Track 15: AI for Pharma & Biotech

One of the biggest bottlenecks in drug development is in the early research stage. This stage is time needed to go from identifying a potential disease target to testing a drug candidate’s probability of hitting that target. This stage can take four to six years. Ambitious AI techniques are aiming to compress this process to one year. As of August 2018, over 25 pharmaceutical companies and over 95 startups are using artificial intelligence for drug discovery. Time to develop new life-saving drugs can be drastically reduced by using AI. The Inaugural AI for Pharma and Biotech track will discuss opportunities that biopharma organizations are using to harness the power of AI and machine learning technologies to maximize and accelerate drug discovery efforts from early stage to adoption to practical application. Presentations will also discuss challenges of these technologies being sophisticated enough to make sense of complex medical data.

Final Agenda

Tuesday, April 16

7:00 am Workshop Registration Open and Morning Coffee

8:0011:30 Recommended Morning Pre-Conference Workshops*

W4. AI for Pharma

12:304:00 pm Recommended Afternoon Pre-Conference Workshops*

W11. Digital Data Strategy for the Lab

* Separate registration required.

2:006:30 Main Conference Registration Open


5:007:00 Welcome Reception in the Exhibit Hall with Poster Viewing

Wednesday, April 17

7:30 am Registration Open and Morning Coffee


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

harborview 2

10:50 Chairperson’s Remarks

Richard Harrison, PhD, Products – Life Sciences, Senior Manager, Accenture

11:00 Next Generation Cognitive Supercomputing and Its Impact on Precision Medicine: Challenges, Trends and Opportunities

Edmon Begoli, PhD, Chief Data Architect, Oak Ridge National Laboratory

The impact of AI methods and big data technologies in pharma research and genomic medicine to advance precision medicine initiatives are taking on more importance. AI is becoming key player in the convergence of medical data and computer technologies. This talk gives a big picture viewpoint on the evolvement of AI’s role, what the key drivers and challenges are, and trends to look for during the next 10-15 years.

11:30 From Hype to Reality: Data Science Enabling Personalized Medicine

Holger Fröhlich, PhD, Director and Head of Data Science Enablement, R&D Informatics, UCB BioSciences GmbH

Personalized, precision, P4, or stratified medicine is understood as a medical approach in which patients are stratified based on their disease subtype, risk, prognosis, or treatment response using specialized diagnostic tests. The key idea is to base medical decisions on individual patient characteristics, including molecular and behavioral biomarkers, rather than on population averages. Personalized medicine is deeply connected to and dependent on data science, specifically machine learning (often named Artificial Intelligence in the mainstream media). While during recent years there has been a lot of enthusiasm about the potential of ‘big data’ and machine learning-based solutions, there exist only few examples that impact current clinical practice. The lack of impact on clinical practice can largely be attributed to insufficient performance of predictive models, difficulties to interpret complex model predictions, and lack of validation via prospective clinical trials that demonstrate a clear benefit compared to the standard of care. In my talk, I will review the potential of state-of-the-art data science approaches for personalized medicine, discuss open challenges, and highlight directions that may help to overcome them in the future.

Dell-EMC 12:00 pm Harness AI and Redefine Precision Medicine Infrastructure with Dell EMC

Sanjay Joshi, Industry CTO, Healthcare Dell EMC, Global CTO Office, Dell EMC

AI is making data your top asset; but unlocking its value isn’t a one-click action. Without AI, it’s difficult to generate value from data of lifestyle information from IoT devices, TBs of genomics data, and population studies. We’ll focus on key attributes of AI solutions that drive success in Life Sciences: enable faster diagnoses, affordable genomics, and improved patient outcomes.

12:30 Session Break

Elsevier-square 12:40 Luncheon Presentation I: Productionising AI – Moving Beyond “Fire and Forget” to Predictable, Predictive Algorithms

Tim Miller, Vice President, Life Sciences Platform Solutions, Elsevier

Everybody is “doing AI” in Life Sciences right now, but how do we know we are doing it right?  Are we picking the best models for our problem? Are we getting the quality of data we need? And, are we able to translate successful AI experiments into productionised capabilities that integrate with our business goals? 

TataConsultancyServices 1:10 NEW: Luncheon Presentation II: Enabling Perpetual Digital Transformation in Research & Development

Vikram Karakoti, Head, Life Sciences Business Unit, North America, Tata Consultancy Services

Life Sciences companies today are inverting the pyramid by embedding enabling technologies in business platforms. “Enabling Perpetual Digital Transformation in R&D” explores how these digital platforms are re-constructed, and coupled with an “enterprise agile” R&D organization to yield exponential improvements in speed, capacity, cost, quality and improved outcomes in product research and clinical development; with real-life examples of just how the new paradigm is being embraced by leading Life Sciences companies.

1:40 Session Break

harborview 2

1:50 Chairperson’s Remarks

Edwin Addison, PhD, MBA, JD, CEO, Cloud Pharmaceuticals

1:55 Analysis of Off-Label Uses of Drugs for Rare Diseases

Matthew Clark, PhD, Director, Scientific Services, Life Sciences, Elsevier

Many rare diseases do not have approved treatments. It may be that drugs approved for other indications may be useful to treat these diseases, but it is difficult to gather information outside of formal publications. However, the FDA adverse event database, FAERS, captures prescribing indications for all drugs administered to a patient when any adverse event is reported. By mining this data one can see what individual physicians are using to treat diseases and compare to treatments that appear in formal trials. We will also compare the “real life” treatments to those that can be found using informatics.

2:25 Using AI to Identify and Navigate Relationships and Identify Context for Pharma Data

Peter Henstock, PhD, Machine Learning & AI Technical Lead, Business Technology, Pfizer, Inc.

As our pharma data sets increase in size, the ability to fully utilize them has become more challenging. A baseline approach is search capability provided in various forms from the databases-level queries through enterprise-level results. The limitations are being able to create the right queries to find all the relevant information without having to craft the perfect queries or sift through 1000s of entries. The approach draws upon text mining, information retrieval and network analysis all behind a common user interface and is currently being developed for multiple databases.

Dassault-Systems 2:55 Accelerating Drug Discovery with Generative Design and Active Learning

Ton Van Daelen, Portfolio Lead, Scientific Informatics, Dassault Systemes

Enabling pharmaceutical and biotech businesses to produce safe, efficacious medicines is key to improving productivity and maintaining competitiveness.  By integrating machine-learning approaches with generative molecular enumeration algorithms, we can transform the traditional Design, Make, Test, Analyze innovation cycle in drug research. LS organizations can achieve business transformation in molecular discovery by improving quality of lead molecules and shortening discovery timelines.

3:25 Refreshment Break in the Exhibit Hall with Poster Viewing, Meet the Experts: Bio-IT World Editorial Team, and Book Signing with Joseph Kvedar, MD, Author, The Internet of Healthy Things℠ (Book will be available for purchase onsite)


4:00 PANEL DISCUSSION: The Difference between Biomarkers and Diagnostics: It’s Bigger Than You Think


Michael N. Liebman, PhD, IPQ Analytics, LLC and Strategic Medicine, Inc.


Michael Montgomery, MD, Global Executive Director, Incyte Corporation

Jonathan Morris, MD, Vice President, Provider Solutions; Chief Medical Informatics Officer, Real World Insights, IQVIA

Jun Zhu, PhD, Professor, Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai

Biomarkers are used to evaluate cancer risk, detect end stage cancer and suggest optimal therapy for specific patients. Recent advances in -omics research continue to enable researchers to classify molecular fingerprints of specific cancers. Discovery and development of new cancer markers remains a major research focus to improve screening, diagnosis, and treatment but is hampered by the limited knowledge of the details of disease progression. This challenges the ability to identify markers that may be causal rather than correlative and impacts their use as true diagnostics. By example, literature analysis of 250,000 papers listing biomarkers in cancer yield less than 100 FDA approved diagnostics. Every experiment yields a biomarker; however, every experiment does not yield a diagnostic that can more accurately drive clinical action. How can we close this gap? It is critical to develop a better understanding of the disease process and how observations from genomics, proteomics, and metabolomics may impact that process in different ways. This interactive panel will explore experimental and analytic methods, issues and challenges impacting identification, validation, development and implementation in cancer, diagnosis and treatment.

5:30 Best of Show Awards Reception in the Exhibit Hall with Poster Viewing

Thursday, April 18

7:30 am Registration Open and Morning Coffee


9:45 Coffee Break in the Exhibit Hall and Poster Competition Winners Announced

Harborview 2

10:30 Chairperson’s Remarks

Daniel H. Robertson, PhD, Vice President, Digital Technology; Director, Center for Applied Data Sciences, Indiana Biosciences Research Institute

10:40 Making Real World Data Prepared to Apply Machine Learning and AI for Discovery Research

Daniel H. Robertson, PhD, Vice President, Digital Technology; Director, Center for Applied Data Sciences, Indiana Biosciences Research Institute

Although much of the major healthcare systems transition to electronic medical record (EHR) systems to digitally capture the patient data is complete, this data is not readily available or in the form to enable advanced analyses within discovery. Working with EHR data extracted from a large health information exchange, we have developed a robust and standardized data-cleaning pipeline to produce a clean, high-quality and normalized dataset ready for research. This process is transferable to other EHR datasets and leverages modern cloud-based big data tools. Finally, this data has been used to enable discovery research including understanding of disease progression, medication pathways, patient stratification, and digital diagnostics.

11:10 Boosting Drug Discovery with Machine Learning

Rishi Gupta, PhD, Senior Research Scientist, AbbVie, Inc.

Abhik Seal, PhD, Senior Data Scientist, AbbVie, Inc.

IBM_Blue 11:40 NEW: Applying Structure to the Unstructured: Using AI to Distill Insights from Disparate Unstructured Data Sources

Eric Baldwin, PhD, Solution Executive, IBM Watson Health, IBM

Unstructured data is a significant source of cross-disciplinary insight. However, it’s a significant hurdle to manually read, digest and extrapolate a holistic view. Learn how AI applies a common framework to the disparate data using NLP and predictive analytics to construct a network of known and inferred connections between biological concepts enabling researchers to make informed, cross-silo decisions.

12:10 pm Session Break

accenture 12:20 Luncheon Presentation: From Hype to Reality: AI is a Key Enabler in Accelerating Drug Discovery and Development

Kailash Swarna, PhD, MBA, Industry Principal Director, Global Life Sciences, Accenture

The recent acceleration of interest in the applications of AI and ML in drug discovery and development has created significant perturbation in life sciences R&D. Separating fact from fiction, and demonstrating tangible and differentiated value of the application of AI is critically important - now more than ever. The technology industry and Pharma R&D are at an inflection point - interests and outcomes can converge or diverge - depending on the value that AI can deliver.

12:50 Session Break

1:20 Dessert Refreshment Break in the Exhibit Hall with Poster Viewing

Harborview 2

1:55 Chairperson’s Remarks

Bino John, PhD, Associate Director, AstraZeneca

2:00 FEATURED PRESENTATION: Application of Machine Learning and Artificial Intelligence as a Driver of Productivity in Drug Discovery & Development

Morten Sogaard, Vice President, Target Sciences & Technologies, External Sciences & Innovation, Worldwide R&D, Pfizer

This talk will provide an overview of the impact of AI on productivity on pharma with the focus on three areas – process engineering & automation, drug design and manufacturing, and target and biomarker discovery and validation, illustrated by specific examples.

2:30 Intersection of AI Techniques and Rare Disease Diagnosis

Margaret Bray, PhD, Senior Data Scientist, Alexion

A look into the latest AI techniques applied to the field of rare disease diagnostics as well as a look at the limitation of current methodologies and areas for future growth.

3:00 Automated Compliance and Quality Checks

Etzard Stolte, PhD, Global Head Knowledge Management PTD, F. Hoffmann-La Roche

Machine learning technologies, like natural language processing (NLP), have reached the maturity for automated quality controls of operational information, e.g. as compliance and quality supervision tools. Over the last years Pharma Technical Development at Roche has created a single front end for many business and validated systems that uses a mixture of curation and supervised learning tools to increase compliance and reduce operational costs. This talk will present our learnings, as well as the limitations and opportunities we see for the future.

3:30 AI for Improving Drug Safety to Accelerate Drug Development

Bino John, PhD, Associate Director, AstraZeneca

Drug candidates that result from millions of dollars in investment frequently fail during clinical or preclinical testing phases due to safety concerns. Such safety related failures continue to pose a challenge to the industry. This talk will highlight some of the efforts at AstraZeneca that seek to use AI/ML approaches to minimize such clinical/preclinical failures.

4:00 Conference Adjourns

Purchase on Demand