medchem

You can filter a compound library for drug-likeness and structural alerts by applying rule-based thresholds like Lipinski and Veber alongside PAINS detection to remove problematic molecules. This process utilizes parallel batch processing to return a DataFrame of compounds that pass all selected checks.

The best way to prioritize molecules for hit-to-lead triage is to combine structural alert removal, complexity ranking, and chemical-group detection. Applying query-based logic and Lilly demerit support enables deterministic compound selection from large screening libraries.

Yes, you can apply custom medicinal chemistry rules to filter supplier compound libraries. The workflow supports query-based review logic and rule evaluation to identify compounds fitting a desired design space, returning boolean masks and DataFrames for consistent screening.

Yes, the workflow supports PAINS and NIBR structural risk screening before lead optimization. It detects common unwanted motifs and promiscuous structures, allowing researchers to apply specific alert catalogs to prevent wasted downstream effort.

You can use pandas and rdkit for batch library cleanup by processing compound data through rule evaluations and parallel batch processing. The system outputs DataFrames and boolean masks, integrating datamol and medchem to isolate molecules meeting your medicinal chemistry criteria.