Berkeley with a double major in molecular and cell biology and Italian studies.   She is a member of AACR.

This conference is being sponsored by Sbarro Health Research Organization and the Department of Biology, College of Science & Technology, Temple University.

To join by Zoom click the link below

https://temple.zoom.us/j/94458267823 

A QR code will be supplied at conference start, in addition to Zoom chat, to allow for questions to be submitted.

This conference is free to join on Zoom and will be covered live on @pharmaBI 

and on

 

Read Full Post »

Eight Subcellular Pathologies driving Chronic Metabolic Diseases – Methods for Mapping Bioelectronic Adjustable Measurements as potential new Therapeutics: Impact on Pharmaceuticals in Use

Eight Subcellular Pathologies driving Chronic Metabolic Diseases – Methods for Mapping Bioelectronic Adjustable Measurements as potential new Therapeutics: Impact on Pharmaceuticals in Use

Curators:

 

THE VOICE of Aviva Lev-Ari, PhD, RN

In this curation we wish to present two breaking through goals:

Goal 1:

Exposition of a new direction of research leading to a more comprehensive understanding of Metabolic Dysfunctional Diseases that are implicated in effecting the emergence of the two leading causes of human mortality in the World in 2023: (a) Cardiovascular Diseases, and (b) Cancer

Goal 2:

Development of Methods for Mapping Bioelectronic Adjustable Measurements as potential new Therapeutics for these eight subcellular causes of chronic metabolic diseases. It is anticipated that it will have a potential impact on the future of Pharmaceuticals to be used, a change from the present time current treatment protocols for Metabolic Dysfunctional Diseases.

According to Dr. Robert Lustig, M.D, an American pediatric endocrinologist. He is Professor emeritus of Pediatrics in the Division of Endocrinology at the University of California, San Francisco, where he specialized in neuroendocrinology and childhood obesity, there are eight subcellular pathologies that drive chronic metabolic diseases.

These eight subcellular pathologies can’t be measured at present time.

In this curation we will attempt to explore methods of measurement for each of these eight pathologies by harnessing the promise of the emerging field known as Bioelectronics.

Unmeasurable eight subcellular pathologies that drive chronic metabolic diseases

  1. Glycation
  2. Oxidative Stress
  3. Mitochondrial dysfunction [beta-oxidation Ac CoA malonyl fatty acid]
  4. Insulin resistance/sensitive [more important than BMI], known as a driver to cancer development
  5. Membrane instability
  6. Inflammation in the gut [mucin layer and tight junctions]
  7. Epigenetics/Methylation
  8. Autophagy [AMPKbeta1 improvement in health span]

Diseases that are not Diseases: no drugs for them, only diet modification will help

Image source

Robert Lustig, M.D. on the Subcellular Processes That Belie Chronic Disease

https://www.youtube.com/watch?v=Ee_uoxuQo0I

 

Exercise will not undo Unhealthy Diet

Image source

Robert Lustig, M.D. on the Subcellular Processes That Belie Chronic Disease

https://www.youtube.com/watch?v=Ee_uoxuQo0I

 

These eight Subcellular Pathologies driving Chronic Metabolic Diseases are becoming our focus for exploration of the promise of Bioelectronics for two pursuits:

  1. Will Bioelectronics be deemed helpful in measurement of each of the eight pathological processes that underlie and that drive the chronic metabolic syndrome(s) and disease(s)?
  2. IF we will be able to suggest new measurements to currently unmeasurable health harming processes THEN we will attempt to conceptualize new therapeutic targets and new modalities for therapeutics delivery – WE ARE HOPEFUL

In the Bioelecronics domain we are inspired by the work of the following three research sources:

  1. Biological and Biomedical Electrical Engineering (B2E2) at Cornell University, School of Engineering https://www.engineering.cornell.edu/bio-electrical-engineering-0
  2. Bioelectronics Group at MIT https://bioelectronics.mit.edu/
  3. The work of Michael Levin @Tufts, The Levin Lab
Michael Levin is an American developmental and synthetic biologist at Tufts University, where he is the Vannevar Bush Distinguished Professor. Levin is a director of the Allen Discovery Center at Tufts University and Tufts Center for Regenerative and Developmental Biology. Wikipedia
Born: 1969 (age 54 years), Moscow, Russia
Education: Harvard University (1992–1996), Tufts University (1988–1992)
Affiliation: University of Cape Town
Research interests: Allergy, Immunology, Cross Cultural Communication
Awards: Cozzarelli prize (2020)
Doctoral advisor: Clifford Tabin
Most recent 20 Publications by Michael Levin, PhD
SOURCE
SCHOLARLY ARTICLE
The nonlinearity of regulation in biological networks
1 Dec 2023npj Systems Biology and Applications9(1)
Co-authorsManicka S, Johnson K, Levin M
SCHOLARLY ARTICLE
Toward an ethics of autopoietic technology: Stress, care, and intelligence
1 Sep 2023BioSystems231
Co-authorsWitkowski O, Doctor T, Solomonova E
SCHOLARLY ARTICLE
Closing the Loop on Morphogenesis: A Mathematical Model of Morphogenesis by Closed-Loop Reaction-Diffusion
14 Aug 2023Frontiers in Cell and Developmental Biology11:1087650
Co-authorsGrodstein J, McMillen P, Levin M
SCHOLARLY ARTICLE
30 Jul 2023Biochim Biophys Acta Gen Subj1867(10):130440
Co-authorsCervera J, Levin M, Mafe S
SCHOLARLY ARTICLE
Regulative development as a model for origin of life and artificial life studies
1 Jul 2023BioSystems229
Co-authorsFields C, Levin M
SCHOLARLY ARTICLE
The Yin and Yang of Breast Cancer: Ion Channels as Determinants of Left–Right Functional Differences
1 Jul 2023International Journal of Molecular Sciences24(13)
Co-authorsMasuelli S, Real S, McMillen P
SCHOLARLY ARTICLE
Bioelectricidad en agregados multicelulares de células no excitables- modelos biofísicos
Jun 2023Revista Española de Física32(2)
Co-authorsCervera J, Levin M, Mafé S
SCHOLARLY ARTICLE
Bioelectricity: A Multifaceted Discipline, and a Multifaceted Issue!
1 Jun 2023Bioelectricity5(2):75
Co-authorsDjamgoz MBA, Levin M
SCHOLARLY ARTICLE
Control Flow in Active Inference Systems – Part I: Classical and Quantum Formulations of Active Inference
1 Jun 2023IEEE Transactions on Molecular, Biological, and Multi-Scale Communications9(2):235-245
Co-authorsFields C, Fabrocini F, Friston K
SCHOLARLY ARTICLE
Control Flow in Active Inference Systems – Part II: Tensor Networks as General Models of Control Flow
1 Jun 2023IEEE Transactions on Molecular, Biological, and Multi-Scale Communications9(2):246-256
Co-authorsFields C, Fabrocini F, Friston K
SCHOLARLY ARTICLE
Darwin’s agential materials: evolutionary implications of multiscale competency in developmental biology
1 Jun 2023Cellular and Molecular Life Sciences80(6)
Co-authorsLevin M
SCHOLARLY ARTICLE
Morphoceuticals: Perspectives for discovery of drugs targeting anatomical control mechanisms in regenerative medicine, cancer and aging
1 Jun 2023Drug Discovery Today28(6)
Co-authorsPio-Lopez L, Levin M
SCHOLARLY ARTICLE
Cellular signaling pathways as plastic, proto-cognitive systems: Implications for biomedicine
12 May 2023Patterns4(5)
Co-authorsMathews J, Chang A, Devlin L
SCHOLARLY ARTICLE
Making and breaking symmetries in mind and life
14 Apr 2023Interface Focus13(3)
Co-authorsSafron A, Sakthivadivel DAR, Sheikhbahaee Z
SCHOLARLY ARTICLE
The scaling of goals from cellular to anatomical homeostasis: an evolutionary simulation, experiment and analysis
14 Apr 2023Interface Focus13(3)
Co-authorsPio-Lopez L, Bischof J, LaPalme JV
SCHOLARLY ARTICLE
The collective intelligence of evolution and development
Apr 2023Collective Intelligence2(2):263391372311683SAGE Publications
Co-authorsWatson R, Levin M
SCHOLARLY ARTICLE
Bioelectricity of non-excitable cells and multicellular pattern memories: Biophysical modeling
13 Mar 2023Physics Reports1004:1-31
Co-authorsCervera J, Levin M, Mafe S
SCHOLARLY ARTICLE
There’s Plenty of Room Right Here: Biological Systems as Evolved, Overloaded, Multi-Scale Machines
1 Mar 2023Biomimetics8(1)
Co-authorsBongard J, Levin M
SCHOLARLY ARTICLE
Transplantation of fragments from different planaria: A bioelectrical model for head regeneration
7 Feb 2023Journal of Theoretical Biology558
Co-authorsCervera J, Manzanares JA, Levin M
SCHOLARLY ARTICLE
Bioelectric networks: the cognitive glue enabling evolutionary scaling from physiology to mind
1 Jan 2023Animal Cognition
Co-authorsLevin M
SCHOLARLY ARTICLE
Biological Robots: Perspectives on an Emerging Interdisciplinary Field
1 Jan 2023Soft Robotics
Co-authorsBlackiston D, Kriegman S, Bongard J
SCHOLARLY ARTICLE
Cellular Competency during Development Alters Evolutionary Dynamics in an Artificial Embryogeny Model
1 Jan 2023Entropy25(1)
Co-authorsShreesha L, Levin M
5

5 total citations on Dimensions.

Article has an altmetric score of 16
SCHOLARLY ARTICLE
1 Jan 2023BIOLOGICAL JOURNAL OF THE LINNEAN SOCIETY138(1):141
Co-authorsClawson WP, Levin M
SCHOLARLY ARTICLE
Future medicine: from molecular pathways to the collective intelligence of the body
1 Jan 2023Trends in Molecular Medicine
Co-authorsLagasse E, Levin M

THE VOICE of Dr. Justin D. Pearlman, MD, PhD, FACC

PENDING

THE VOICE of  Stephen J. Williams, PhD

Ten TakeAway Points of Dr. Lustig’s talk on role of diet on the incidence of Type II Diabetes

 

  1. 25% of US children have fatty liver
  2. Type II diabetes can be manifested from fatty live with 151 million  people worldwide affected moving up to 568 million in 7 years
  3. A common myth is diabetes due to overweight condition driving the metabolic disease
  4. There is a trend of ‘lean’ diabetes or diabetes in lean people, therefore body mass index not a reliable biomarker for risk for diabetes
  5. Thirty percent of ‘obese’ people just have high subcutaneous fat.  the visceral fat is more problematic
  6. there are people who are ‘fat’ but insulin sensitive while have growth hormone receptor defects.  Points to other issues related to metabolic state other than insulin and potentially the insulin like growth factors
  7. At any BMI some patients are insulin sensitive while some resistant
  8. Visceral fat accumulation may be more due to chronic stress condition
  9. Fructose can decrease liver mitochondrial function
  10. A methionine and choline deficient diet can lead to rapid NASH development

 

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 »

Genomic data can predict miscarriage and IVF failure

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

Infertility is a major reproductive health issue that affects about 12% of women of reproductive age in the United States. Aneuploidy in eggs accounts for a significant proportion of early miscarriage and in vitro fertilization failure. Recent studies have shown that genetic variants in several genes affect chromosome segregation fidelity and predispose women to a higher incidence of egg aneuploidy. However, the exact genetic causes of aneuploid egg production remain unclear, making it difficult to diagnose infertility based on individual genetic variants in mother’s genome. Although, age is a predictive factor for aneuploidy, it is not a highly accurate gauge because aneuploidy rates within individuals of the same age can vary dramatically.

Researchers described a technique combining genomic sequencing with machine-learning methods to predict the possibility a woman will undergo a miscarriage because of egg aneuploidy—a term describing a human egg with an abnormal number of chromosomes. The scientists were able to examine genetic samples of patients using a technique called “whole exome sequencing,” which allowed researchers to home in on the protein coding sections of the vast human genome. Then they created software using machine learning, an aspect of artificial intelligence in which programs can learn and make predictions without following specific instructions. To do so, the researchers developed algorithms and statistical models that analyzed and drew inferences from patterns in the genetic data.

As a result, the scientists were able to create a specific risk score based on a woman’s genome. The scientists also identified three genes—MCM5, FGGY and DDX60L—that when mutated and are highly associated with a risk of producing eggs with aneuploidy. So, the report demonstrated that sequencing data can be mined to predict patients’ aneuploidy risk thus improving clinical diagnosis. The candidate genes and pathways that were identified in the present study are promising targets for future aneuploidy studies. Identifying genetic variations with more predictive power will serve women and their treating clinicians with better information.

References:

https://medicalxpress-com.cdn.ampproject.org/c/s/medicalxpress.com/news/2022-06-miscarriage-failure-vitro-fertilization-genomic.amp

https://pubmed.ncbi.nlm.nih.gov/35347416/

https://pubmed.ncbi.nlm.nih.gov/31552087/

https://pubmed.ncbi.nlm.nih.gov/33193747/

https://pubmed.ncbi.nlm.nih.gov/33197264/

Read Full Post »

Data Science: Step by Step – A Resource for LPBI Group One-Year Internship in IT, IS, DS

Reporter: Aviva Lev-Ari, PhD, RN

9 free Harvard courses: learning Data Science

In this article, I will list 9 free Harvard courses that you can take to learn data science from scratch. Feel free to skip any of these courses if you already possess knowledge of that subject.

Step 1: Programming

The first step you should take when learning data science is to learn to code. You can choose to do this with your choice of programming language?—?ideally Python or R.

If you’d like to learn R, Harvard offers an introductory R course created specifically for data science learners, called Data Science: R Basics.

This program will take you through R concepts like variables, data types, vector arithmetic, and indexing. You will also learn to wrangle data with libraries like dplyr and create plots to visualize data.

If you prefer Python, you can choose to take CS50’s Introduction to Programming with Python offered for free by Harvard. In this course, you will learn concepts like functions, arguments, variables, data types, conditional statements, loops, objects, methods, and more.

Both programs above are self-paced. However, the Python course is more detailed than the R program, and requires a longer time commitment to complete. Also, the rest of the courses in this roadmap are taught in R, so it might be worth learning R to be able to follow along easily.

Step 2: Data Visualization

Visualization is one of the most powerful techniques with which you can translate your findings in data to another person.

With Harvard’s Data Visualization program, you will learn to build visualizations using the ggplot2 library in R, along with the principles of communicating data-driven insights.

Step 3: Probability

In this course, you will learn essential probability concepts that are fundamental to conducting statistical tests on data. The topics taught include random variables, independence, Monte Carlo simulations, expected values, standard errors, and the Central Limit Theorem.

The concepts above will be introduced with the help of a case study, which means that you will be able to apply everything you learned to an actual real-world dataset.

Step 4: Statistics

After learning probability, you can take this course to learn the fundamentals of statistical inference and modelling.
This program will teach you to define population estimates and margin of errors, introduce you to Bayesian statistics, and provide you with the fundamentals of predictive modeling.

Step 5: Productivity Tools (Optional)

I’ve included this project management course as optional since it isn’t directly related to learning data science. Rather, you will be taught to use Unix/Linux for file management, Github, version control, and creating reports in R.

The ability to do the above will save you a lot of time and help you better manage end-to-end data science projects.

Step 6: Data Pre-Processing

The next course in this list is called Data Wrangling, and will teach you to prepare data and convert it into a format that is easily digestible by machine learning models.

You will learn to import data into R, tidy data, process string data, parse HTML, work with date-time objects, and mine text.

As a data scientist, you often need to extract data that is publicly available on the Internet in the form of a PDF document, HTML webpage, or a Tweet. You will not always be presented with clean, formatted data in a CSV file or Excel sheet.

By the end of this course, you will learn to wrangle and clean data to come up with critical insights from it.

Step 7: Linear Regression

Linear regression is a machine learning technique that is used to model a linear relationship between two or more variables. It can also be used to identify and adjust the effect of confounding variables.

This course will teach you the theory behind linear regression models, how to examine the relationship between two variables, and how confounding variables can be detected and removed before building a machine learning algorithm.

Step 8: Machine Learning

Finally, the course you’ve probably been waiting for! Harvard’s machine learning program will teach you the basics of machine learning, techniques to mitigate overfitting, supervised and unsupervised modelling approaches, and recommendation systems.

Step 9: Capstone Project

After completing all the above courses, you can take Harvard’s data science capstone project, where your skills in data visualization, probability, statistics, data wrangling, data organization, regression, and machine learning will be assessed.

With this final project, you will get the opportunity to put together all the knowledge learnt from the above courses and gain the ability to complete a hands-on data science project from scratch.

Note: All the courses above are available on an online learning platform from edX and can be audited for free. If you want a course certificate, however, you will have to pay for one.

Building a data science learning roadmap with free courses offered by MIT.

8 Free MIT Courses to Learn Data Science Online

 enrolled into an undergraduate computer science program and decided to major in data science. I spent over $25K in tuition fees over the span of three years, only to graduate and realize that I wasn’t equipped with the skills necessary to land a job in the field.

I barely knew how to code, and was unclear about the most basic machine learning concepts.

I took some time out to try and learn data science myself — with the help of YouTube videos, online courses, and tutorials. I realized that all of this knowledge was publicly available on the Internet and could be accessed for free.

It came as a surprise that even Ivy League universities started making many of their courses accessible to students worldwide, for little to no charge. This meant that people like me could learn these skills from some of the best institutions in the world, instead of spending thousands of dollars on a subpar degree program.

In this article, I will provide you with a data science roadmap I created using only freely available MIT online courses.

Step 1: Learn to code

I highly recommend learning a programming language before going deep into the math and theory behind data science models. Once you learn to code, you will be able to work with real-world datasets and get a feel of how predictive algorithms function.

MIT Open Courseware offers a beginner-friendly Python program for beginners, called Introduction to Computer Science and Programming.

This course is designed to help people with no prior coding experience to write programs to tackle useful problems.

Step 2: Statistics

Statistics is at the core of every data science workflow — it is required when building a predictive model, analyzing trends in large amounts of data, or selecting useful features to feed into your model.

MIT Open Courseware offers a beginner-friendly course called Introduction to Probability and Statistics. After taking this course, you will learn the basic principles of statistical inference and probability. Some concepts covered include conditional probability, Bayes theorem, covariance, central limit theorem, resampling, and linear regression.

This course will also walk you through statistical analysis using the R programming language, which is useful as it adds on to your tool stack as a data scientist.

Another useful program offered by MIT for free is called Statistical Thinking and Data Analysis. This is another elementary course in the subject that will take you through different data analysis techniques in Excel, R, and Matlab.

You will learn about data collection, analysis, different types of sampling distributions, statistical inference, linear regression, multiple linear regression, and nonparametric statistical methods.

Step 3: Foundational Math Skills

Calculus and linear algebra are two other branches of math that are used in the field of machine learning. Taking a course or two in these subjects will give you a different perspective of how predictive models function, and the working behind the underlying algorithm.

To learn calculus, you can take Single Variable Calculus offered by MIT for free, followed by Multivariable Calculus.

Then, you can take this Linear Algebra class by Prof. Gilbert Strang to get a strong grasp of the subject.

All of the above courses are offered by MIT Open Courseware, and are paired with lecture notes, problem sets, exam questions, and solutions.

Step 4: Machine Learning

Finally, you can use the knowledge gained in the courses above to take MIT’s Introduction to Machine Learning course. This program will walk you through the implementation of predictive models in Python.

The core focus of this course is in supervised and reinforcement learning problems, and you will be taught concepts such as generalization and how overfitting can be mitigated. Apart from just working with structured datasets, you will also learn to process image and sequential data.

MIT’s machine learning program cites three pre-requisites — Python, linear algebra, and calculus, which is why it is advisable to take the courses above before starting this one.

Are These Courses Beginner-Friendly?

Even if you have no prior knowledge of programming, statistics, or mathematics, you can take all the courses listed above.

MIT has designed these programs to take you through the subject from scratch. However, unlike many MOOCs out there, the pace does build up pretty quickly and the courses cover a large depth of information.

Due to this, it is advisable to do all the exercises that come with the lectures and work through all the reading material provided.

SOURCE

Natassha Selvaraj is a self-taught data scientist with a passion for writing. You can connect with her on LinkedIn.

https://www.kdnuggets.com/2022/03/8-free-mit-courses-learn-data-science-online.html

Read Full Post »

Emergence of a new SARS-CoV-2 variant from GR clade with a novel S glycoprotein mutation V1230L in West Bengal, India

Authors: Rakesh Sarkar, Ritubrita Saha, Pratik Mallick, Ranjana Sharma, Amandeep Kaur, Shanta Dutta, Mamta Chawla-Sarkar

Reporter and Original Article Co-Author: Amandeep Kaur, B.Sc. , M.Sc.

Abstract
Since its inception in late 2019, SARS-CoV-2 has evolved resulting in emergence of various variants in different countries. These variants have spread worldwide resulting in devastating second wave of COVID-19 pandemic in many countries including India since the beginning of 2021. To control this pandemic continuous mutational surveillance and genomic epidemiology of circulating strains is very important. In this study, we performed mutational analysis of the protein coding genes of SARS-CoV-2 strains (n=2000) collected during January 2021 to March 2021. Our data revealed the emergence of a new variant in West Bengal, India, which is characterized by the presence of 11 co-existing mutations including D614G, P681H and V1230L in S-glycoprotein. This new variant was identified in 70 out of 412 sequences submitted from West Bengal. Interestingly, among these 70 sequences, 16 sequences also harbored E484K in the S glycoprotein. Phylogenetic analysis revealed strains of this new variant emerged from GR clade (B.1.1) and formed a new cluster. We propose to name this variant as GRL or lineage B.1.1/S:V1230L due to the presence of V1230L in S glycoprotein along with GR clade specific mutations. Co-occurrence of P681H, previously observed in UK variant, and E484K, previously observed in South African variant and California variant, demonstrates the convergent evolution of SARS-CoV-2 mutation. V1230L, present within the transmembrane domain of S2 subunit of S glycoprotein, has not yet been reported from any country. Substitution of valine with more hydrophobic amino acid leucine at position 1230 of the transmembrane domain, having role in S protein binding to the viral envelope, could strengthen the interaction of S protein with the viral envelope and also increase the deposition of S protein to the viral envelope, and thus positively regulate virus infection. P618H and E484K mutation have already been demonstrated in favor of increased infectivity and immune invasion respectively. Therefore, the new variant having G614G, P618H, P1230L and E484K is expected to have better infectivity, transmissibility and immune invasion characteristics, which may pose additional threat along with B.1.617 in the ongoing COVID-19 pandemic in India.

Reference: Sarkar, R. et al. (2021) Emergence of a new SARS-CoV-2 variant from GR clade with a novel S glycoprotein mutation V1230L in West Bengal, India. medRxiv. https://doi.org/10.1101/2021.05.24.21257705https://www.medrxiv.org/content/10.1101/2021.05.24.21257705v1

Other related articles were published in this Open Access Online Scientific Journal, including the following:

Fighting Chaos with Care, community trust, engagement must be cornerstones of pandemic response

Reporter: Amandeep Kaur

https://pharmaceuticalintelligence.com/2021/04/13/fighting-chaos-with-care/

T cells recognize recent SARS-CoV-2 variants

Reporter: Aviva Lev-Ari, PhD, RN

https://pharmaceuticalintelligence.com/2021/03/30/t-cells-recognize-recent-sars-cov-2-variants/

Need for Global Response to SARS-CoV-2 Viral Variants

Reporter: Aviva Lev-Ari, PhD, RN

https://pharmaceuticalintelligence.com/2021/02/12/need-for-global-response-to-sars-cov-2-viral-variants/

Identification of Novel genes in human that fight COVID-19 infection

Reporter: Amandeep Kaur, B.Sc., M.Sc.

https://pharmaceuticalintelligence.com/2021/04/19/identification-of-novel-genes-in-human-that-fight-covid-19-infection/

Mechanism of Thrombosis with AstraZeneca and J & J Vaccines: Expert Opinion by Kate Chander Chiang & Ajay Gupta, MD

Reporter & Curator: Dr. Ajay Gupta, MD

https://pharmaceuticalintelligence.com/2021/04/14/mechanism-of-thrombosis-with-astrazeneca-and-j-j-vaccines-expert-opinion-by-kate-chander-chiang-ajay-gupta-md/

Read Full Post »

Older Posts »