Feeds:
Posts
Comments

Posts Tagged ‘Big data’


Best Big Data?

Larry H. Bernstein, MD, FCAP, Curator

LPBI

 

 

What’s The Big Data?

Google’s RankBrain Outranks the Best Brains in the Industry

Bloomberg recently broke the news that Google is “turning its lucrative Web search over to AI machines.” Google revealed to the reporter that for the past few months, a very large fraction of the millions of search queries Google responds to every second have been “interpreted by an artificial intelligence system, nicknamed RankBrain.”

The company that has tried hard to automate its mission to organize the world’s information was happy to report that its machines have again triumphed over humans. When Google search engineers “were asked to eyeball some pages and guess which they thought Google’s search engine technology would rank on top,” RankBrain had an 80% success rate compared to “the humans [who] guessed correctly 70 percent of the time.”

There you have it. Google’s AI machine RankBrain, after only a few months on the job, already outranks the best brains in the industry, the elite engineers that Google typically hires.

Or maybe not. Is RankBrain really “smarter than your average engineer” and already “living up to its AI hype,” as the Bloomberg article informs us, or is this all just, well, hype?

Desperate to find out how far our future machine overlords are already ahead of the best and the brightest (certainly not “average”), I asked Google to shed more light on the test, e.g., how do they determine the “success rate”?

“That test was fairly informal, but it was some of our top search engineers looking at search queries and potential search results and guessing which would be favored by users. (We don’t have more detail to share on how that’s determined; our evaluations are a pretty complex process).”

I guess both RankBrain and Google search engineers were given possible search results to a given query and RankBrain outperformed humans in guessing which are the “better” results, according to some undisclosed criteria.

I don’t know about you, but my TinyBrain is still confused. Wouldn’t Google search engine, with or without RankBrain, outperform any human being, including the smartest people on earth, in terms of “guessing” which search results “would be favored by users”? Haven’t they been mining the entire corpus of human knowledge for more than fifteen years and, by definition, have produced a search engine that “understands” relevance more than any individual human being?

The key to the competition, I guess, is that the “search queries” used in it were not just any search queries but complex queries containing words that have different meaning in different context. It’s the kind of queries that will stump most human beings and it’s quite surprising that Google engineers scored 70% on search queries that presumably require deep domain knowledge in all human endeavors, in addition to search expertise.

The only example of a complex query given in the Bloomberg article is “What’s the title of the consumer at the highest level of a food chain?” The word “consumer” in this context is a scientific term for something that consumes food and the label (the “title”) at highest level of the food chain is “predator.”

This explanation comes from search guru Danny Sullivan who has come to the rescue of perplexed humans like me, providing a detailed RankBrain FAQ, up to the limits imposed by Google’s legitimate reluctance to fully share its secrets. Sullivan: “From emailing with Google, I gather RankBrain is mainly used as a way to interpret the searches that people submit to find pages that might not have the exact words that were searched for.”

Sullivan points out that a lot of work done by humans is behind Google’s outstanding search results (e.g., creating a synonym list or a database with connections between “entities”—places, people, ideas, objects, etc.). But Google needs now to respond to some 450 million new queries per day, queries that have never been entered before into its search engine.

RankBrain “can see patterns between seemingly unconnected complex searches to understand how they’re actually similar to each other,” writes Sullivan. In addition, “RankBrain might be able to better summarize what a page is about than Google’s existing systems have done.”

Finding out the “unknown unknowns,” discovering previously unknown (to humans) links between words and concepts is the marriage of search technology with the hottest trend in big data analysis—deep learning. The real news about RankBrain is that it is the first time Google applied deep learning, the latest incarnation of “neural networks” and a specific type of machine learning, to its most prized asset—its search engine.

Google has been doing machine learning since its inception. The first published paper listed in the AI and  machine learning section of its research page is from 2001, and, to use just one example, Gmail is so good at detecting spam because of machine learning). But Goggle hasn’t applied machine learning to search. That there has been internal opposition to doing so we learn from a summary of a 2008 conversation between Anand Rajaraman and Peter Norvig, co-author of the most popular AI textbook and leader of Google search R&D since 2001. Here’s the most relevant excerpt:

The big surprise is that Google still uses the manually-crafted formula for its search results. They haven’t cut over to the machine learned model yet. Peter suggests two reasons for this. The first is hubris: the human experts who created the algorithm believe they can do better than a machine-learned model. The second reason is more interesting. Google’s search team worries that machine-learned models may be susceptible to catastrophic errors on searches that look very different from the training data. They believe the manually crafted model is less susceptible to such catastrophic errors on unforeseen query types.

This was written three years after Microsoft has applied machine learning to its search technology. But now, Google got over its hubris. 450 million unforeseen query types per day are probably too much for “manually crafted models” and google has decided that a “deep learning” system such as RankBrain provides good enough protection against “catastrophic errors.”

Read Full Post »


Better bioinformatics

Larry H. Bernstein, MD, FCAP, Curator

LPBI

 

Big data in biomedicine: 4 big questions

Eric Bender  Nature Nov 2015; S19, 527.     http://dx.doi.org:/10.1038/527S19a

http://www.nature.com/nature/journal/v527/n7576_supp/full/527S19a.html

Gathering and understanding the deluge of biomedical research and health data poses huge challenges. But this work is rapidly changing the face of medicine.

 

http://www.nature.com/nature/journal/v527/n7576_supp/images/527S19a-g1.jpg

 

1. How can long-term access to biomedical data that are vital for research be improved?

Why it matters
Data storage may be getting cheaper, particularly in cloud computing, but the total costs of maintaining biomedical data are too high and climbing rapidly. Current models for handling these tasks are only stopgaps.

Next steps
Researchers, funders and others need to analyse data usage and look at alternative models, such as ‘data commons’, for providing access to curated data in the long term. Funders also need to incorporate resources for doing this.

Quote
“Our mission is to use data science to foster an open digital ecosystem that will accelerate efficient, cost-effective biomedical research to enhance health, lengthen life and reduce illness and disability.” Philip Bourne, US National Institutes of Health.

 

2. How can the barriers to using clinical trial results and patients’ health records for research be lowered?

Why it matters
‘De-identified’ data from clinical trials and patients’ medical records offer opportunities for research, but the legal and technical obstacles are immense. Clinical study data are rarely shared, and medical records are walled off by privacy and security regulations and by legal concerns.

Next steps
Patient advocates are lobbying for access to their own health data, including genomic information. The European Medicines Agency is publishing clinical reports submitted as part of drug applications. And initiatives such as CancerLinQ are gathering de-identified patient data.

Quote
“There’s a lot of genetic information that no one understands yet, so is it okay or safe or right to put that in the hands of a patient? The flip side is: it’s my information — if I want it, I should get it.”Megan O’Boyle, Phelan-McDermid Syndrome Foundation.

 

3. How can knowledge from big data be brought into point-of-care health-care delivery?

Why it matters
Delivering precision medicine will immensely broaden the scope of electronic health records. This massive shift in health care will be complicated by the introduction of new therapies, requiring ongoing education for clinicians who need detailed information to make clinical decisions.

Next steps
Health systems are trying to bring up-to-date treatments to clinics and build ‘health-care learning systems’ that integrate with electronic health records. For instance, the CancerLinQ project provides recommendations for patients with cancer whose treatment is hard to optimize.

Quote
“Developing a standard interface for innovators to access the information in electronic health records will connect the point of care to big data and the full power of the web, spawning an ‘app store’ for health.” Kenneth Mandl, Harvard Medical School.

 

4. Can academia create better career tracks for bioinformaticians?

Why it matters
The lack of attractive career paths in bioinformatics has led to a shortage of scientists that have both strong statistical skills and biological understanding. The loss of data scientists to other fields is slowing the pace of medical advances.

Next steps
Research institutions will take steps, including setting up formal career tracks, to reward bioinformaticians who take on multidisciplinary collaborations. Funders will find ways to better evaluate contributions from bioinformaticians.

Quote
“Perhaps the most promising product of big data, that labs will be able to explore countless and unimagined hypotheses, will be stymied if we lack the bioinformaticians that can make this happen.” Jeffrey Chang, University of Texas.

 

Eric Bender is a freelance science writer based in Newton, Massachusetts.

Read Full Post »


  • Oracle Industry Connect Presents Their 2015 Life Sciences and Healthcare Program

 

Reporter: Stephen J. Williams, Ph.D. and Aviva Lev-Ari, Ph.D., R.N.

oraclehealthcare

Copyright photo Oracle Inc. (TM)

 

Transforming Clinical Research and Clinical Care with Data-Driven Intelligence

March 25-26 Washington, DC

For more information click on the following LINK:

https://www.oracle.com/oracleindustryconnect/life-sciences-healthcare.html

oracle-healthcare-solutions-br-1526409

https://www.oracle.com/industries/health-sciences/index.html  

Oracle Health Sciences: Life Sciences & HealthCare — the Solutions for Big Data

Healthcare and life sciences organizations are facing unprecedented challenges to improve drug development and efficacy while driving toward more targeted and personalized drugs, devices, therapies, and care. Organizations are facing an urgent need to meet the unique demands of patients, regulators, and payers, necessitating a move toward a more patient-centric, value-driven, and personalized healthcare ecosystem.

Meeting these challenges requires redesigning clinical R&D processes, drug therapies, and care delivery through innovative software solutions, IT systems, data analysis, and bench-to-bedside knowledge. The core mission is to improve the health, well-being, and lives of people globally by:

  • Optimizing clinical research and development, speeding time to market, reducing costs, and mitigating risk
  • Accelerating efficiency by using business analytics, costing, and performance management technologies

 

  • Establishing a global infrastructure for collaborative clinical discovery and care delivery models
  • Scaling innovations with world-class, transformative technology solutions
  • Harnessing the power of big data to improve patient experience and outcomes

The Oracle Industry Connect health sciences program features 15 sessions showcasing innovation and transformation of clinical R&D, value-based healthcare, and personalized medicine.

The health sciences program is an invitation-only event for senior-level life sciences and healthcare business and IT executives.

Complete your registration and book your hotel reservation prior to February 27, 2015 in order to secure the Oracle discounted hotel rate.

Learn more about Oracle Healthcare.

General Welcome and Joint Program Agenda

Wednesday, March 25

10:30 a.m.–12:00 p.m.

Oracle Industry Connect Opening Keynote

Mark Hurd, Chief Executive Officer, Oracle

Bob Weiler, Executive Vice President, Global Business Units, Oracle

Warren Berger, Author of “A More Beautiful Question: The Power of Inquiry to Spark Breakthrough Ideas.”

12:00 p.m.–1:45 p.m.

Networking Lunch

1:45 p.m.–2:45 p.m.

Oracle Industry Connect Keynote

Bob Weiler, Executive Vice President, Global Business Units, Oracle

2:45 p.m.–3:45 p.m.

Networking Break

3:45 p.m.–5:45 p.m.

Life Sciences and Healthcare General Session

Robert Robbins, President, Chief Executive Officer, Texas Medical Center

Steve Rosenberg, Senior Vice President and General Manager Health Sciences Global Business Unit, Oracle

7:00 p.m.–10:00 p.m.

Life Sciences and Healthcare Networking Reception

National Museum of American History
14th Street and Constitution Avenue, NW
Washington DC 20001

Life Sciences Agenda

Thursday, March 26

7:00 a.m.–8:00 a.m.

Networking Breakfast

8:00 a.m.–9:15 a.m.

Digital Trials and Research Models of the Future 

Markus Christen, Senior Vice President and Head of Global Development, Proteus

Praveen Raja, Senior Director of Medical Affairs, Proteus Digital Health

Michael Stapleton, Vice President and Chief Information Officer, R&D IT, Merck

9:15 a.m.–10:30 a.m.

Driving Patient Engagement and the Internet of Things 

Howard Golub, Vice President of Clinical Research, Walgreens

Jean-Remy Behaeghel, Senior Director, Client Account Management, Product Development Solutions, Vertex Pharmaceuticals

10:30 a.m.–10:45 a.m.

Break

10:45 a.m.–12:00 p.m.

Leveraging Data and Advanced Analytics to Enable True Pharmacovigilance and Risk Management 

Leonard Reyno, Senior Vice President, Chief Medical Officer, Agensys

 

Accelerating Therapeutic Development Through New Technologies 

Andrew Rut, Chief Executive Officer, Co-Founder and Director, MyMeds&Me

12:45 a.m.–1:45 p.m.

Networking Lunch

1:45 p.m.–2:30 p.m.

Oracle Industry Connect Keynote

2:30 p.m.–2:45 p.m.

Break

2:45 p.m.–3:15 p.m.

Harnessing Big Data to Increase R&D Innovation, Efficiency, and Collaboration 

Sandy Tremps, Executive Director, Global Clinical Development IT, Merck

3:15 p.m.–3:30 p.m.

Break

3:30 p.m.–4:45 p.m.

Transforming Clinical Research from Planning to Postmarketing 

Kenneth Getz, Director of Sponsored Research Programs and Research Associate Professor, Tufts University

Jason Raines, Head, Global Data Operations, Alcon Laboratories

4:45 p.m.–6:00 p.m.

Increasing Efficiency and Pipeline Performance Through Sponsor/CRO Data Transparency and Cloud Collaboration 

Thomas Grundstrom, Vice President, ICONIK, Cross Functional IT Strategies and Innovation, ICON

Margaret Keegan, Senior Vice President, Global Head Data Sciences and Strategy, Quintiles

6:00 p.m.–9:00 p.m.

Oracle Customer Networking Event

Healthcare Agenda

Thursday, March 26

7:00 a.m.–8:15 a.m.

Networking Breakfast

8:30 a.m.–9:15 a.m.

Population Health: A Core Competency for Providers in a Post Fee-for-Service Model 

Margaret Anderson, Executive Director, FasterCures

Balaji Apparsamy, Director, Business Intellegence, Baycare

Leslie Kelly Hall, Senior Vice President, Policy, Healthwise

Peter Pronovost, Senior Vice President, Patient Safety & Quality, Johns Hopkins

Sanjay Udoshi, Healthcare Product Strategy, Oracle

9:15 a.m.–9:30 a.m.

Break

9:30 a.m.–10:15 a.m.

Population Health: A Core Competency for Providers in a Post Fee-for-Service Model (Continued)

10:15 a.m.–10:45 a.m.

Networking Break

10:45 a.m.–11:30 a.m.

Managing Cost of Care in the Era of Healthcare Reform 

Chris Bruerton, Director, Budgeting, Intermountain Healthcare

Tony Byram, Vice President Business Integration, Ascension

Kerri-Lynn Morris, Executive Director, Finance Operations and Strategic Projects, Kaiser Permanente

Kavita Patel, Managing Director, Clinical Transformation, Brookings Institute

Christine Santos, Chief of Strategic Business Analytics, Providence Health & Services

Prashanth Kini, Senior Director, Healthcare Product Strategy, Oracle

11:30 a.m.–11:45 a.m.

Break

11:45 a.m.–12:45 p.m.

Managing Cost of Care in the Era of Healthcare Reform (Continued)

12:45 p.m.–1:45 p.m.

Networking Lunch

1:45 p.m.–2:30 p.m.

Oracle Industry Connect Keynote

2:30 p.m.–2:45 p.m.

Break

2:45 p.m.–3:30 p.m.

Precision Medicine 

Annerose Berndt, Vice President, Analytics and Information, UPMC

James Buntrock, Vice Chair, Information Management and Analytics, Mayo Clinic

Dan Ford, Vice Dean for Clinical Investigation, Johns Hopkins Medicine

Jan Hazelzet, Chief Medical Information Officer, Erasmus MC

Stan Huff, Chief Medical Information Officer, Intermountain Healthcare

Vineesh Khanna, Director, Biomedical Informatics, SIDRA

Brian Wells, Vice President, Health Technology, Penn Medicine

Wanmei Ou, Senior Product Strategist, Healthcare, Oracle

3:30 p.m.–3:45 p.m.

Networking Break

3:45 p.m.–4:30 p.m.

Precision Medicine (Continued)

4:30 p.m.–4:45 p.m.

Break

6:00 p.m.–9:00 p.m.

Oracle Customer Networking Event

Additional Links to Oracle Pharma, Life Sciences and HealthCare

 
Life Sciences | Industry | Oracle <http://www.oracle.com/us/industries/life-sciences/overview/>

http://www.oracle.com/us/industries/life-sciences/overview/

 
Oracle Corporation

 
Oracle Applications for Life Sciences deliver a powerful combination of technology and preintegrated applications.

  • Clinical

<http://www.oracle.com/us/industries/life-sciences/clinical/overview/index.html>

  • Medical Devices

<http://www.oracle.com/us/industries/life-sciences/medical/overview/index.html>

  • Pharmaceuticals

<http://www.oracle.com/us/industries/life-sciences/pharmaceuticals/overview/index.html>

 
Life Sciences Solutions | Pharmaceuticals and … – Oracle <http://www.oracle.com/us/industries/life-sciences/solutions/index.html>

http://www.oracle.com  Industries  Life Sciences

 
Oracle Corporation

 
Life Sciences Pharmaceuticals and Biotechnology.

 
Oracle Life Sciences Data Hub – Overview | Oracle <http://www.oracle.com/us/products/applications/health-sciences/e-clinical/data-hub/index.html>

http://www.oracle.com  …  E-Clinical Solutions

 
Oracle Corporation

 
Oracle Life Sciences Data Hub. Better Insights, More Informed Decision-Making. Provides an integrated environment for clinical data, improving regulatory …

 
Pharmaceuticals and Biotechnology | Oracle Life Sciences <http://www.oracle.com/us/industries/life-sciences/pharmaceuticals/overview/index.html>

http://www.oracle.com/us/…/life-sciences/…/index.html

 
Oracle Corporation

 
Oracle Applications for Pharmaceuticals and Biotechnology deliver a powerful combination of technology and preintegrated applications.

 
Oracle Health Sciences – Healthcare and Life Sciences … <https://www.oracle.com/industries/health-sciences/>

https://www.oracle.com/industries/health-sciences/

 
Oracle Corporation

 
Oracle Health Sciences leverages industry-shaping technologies that optimize clinical R&D, mitigate risk, advance healthcare, and improve patient outcomes.

 
Clinical | Oracle Life Sciences | Oracle <http://www.oracle.com/us/industries/life-sciences/clinical/overview/index.html>

http://www.oracle.com  Industries  Life Sciences  Clinical

 
Oracle Corporation

 
Oracle for Clinical Applications provides an integrated remote data collection facility for site-based entry.

 
Oracle Life Sciences | Knowledge Zone | Oracle … <http://www.oracle.com/partners/en/products/industries/life-sciences/get-started/index.html>

http://www.oracle.com/partners/…/life-sciences/…/index.ht&#8230;

 
Oracle Corporation

 
This Knowledge Zone was specifically developed for partners interested in reselling or specializing in Oracle Life Sciences solutions. To become a specialized …

 
[PDF]Brochure: Oracle Health Sciences Suite of Life Sciences … <http://www.oracle.com/us/industries/life-sciences/oracle-life-sciences-solutions-br-414127.pdf>

http://www.oracle.com/…/life-sciences/oracle-life-sciences-s&#8230;

 
Oracle Corporation

 
Oracle Health Sciences Suite of. Life Sciences Solutions. Integrated Solutions for Global Clinical Trials. Oracle Health Sciences provides the world’s broadest set …

 

 

Read Full Post »


10:15AM 11/13/2014 – 10th Annual Personalized Medicine Conference at the Harvard Medical School, Boston

REAL TIME Coverage of this Conference by Dr. Aviva Lev-Ari, PhD, RN – Director and Founder of LEADERS in PHARMACEUTICAL BUSINESS INTELLIGENCE, Boston http://pharmaceuticalintelligence.com

10:15 a.m. Panel Discussion — IT/Big Data

IT/Big Data

The human genome is composed of 6 billion nucleotides (using the genetic alphabet of T, C, G and A). As the cost of sequencing the human genome is decreasing at a rapid rate, it might not be too far into the future that every human being will be sequenced at least once in their lifetime. The sequence data together with the clinical data are going to be used more and more frequently to make clinical decisions. If that is true, we need to have secure methods of storing, retrieving and analyzing all of these data.  Some people argue that this is a tsunami of data that we are not ready to handle. The panel will discuss the types and volumes of data that are being generated and how to deal with it.

IT/Big Data

   Moderator:

Amy Abernethy, M.D.
Chief Medical Officer, Flatiron

Role of Informatics, SW and HW in PM. Big data and Healthcare

How Lab and Clinics can be connected. Oncologist, Hematologist use labs in clinical setting, Role of IT and Technology in the environment of the Clinicians

Compare Stanford Medical Center and Harvard Medical Center and Duke Medical Center — THREE different models in Healthcare data management

Create novel solutions: Capture the voice of the patient for integration of component: Volume, Veracity, Value

Decisions need to be made in short time frame, documentation added after the fact

No system can be perfect in all aspects

Understanding clinical record for conversion into data bases – keeping quality of data collected

Key Topics

Panelists:

Stephen Eck, M.D., Ph.D.
Vice President, Global Head of Oncology Medical Sciences,
Astellas, Inc.

Small data expert, great advantage to small data. Populations data allows for longitudinal studies,

Big Mac Big Data – Big is Good — Is data been collected suitable for what is it used, is it robust, limitations, of what the data analysis mean

Data analysis in Chemical Libraries – now annotated

Diversity data in NOTED by MDs, nuances are very great, Using Medical Records for building Billing Systems

Cases when the data needed is not known or not available — use data that is available — limits the scope of what Valuable solution can be arrived at

In Clinical Trial: needs of researchers, billing clinicians — in one system

Translation of data on disease to data object

Signal to Noise Problem — Thus Big data provided validity and power

 

J. Michael Gaziano, M.D., M.P.H., F.R.C.P.
Scientific Director, Massachusetts Veterans Epidemiology Research
and Information Center (MAVERIC), VA Boston Healthcare System;
Chief Division of Aging, Brigham and Women’s Hospital;
Professor of Medicine, Harvard Medical School

at BWH since 1987 at 75% – push forward the Genomics Agenda, VA system 25% – VA is horizontally data integrated embed research and knowledge — baseline questionnaire 200,000 phenotypes – questionnaire and Genomics data to be integrated, Data hierarchical way to be curated, Simple phenotypes, validate phenotypes, Probability to have susceptibility for actual disease, Genomics Medicine will benefit Clinicians

Data must be of visible quality, collect data via Telephone VA – on Med compliance study, on Ability to tolerate medication

–>>Annotation assisted in building a tool for Neurologist on Alzheimer’s Disease (AlzSWAN knowledge base) (see also Genotator , a Disease-Agnostic Tool for Annotation)

–>>Curation of data is very different than statistical analysis of Clinical Trial Data

–>>Integration of data at VA and at BWH are tow different models of SUCCESSFUL data integration models, accessing the data is also using a different model

–>>Data extraction from the Big data — an issue

–>>Where the answers are in the data, build algorithms that will pick up causes of disease: Alzheimer’s – very difficult to do

–>>system around all stakeholders: investment in connectivity, moving data, individual silo, HR, FIN, Clinical Research

–>>Biobank data and data quality

 

Krishna Yeshwant, M.D.
General Partner, Google Ventures;
Physician, Brigham and Women’s Hospital

Computer Scientist and Medical Student. Were the technology is going?

Messy situation, interaction IT and HC, Boston and Silicon Valley are focusing on Consumers, Google Engineers interested in developing Medical and HC applications — HUGE interest. Application or Wearable – new companies in this space, from Computer Science world to Medicine – Enterprise level – EMR or Consumer level – Wearable — both areas are very active in Silicon Valley

IT stuff in the hospital HARDER that IT in any other environment, great progress in last 5 years, security of data, privacy. Sequencing data cost of big data management with highest security

Constrained data vs non-constrained data

Opportunities for Government cooperation as a Lead needed for standardization of data objects

 

Questions from the Podium:

  • Where is the Truth: do we have all the tools or we don’t for Genomic data usage
  • Question on Interoperability
  • Big Valuable data — vs Big data
  • quality, uniform, large cohort, comprehensive Cancer Centers
  • Volume of data can compensate quality of data
  • Data from Imaging – Quality and interpretation – THREE radiologist will read cancer screening

 

 

 

– See more at: http://personalizedmedicine.partners.org/Education/Personalized-Medicine-Conference/Program.aspx#sthash.qGbGZXXf.dpuf

 

@HarvardPMConf

#PMConf

@SachsAssociates

@Duke_Medicine

@AstellasUS

@GoogleVentures

@harvardmed

@BrighamWomens

@kyeshwant

Read Full Post »


1:45PM 11/12/2014 – 10th Annual Personalized Medicine Conference at the Harvard Medical School, Boston

REAL TIME Coverage of this Conference by Dr. Aviva Lev-Ari, PhD, RN – Director and Founder of LEADERS in PHARMACEUTICAL BUSINESS INTELLIGENCE, Boston http://pharmaceuticalintelligence.com

 

1:45 p.m. Panel Discussion – Oncology

Oncology

There has been a remarkable transformation in our understanding of the molecular genetic basis of cancer and its treatment during the past decade or so. In depth genetic and genomic analysis of cancers has revealed that each cancer type can be sub-classified into many groups based on the genetic profiles and this information can be used to develop new targeted therapies and treatment options for cancer patients. This panel will explore the technologies that are facilitating our understanding of cancer, and how this information is being used in novel approaches for clinical development and treatment.

Oncology

Opening Speaker & Moderator:

Lynda Chin, M.D.
Department Chair, Department of Genomic Medicine
MD Anderson Cancer Center     @MDAnderson   #endcancer

  • Who pays for personalized medicine?
  • potential of Big data, analytics, Expert systems, so not each MD needs to see all cases, Profile disease to get same treatment
  • business model: IP, Discovery, sharing, ownership — yet accelerate therapy
  • security of healthcare data
  • segmentation of patient population
  • management of data and tracking innovations
  • platforms to be shared for innovations
  • study to be longitudinal,
  • How do we reconcile course of disease with personalized therapy
  • phenotyping the disease vs a Patient in wait for cure/treatment

Panelists:

Roy Herbst, M.D., Ph.D.    @DrRoyHerbstYale

Ensign Professor of Medicine and Professor of Pharmacology;
Chief of Medical Oncology, Yale Cancer Center and Smilow Cancer Hospital     @YaleCancer

Development new drugs to match patient, disease and drug – finding the right patient for the right Clinical Trial

  • match patient to drugs
  • partnerships: out of 100 screened patients, 10 had the gene, 5 were able to attend the trial — without the biomarker — all 100 patients would participate for the WRONG drug for them (except the 5)
  • patients wants to participate in trials next to home NOT to have to travel — now it is in the protocol
  • Annotated Databases – clinical Trial informed consent – adaptive design of Clinical Trial vs protocol
  • even Academic MD can’t read the reports on Genomics
  • patients are treated in the community — more training to MDs
  • Five companies collaborating – comparison of 6 drugs in the same class
  • if drug exist and you have the patient — you must apply personalized therapy

 

Lincoln Nadauld, M.D., Ph.D.
Director, Cancer Genomics, Huntsman Intermountain Cancer Clinic @lnadauld @intermountain

  • @Stanford, all patients get Tumor profiles Genomic results, interpretation – deliver personalized therapy
  • Outcomes from Genomics based therapies
  • Is survival superior
  • Targeted treatment – Health economic impact is cost lower or not for same outcome???
  • genomic profiling of tumors: Genomic information changes outcome – adverse events lower
  • Path ways and personalized medicine based on Genomics — integration not yet been worked out

Question by Moderator: Data Management

  • Platform development, clinical knowledge system,
  • build consortium of institutions to share big data – identify all patients with same profile

 

 

 

 

See more at  http://personalizedmedicine.partners.org/Education/Personalized-Medicine-Conference/Program.aspx#sthash.qGbGZXXf.dpuf

@HarvardPMConf

#PMConf

@SachsAssociates

Read Full Post »


 

Bioinformatics

Track 4 explores technologies and tools that bring together relevant -omic data from multiple physical locations for analysis. Case studies and results will be presented to illustrate how virtual data integration across multiple research initiatives can be applied to any disease. Other topics covered include collaboration tools, biomarker research, imaging, computational models, clinically actionable variants, and gene mapping and expression.

Final Agenda

 

Download Brochure | Pre-Conference Workshops

 

TUESDAY, APRIL 29

 

7:00 am Workshop Registration and Morning Coffee

8:00 – 11:30 Recommended Morning Pre-Conference Workshops*

Data Visualization in Biology: From the Basics to Big Data
Analyzing NGS Data in Galaxy

12:30 – 4:00 pm Recommended Afternoon Pre-Conference Workshops*

Big Data Analytics
Running a Local Galaxy Instance

*Separate Registration Required. Click here for detailed information.

 

2:00 – 7:00 pm Main Conference Registration

4:00 Event Chairperson’s Opening Remarks

Cindy Crowninshield, RD, LDN, Conference Director, Cambridge Healthtech Institute

 

4:05 PLENARY KEYNOTE SESSION

Click here for detailed information.

 

5:00 – 7:00 Welcome Reception in the Exhibit Hall with Poster Viewing

iPad® mini & Bose® QuietComfort 15 Noise Cancelling Headphones Raffle! Drawing held at 6:30pm!*

 

*Apple® & Bose® are not sponsors or participants in this program.

 

WEDNESDAY, APRIL 30

7:00 am Registration Open and Morning Coffee

8:00 Chairperson’s Opening Remarks

Phillips Kuhl, Co-Founder and President, Cambridge Healthtech Institute

 

8:05 PLENARY KEYNOTE SESSION

Click here for detailed information.

 

9:00 Benjamin Franklin Award & Laureate Presentation

9:30 Best Practices Awards Program

9:45 Coffee Break in the Exhibit Hall with Poster Viewing

 

BIOINFORMATICS FOR BIG DATA

10:50 Chairperson’s Remarks

11:00 Data Management Best Practices for Genomics Service Providers

Vas Vasiliadis, Director, Products, Computation Institute, University of Chicago and Argonne National Laboratory

Genomics research teams in academia and industry are increasingly limited at all stages of their work by large and unwieldy datasets, poor integration between the computing facilities they use for analysis, and difficulty in sharing analysis results with their customers and collaborators. We will discuss issues with current approaches and describe emerging best practices for managing genomics data through its lifecycle.

11:30 NGS Analysis to Drug Discovery: Impact of High-Performance Computing in Life Sciences

Bhanu Rekepalli, Ph.D., Assistant Professor and Research Scientist, Joint Institute for Computational Sciences, The University of Tennessee, Oak Ridge National Laboratory

We are working with small-cluster-based applications most widely used by the scientific community on the world’s premier supercomputers. We incorporated these parallel applications into science gateways with user-friendly, web-based portals. Learn how the research at UTK-ORNL will help to bridge the gap between the rate of big data generation in life sciences and the speed and ease at which biologists and pharmacists can study this data.

RemedyMD

12:00 pm The Future of Biobank Informatics

Bruce Pharr, Vice President, Product Marketing, Laboratory Systems, Remedy Informatics

As biobanks become increasingly essential to basic, translational, and clinical research for genetic studies and personalized medicine, biobank informatics must address areas from biospecimen tracking, privacy protection, and quality management to pre-analytical and clinical collection/identification of study data elements. This presentation will examine specific requirements for third-generation biobanks and how biobank informatics will meet those requirements.

YarcData

12:15 Learn How YarcData’s High Performance Hadoop and Graph Analytics Appliances Make It Easy to Use Big Data in Life Sciences

Ted Slater, Senior Solutions Architect, Life Sciences, YarcData, a division of Cray

YarcData, a division of Cray, offers high performance solutions for big data using Hadoop and graph analytics at scale, finally giving researchers the power to leverage all the data they need to stratify patients, discover new drug targets, accelerate NGS analysis, predict biomarkers, and better understand diseases and their treatments.

12:30 Luncheon Presentations (Sponsorship Opportunities Available) or Lunch on Your Own

1:50 Chairperson’s Remarks

1:55 Integration of Multi-Omic Data Using Linked Data Technologies

Aleksandar Milosavljevic, Ph.D., Professor, Human Genetics; Co-Director, Program in Structural & Computational Biology and Molecular Biophysics; Co-Director, Computational and Integrative Biomedical Research Center, Baylor College of Medicine

By virtue of programmatic interoperability (uniform REST APIs), Genboree servers enable virtual integration of multi-omic data that is distributed across multiple physical locations. Linked Data technologies of the Semantic Web provide an additional “logical” layer of integration by enabling distributed queries across the distributed data and by bringing multi-omic data into the context of pathways and other background knowledge required for data interpretation.

2:25 Building Open Source Semantic Web-Based Biomedical Content Repositories to Facilitate and Speed Up Discovery and Research

Bhanu Bahl, Ph.D., Director, Clinical and Translational Science Centre, Harvard Medical School

Douglas MacFadden, CIO, Harvard Catalyst at Harvard Medical School

Eagle-i open source network at Harvard provides a state-of-the-art informatics platform to support the quality control and annotation of resources establishing a sound foundation for a well-curated resource collection in accordance with Semantic Web and Linked Open Data principles. Learn how this ontology-centric architecture is used to efficiently store, create, and search data.

TessellaNEW

2:55 Data Experts: Improving Translational Drug-Development Efficiency

Jamie MacPherson, Ph.D., Consultant, Tessella

We report on a novel approach to translational informatics support: embedding ‘Data Experts’ within drug-project teams. Data experts combine first-line informatics support and Business Analysis. They help teams exploit data sources that are diverse in type, scale and quality; analyse user-requirements and prototype potential software solutions. We then explore scaling this approach from a specific drug development team to all.

3:25 Refreshment Break in the Exhibit Hall with Poster Viewing

 

BIOLOGICAL NETWORKS

4:00 Network Verification Challenge: A Reputation-Based Crowd-Sourced Peer Review Platform for Network Biology

William Hayes, Ph.D., Senior Vice President, Platform Development, IT/Informatics, Selventa

Anselmo DiFabio, Vice President, Technology, Applied Dynamic Solutions

The Network Verification Challenge proposes a new approach for peer review for Network biology. The use of a reputation-based crowd-sourced platform can make previously overwhelming efforts in capturing large-scale network biology and validating it possible. The same approach for peer review can also be applied inside bioPharma for internal collaboration and validation of network biology in and across therapeutic areas.

4:30 NDEx, the Network Data Exchange: Bridging the Knowledge Gap for Commercial and Academic Collaboration on Biological Networks

Dexter Pratt, Project Director, NDEx, Cytoscape Consortium

NDEx is a public portal for collaboration and publication for scientists and organizations working with biological networks of multiple types and in multiple formats. This talk presents key features of the NDEx portal and the underlying open-source server software. The status of NDEx in collaborations with other organizations and the use (or development) of standards will be summarized.

5:00 Sponsored Presentations (Opportunities Available)

5:30 – 6:30 Best of Show Awards Reception in the Exhibit Hall

THURSDAY, MAY 1

7:15 am Registration Open

7:15 Breakfast Presentation (Sponsorship Opportunity Available) or Morning Coffee

8:30 Chairperson’s Opening Remarks

Kevin Davies, Ph.D., Vice President Business Development & Publisher C&EN, American Chemical Society; Founding Editor, Bio-IT World

 

8:35 PLENARY KEYNOTE SESSION

Click here for detailed information.

 

10:00 Coffee Break in the Exhibit Hall and Poster Competition Winners Announced

 

BIOINFORMATICS ACROSS MULTIPLE RESEARCH INITIATIVES

10:30 Chairperson’s Opening Remarks

10:35 Analysis of Genomics Data in an Internal Cloud Computing Environment

Philip Groth, Ph.D., IT Business Partner Genomics, R&D IT – Research, Bayer HealthCare

This talk presents the technical set-up of vCloud, an in-house cloud solution, maintenance and running an internal cloud-computing environment, and how this set-up enables fast & secure analysis of large-scale genomics data. Results of analyzing genomic data from over 4,000 cancer patients will be presented.

11:05 Genome-Wide Multi-Omics Profiling of Colorectal Cancer Identifies Immune Determinants Strongly Associated with Relapse

Subha Madhavan, Ph.D., Director, Innovation Center for Biomedical Informatics, Oncology, Georgetown University

This presentation demonstrates the use of novel informatics methods and data integration approaches in identifying prognostic markers of cancer. The use and benefit of adjuvant chemotherapy to treat patients with state II colorectal cancer (CRC) is not well understood since the majority of these patients are cured by surgery alone.

11:35 Sponsored Presentations (Opportunities Available)

12:05 pm Luncheon Presentations (Sponsorship Opportunities Available) or Lunch on Your Own

1:15 Dessert Refreshment Break in the Exhibit Hall with Poster Viewing

1:55 Chairperson’s Remarks

2:00 An Algorithm to Access Human Memory Showing Alzheimer Symptoms When Distorted

Simon Berkovich, Ph.D., Professor, Computer Science, The George Washington University

This talk presents a novel theoretical framework for bioinformatics. Access to a holographic model of the brain encounters a particular problem of multiple responses resolution. For the given milieu, we employ a digital-analog adjustment of a streaming algorithm for finding a predominant element. Receptacles deterioration incurs preferential recall of prior life stages akin to Alzheimer’s disease.

 

MACHINE LEARNING MODELS

2:30 Accurate Prediction of Clinical Stroke Scales from Robotic Measurements

Dimitris K. Agrafiotis, Ph.D., FRSC, Vice President and Chief Data Officer, Covance

Here, we describe a novel approach that combines robotic devices and advanced machine learning algorithms to derive predictive models of clinical assessments of motor function following stroke. We show that it is possible to derive sensitive biomarkers of motor impairment using a few easily obtained robotic measurements, which can then be used to improve the efficiency and cost of clinical trials.

3:00 GPS Engineering: Machine Learning Approaches to Biological Engineering

Drew Regitsky, Scientist, Bioengineering, Calysta Energy

This talk presents a potential new approach to computational representations of biological systems and applying multidimensional analysis to predicting the behavior of complex systems. Several case studies will be presented to demonstrate applications of the methods and examples of the output of data analysis.

3:30 A Multiclass Extreme-Learning-Machine Approach to the Discovery of Multiple Cancer Biomarkers: Using Binary Coded Genetic Algorithm and IPA Analysis

Saras Saraswathi, Ph.D., Clinical Instructor, Pediatrics, Ohio State University; Postdoctoral Research Associate, Battelle Center for Mathematical Medicine, Research Institute, Nationwide Children’s Hospital

The neural network-based Extreme Learning Machine is combined with a Binary Coded Genetic Algorithm to select a small set of 92 genes which simultaneously classify 14 different types of cancers simultaneously, to high accuracy. IPA analysis of the selected genes reveals that over 60% of the selected genes are related to many cancers that are being classified.

4:00 Conference Adjourns

SOURCE

http://www.bio-itworldexpo.com/Bioinformatics/

 

Read Full Post »


Cambridge Healthtech Institute’s Sixth Annual

Integrated R&D Informatics & Knowledge Management

Supporting Collaboration, Externalization, Globalization & Translational Research

February 10-12, 2014 | Moscone North Convention Center | San Francisco, CA

Reporter: Aviva Lev-Ari, PhD, RN

For the past five years, Integrated R&D Informatics & Knowledge Management has brought together senior executives and leaders in R&D informatics from pharma, large biotech and their partners to discuss the latest ways to manage the integration of data from disparate sources to create valuable knowledge for their organizations. This year’s conference will focus on addressing how informatics teams are enabling and supporting internal collaboration along with externalization of data, helping deal with pre-competitive activities, as well as continuing to support translational research, all directed at the overall goal of improving productivity and efficiency in a cost-effective manner.

 

Day 1 | Day 2 | Day 3 | Download Brochure

Monday, February 10

10:30 am Conference Program Registration

 

EXTERNAL COLLABORATION BEST PRACTICES: GETTING VALUE OUT OF DATA WITH YOUR COLLABORATORS

11:50 Chairperson’s Opening Remarks

Martin Leach, Vice President, Research & Development IT, Biogen Idec

12:00 pm Roche’s Translational and Clinical Research Center (TCRC): How Our Big Data and Externalization Strategy Impacts Drug Discovery

Juergen Hammer, Ph.D., MBA, Pharma Research and Early Development Informatics (pREDi), pREDi Center Head; Global Head, Disease & Translational Informatics, Roche Translational Clinical Research Center

Pharmaceutical companies increasingly embed their research and early development organizations into vibrant academic hubs to enhance innovation and asset finding. Roche has recently opened “TCRC, Inc.”, soon to be located in New York City. The presentation will focus on our Big Data and Externalization approaches to support the TCRC, and will exemplify how we impact drug development decisions using informatics.

12:30 The Lilly Open Innovation Drug Discovery Program (OIDD)

Daniel H. Robertson, Ph.D., Senior Director, LRL IT Research, Eli Lilly and Company

Through OIDD, Lilly has established a network of top global research talent at academic and biotech institutions to provide them access to proprietary, in vitro phenotypic, and target-based assays (PD2 and TargetD2). In addition to supplying data that may lead to potential collaborations, Lilly has recently been partnering to deploy additional design tools for OIDD investigators to assist in designing compounds submitted to the assays through this collaboration.

1:00 Session Break

Sponsored by
Elsevier

1:15 Luncheon Presentation I: Building and Linking Disease and Drug Target Profiles Using Semantic Search Technologiesnt

Maria Shkrob, Ph.D.,Senior Bioinformatics Scientist, Elsevier

Researchers face a growing challenge in managing vast quantities of unstructured data to find relevant information that can guide their research. A new semantic search engine that incorporates text-mining capability along with customizable dictionaries and taxonomies rapidly finds facts and provides summary tables from multiple sources, including scientific abstracts and full-texts, grant applications, and in-house documents. This ability to accurately retrieve and summarize information significantly increases researcher productivity compared to traditional keyword search.

1:45 Luncheon Presentation II (Sponsorship Opportunity Available) 

2:15 Session Break

2:30 Chairperson’s Remarks

Martin Leach, Vice President, Research & Development IT, Biogen Idec

2:35 Building an Informatics Ecosystem for Externalized R&D

Sándor Szalma, Ph.D., Head, External Innovation, R&D IT, Janssen Research & Development, LLC

Pharma companies have historically been involved in many partnerships fueling their discovery engines, supported with non-optimal IT systems. With recent wide-spread adaptation of hosted solutions and cloud computing, there is an opportunity now to implement informatics solutions such that collaborative exploration of the data generated in partnerships becomes possible. We also discuss the opportunities to build parts of the ecosystem in a pre-competitive manner and our experience in deploying open source tools.

3:05 Cloud Solutions Spanning Applications across R&D, Development, G&A, and Compliance Functions

John Reynders, CIO, Moderna Therapeutics; former Vice President, Research & Development Information, AstraZeneca

This presentation will overview Moderna’s aggressive push into cloud solutions spanning applications across R&D, development, G&A, and compliance functions. Moderna’s cloud-based informatics workflows for the design, development, screening, and delivery of messenger RNA therapeutics will be shared along with associated challenges of Big Data, cloud security, collaboration, and cross-cloud integration.

3:35 PANEL DISCUSSION: Approaches and Lessons Learned to Build a Comprehensive R&D Search Capability

Martin Leach, Vice President, Research & Development IT, Biogen Idec

The accessibility of information within any R&D organization is key to the successful collaboration and development of a research pipeline. The holy grail for most research organizations is the one-stop search (aka. Google-like search for R&D). In this panel we will discuss the approaches a number of research organizations have taken, successes, failures and lessons learned.

Panelists:

John Koch, Director, Scientific Information Architecture & Search, Merck

Hongmei Huang, Ph.D., Director, NIBR IT, Novartis

Sponsored by
Thomson Reuters

4:05 Efficient Data Mining for Precision Medicine
Sirimon O’Charoen, Ph.D., Manager, Translational Medicine, Life Sciences Professional Services, Thomson Reuters

4:35 Refreshment Break and Transition to Plenary Keynote

 

5:00 Plenary Keynote Session (Click Here For More Details)

 

6:15 Grand Opening Reception in the Exhibit Hall with Poster Viewing

7:45 Close of Day

Tuesday, February 11

7:00 am Registration and Morning Coffee

 

8:00 Plenary Keynote Session (Click Here For More Details) 

 

Sponsored by
Slone Partners

9:15 Refreshment Break in the Exhibit Hall with Poster Viewing

 

REGISTRATION SYSTEMS

10:25 Chairperson’s Remarks

Arturo J. Morales, Ph.D., Global Lead, Biology Platform Informatics, Novartis Institutes for Biomedical Research

10:30 Registration Systems: Applications or Data Stores?

Arturo J. Morales, Ph.D., Global Lead, Biology Platform Informatics, Novartis Institutes for Biomedical Research

Registration systems are not applications that usually stand on their own. Their value comes from the enablement of downstream data analysis and sample tracking through proper management of concept and sample metadata. As such, most registration systems offer little intrinsic value to those that use it directly and user compliance can be a challenge. Thus, it is important to adapt to workflows, as opposed to making users adapt to them.

11:00 Development of a LIMS Platform to Manage Biological Therapeutics

David M. Sedlock, Ph.D., Senior Director, Research & Development Systems, Takeda Cambridge US

The management of biological samples for testing as biotherapeutic agents requires a unique type of LIMS to handle both workflows and sample registration. We are currently engaged in a couple of projects at Takeda to create a working solution for both research and preclinical development samples to be managed across multiple R&D sites. The project status and business impact will be reviewed.

11:30 An Enhanced Electronic Laboratory Notebook to Support Biologics Research and Development

Beth Basham, Ph.D., Director, Account Management, Biologics Discovery & IT Site Lead, Merck

Merck is evolving our electronic lab notebook from a straightforward paper notebook replacement to a platform that structures data and results, provides basic LIMS-like capabilities and enables powerful search and analytics. We will share our experiences in providing a solution to support some of the stages of biologics research and development.

12:00 pm Biological Registration Systems at UCB and How They Integrate into the Discovery Workflow

David Lee, Ph.D., Principal Scientist, Informatics, UCB

The benefits of informatics-driven data management systems are well known in the small molecule therapeutics arena. Extending these systems to supporting biotherapeutics presents a number of challenges. We present a novel data management system, BioQuest, integrating bespoke and best in class software systems designed to capture and integrate NBE data at UCB. We will focus on registration systems, in particular on the antibody and non-antibody protein registration system based on the Genedata Biologics platform.

12:30 Session Break

Sponsored by
CambridgeSemantics

12:40 Luncheon Presentation I

Speaker to be Announced

1:10 Luncheon Presentation II (Sponsorship Opportunity Available)

1:40 Refreshment Break in the Exhibit Hall with Poster Viewing

 

PRE-COMPETITIVE COLLABORATION & SUPPORTING PUBLIC-PRIVATE PARTNERSHIPS

2:15 Chairperson’s Remarks

Barry Bunin, Ph.D., CEO, Collaborative Drug Discovery (CDD, Inc.)

Sponsored by
CollaborativeDrugDiscovery

2:20 Modern Drug Research Informatics Applications to CNS, Infectious, Neglected, Rare, and Commercial Diseases

Barry Bunin, Ph.D., CEO, Collaborative Drug Discovery (CDD, Inc.)

There are currently hundreds of commodity technologies for handling scientific information – each with its own scope and limitations. The application of collaborative technologies to interrogate potency, selectively, and therapeutic windows of small molecule structure activity relationship (SAR) data will be presented in 5 case studies. Given external (public and collaborative) data grows faster than internal data, novel collaborative technologies to gracefully manage combined external and private data provide an ever-increasing competitive advantage.

2:50 tranSMART: Use Cases from Deployments Highlighting Emerging Models for Pre-Competitive Collaboration and Open Source Sustainability

Dan Housman, CTO, Translational Research, Recombinant By Deloitte

The tranSMART open source translational research knowledge management software continues to make forward progress since the initial release in 2012. Specific use cases from a variety of projects incorporating tranSMART will be walked through to highlight emerging pre-competitive collaboration models including opportunities, new capabilities, and unresolved challenges. The current state of open project sustainability and approaches taken by Recombinant and other groups to ensure the software increases in value for adopters will be explored.

3:20 The Innovative Medicines Initiative: Collaborating around Knowledge Management

Anthony Rowe, Ph.D., Principal Scientist, External Innovation, Johnson & Johnson

The Innovative Medicines Initiative (IMI) is a public-private partnership between the European Federation of Pharmaceutical Industry and Associates (EFPIA) and the European Union. It is dedicated to overcoming key bottlenecks in pharmaceutical research by enabling pre-competitive collaboration between industry and academic scientists. In this talk we will review the Knowledge Management activities undertaken by the IMI and how they are delivering new services and capabilities that can enhance pharmaceutical R&D.

 

Sponsored by
Certara

3:50 Bringing Scientific Data to Life: Agile Data Access and Analysis from Discovery to Development

Jonathan Feldmann, Vice President, Scientific Informatics, Certara

4:20 Valentine’s Day Celebration in the Exhibit Hall with Poster Viewing

5:20 Breakout Discussions in the Exhibit Hall

These interactive discussion groups are open to all attendees, speakers, sponsors, & exhibitors. Participants choose a specific breakout discussion group to join. Each group has a moderator to ensure focused discussions around key issues within the topic. This format allows participants to meet potential collaborators, share examples from their work, vet ideas with peers, and be part of a group problem-solving endeavor. The discussions provide an informal exchange of ideas and are not meant to be a corporate or specific product discussion.

Collaboration, Externalization and Privacy

Micahel H. Elliott, CEO, Atrium Research & Consulting

  • At what extent is data exchange required in the era of R&D virtualization?
  • How do we balance ollaboration with security risk?
  • What tools are required to enable virtualization?  Will these be vendor supplied or custom?

Biological Registration Systems

Arturo J. Morales, Ph.D., Global Lead, Biology Platform Informatics, Novartis Institutes for Biomedical Research

  • How do we implement systems that users want to use?
  • What are some good practices?
  • Where are data standards making a difference?

Data Integration Today

Ajay Shah, Ph.D., Director, Research Informatics, City of Hope National Medical Center

  • Building extensible software platform for integrating basic, clinical and translational research data – technology, data and cultural challenges
  • Integrating deeper analysis and natural language processing tools to leverage the platform for translational research
  • Case studies from participants and discussion

Translational Informatics

Shoibal Datta, Director, Data Sciences, Biogen Idec

  • What does the perfect translational informatics platform look like and how do we get there?
  • Where does translation stop?
  • What does the Affordable Care Act mean to the future of Real World Evidence

6:30 Close of Day

 

Wednesday, February 12

7:00 am Breakfast Presentation (Sponsorship Opportunity Available) or Morning Coffee

 

8:00 Plenary Keynote Session (Click Here For More Details) 

 

9:45 Refreshment Break and Poster Competition Winner Announced in the Exhibit Hall

 

DATA INTEGRATION & SHARING: TOOLS AND POLICIES FOR VISUALIZATION AND ANALYSIS

10:35 Chairperson’s Remarks

Larry Hunter, Ph.D., Director, Center for Computational Pharmacology & Computational Bioscience Program, Professor, Pharmacology, University of Colorado

10:40 Knowledge-Based Analysis at Genomic Scale

Larry Hunter, Ph.D., Director, Center for Computational Pharmacology & Computational Bioscience Program, Professor, Pharmacology, University of Colorado

High-throughput instruments and the explosion of new results in the scientific literature is both a blessing and a curse to the bench researcher. Effective design and implementation of computational tools that genuinely facilitate the generation of novel and significant scientific insights remains poorly understood. This talk presents efforts that combine natural language processing for information extraction, graphical network models for semantic data integration, and some novel user interface approaches into a system that has facilitated several significant discoveries.

11:00 Combining Visual Analytics and Parallel Computing for Data-Driven Analysis Pipeline Selection and Optimization to Support the Big Data to Knowledge Transformation

Richard Scheuermann, Director, Informatics, J. Craig Venter Institute

This presentation describes our efforts at the J. Craig Venter Institute (JCVI) in collaboration with the Texas Advanced Computing Center (TACC) in the development of a high performance cyber-infrastructure that combines visual analytics and parallel computing for data-driven selection and optimization of analytical pipelines based on objective performance metrics. We demonstrate the application of these principles and infrastructure for the analysis of genome-wide gene expression and high-throughput, high dimensional flow cytometry data in clinical and translational research settings.

11:20 Real World Evidence for Pharma: Improving Traditional Research by Enhancing Real World Data Environment

Arpit Davé, Director, IT, Bristol-Myers Squibb

Life sciences organizations have started to change the way they discover, develop, and commercialize medicines to address patient, regulators and payer needs at every stage of the product lifecycle. Real world data (longitudinal and integrated patient information) is the key to answering complex questions in R&D and product commercialization. In order to access patient data across boundaries, companies and regulators are experimenting with various data and analytics collaboration models. This talk presents key lessons learned.

11:40 Spotfire Templates for Analysis & Visualization of Project Data

Sandhya Sreepathy, PMP, Head of Operations, Global Discovery Chemistry, Novartis

There has been a significant increase in the usage of Spotfire by project teams in Emeryville for visualization and analysis of data. To help streamline development activity and support the needs of project teams with data analysis and visualization, NIBR-IT in collaboration with computational chemistry group in Emeryville developed project based Spotfire templates. Templates were built leveraging existing technologies for retrieval/import of data and incorporated common elements of analysis and visualization(scaffold assignment, ligand, lipophilic efficiency, activity ratios, r-group decomposition etc). Predefined visualizations and filters helped accelerate project team decision making.

12:10 pm Session Break

12:20 Luncheon Presentation (Sponsorship Opportunity Available) or Lunch on Your Own

1:00 Refreshment Break in the Exhibit Hall and Last Chance for Poster Viewing

 

HOW BIG DATA WILL DRIVE RESEARCH FORWARD

1:40 Chairperson’s Remarks

Michael H. Elliott, CEO, Atrium Research & Consulting LLC

1:45 Harnessing Big Data to Accelerate Drug Development

Vinod Kumar, Ph.D., Senior Investigator, Computational Biology, GlaxoSmithKline Pharmaceuticals

With the rapid development of high-throughput technologies and ever-increasing accumulation of whole genome-level datasets, an increasing number of diseases and drugs can be comprehensively characterized by the changes they induce in gene expression, protein, metabolites and phenotypes. Integrating and querying such large volumes of data, often spanning domains and residing in diverse sources, constitutes a significant obstacle. This talk presents two distinct approaches that utilize these data types to systematically evaluate and suggest new disease indications for new and existing drugs.

2:15 Drug Process Design Improvement based on Data Management and Analysis

Valérie Vermylen, Knowledge Management, Director, GPS, UCB

Most of the scientific process data generated are not free to access, even if managed in databases. At UCB, data was recently made available including its context. It allows process developers to draw easily designed space and define critical parameters. To support investigation studies as impact analysis, manufacturing dashboards and trends are automatically published. An example of correlation between process data and patients’ clinical responses will be presented as an illustration of advanced data analysis.

2:45 The Library of Integrated Network-based Cellular Signatures (LINCS) Information FramEwork (LIFE)

Stephan C. Schürer, Ph.D., Associate Professor, Pharmacology, Center for Computational Science at Miller School of Medicine, University of Miami

The NIH-funded LINCS consortium is producing an extensive dataset of cellular response signatures to a variety of small molecule and genetic perturbations. We have been developing the LINCS Information FramEwork (LIFE) – a specialized knowledge-driven search system for LINCS data.

Sponsored by
Schrodinger

3:15 An Enhanced Molecular Design Platform That Fosters Ideation, Knowledge Transfer, and Collaboration

John Conway, Enterprise Informatics, Schrödinger, Inc.

Drug discovery is the ultimate team sport. Schrödinger is developing a collaborative and knowledge engineered platform—LiveDesign—to help scientists not only capture their ideas and best practices, but to exploit and share these with select team members. Above and beyond the aggregation of 2D data, this platform will allow users to bring together 3D data with its associated annotations. LiveDesign will ultimately lead to better patient outcomes, promoting better scientific communication by exposing data, ideas, and colleague feedback during the design and redesign phases of molecular discovery.

3:45 Refreshment Break

 

FROM BIG DATA TO TRANSLATIONAL INFORMATICS

4:00 Chairperson’s Remarks

Shoibal Datta, Ph.D., Director, Data Sciences, Biogen Idec

4:05 Designing and Building a Data Sciences Capability to Support R&D and Corporate Big Data Needs

Shoibal Datta, Ph.D., Director, Data Sciences, Biogen Idec

To achieve Biogen Idec’s strategic goals, we have built a cross-disciplinary team to focus on key areas of interest and the required capabilities. To provide a reusable set of IT services we have broken down our platform to focus on the Ingestion, Digestion, Extraction and Analysis of data. In this presentation, we will outline how we brought focus and prioritization to our data sciences needs, our data sciences architecture, lessons learned and our future direction.

4:35 Translational Informatics: Decomposing to Singularity

John Shon, M.D., Head, Translational Informatics IT, Johnson & Johnson

There has been an explosion of data across discovery, development, and beyond and all informatics groups are struggling with major challenges in computation, storage and analysis. In a large pharmaceutical environment, the value propositions of informatics lie primarily in three dimensions which I describe. In the larger hyperdynamic environments of research technologies, information technologies, and modern science, interdisciplinary and collaborative approaches become imperative to execute translational strategies effectively.

5:05 Integrating Translational Research Tools

Erik Bierwagen, Ph.D., Principal Programmer Analyst, Department of Bioinformatics, Genentech, Inc.

This talk will cover our efforts at creating an integrated informatics system for animal studies from birth to death and beyond. Our efforts span many different disciplines and groups, but share the common effort of integrating data seamlessly.

5:35 Close of Conference Program

SOURCE

 

Read Full Post »


Reporter: Larry H Bernstein, MD, FCAP

Big Data in Genomic Medicine

Image Source: Created by Noam Steiner Tomer 7/31/2020

Pathologists May Be Healthcare’s Rock Stars of Big Data in Genomic Medicine’s ’Third Wave’

Published: December 17 2012

Pathologists are positioned to be the primary interpreters of big data as genomic medicine further evolves

Pathologists and clinical laboratory managers may be surprised to learn that at least one data scientist has proclaimed pathologists the real big data rock stars of healthcare. The reason has to do with the shift in focus of genomic medicine from therapeutics and presymptomatic disease assessment to big data analytics.

In a recent posting published at Forbes.com, data scientist Jim Golden heralded the pronouncement of Harvard pathologist Mark S. Boguski, M.D., Ph.D., FACM. He declared that “The time of the $1,000 genome meme is over!”

DNA Sequencing Systems and the $1,000 Genome

Golden has designed, built, and programmed DNA sequencing devices. He apprenticed under the Human Genome program and spent 15 years working towards the $1,000 genome. “I’m a believer,” he blogged. “[That’s] why I was so intrigued [by Boguski’s remarks].

Boguski is Associate Professor of Pathology at the Center for Biomedical Informatics at Harvard Medical School and the Department of Pathology at Beth Israel Deaconess Medical Center. It was in a presentation at a healthcare conference in Boston that Boguski pronounced that it is time for the $1,000 genome to go.

“Big data analytics” will be required for translational medicine to succeed in the Third Wave of Genetic Medicine. That’s the opinion of Mark S. Boguski, M.D., Ph.D., who is a pathologist-informatist at Harvard Medical School and Beth Israel Deaconess Medical Center. Boguski predicts that pathologists are positioned to become the “rock stars” of big data analytics. For pathologists and clinical laboratory administrators, that means that big computer power will become increasingly important for all medical laboratories. (Photo by Medicine20Congress.com.)

Both Golden and Boguski acknowledged the benefits generated by the race to the $1,000 genome. Competition to be first to achieve this milestone motivated scientists and engineers to swiftly drive down the cost of decoding DNA. The result was a series of advances in instrumentation, chemistry, and biology.

Pathologists and Big Data Analytics

“Our notions about how genome science and technology would improve health and healthcare have changed,” Boguski wrote in an editorial published at Future Medicine. He then noted that the focus has shifted to big data analytics.

In the editorial, Boguski described the phases of development of genomic medicine as “waves.” The first wave occurred during the mid- to late-1990s. It focused on single- nucleotide polymorphisms (SNP) and therapeutics.

Medical Laboratories Have Opportunity to Perform Presymptomatic Testing

The second wave focused on presymptomatic testing for disease risk assessment and Genome Wide Association Studies (GWAS). Researchers expected this data to help manage common diseases.

The first two waves of medical genomics were conducted largely by the pharmaceutical industry, as well as with  primary care and public health communities, according to Boguski. Considerable optimism accompanied each wave of medical genomics.

“Despite the earlier optimism, progress in improving human health has been modest and incremental, rather than paradigm-shifting,” noted Boguski, who wrote that,to date, only a handful of genome-derived drugs have reached the market. He further observed that products such as direct-to-consumer genomic testing have proved more educational and recreational than medical.

“Third Wave” of Genomic Medicine

It was rapid declines in the cost of next-generation DNA sequencing technologies that now has triggered the third wave of genomic medicine. Its focus is postsymptomatic genotyping for individualized and optimized disease management.

“This is where genomics is likely to bring the most direct and sustained impact on healthcare for several reasons,” stated Boguski. “Genomics technologies enable disease diagnosis of sufficient precision to drive both cost-effective [patient] management and better patient outcomes. Thus, they are an essential part of the prescription for disruptive healthcare reform.”

Boguski reiterated the case for the value of laboratory medicine. He stated the following critical—but often overlooked—points, each of which is familiar to pathologists and clinical laboratory managers:

1. Pathologist-directed, licensed clinical laboratory testing has a major effect on clinical decision-making.

2. Medical laboratory testing services account for only about 2% of healthcare expenditures in the United States.

3. Medical laboratory services strongly influence the remaining 98% of costs through the information they provide on the prevention, diagnosis, treatment, and management of disease.

Molecular Diagnostics Reaching Maturity for Clinical Laboratory Testing

“Genome analytics are just another technology in the evolution of molecular diagnostics,” Boguski declared in his editorial.

Read more: Pathologists May Be Healthcare’s Rock Stars of Big Data in Genomic Medicine’s ’Third Wave’ | Dark Daily http://www.darkdaily.com/pathologists-may-be-healthcare%e2%80%99s-rock-stars-of-big-data-in-genomic-medicines-third-wave-1217#ixzz2FL24IRAA

English: Created by Abizar Lakdawalla.

English: Created by Abizar Lakdawalla. (Photo credit: Wikipedia)

English: Workflow for DNA nanoball sequencing

English: Workflow for DNA nanoball sequencing (Photo credit: Wikipedia)

DNA sequence

DNA sequence (Photo credit: Wikipedia)

Big Data: water wordscape

Big Data: water wordscape (Photo credit: Marius B)

Comment & Response

Right now the cost of the testing and the turnaround times are not favorable. It is going to take a decade or more for clinical labs to catch up. For some time it will be send out tests to Quest, LabCorp, and State or University lab consortia.

The power of the research technology is pushing this along, but for Personalized Medicine the testing should be coincident with the patient visit, and the best list of probable issues should be accessible on the report screen. The EHR industry is dominated by 2 companies that I see have no interest in meeting the needs of the physicians. The payback has to be on efficient workflow, accurate assessment of the record, and timely information. The focus for 25 years has been on billing structure. But even the revised billing codes (ICD10) can’t be less than 5 years out-of-date because of improvements in the knowledge base and improvements in applied math algorithms.

The medical record still may have information buried min a word heap, and the laboratory work is a go-to-you know where sheet with perhaps 15 variables on a page, with chemistry and hematology, immunology, blood bank, and microbiology on separate pages. The ability of the physician to fully digest the information with “errorless” discrimination is tested, and the stress imposed by the time for each patient compromises performance. There is work going on in moving proteomics along to a high throughput system for improved commercial viability, that was reported by Leigh Anderson a few years ago. The genomics is more difficult, but the genomics is partly moving to rapid micropanel tools.

In summary, there are 3 factors:

1. Automation and interpretation
2. Integration into the EHR in real time and usable by a physician.
3. The sorting out of the highest feature “predictors” and classifying them into clinically meaningful sets and subsets.

When this is done, then the next generation of recoding will be in demand.
The Automated Malnutrition Assessment
Gil David1, Larry Bernstein2, Ronald R. Coifman1

1Department of Mathematics, Program in Applied Mathematics,
Yale University, New Haven, CT 06510, USA,
2Triplex Consulting, Trumbull, CT 06611

Abstract

Introduction: We propose an automated nutritional assessment (ANA) algorithm that provides a method for malnutrition risk prediction with high accuracy and reliability.

Materials and Methods: The database used for this study is a file of 432 patients, where each patient is described by 4 laboratory parameters and 11 clinical parameters. A malnutrition risk assessment of low (1), moderate (2) or high (3) was assigned by a dietitian for each patient. An algorithm for data organization and classification via characteristic metrics is proposed. For each patient, the algorithm characterizes its unique profile and builds a characteristic metric to identify similar patients who are mapped into a classification.

Results: The algorithm assigned a malnutrition risk level for each patient based on different training sizes that were taken out of the data.

Our method resulted in an average error (distance between the automated score and the real score) of 0.386, 0.3507, 0.3454, 0.34 and 0.2907 for 10%, 30%, 50%, 70% and 90% training sizes, respectively.

Our method outperformed the compared method even when our method used a smaller training set then the compared method. In addition, we show that the laboratory parameters themselves are sufficient for the automated risk prediction and organize the patients into clusters that correspond to low, low-moderate, moderate, moderate-high and high risk areas.

Discussion: The problem of rapidly identifying risk and severity of malnutrition is crucial for minimizing medical and surgical complications. These are not easily performed or adequately expedited. We characterize for each patient a unique profile and map similar patients into a classification. We also find that the laboratory parameters themselves are sufficient for the automated risk prediction.

Keywords: Network Algorithm, unsupervised classification, malnutrition screening, protein energy malnutrition (PEM), malnutrition risk, characteristic metric, characteristic profile, data characterization, non-linear differential diagnosis.

Read Full Post »

« Newer Posts