What’s New Out West: Preview Of Bio-IT World’s First West Coast Event

February 20, 2019 | This year Bio-IT World is taking the show on the road. After 17 years in Boston, the Bio-IT World Conference & Expo is visiting the West Coast. We are launching Bio-IT World West, a program within the Molecular Medicine Tri-Conference focused on bioinformatics, data management, and machine learning.

The plenary program is outstanding. Monday evening, Sarah Gray will share a touching first person account of tissue donation for biomedical research. Years later, she tracked down each donation. Arupa Ganguly received some of the tissue. She directs the genetic diagnostic lab at the University of Pennsylvania and studies retinoblastoma, a childhood-onset cancer caused by mutations in tumor suppression gene. Together Gray and Ganguly will share their experience and perspective on biospecimen donation.

On Tuesday morning, Marty Tenenbaum will lead a panel of broad clinical and biomedical expertise to explore how algorithms trained on population-wide data sets, combined with a deeper understanding of -omics, are transforming disease detection and diagnosis, clinical testing, treatment personalization, and clinical trials. To get there, emerging technologies must be integrated into a synergistic global system that continuously learns from every patient and experiment.

Finally on Wednesday morning, an emerging technologies panel will feature industry speakers on the cutting edge of what’s new. Moderated by Kristin Ciriello Pothier and Scott Palmer both of Parthenon-EY, the panel will include Ardy Arianpour, Seqster; Norman Packard, Daptics; Chris Ianelli, iSpecimen; Martha Najib, Ximedica; Trevor Johnson, Flagship Biosciences; Florian Bell, Qorvo Biotechnologies; Lauren Shields, Benchling; Paul Smith, ANGLE Biosciences; and Michael Fero, TeselaGen Biotechnology.

In the session rooms, Bio-IT World West has rich content across four programs: Integrated Pharma Informatics, Bioinformatics for Big Data, Data Management in the Cloud, and Machine Learning and Artificial Intelligence. Additionally, the program includes short courses and seminars on data visualization, data science, image analysis and computer vision, and process development in the clinical laboratory.

We’ve got lots flagged in our program. Here are some of the talks we are looking forward to.

—The Editors

Representatives from Bristol Myers Squibb, Merck, Pfizer, Alexion, AstraZeneca, Novartis, and more are featured on the pharma informatics program. Tom Plasterer, Director, Semantic Technologies, Science & Enabling Units IT, AstraZeneca, will kick off the program. The FAIR Data evangelist admits that the hype may have outpaced a clear return on the data stewardship investment, but he’s making the case for FAIR data knowledge graphs. Monday, March 11, 12:30

Sandor Szalma will share how Takeda used a global computational biology team to expand capabilities to enable reverse translation across the diseases of our interest. In this presentation, I will discuss our computational infrastructural approach and a couple of initial computational experiments to explore real-world data and machine learning methodologies to better understand patient journeys in support of the research and development organization.

Tom Defay of Alexion will discuss the effectiveness and potential of diagnosing rare diseases by combining phenotypic information automatically extracted from the patient’s EMR with a patient’s genome sequence. Monday, March 11, 11:30

Wearable portable biosensors allow frequent measurement of health-related physiology. Mike Snyder’s group at Stanford University has used smart watches and other devices to detect the onset of infectious diseases such as Lyme disease, and continuous glucose monitors to detect individuals with glucose dysregulation. Snyder will argue that these devices can help build personalized models for monitoring health status and early onset of disease. Monday, March 11, 2:40

Two speakers from 23andMe, Olga Sazonova and Sarah Laskey will discuss 23andMe and the Mission of Personalized Healthcare. 23andMe has built the world’s largest consented, re-contactable database for genetic research, with more than four million consented participants and one billion individual survey responses. The company is applying statistical genetics and machine learning to uncover novel genetic risk factors for complex disease, advance drug discovery, and offer personalized predictions of disease risk to all 23andMe customers. (Sazonova and Laskey previewed their discussion for Bio-IT World.) Tuesday, 2:40

Renee Deehan Kenney, also of PatientsLikeMe, will share how the company has begun collecting and analyzing biosamples on a diverse array of omics platforms, including DNA and RNA sequencing, methylomics, immunosignature, metabolomics, and proteomics measurements. Kenney will discuss the development of a biocomputing platform that applies machine learning and other modeling techniques to aid researchers in extracting meaningful health insights from complex biological and phenomic data sets, and a case study that demonstrates the utility of the platform. Wednesday, 3:45

There will be several sessions digging into definitions, challenges, and innovations of data commons. On Tuesday at 10:25, Robert Grossman from the University of Chicago will share a data commons framework for data management, describing how data commons and data ecosystems can be built using the Data Commons Framework Services (DCFS) and how the DCFS support the management of data objects, such as BAM files, CRAM files and images, and structured data, such as clinical data.

In a panel on Wednesday at 11:30, moderated by Matthew Trunnell of Fred Hutchinson Cancer Research Center, panelists will tackle why should you organize your data into a commons, give NIH data commons pilot phase updates and future directions, and discuss the role of data commons in promoting open access and open science. Panelists include Stanley Ahalt, University of North Carolina; Adam C. Resnick, The Children’s Hospital of Philadelphia; Lucila Ohno-Machado, San Diego Health; and Michael Kellen, Sage Bionetworks.

Jinghui Zhang, of St. Jude Children’s Research Hospital, will present the driver genes identified from a pan-cancer analysis of 1,699 pediatric cancers and neoepitopes identified from integrative analysis of whole-genome and RNA-seq. Zhang’s team is responsible for building the St Jude Cloud. Monday, noon

Chris Dwan, an independent life sciences consultant, is chairing a session on hype vs reality in cloud capabilities starting at 2:00 on Tuesday. He kicks off the session by tackling legacy and migration challenges around aging decade-old cloud systems. The diversity of solutions in the marketplace mean that cross-cloud interoperability, data locality, and functional “skew” between clouds can be a significant challenge. Dwan will share practical experience and success strategies for managing through this second decade of the cloud. Tanya Cashorali, founder of TCB Analytics, is up next, addressing concerns of the still cloud-unsure. Cashorali will look at common negative perceptions of the cloud, along with implementation strategies that help mitigate these concerns. She’ll share examples of healthcare and pharmaceutical companies that successfully moved to the cloud, and how they navigated pushback from IT and the business. Finally Ruchi Munshi, The Broad Institute, will discuss compute in the cloud. Cloud platforms provide researchers access to so much compute that the next problem is learning how to use those resources effectively. Munshi will talk about various tools that leverage cloud resources to power analysis of genetic data.

Atul Butte, University of California, San Francisco, will share his lab’s use of publicly-available molecular measurements to find new uses for drugs, including new therapies for autoimmune diseases and cancer, discovering new druggable targets in disease, the evaluation of patients and populations presenting with whole genomes sequenced, integrating and reusing the clinical and genomic data that result from clinical trials, discovering new diagnostics including blood tests for complications during pregnancy, and how the next generation of biotech companies might even start in your garage. Monday, Noon

Imran Haque, formerly of Freenome, will argue that empirical biomarker discovery has failed to grapple with data set sizes in biology that are several orders of magnitude smaller than those in other fields where machine learning has had success. The solution, he believes, is research to bridge the gap between the mechanistic and empirical approaches, and in doing so address part of this data shortage. Tuesday, 2:10

Sanjay Joshi, Dell EMC, will share an overview of the data science process of engineering, DevOps, transformation and continuous model tuning, understanding the topic & disease, explainable machine learning, and regulatory process. Thursday, 10:00

Yuval Itan, Icahn School of Medicine at Mount Sinai, will explore new methods to detect pathogenic mutations and genes using machine learning. Current computational methods are inefficient in differentiating pathogenic mutations from neutral genetic variants that are predicted to be damaging and cannot predict the functional outcome of mutations, he argues. He will present deep learning approaches to detect pathogenic mutations and visualization tools for better using NGS data. Thursday, 4:45