use cases
start with a target. leave with a route.
target assessment through lead optimization, with a concrete output at the end. pick the one closest to your problem and follow it end to end — from chat, curl, the CLI, or an MCP client, on the model you choose.
six workflows
each one ends in something you keep.
compound screening
run genmol, diffdock and admet-ai across a compound library, then keep the ranked candidates and their run record.
molecular optimization
modify a lead compound, score the variants for binding, safety and drug-likeness, and export the ranked table.
target identification
combine bioinformatics and structural tools to score target candidates, with the evidence and run behind each score.
ADMET prediction
run ADMET-AI before synthesis to score absorption, metabolism, excretion and toxicity, and keep the property table.
chemical library design
generate target-specific libraries, filter them for drug-like properties, and export the compounds for screening.
biomarker discovery
run multi-omic analysis to rank candidate biomarkers and export the evidence behind the ranking.
next