Collins Lab (MIT) Internal Datasets

This repository contains screening results collected by the Collins Lab at the Broad Institute of MIT and Harvard for 38K+ compounds (tested at 50 µM for growth inhibition as measured by OD600 values) against 7 bacterial pathogens: Escherichia coli, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, Staphylococcus aureus, Neisseria gonorrhoeae and Mycobacterium tuberculosis. The repository also contains data for 38K+ compounds (tested at 10 µM for growth inhibition as measured by resazurin-based viability assay) against 3 human cell lines: HepG2 cells, HSkMCs, and IMR-90. The data (published and unpublished) were generated as part of the Antibiotics-AI Project. Related publications: Anahtar MN, Valeri JA, Modaresi SM, Krishnan A, Donghia NM, Palace SG, et al. Deep learning-enabled discovery of antibiotics effective against Neisseria gonorrhoeae. Science Translational Medicine. 2026 link Krishnan A, Anahtar MN, Valeri JA, Jin W, Donghia NM, Sieben L, et al. A generative deep learning approach to de novo antibiotic design. Cell. 2025 link Wong F, Omori S, Li A, Krishnan A, Lach RS, Rufo J, Wilson MZ, Collins JJ. An explainable deep learning platform for molecular discovery. Nature Protocols. 2025 link Wong F, Zheng EJ, Omori S, et al. Discovery of a structural class of antibiotics with explainable deep learning. Nature. 2024 link Liu G, Catacutan DB, Rathod K, Swanson K, Jin W, Mohammed JC, et al. Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii. Nature Chemical Biology. 2023 link Wong F, Krishnan A, Zheng EJ, Stärk H, Manson AL, Earl AM, Jaakkola T, Collins JJ. Benchmarking AlphaFold-enabled molecular docking predictions for antibiotic discovery. Molecular Systems Biology. 2022 link Stokes JM, Yang K, Swanson K, Jin W, Cubillos-Ruiz A, Donghia NM, et al. A deep learning approach to antibiotic discovery. Cell. 2020 link