Bridge2AI project seeks to map the spatiotemporal architecture of human cells and use these maps towards the grand challenge of interpretable genotype-phenotype learning. In genomics and precision medicine, machine learning models are often “black boxes,” predicting phenotypes from genotypes without understanding the mechanisms by which such translation occurs. .
Data Acquisition Module will generate comprehensive datasets for 100 chromatin modifiers and 100 metabolic enzymes involved in cancer, neuropsychiatric, and cardiac disorders across ethnicities and sexes. Data will be acquired in the triple-negative breast cancer cell line MDA-MB-468, including upon treatment with paclitaxel or ribociclib, and in two iPSC lines in the undifferentiated state as well as in differentiated neurons and cardiomyocytes using complementary mapping approaches. Leads: Emma Lundberg (PI) and Prashant Mali (Co-PI) Read more..
The Tools module addresses three aims: Dissemination of project data and cell maps.
Creation of tools for building cell maps from the three primary data streams. Creation of tools that enable cell maps to power a range of AI/ML applications in the biomedical community.
All three of these aims will be supported by acquisition of Graphical Processing Unit (GPU) computing hardware, which will ramp up each year in anticipation of use in training and pilot use by ML researchers. Leads: Trey Ideker (PI) and Andre Sali (Co-PI) Read more..
The purpose of the CM4AI Teaming Module is to integrate and expand technical and scientific knowledge and expertise within a culture that promotes ethical considerations and diverse interdisciplinary perspectives. The Teaming Module will facilitate communication and collaboration among investigators and personnel from diverse geographical areas, disciplinary boundaries, and cultures. Leads: Jake Chen (PI) and Ying Ding (co-PI). Read more..
The Cell Maps for AI (CM4AI) Standards Module will provide original, interim and final datasets and software from the CM4AI Data Acquisition and Tools pipeline, with final AI-ready results, as comprehensively FAIR (Findable – Accessible – Interoperable – Reusable) digital objects for uptake and reuse by biomedical Artificial Intelligence (AI) applications. Leads Tim Clark (PI) and Sarah Ratcliffe (Co-PI) Read more..
Ethics Module will develop new knowledge and resources to identify, anticipate, address, and provide guidance towards the development, sharing and usage of ethical and trustworthy AI for human cell architecture (HCA) mapping and for functional genomics. Our Module will use a modified Value-Sensitive Design (VSD) approach to carry out an ethical inquiry into the specifics of HCA data generation and downstream clinical usages (e.g., uses of systematic genotype-phenotype mapping).
Leads: Jean-Christophe Bélisle-Pipon, (PI) and Vardit Ravitsky (PI) and Yael Bensoussan (Co-PI) Read more..
Skills and Workforce
Skills and Workforce module will develop an infrastructure to support flexible educational offerings and modalities to be customizable to the needs of a diverse research community. By collaborating with end users and Bridge2AI members, our module will 1) foster skill development for existing researchers and practitioners, 2) attract a diverse array of new individuals to this emerging field, and 3) develop a strong AI/ML-biomedical research workforce. Leads: Wade Schultz (PI) and Cynthia Brandt (Co-PI) and Samah Fodeh (Co-PI) Read more..