Ultra-high-throughput screening of antimicrobial combination therapies using a two-stage transparent machine learning model
Reuter, M. M.; Lev, K. L.; Albo, J.; Singh Arora, H.; Liu, N.; Tan, S.; Shay, M. R.; Sarkar, D.; Robida, A.; Sherman, D. H.; Richardson, R. J.; Cira, N. J.; Chandrasekaran, S.
Show abstract
Here, we present M2D2, a two-stage machine learning (ML) pipeline that identifies promising antimicrobial drug combinations, which are crucial for combating drug resistance. M2D2 addresses key challenges in drug combination discovery by predicting drug synergies using computationally generated drug-protein interaction data, thereby circumventing the need for expensive omics data. The model improves the accuracy of drug target identification using high-throughput experimental and computational methods via feedback between ML stages. M2D2s transparent framework provides mechanistic insights into drug interactions and was benchmarked against chemogenomics, transcriptomics, and metabolomics datasets. We experimentally validated M2D2 using high-throughput screening of 946 combinations of Food and Drug Administration (FDA)- approved drugs and antibiotics against Escherichia coli. We discovered synergy between a cerebrovascular drug and a widely used penicillin antibiotic and validated predicted mechanisms of action using genome-wide CRISPR inhibition screens. M2D2 offers a transparent ML tool for rapidly designing combination therapies and guides repurposing efforts while providing mechanistic insights.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Machine Learning Identifies Novel Candidates for DrugRepurposing in Alzheimer's Disease 95%
- The Endo-GeneScreen Platform Identifies Drug-Like Probes that Regulate Endogenous Protein Levels within Physiological Contexts 95%
- Predicting compound activity from phenotypic profiles and chemical structures 95%
Similar papers in this journal
- Defining subpopulations of differential drug response to reveal novel target populations 96%
- Network-driven cancer cell avatars for combination discovery and biomarker identification for DNA Damage Response inhibitors 95%
- Single-cell characterization of step-wise acquisition of carboplatin resistance in ovarian cancer 94%
Similar papers in this journal
- LIGHTHOUSE illuminates therapeutics for a variety of diseases including COVID-19 96%
- Inference of drug off-target effects on cellular signaling using Interactome-Based Deep Learning 95%
- A Highly-Efficient, Scalable Pipeline for Fixed Feature Extraction from Large-Scale High-Content Imaging Screens 94%
Similar papers in this journal
- A scalable platform for efficient CRISPR-Cas9 chemical-genetic screens of DNA damage-inducing compounds 96%
- Tales of 1,008 Small Molecules: Phenomic Profiling through Live-cell Imaging in a Panel of Reporter Cell Lines 95%
- Evaluation of Connectivity Map shows limited reproducibility in drug repositioning 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.