Health AI Central
Peer-Reviewed Publication
Nat Protoc2025;20(4):1020-1056.April 1, 2025Journal Article

An explainable deep learning platform for molecular discovery.

Felix Wong1,2,3, Satotaka Omori1,3, Alicia Li3, Aarti Krishnan1,2, Ryan S Lach3, Joseph Rufo4,5,6,7, Maxwell Z Wilson3,4,5,6,7, James J Collins8,9,10
1Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA, USA.
2Institute for Medical Engineering and Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA.
3Integrated Biosciences, Inc., Redwood City, CA, USA.
4Center for BioEngineering, University of California Santa Barbara, Santa Barbara, CA, USA.
5Biomolecular Science and Engineering Program, University of California Santa Barbara, Santa Barbara, CA, USA.
6Department of Molecular, Cellular, and Developmental Biology, University of California Santa Barbara, Santa Barbara, CA, USA.
7Neuroscience Research Institute, University of California Santa Barbara, Santa Barbara, CA, USA.
8Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, MA, USA. jimjc@mit.edu.
9Institute for Medical Engineering and Science and Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. jimjc@mit.edu.
10Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, MA, USA. jimjc@mit.edu.
PubMed PMC DOI PDF

Abstract

Deep learning approaches have been increasingly applied to the discovery of novel chemical compounds. These predictive approaches can accurately model compounds and increase true discovery rates, but they are typically black box in nature and do not generate specific chemical insights. Explainable deep learning aims to 'open up' the black box by providing generalizable and human-understandable rea…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.