2018 Archived Content
Track 6: Bioinformatics

Track 6 assembles thought leaders who will present case studies using computational resources and tools that take data from multiple –omics sources and align it with clinical action. Turning big data into smart data can lead to real time assistance in disease prevention, prognosis, diagnostics, and therapeutics. With the ever-increasing volume of information generated for curing or treating diseases and cancers, bioinformatics technologies, tools and techniques play a critical role in turning data into actionable knowledge to meet unstated and unmet medical needs.

Tuesday, May 15

7:00 am Workshop Registration Open (Commonwealth Hall) and Morning Coffee (Foyer)


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

W3. D2K, Transforming Data to Knowledge with Cloud, IoT & Machine Learning (AI) – Part I

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

W9. D2K, Transforming Data to Knowledge with Cloud, IoT & Machine Learning (AI) – Part II

* Separate registration required.

2:006:30 Main Conference Registration Open (Commonwealth Hall)

4:00 PLENARY KEYNOTE SESSION (Amphitheater & Harborview 2)

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

Wednesday, May 16

7:00 am Registration Open (Commonwealth Hall) and Morning Coffee (Foyer)

8:00 PLENARY KEYNOTE SESSION (Amphitheater & Harborview 2)


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

Harborview 1

10:50 Chairperson’s Remarks

Rupert Yip, PhD, Director, Product Management Hereditary Diseases, QIAGEN

11:00 BioCompute: A Framework to Harmonize Bioinformatics

Vahan Simonyan, PhD, Lead Scientist & R&D Director, High-Performance Integrated Virtual Environment (HIVE), FDA

Significant healthcare decisions and biomedical research are based on big data analysis using sophisticated computational pipelines. The complexity and the lack of harmonized methods to communicate computational protocols has led to a crisis of reproducible research: by some estimates 60-70% of researchers are not able to reproduce results. The FDA has partnered with The George Washington University to create and an international BioCompute consortium to devise a standard specification document enabling consistency in bioinformatic workflows in research and regulatory domains. The consortium includes academia, pharma, and regulatory organizations from across the world. The first BioCompute release has been issued https://osf.io/myuxq/ and has found reverberations after the press release https://smhs.gwu.edu/news/gw-led-consortium-fda-release-new-specifications-advance-genomic-data-analysis.

11:30 Arvados – A Multifunctional Platform for Scientific Applications at Roche

Moritz Gilsdorf, Scientific Application Engineer, Roche

Arvados, mostly known as a platform for managing big Omics datasets as well as for automated processing using analysis pipelines, has also a big potential to be a powerful backend for a big variety of scientific applications from different areas. This talk will present how we currently use Arvados, showcase new applications and how they benefit from the platform.


12:00 pm Pathway and Network Machine Learning Analysis to Prioritize Causal Genes in Parkinson’s Disease

Alexandr Ivliev, Principal Research Sciences, Life Sciences, Clarivate Analytics

How can big data be leveraged for target ID and drug discovery? Current advances in human genetics have already revealed drivers for numerous diseases. This talk will describe application of pathway and network analyses in conjunction with machine learning techniques to identify causal genes and therapeutic targets for Parkinson’s disease.


12:15 Solving Challenges in Biologics Drug Discovery with Integrated Informatics

Andrew Le Beau, Senior Manager, Biologics, Marketing, Dotmatics Inc

Biologics drug discovery requires informatics systems that support both unique capabilities and traditional competencies such as screening, inventory, etc. Support for cross-institutional collaboration is also critical Properly integrated systems facilitate faster, fully-informed decision-making Examples of customer success stories highlighting BioELN, Biological Registration, and Vortex Bioinformatics, will be given.

12:30 Session Break


12:40 Luncheon Presentation I: AI, Machine Learning and Big Data for Life Sciences; the Good the Bad and the Ugly

Frederik van den Broek, PhD, Consultant, R&D Solutions, Elsevier, Inc

Many believe that Artificial Intelligence has the potential to revolutionise life sciences and healthcare. However, there are significant pitfalls in the application of AI and Big Data. This talk will present an overview of best and worst practices in applying AI and Machine learning to life sciences to facilitate successful use of these techniques in today’s competitive drug discovery environment.


1:10 Luncheon Presentation II: Understanding Innate Resistance to anti-PD-1 Therapy in Melanoma through Transcriptomics

Jean-Noël Billaud, PhD, Senior Principal Scientist, Bioinformatics Business Area, QIAGEN

Understanding innate resistance to anti-PD-1 therapy in melanoma through transcriptomics Immunotherapy consisting of blocking immune checkpoints, such as PD-1, has shown promise in treating melanoma. However, innate and acquired resistance to anti-PD-1 therapy often results in recurrence after initial successful treatment leading to advanced metastatic melanoma.This presentation will show the combined power of OmicSoft’s OncoLand Explorer, Array Suite and Ingenuity Pathway Analysis (QIAGEN) to analyze and interpret whole transcriptome from RNA-sequencing from pre-treatment mRNAs of patients with advanced metastatic melanoma and with respect to their subsequent immunotherapy treatment outcomes. We will provide highlights into the biological signatures that determine non-responder versus responder status.

1:40 Session Break

Harborview 1

1:50 Chairperson’s Remarks
Jeffrey Rosenfeld, PhD, Manager, Biomedical Informatics Shared Resource and Assistant Professor of Pathology and Laboratory Medicine, Rutgers Cancer Institute of New Jersey 

1:55 MetroNome - Designing a Genomic Data Laboratory with Visualization Tools to Empower Researchers to Make Discoveries

Christian Stolte, Data Visualization Designer, Informatics Research Innovation, New York Genome Center

Studying complex disease requires access to large volumes of data, and the ability to identify relationships across many data dimensions. Researchers must have the tools to combine results from several projects, filter those results to find the subjects that meet the phenotypic and genotypic criteria of their new studies, and then use those aggregated datasets to find complex associations and to gain the statistical power needed to validate results. Our goal has been to make such tools available to researchers without the need for bioinformaticians to produce those results. MetroNome reveals connections between variants and their effect on health. Without writing code, and while protecting privacy, MetroNome provides web-based tools for data exploration that use intuitive visualizations. It is built on a database that connects genomic and clinical data, across projects and diseases. We leverage public datasets for comparison and increased statistical power.

2:25 An Integrated Systems Pharmacology Approach to Aid the Prediction of Adverse Drug Reactions

Malika Mahoui, PhD, Senior Research Scientist-IT, Eli Lilly and Company

Using bioinformatics tools, an integrated systems pharmacology approach is proposed to aid in the prediction of potential ‘on-target’ and ‘off-target’ Adverse Drug Reactions (ADRs) for a new drug in a pathway that is targeted by other drug therapies. To accomplish this, high quality annotated databases supported with analytics and visual descriptive techniques are being used to collate information about upstream and downstream proteins in a pathway along with tissue distributions, and additionally integrated with clinical information of other drugs and their ADRs known to interact with the proteins in that same pathway. A target gene was selected for a proof-of-concept evaluation to test this systems pharmacology pathway approach, with the aim to complement and inform additional safety assessments to conduct during drug development.

2:55 How to Free Up Time for Your BioInformatics Team: Empowering Researchers to Run Common Analyses and Interpret Their Data

Jean Lozach, CTO, OnRamp BioInformatics, Inc.

OnRamp.Bio’s flagship product, Rosalind™, provides the first-ever genomics analysis platform designed specifically for life science researchers to analyze and interpret their own data, eliminating the wait while reducing costs through a simplified per-sample pricing model. This discussion with demonstrate how to set up an experiment on Rosalind™ in minutes and explore interactive results within hours (no BioInformatics experience required).

 BIOVIA 3:10 Driving Biotherapeutic Design with “Modeling as a Service”

Sean McGee, Product Marketing Manager, BIOVIA

The increasing demands on biopharmaceutical R&D has driven accelerated adoption of in silico modeling and simulation across a variety of disciplines. However, this growing demand for high quality models has in turn placed strain on the ability of experienced modelers, limiting their impact on the organization. There is a need to deploy widely applicable models as web services or applications to researchers at the lab bench. Deploying models “as a service” extends the expertise of expert users at an enterprise level, freeing up their time to focus on high-value projects and allowing users of all skill levels to increasingly guide their research with the models that are of most use to them.

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

Harborview 1

4:00 Building Integrated Pipeline for Cancer Genome Analysis: Role of Mobile Genetic Elements in Cancers

Kamal Rawal, PhD, Senior Assistant Professor, Biotechnology and Bioinformatics, Jaypee Institute of Information Technology (JIIT)

Cancer is a major public health problem worldwide and represents one of the leading causes of deaths across the world. With the development of high-throughput sequencing technologies, we have witnessed a data explosion and systematic study of the cancer genome including point mutations and structural alternations for a large number of cancer types, enabling the differentiation of cancer subtypes. Transposable elements (TEs), or mobile genetic elements (MGEs), are the most abundant elements in mammalian genomes and found in nearly 100 cases of diseases including cancers. Previously, we have conducted detailed analyses of genes reported to be susceptible to TE insertion leading to diseases such as muscular dystrophy and cancers (Rawal and Ramaswamy 2011, Nuc. Acid Res.). Here, we present a new method (software pipeline) to determine exact position and insertion mechanism of transposable elements in cancer genomes using machine learning method. We also show new techniques to integrate somatic mutation data with results from genome-wide characterizations experiments and clinical data elements (e.g. outcome and response to therapy). ELAN, the suite of tools described here uses standard techniques to identify different MGEs and their distribution on the cancer genome. One component, DNASCANNER analyses known insertion sites of MGEs for the presence of signals that are based on a combination of local physical and chemical properties. ISF (insertion site finder) is a machine-learning tool that incorporates information derived from DNASCANNER. ISF permits classification of a given DNA sequence as a potential insertion site or not, using a support vector machine. We have studied the genomes of Homo sapiens , Mus musculus , Drosophila melanogaster and Entamoeba histolytica via a protocol whereby DNASCANNER is used to identify a common set of statistically important signals flanking the insertion sites in the various genomes. These are used in ISF for insertion site prediction, and the current accuracy of the tool is over 65%. We find similar signals at gene boundaries and splice sites. Together, these data are suggestive of a common insertion mechanism that operates in a variety of eukaryotes.

4:30 Analysis of Cancer Genome Variation from Long DNA and RNA Sequencing  

Jeffrey Rosenfeld, PhD, Manager, Biomedical Informatics Shared Resource and Assistant Professor of Pathology and Laboratory Medicine, Rutgers Cancer Institute of New Jersey

Cancer genomes are full of rearrangements which drive the oncogenesis. Using long reads, we have been able to accurately determine the structure of important cancer genes in breast cancer including BRCA1 and HER2. The variation in these genes cannot be accurately determined with short reads due to their repetitive structure. In addition, we have used RNA sequencing to determine the full sequence of kinase fusions in cancer. These fusions play a critical role in the progression of many types of cancer and understanding their full structure will lead to greater insight and improved therapies.

5:00 Ontology Learning and Personalization

Anna Lyubetskaya, Data Scientist, Engineering, Copyright Clearance Center

In this talk, we’ll discuss a framework that enables learning of ontologies in a semi-supervised manner through the best machine learning and distributed computing approaches. We discuss issues inherent to data science: input data filtering and enrichment, robust iterative learning, cross-validation, rapid prototyping, and transition between prototyping and production.

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


7:0010:00 Bio-IT World After Hours @Lawn on D
 **Conference Registration Required. Please bring your conference badge, wristband, and photo ID for entry.   

Thursday, May 17

7:30 am Registration Open (Commonwealth Hall) and Morning Coffee (Foyer)

8:00 PLENARY KEYNOTE SESSION & AWARDS PROGRAM (Amphitheater & Harborview 2)

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

Harborview 1

10:30 Chairperson’s Remarks
Bino John, PhD, Computational Biology and Systems Biology Group Leader, Dow-Dupont Ag Division

10:40 PANEL DISCUSSION: Careers in Big Data - Tips and Best Practices from Industry Leaders

Stephanie Hintzen, Bioinformatics System Programmer, Dana Farber Cancer Institute (Moderator)
Chrystal Mavros, Research Assistant, Molecular Genetics Core Facility, Boston Children’s Hospital Center for Life Science (Moderator)
Jeremy Jenkins, PhD, Head of Chemical Biology & Therapeutics Informatics, Novartis Institutes for BioMedical Research (NIBR)
Bino John, PhD, Computational Biology and Systems Biology Group Leader, Dow-Dupont Ag Division
Joseph Lehar, PhD, Executive Director, Computational Biology, MRL, Merck
Patrice Milos, PhD, President and CEO, Medley Genomics
Michelle Penny, PhD, Senior Director, Head of Translational Genome Sciences, Biogen
Daniel Robertson, PhD, Research Fellow and Vice President of Digital Technology, Indiana Biosciences Research Institute

Do you know what it takes to get hired and succeed in industry? Come join us to discuss and get perspectives from seasoned thought leaders on getting hired and staying hired!

12:10 pm Enjoy Lunch on Your Own

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

Harborview 1

1:55 Chairperson’s Remarks
Rich Lysakowski, PhD, Senior Business Analyst & Informatics Engineer, Astrix Technologies; Professor of Bioinformatics & Data Science, Network Technology Academy Institute

2:00 Translating Big Data Analysis to Decision Making in Pivotal Clinical Studies

Sheng Feng, PhD, Vice President and Head of Bioinformatics, Green-Valley Pharmaceutical Company, Shanghai, China

Big Data analysis is often exploratory, while pivotal clinical studies demand confirmative evidences in making important decisions. In most cases, what happens in Big Data analysis, stays in Big Data analysis. In this talk, I will discuss a number of technical strategies making Big Data analyses more useful in clinical studies, including a combination of data analyses and simulations to mimic real-world clinical situations; re-shaping the data structure and contents to satisfy specific clinical needs; balancing scientific and clinical questions, as well as activities of exploratory vs. confirmative analyses; fine tuning result interpretations and integrating data analysts with the clinical development teams. In rare cases, seamless translating Big Data analysis to decision making in clinical studies is possible.

2:30 Computational Sciences at a Digital Biotech

Iain McFadyen, PhD, Senior Director, Computational Sciences, Moderna Therapeutics

Moderna Therapeutics is pioneering mRNA medicines, a ‘software-like’ approach whereby we direct the body’s own cells to create proteins to fight and prevent disease. To maximize the enormous potential this new therapeutic approach may have in addressing unmet needs across a broad spectrum of diseases, we are working towards being a truly digital biotech. To support this mission, we’ve built a suite of computational science capabilities that encompasses and integrates bioinformatics, computational biology, computational chemistry, cheminformatics, data science, and more. In this talk, we’ll describe those capabilities and share examples of applications to a variety of specific questions, including process optimization, fundamental research, therapeutic programs, and more. These capabilities are built on top of an integrated informatics platform that will be described in a separate talk by David Johnson, Director of Informatics, Moderna Therapeutics, in Track 2 Data Computing.

Harborview 1

3:00 PORTIN: A Game Changer within Translational Data Integration

Christiane Unger, IT Business Partner, Bayer Business Services

PORTIN is a platform in which biomarker/genomic, biosample and clinical/phenotype information is integrated to make better and more efficient use of the available data. For a successful implementation, besides technology and data, cultural and organizational aspects are just as important to consider. In this talk, we will discuss shift in behavior mindset of who owns the data, collaboration with cross-functional teams, and governance of translational research processes.

Shift in Mindset: Data often become “my” data. To motivate people changing behavior it’s also important to have answers to the question: “what’s in for me”.

Collaboration: Cross-functional teams with experts from biomarker, clinical and mathematical functions lay the foundation for a joint data approach and guidelines on data integration.

Governance: In order to establish a sustainable organization for translational research, adequate processes need to be set up or adjusted internally and externally.  

3:30 Embracing Pre-Competitive Collaboration in the Life Sciences

Carmen Nitsche, Business Development Consultant, Business Development, Pistoia Alliance

Gerhard Noelken, MD, Business Development Europe, Pistoia Alliance, Inc.

Precompetitive collaboration is becoming a requirement for the life sciences industry as it strives to deliver better patient outcomes faster. In this talk, we will survey the current state of alliances and provide updates on some recent successful projects at the Pistoia Alliance. We will also consider future areas ready for a collaborative approach to advance innovation.

4:00 Conference Adjourns

Register Early and Save

Data Platforms and Storage Infrastructure