UGM-2021

Welcome to Elucidata's

USER GROUP MEETING 2021

 October 27, 2021 | 9 AM – 1:30 PM (Pacific Time)

We’re excited to host Elucidata’s 2nd User Group Meeting, bringing the latest on omics data ingestion, the role of Machine Learning in the future of drug discovery, and the value of early access to curated omics data. This virtual event features thought-provoking seminars from data science leaders in drug discovery, panel discussions on the challenges and opportunities of setting up a robust data infrastructure in laboratories, and user-led presentations on drug asset discovery using public omics data. 

KEYNOTE SPEAKERS

Gary Churchill

Professor
the jackson laboratory

Integration of Multi-Omics Data across Human & Mouse

Marina sirota

Associate Professor
Bakar Computational Health Sciences Institute, UCSF

Computational Drug Discovery in the era of Precision Medicine

SPEAKERS

Aaron Mackey

VP Computational Multiomics
Roivant Sciences

elucidata abhishek jha co founder ceo

Abhishek Jha

CEO & Co-Founder
Elucidata

Bevan Emma Huang

Sr. Director
Johnson & Johnson

Brandon AllGood

Chief AI officer
valo health

dewakar sangaraju

Sr. scientist & metabolomics group head - genentech

Dr. Rama Balakrishnan

Biomedical Ontology Specialist genentech

Richard Kibbey

Co-founder, Scientific Advisory Board - Elucidata

Shashank Jatav

director, data products
elucidata

elucidata Shefali Lathwal research lead

shefali lathwal

lead scientist
elucidata

soumya luthra

director, customer success
elucidata

swetabh elucidata co founder ceo

Swetabh pathak

cto & co-founder
elucidata

Todd Harris

Founder & CEO
Tyra Biosciences

AGENDA

09 - 9.10 am

Welcome Note

Speaker: Abhishek Jha, Co-Founder & CEO at Elucidata; Prof. Richard Kibbey, Scientific Co-Founder at Elucidata

9.10 - 9.40 am

Keynote Presentation 1: Integration of multi-omics data across human and mouse

Speaker: Gary Churchill, Professor at the Jackson Laboratory

The Churchill lab applies a systems approach to study the genetics of health and diseases, incorporating new methods & software that help investigate complex disease-related traits in the mouse. In his keynote address, Professor Gary Churchill will discuss how integration of human and mouse Multi-Omics Data helps characterize the genetic architecture of diseases.

9.40 - 10.10 am

A Data-Centric Approach to AI initiatives - The Changing Paradigm

Speaker: Abhishek Jha, Co-Founder & CEO at Elucidata

The recent surge in biomedical data has resulted in corresponding advances in ML algorithms for insight discovery. However, AI-driven drug design carries several challenges - the need for appropriate datasets, FAIR quality data & the ability to generate and test evolving biological hypotheses, to name a few. In this session, we discuss how a data-centric approach recognizes the value of ML-Ready data & significantly improves the efficiency of ML-Driven drug discovery initiatives.

10.10 - 10.40 am

Keynote Presentation 2: Computational Drug Discovery in the era of Precision Medicine

Speaker: Marina Sirota, Associate Professor at the Bakar Computational Health Sciences Institute, UCSF

Marina and her team at UCSF apply integrative computational methods in the context of disease diagnostics and therapeutics. Their primary focus is on leveraging and integrating different types of omics and clinical data to better understand the role of the immune system in diseases. Join this session as she discusses the role of computational drug discovery in precision medicine.

10.40 - 11.10 am

ML Applications of the Future: The Building Blocks

Speaker: Swetabh Pathak, Co-Founder & CTO at Elucidata

ML applications in drug research have matured from automating routine, low-level analyses to predicting the most complex structures we know of. However, quality data remains crucial to validate these approaches and generate accurate predictions and insights. Through this segment, we discuss the opportunities of applying ML across the drug research process & the steps discovery teams must take to accommodate this paradigm shift.

Track 1

Track 2

Data & Technology

Polly Enabled Solutions

11.15 - 11.45 am

Thinking about Data Quality

Speaker: Shefali Lathwal, Lead Scientist

While the value of FAIR biomolecular data to the research community is uncontested, data quality control methods show high variability across data types and use cases. This necessitates a standard framework that addresses the overall quality of biomedical data. In this session, we will discuss our approach towards measuring, improving, and maintaining high-quality data.

11.15 - 11.45 am

High throughput Metabolomics Analysis using Polly

Speaker: Dewakar Sangaraju, Sr. Scientist at Genentech

Faster downstream analysis & visualization of data is a bottleneck in the use of Metabolomics techniques for identifying metabolite signatures. This session will demonstrate how our partner, Genentech, leverages production-ready GUI applications developed by Elucidata experts to accelerate insight generation & uncover complex relationships in data.

11.45 - 12.15 pm

Maximizing data value for Biopharma through FAIR & Quality Implementation

Speaker: Dr Rama Balakrishnan, Biomedical Ontology Specialist at Genentech

Dr. Rama Balakrishnan and her team aims to FAIRify legacy datasets in different Therapeutic Areas (TA) and design processes for prospective FAIRification of future studies. This session details the need for FAIR data metrics, Data Quality Assessment (DQA) for clinical trials as well as EHR data, and how to accelerate the generation of new medical treatments through FAIR data.

11.45 - 12.15 pm

Target Identification using public data

Speaker: Todd Harris, Founder & CEO at Tyra Biosciences; Abhishek Jha, Co-Founder & CEO at Elucidata

The power of multi-omics data is evident in the recent surge of molecular biology-based therapeutic breakthroughs, but the complexity of managing multi-dimensional data from disparate sources continues to be a challenge. This session details a real-world use case on how Polly powers curated ML-ready omics data, enabling an integrative multi-omics approach that helps identify safe & efficacious drug targets.

12.15 - 12.45 pm

Curating Biomedical Molecular Data at Scale, our IP

Speaker: Shashank Jatav - Director, Data Products

Elucidata’s proprietary curation platform, built on top of NLP-based AI models, generates harmonized metadata annotations with scientific context at an accuracy matching that of human experts. In this session, we will look at how the platform enables data curation at scale and equips users with ML-Ready biomolecular data for their drug discovery workflows.

12.15 - 12.45 pm

Engagement Models & Polly Enabled Solutions

Speaker: Soumya Luthra - Director, Customer Success

Through a combination of our data platform Polly and in-house bioinformatics experts, we empower multi-disciplinary R&D teams with production-ready pipelines & applications, scale their data curation efforts and help them get to quicker actionable insights. Take a quick tour of Polly Enabled Solutions & see how they add value to your bioinformatics enterprise.

12.50 - 1.20 pm

Panel Discussion: Challenges & Opportunities of setting up a Data Infrastructure

Panelists:: Aaron Mackey, VP at Roivant Sciences; Brandon Allgood, Chief AI Officer at Valo Health; Bevan Emma Huang, Sr. Director at Johnson & Johnson; Swetabh Pathak, CTO & Co-Founder at Elucidata

The complexities of managing and delivering value from high throughput multi-omics data far outpace traditional approaches to IT infrastructure. Thus, building a robust, centralized ecosystem that ingests, stores & pre-processes these data for downstream ML applications becomes critical. Join our panel of industry experts as they make a case for strategic investments in biomedical data management and shed light on the challenges of building a data infrastructure from the ground up.

1.20 - 1.30 pm

Ending Note

Speaker:: Abhishek Jha, Co-Founder & CEO at Elucidata