NC BERD Seminar: Machine Learning for Precise Diagnostics and Therapeutics

Drug discoveries have been instrumental in improving global health over the last century, but the median drug now takes about 10 years to bring to market and costs over a billion dollars to develop. Rohit Singh, PhD, works to expedite the development of precise diagnostics and therapeutics by applying machine learning. In this seminar, Singh will outtline two recent research directions. In the first part, Singh uses single-cell multiomics to discover regulatory mechanisms governing the interaction between the epigenome, transcription factors, and target genes. This approach relies on methodological innovation, developing new Granger causal inference techniques to capitalize on the "parallax" between simultaneous but separate measures of cell state. In the second part, Singh will introduce the application of large language models to model protein interaction and function. These protein language models enable powerful new approaches to predicting and understanding protein-protein and protein-drug interactions. This seminar will conclude with a prospective look at how similar methods may help answer foundational questions in both basic and translational science.

Speaker:
Rohit Singh, PhD
Assistant Professor
Departments of Biostatistics & Bioinformatics and Cell Biology
Duke University

This event is sponsored by Duke University Departments of Computational Biology and Bioinformatics (CBB) and Biostatistics and Bioinformatics, the Duke Center for Genomic and Computational Biology (GCB), the Precision Genomics Collaboratory, and the Duke University School of Medicine. It is being cross-promoted by the North Carolina BERD Consortium (Duke University School of Medicine, University of North Carolina-Chapel Hill, and Wake Forest School of Medicine).

Engagement in Research Interactive Workshop: Developing and Implementing Your Community/Patient Engagement Plan

In this session, participants will have the opportunity to ask questions about and seek feedback on their patient and/or community engagement plans from facilitators (UNC engagement staff & community partners) and other attendees. This session serves as an interactive workshop in which participants will get a chance to: 1) discuss their engagement plans; 2) troubleshoot issues they are experiencing; 3) get new ideas while learning from others; and 4) leave the session with an updated engagement plan document.

To attend, participants must be in the process of developing or implementing a patient and/or community engagement plan for an active or upcoming project. Those who have engagement plans from previous projects may also be interested in attending, as this workshop may present an opportunity to improve upon or revise a prior engagement plan for future use. Participants must have attended one or more of the Engaging Patient, Community, and Other Partners in Your Research: Online Training Series sessions offered by NC TraCS and UNC Lineberger OR have some knowledge of engagement in research, whether from prior trainings or personal experience. This workshop focuses on research partner engagement, which involves collaborating with patient, community, or other partners who are not enrolled in your study to improve the study's design, conduct, and/or dissemination (it does NOT focus on research participant engagement, where the goal is to retain participants who are enrolled in a study).

Preparing for this workshop: When completing the Eligibility Screener in Qualtrics, you will have the opportunity to download the 1-page Engagement Plan Template. You do not have to submit your engagement plan in advance of the workshop; however, please come to the session with an engagement plan document that you can share with the group during discussion (e.g., a completed Engagement Plan Template or previously written engagement plan).

Please note: We will not be presenting information about engaging patient, community, or other partners in research during this session; instead, we will ask participants to share where they are with their projects/engagement plans, ask questions about their engagement plans, and collectively discuss strategies for moving their engagement plans forward.

ELIGIBILITY SCREENER

The Engaging Patient, Community, and Other Partners in Your Research: Online Training Series is a multi-part online training series about engaging patient, community, and other partners in research. You may register for the entire series OR any single training session.

Part 1 will focus on the basics of research engagement, providing an overview of patient and community engagement and its benefits, debunking common myths and misconceptions, and providing considerations and next steps for incorporating engagement approaches into your research.

Part 2 will cover specific engagement methods, including consultative community feedback sessions, advisory boards, and working with patient and community partners as members of a research team.

Part 3 will focus on the nuances of building and maintaining partnerships, outlining best practices for developing and strengthening mutually beneficial partnerships and discussing common partnership challenges and solutions.

Those who are in the process of developing, implementing, or revising a patient and/or community engagement plan for an active or upcoming project may be interested in attending our Engagement in Research Interactive Workshop, during which participants will have the opportunity to ask questions and seek feedback on their engagement plans in a small group setting.

This training series was developed collaboratively with patient, community, and researcher partners and is co-sponsored by the UNC Lineberger Comprehensive Cancer Center and NC TraCS Institute.

The NC TraCS Biostatistics Seminar Series helps clinical and translational researchers collaborate more effectively with consulting biostatisticians by building deeper understanding of key statistical concepts and methods. Researchers then are better able to (1) evaluate relevance of the concept or method for research aim(s) definition and choice of study design; and (2) properly interpret the results of data analysis.

Almost all grant applications require a statistical power analysis. In this seminar, Todd Schwartz, DrPH, will explain the basics of what power analysis is, how it works, and how to conduct one.

Schwartz is a professor in the department of Biostatistics at the UNC Gillings School of Global Public Health. He works collaboratively with the UNC School of Nursing (joint faculty appointment), the UNC Thurston Arthritis Research Center (Co-Director of the NIAMS-funded Methodology Core) and the UNC Eshelman School of Pharmacy (adjunct faculty appointment). Much of his efforts are focused on supporting various projects across these units with regard to their biostatistical aspects, including consultation on design, conduct, analysis and dissemination. He also has published on innovative pedagogical methods, including the ‘flipped’ classroom.

Register