We build machine learning models that identify combinations of existing drugs that work together against resistant bacteria — finding therapies that standard screening misses.
New antibiotics take 10–15 years and over $1 billion to develop. Meanwhile, antimicrobial resistance is accelerating. But effective drug combinations may already exist — if we know where to look.
Our ML pipeline analyzes efflux pump substrate profiles, resistance gene networks, molecular fingerprints, and MIC data to predict which drug combinations will show synergistic activity.
We partner with contract research organizations for independent in vitro validation — checkerboard synergy assays, MBEC biofilm testing, and time-kill kinetics.
We work with clinical researchers who have real-world treatment data from carbapenem-resistant infections, bridging computational predictions to patient outcomes.
Our model predicted azithromycin + meropenem as a top synergy candidate against carbapenem-resistant Gram-negatives. This prediction was independently confirmed by clinical observations from a collaborating research group treating patients in active care — before they were aware of our computational results.
Background in computer science, AI systems, and clinical research. Formerly a therapist specializing in PTSD treatment using VR-based exposure therapy (published). Now applying computational methods to antimicrobial resistance. Based in Grand Rapids, Michigan.
We work with researchers and institutions advancing the fight against AMR:
Clinical Research Partners
Collaborators with real-world treatment data from carbapenem-resistant infections in active patient care.
Contract Research Organizations
Independent laboratories providing in vitro validation of our computational predictions.
Academic Consultants
Subject matter experts in Gram-negative resistance mechanisms and antimicrobial pharmacology.
Interested in collaboration or learning more about our work?
toverly@vibemeshlabs.com