Identify biological targets from compound structures and prioritize hypotheses.
npx skills add https://github.com/patsnap/skills --skill target-discovery
Please help me install this Agent Skill. Skill: target-discovery Source: https://github.com/patsnap/skills/tree/main/open-platform/target-discovery Command: npx skills add https://github.com/patsnap/skills --skill target-discovery
This Skill helps teams start from one or many compound structures and rapidly identify the most plausible biological targets, so discovery work can move from chemical inventory to testable hypotheses.
Give this skill one or more SMILES strings and ask it to analyze likely targets, patent risk, and optimization paths, optionally requesting a PPT or PDF report.
High-intent search queries and answers about installing and using this skill.
To identify biological targets from compound structures, provide SMILES strings to perform scaffold analysis and similarity search against known active molecules, generating ranked target hypotheses for drug discovery.
Yes, you can input one or more SMILES strings to run ADMET filtering for drug-likeness and toxicity, followed by similarity analysis to find likely biological targets and extract structure-activity relationships.
Reverse target fishing identifies likely biological targets for proprietary compound libraries by analyzing shared chemical scaffolds and performing similarity searches to generate validated target hypotheses and assess patent risk.
To assess FTO and patent risk for a compound library, validate target intelligence and check patent exposure against identified biological targets to support ranked recommendations for drug discovery workflows.
Yes, target discovery extracts structure-activity relationships by finding nearby known active molecules through similarity search, enabling scaffold analysis and interpretation to guide compound optimization paths.
Yes, you can optionally request a PPT or PDF report summarizing target hypotheses, ADMET filtering results, FTO assessment, and structure-activity relationships to support decision making in research workflows.
inflexa-aiAutomate molecular structure analysis and QSAR modeling workflows with RDKit and DeepChem.
awslabsEvaluate biological hypotheses for translational readiness across T0-T4 stages.
jackspaceQuery ChEMBL bioactive molecules and bioactivity data via Python client.
Obviously-NotValidate patent findings and generate structured search queries for patent research.
