#BioIT21: Insider’s Guide to Making the Most of the Hybrid Program

August 4, 2021

August 4, 2021 | The Bio-IT World Conference and Expo will be happening both in-person and online this year—giving our community even more options for learning and connection. 

Both in-person and virtual attendees will have access to all of the event content: 10 tracks, a new full-day training seminar, and additional workshops. In Boston, attendees can engage with industry experts across six in-person tracks and networking opportunities and catch up with anything they missed (or want to view again) from the virtual session archives. Attendees joining online will have access to all 10 tracks in real time as well as in the archives.

The program is full of great content, speakers and insights into both where we’ve come from and where we’re going. We’ve been busy marking our schedules and making our plans. Here is what we’ve flagged thus far. –the Editors


The Plenary Program 

Three, live keynote sessions will anchor the program starting with a pharma executive roundtable. Over the past year many pharmaceutical companies have been forced to accelerate their digital transformation plans. A panel of biopharma executives will share how they are broadening their digital strategies and capabilities to develop products and services at scale, streamline operations, and drive innovation in life sciences R&D. Panelists include Ramesh V. Durvasula, Eli Lilly & Co.; Michael Montello, GlaxoSmithKline; Bryn Roberts, Roche; Holly Soares, Pfizer; Diane Wuest, Sanofi; and Lihua Yu, H3 Biomedicine. (Get a preview of the conversation from recent Q&As with Roberts and Yu.) September 20 

Joshua Denny, CEO of the NIH’s All of Us Research Program, will share the latest on the nation’s population health initiative that currently includes data from over 375,000 participants who have contributed biospecimens, health surveys, and a willingness to share their health records.  In May 2020, the program launched the beta version of the Researcher Workbench. Once researchers register and are approved to use the workbench, they can access individual-level data and a suite of tools to analyze these data. All of Us is committed to catalyzing a robust ecosystem of researchers and providing a rich dataset that drives discovery and improves health. (Get up to date on All of Us with Denny’s outline of the 2021 numbers from this spring.) September 21 

Finally, following a year that has bucked all trends, Chris Dagdigian is back leading a Trends from the Trenches panel. If there was ever a year to peek behind the curtain and see what information technologies have truly pulled their weight, 2021 is it. In his trademark candid style, Dagdigian and his co-panelists will share what is working and what is smoke and mirrors in computing, storage, data transfer, networks, cloud, data science, and machine learning. Dagdigian will be joined by Fernanda S. Foertter, NextSilicon; and Karl Gutwin and Adam Kraut of BioTeam. September 22


Innovative Practices Awards 

Last month, Bio-IT World announced the 2021 Innovative Practices Awards winners and for the first time, all honorees will be presenting their work at the Bio-IT World Conference & Expo. Grand prize awards were granted to Duke Cancer Institute with University of California, San Francisco, Micronoma, and Regeneron Pharmaceuticals. Pure Storage and the Folding@home project received honorable mention recognition. These groups will be presenting their work at the Bio-IT World Conference & Expo--one in-person and three in online presentations--giving the community a chance to immediately connect with the winning teams and learn more about the projects that so impressed our judges.

Julian Hong, University of California, San Francisco, will present the System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT) study, a randomized controlled study that demonstrated that machine learning can be implemented in the clinical setting to direct supplemental clinical evaluations during outpatient cancer radiotherapy and chemoradiation, reducing acute care (emergency visits and hospitalization) in high risk patients from 22.3% to 12.3%. (J. of Clin Oncology DOI: 10.1200/JCO.20.01688) Routine implementation of this system at the Duke Cancer Institute is underway. September 22, Virtual Data Science and Analytics Technologies Track 

Micronoma is the only cancer diagnostic company using the microbiome to detect early-stage cancer. As liquid biopsy is fast becoming an important new direction method for cancer diagnostics, early detection remains a challenge that using the cancer microbiome may be able to solve. Sandrine Miller-Montgomery, President and CEO of Micronoma, will present the company’s promising research, published in Nature in 2020 (DOI: 10.1038/s41586-020-2095-1), which found unique microbial signatures in tissue and blood for most major types of cancer. September 21, Virtual Genome Informatics Track

Quan Yang and Srinivasan Sadanandhamurthy, both of Regeneron Pharmaceuticals, will present the company’s Innovative Practices Award-winning computational data process pipeline, which enables the end-to-end data flow based on a complete cloud-based platform to support a high-throughput data processing and computational services. As a result, the researchers have at the ready, the ability to transfer an average of 2TB in under two hours, and can analyze the data using GPU computation. The pipeline was essential for the resolution of REGEN-COV2 antibody cocktails binding structure to COVID-19 Spike protein and allowed the company to provide an effective therapeutic medicine to fight against the current pandemic in a timely fashion. September 22, Virtual Bioinformatics Track 

Gregory R. Bowman of Washington University and Brian Carpenter of Pure Storage will present the Folding@home project, a distributed computing initiative designed to aid scientists in understanding and treating a wide variety of diseases by simulating protein dynamics. At the start of the pandemic, the Folding@home user community saw a way to be involved, adding more than 400,000 new devices in a few weeks to make Folding@home the most powerful computer in the world. September 21, Data Storage Infrastructure Track


And So Much More

Nimita Limaye from IDC will set the stage for Josh Denny’s presentation in her own keynote address exploring how digital evolution along with a paradigm shift are re-shaping the future of the life sciences industry. Digital resiliency has become the priority, she says, driven by federated-learning models and GPU-powered transformer models. The borders between healthcare and life sciences are blurring and real-world data is being leveraged to drive a precision medicine strategy. September 21 

William S. Sanders will outline The Jackson Laboratory’s Genomic Data Lakes, multi-tiered research storage architecture designed to stabilize and minimize the financial costs required to meet unconstrained research demand for increased research storage capacity. He will provide an overview of the research computing environment at JAX, with a specific focus on the design decisions behind the capacity, performance, and availability choices of the research storage platforms with parallel and distributed computing systems, various data science and data analysis platforms, and data-generating scientific instrumentation. September 21, Data Storage and Infrastructure Track

Sanjay Joshi, Tanium, will lead a panel session on cybersecurity and trust. Data currency, accuracy, provenance and trust are on a critical path for digital health, software and manufacturing supply chains, RWD/RWE and the future of clinical trials. Joshi will be joined by Kathleen Moriarty, Center for Internet Security; Brian D. Bissett, IEEE USA; Ketan Paranjape, Roche Diagnostics; Jyotin Gambhir, SecureFLO; Drummond Reed, Evernym; and Kay Williams, Microsoft and Open Security Software Foundation. September 22, Data Storage and Infrastructure Track

Aleksandar Stojmirovic and Weiwei Schultz, both of Janssen R&D, will share the practices established at Janssen R&D to enable efficient storage and consistent retrieval of molecular research data in a FAIR (Findable, Accessible, Interoperable, Reusable) manner. All incoming data is required to be annotated with standardized metadata describing the context and purpose of its originating study and experiment. Coupled with indexing of metadata in integrated catalogs, this workflow rewards researchers with the ability to seamlessly search and cross-reference translational datasets. September 21, Data Management Track 

Benjamin R. Busby, DNAnexus, moderates an in-person panel on bringing complex multi-omic data to the clinic and clinical research. New methods for multi-omics data are needed to allow for better patient stratification, more targeted treatments, and greater understanding of disease mechanism. He’s joined by Avantika Lal of NVIDIA, Ankita Das of MIODx, and Ahmad Khleifat of King's College London. September 22, Data Management Track 

Rachana Ananthakrishnan and Vas Vasiliadis, both of Globus, University of Chicago, will focus on the “F” and “A” in FAIR data. Ensuring data are Findable and Accessible is particularly challenging at scale. They will describe how capabilities provided by Globus at the University of Chicago make data findable and accessible, using simple frameworks and services that enable rapid development of data portals/commons in a variety of life sciences projects. September 21, Software Applications and Services Track 

Varun Gupta, Mount Sinai Health System, will give a glimpse into the setting up and scaling of a data and analytics ecosystem on cloud for operations and research in a health care setting including exploring how the cloud infrastructure was leveraged for various tools and technologies and how the processes were set up around information lifecycle management to maximize access and visibility to data and reporting assets across the health system is presented. September 21, Cloud Computing Track 

Sabine Schefzick Jalaie will summarize Pfizer's Knowledge Graph journey and highlight lessons learned. By leveraging Knowledge Graph technology to make R&D data FAIR, Pfizer can surface actionable and meaningful insights and make knowledge accessible to and consumable by domain users. Pfizer's KG implementation helps accelerate R&D data discovery and understanding and supports data scientists, researchers, scientists, and clinical and project leads in bringing medicine to the market faster by enabling advanced analytics on demand. September 22, AI for Drug Discovery and Development Track 

Xiong Sean Liu from Novartis will provide an overview of the drug development studies that use both AI and RWD based on a review of articles from the past 20 years. He will also discuss current research gaps and future opportunities. September 22, AI for Drug Discovery and Development Track 

Between discovery and clinical research, translational medicine exists to advance science from laboratories to patients, along the way generating and consuming vast amounts of heterogeneous pan-omics preclinical and clinical data from a multitude of internal and external sources, systems and applications. Tom Plasterer of AstraZeneca will explore the wholistic data interoperability required to meet this goal and explain how AstraZeneca has adopted a data-centric approach that enables frictionless reuse of data across our systems, platforms and applications. September 21, Pharmaceutical R&D Informatics Track

Lilly launched an innovative cloud-based platform, Biologica, that integrates next-generation sequencing, world-class laboratory automation, innovative computational algorithms and multi-parameter optimization, all while meeting FAIR data principles. Helen Li, Eli Lilly & Co., will detail how the platform increased R&D productivity, cost savings, and cost avoidance, with the ultimate goal of discovering new medicines with greater speed and precision. Biologica accelerated discovery, development, and launch (under an EUA) of the first COVID-19 antibody treatment four to five times faster the previous pipelines. September 21, Pharmaceutical R&D Informatics Track

Gene regulatory network inference is instrumental to the discovery of genetic mechanisms driving diverse diseases, including cancer. Rebekka Burkholz, Harvard T.H. Chan School of Public Health casts this problem as graph matching and leverages its connection to machine learning to improve the state of the art in predicting the binding of transcription factors to promoter regions of genes. September 21, Virtual Data Science and Analytics Technologies Track

At Janssen Pharmaceuticals, Bethany F. Hyde has applied unsupervised machine learning on time series data collected from a clinical trial to uncover distinct patterns of patient treatment response. She’ll cover the challenges of using unsupervised machine learning on clinical trial data and the technical solutions to overcome these challenges, including data imputation, cluster optimization, secondary analysis, and clinical interpretation of results. September 22, Virtual Data Science and Analytics Technologies Track

John Quackenbush, Harvard T.H. Chan School of Public Health, will explore using networks to understand genetic and genomic drivers of disease. Biological complexity is challenging, in which many factors, each of small effect size, collectively influence disease risk, development, complexity, and response to therapy in cancer and other complex diseases. By using innovative computational methods built around network representations of biological interactions, we can gain insight into the disease process, develop predictive biomarkers, and identify possible avenues of therapeutic intervention. September 21, Virtual Bioinformatics Track 

Portable DNA sequencing and computing technologies have great potential for point-of-care solutions with real-time results. Laura Boykin, BioTeam, will outline her own experience using the Oxford Nanopore portable genomics technology to sequence whole plant virus genomes on the farms in Uganda, Tanzania and Kenya. She will also cover the gaps in computing she has identified while doing on-farm genomic sequencing and discuss potential applications for biosurveillance. September 22, Virtual Genome Informatics Track

Following a major acquisition, Bristol-Myers Squibb has access to a rich and complex variety of internal and external data sources to drive future therapeutic research and patient benefit. Albert Wang will discuss the challenges and opportunities as we rethink how we manage and provision this data to seamlessly enable computational research. September 21, Virtual Clinical Research and Translational Informatics Track 

Kimberly Robasky, Renaissance Computing Institute (RENCI), and Rebecca Boyles, RTI International, propose combining FAIR principles and Data Readiness Level with concepts on rigor and normalization to lay the foundation for application of AI and other advanced data science technologies in biomedical research. September 21, Virtual Clinical Research and Translational Informatics Track 

Jay Bergeron at Pfizer knows that corporate analytic data systems have been driven by traditional data warehousing models for the better part of two decades. Although effective, and cutting-edge technologies for the time, change control inefficiencies and a greater need for ad hoc analytics led to the data lake paradigm, in which data is consolidated in, and used from, a largely unintegrated state. Bergeron will describe an AWS-based data lake implementation that has been applied to, and is now an enterprise system for, clinical operations as well as emerging support for clinical trial analytics. Components enabling ingestion, cataloging, conformance and reporting will be reviewed. September 21, Virtual Clinical Research and Translational Informatics Track