Topic: Artificial Intelligence / Machine Learning

Speaker:

Tonia Korves, Ph.D.
Lead Data Scientist
Data and Human-Centered Solutions Innovation Center
MITRE Corporation

Abstract
As COVID-19 research rapidly escalated last year, we quickly built a platform to help biomedical experts track published research about potential therapeutics and vaccines. The platform includes a natural language processing pipeline that identifies scientific documents about SARS-CoV-2 and other viruses, particular drugs, and vaccine types, sorted by stages of research, and a dashboard called the COVID-19 Therapeutic Information Browser, available at covidtib.c19hcc.org. The comprehensive data from this platform enables us to characterize COVID-19 drug research over time and at scale, and potentially draw lessons that can inform future decisions. In this talk, we will present our natural language processing methods, the dashboard, and an analysis of trends in published COVID-19 drug research and clinical trials over the past year. We will also discuss other uses for this data, outstanding challenges, and other potential applications of this approach.

Join ZoomGov Meeting
https://nih.zoomgov.com/j/1617561452?pwd=bE5YOVgrL2tHbFZidUJQOWZzdGlpZz09

Meeting ID: 161 756 1452
Passcode: 586729
One tap mobile
+16692545252,,1617561452#,,,,*586729# US (San Jose)
+16468287666,,1617561452#,,,,*586729# US (New York)

Dear colleagues,

We’ll be hosting a special guest lecture by Prof. John Moult from UMD.

Abstract:
Computing the three-dimensional structure of a protein molecule from its amino acid
sequence is a long-standing grand challenge problem. Results from the recent Critical
Assessment of Structure Prediction (CASP14) experiment show that new deep-learning
methods have now provided a dramatic solution, with many computed structures
comparable, likely sometimes better, representations of in vivo protein structures to
those obtained with state-of-the-art experimental techniques of crystallography and
cryo-electron microscopy. These models have already demonstrated an ability to solve
problematic crystal structures, and the results suggest the methods will be successfully
applied to other areas of structural biology and more generally. This is the first solution
of a serious scientific problem by AI, and it will not be the last.
In this talk I’ll describe how the protein modeling field arrived at this point, what sort of
methods were used, characteristics of the computed structures, and some potential
further applications.

Bio:
John Moult is a Fellow at the Institute for Bioscience and Biotechnology Research and
Professor in the Department of Cell Biology and Molecular Genetics at the University of
Maryland. He is co-founder and Chair of CASP (Critical Assessment of Protein structure
Prediction), an organization that conducts large-scale experiments in protein structure
modeling, and joint founder of CAGI, a sister organization for advancing genome
interpretation. He is an ex-crystallographer turned computational biologist. His research
interests include the relationship between genetic variation and human disease, disease
mechanisms, protein structure, and different ways of doing science. (BSc Physics, University of London 1965, D.Phil Molecular Biophysics, University of Oxford 1970)

Join Zoom Meeting
https://umd.zoom.us/j/97941931766

Meeting ID: 979 4193 1766
One tap mobile
+13017158592,,97941931766# US (Washington DC)
+13126266799,,97941931766# US (Chicago)

Workshop Registration

Dear NIH colleagues,

You are invited to participate in the Machine Learning in Genomics: Tools, Resources, Clinical Applications, and Ethics Workshop, held virtually on Tuesday, April 13 – Wednesday, April 14, 2021.

Information about the agenda, speakers and registration can be found on the workshop webpage.

The meeting is organized and hosted by the NHGRI Data Science Working Group, and will kick off with a welcome message from NHGRI Director, Dr. Eric Green.

This meeting is free and open to anyone who registers.

Please direct any questions to natalie.kucher@nih.gov and sean.garin@nih.gov.

Sincerely,

Shurjo Sen (on behalf of the Organizing Committee)

Register

Session Description
This virtual hands-on workshop explores the fundamentals of machine learning using MATLAB. The participants will be introduced to machine learning techniques to quickly explore data, use classification and regression apps to interactively train, compare and tune a model, and optimize the model using hyperparameter tuning. The participants will also learn how to get started with deep learning in MATLAB for data preparation, design, simulation, and deployment of deep neural networks. This is an introductory level class.

Register Now

Faculty:  Shannon McWeeney, PhD – Oregon Health & Science University; NCI Cancer Moonshot DRSN

Moderator:  Santosh Putta, PhD

Target Audience
This series will serve as an excellent resource for all stakeholders interested in expanding their knowledge in computation immune-oncology. Specifically, early career scientists who want to further their training in computational immuno-oncology, as well as more senior career individuals who want to implement these techniques for the first time will greatly benefit from the series.

Learning Objectives
A key goal of this training program is to ensure participants remain on the cutting edge of computational immuno-oncology, to increase the participants’ awareness of the NCI-supported Cancer Moonshot Immunotherapy Networks, to enhance scientific engagements between the Cancer Moonshot(SM) Immunotherapy Networks and the broader cancer immunotherapy community, and to fulfill the Blue Ribbon Panel goal of acceleration of progress in cancer research.

Series Organizers
Kellie N. Smith, PhD – Johns Hopkins School of Medicine
Big Data and Data Sharing Committee, Chair
Song Liu, PhD – Roswell Park Comprehensive Cancer Center, NCI Cancer Moonshot IOTN & DRSN
Big Data and Data Sharing Committee, Co-Chair
Alan Hutson, PhD – Roswell Park Comprehensive Cancer Center, NCI Cancer Moonshot IOTN & DRSN
Big Data and Data Sharing Committee, Immediate Past Chair
Carsten Krieg, PhD – Medical University of South Carolina
Big Data and Data Sharing Committee, Member