Discover novel small-molecule binders for protein targets using structure-based and ligand-based screening. Covers druggability assessment, known-ligand mining (ChEMBL, BindingDB), similarity expansion, ADMET filtering, and synthesis feasibility. Use for hit identification, virtual screening, target

Small Molecule Binder Discovery Strategy Systematic discovery of novel small molecule binders using 60+ ToolUniverse tools across druggability assessment, known ligand mining, similarity expansion, ADMET filtering, and synthesis feasibility. LOOK UP DON'T GUESS Always retrieve actual data from tools before drawing conclusions. Do not assume druggability, binding sites, or compound properties based on target class alone. KEY PRINCIPLES : 1. Report first approach Create report file FIRST, then populate progressively 2. Target validation FIRST Confirm druggability before compound searching 3. Multi strategy approach Combine structure based and ligand based methods 4. ADMET aware filtering Eliminate poor compounds early 5. Evidence grading Grade candidates by supporting evidence 6. Actionable output Provide prioritized candidates with rationale 7. English first queries Always use English terms in tool calls. Respond in the user's language Binding Site Reasoning (Start Here) Before any tool call, reason about the target's structural biology: Is the binding site a well defined pocket (small molecule accessible) or a flat protein protein interface (needs peptide/macrocycle)? This determines your screening strategy. Enzymes with active sites (proteases, kinases, ATPases): deep, well defined pockets. Classic small molecule territory. Prioritize co crystal structure search and known inhibitor scaffold analysis. GPCRs and ion channels : transmembrane pockets. Structure often available; start with GPCRdb and GtoPdb for known pharmacology. Nuclear receptors : deep hydrophobic pockets. Excellent small molecule tractability; ligand based methods are well powered. Protein protein interfaces : flat, large contact surface. Small molecules rarely compete effectively unless there is a "hot spot" cavity. Check whether any allosteric pockets exist before committing to small molecule strategy. Warn the user if no pocket is found. Intrinsically disordered regions : essentially no small molecule approach. Redirect to peptide or degrader strategies. Scaffolding / adaptor proteins : assess co crystal structures for unexpected pockets before declaring undruggable. Use this reasoning to select phases and warn the user about challenges before executing a full workflow. Critical Workflow Requirements 1. Report First Approach (MANDATORY) DO NOT show search process or tool outputs to the user. Instead: 1. Create the report file FIRST Before any data collection: File name: [TARGET] binder discovery report.md Initialize with all section headers from the template (see REPORT TEMPLATE.md) Add placeholder text: [Researching...] in each section 2. Progressively update the report As you gather data, update each section immediately. 3. Output separate data files : [TARGET] candidate compounds.csv Prioritized compounds with SMILES, scores [TARGET] bibliography.json Literature references (optional) 2. Citation Requirements (MANDATORY) Every piece of information MUST include its source: Example: Source: ChEMBL via ChEMBL get target activities (CHEMBL203) Workflow Overview Phases in order: Phase 0 : Tool verification (check parameter names with get tool info ) Phase 1 : Target validation — resolve IDs, assess druggability, identify binding sites, predict structure if needed Phase 2 : Known ligand mining — ChEMBL, BindingDB, GtoPdb, PubChem BioAssay, chemical probes; SAR analysis Phase 3 : Structure analysis — PDB co crystals, EMDB (membrane targets), binding pocket characterization Phase 3.5 : Docking validation — dock reference inhibitor to validate pocket geometry Phase 4 : Compound expansion — similarity/substructure search (seeds: 3 5 diverse actives) + de novo generation Phase 5 : ADMET filtering — physicochemical, bioavailability, toxicity, CYP, structural alerts Phase 6 : Candidate docking and prioritization — score and rank top 20 Phase 6.5 : Literature evidence — PubMed, EuropePMC, OpenAlex Phase 7 : Report synthesis and delivery Phase 0: Tool Verification CRITICAL : Verify tool parameters before calling unfamiliar tools. Common parameter corrections (verify with get tool info if uncertain): OpenTargets : ensemblId (camelCase); ADMETAI : smiles must be a list NvidiaNIM alphafold2 (requires NVIDIA API KEY env var; free key at build.nvidia.com) : sequence not seq ; NvidiaNIM genmol (requires NVIDIA API KEY env var; free key at build.nvidia.com) : SMILES must contain [ {min max}] NvidiaNIM boltz2 (requires NVIDIA API KEY env var; free key at build.nvidia.com) : polymers=[{"molecule type": "protein", "sequence": "..."}] Phase 1: Target Validation 1.1 Identifier Resolution Resolve all IDs upfront and store for downstream queries: 1.2 Druggability Assessment Use multi source triangulation: OpenTargets get target tractability by ensemblID(ensemblId) tractability bucket DGIdb get gene druggability(genes=[gene symbol]) druggability categories OpenTargets get target classes by ensemblID(ensemblId) target class For GPCRs: GPCRdb get protein + GPCRdb get ligands + GPCRdb get structures For antibody landscape: TheraSAbDab search by target(target=target name) Decision Point : If no tractability data and binding site reasoning suggests PPI or disordered region, explicitly warn the user before proceeding. 1.3 Binding Site Analysis ChEMBL search binding sites(target chembl id) get binding affinity by pdb id(pdb id) for co crystallized ligands InterPro get protein domains(accession) for domain architecture 1.4 Structure Prediction (NVIDIA NIM) Requires NVIDIA API KEY . Two options: AlphaFold2 : NvidiaNIM alphafold2(sequence, algorithm="mmseqs2") high accuracy, 5 15 min ESMFold : ESMFold predict structure(sequence) fast (~30s), max 1024 AA pLDDT guidance: =90 very high confidence, 70 90 confident, <70 use with caution. Low pLDDT in the putative binding region undermines docking reliability. Phase 2: Known Ligand Mining Priority order for bioactivity data: 1. ChEMBL get target activities curated, SAR ready 2. BindingDB get ligands by uniprot direct Ki/Kd with literature links 3. GtoPdb search ligands pharmacology focus (GPCRs, channels) 4. PubChem search assays by target gene HTS screens, novel scaffolds 5. OpenTargets get chemical probes by target ensemblID validated probes Key steps: 1. Filter to IC50/Ki/Kd < 10 uM; retrieve molecule details for top actives 2. Identify chemical probes and approved drugs 3. Analyze SAR: common scaffolds, key modifications 4. Check off target selectivity: BindingDB get targets by compound Phase 3: Structure Analysis Tools: PDB search similar structures(query=uniprot, type="sequence") find PDB entries get protein metadata by pdb id(pdb id) resolution, method get binding affinity by pdb id(pdb id) co crystal ligand affinities get ligand smiles by chem comp id(chem comp id) ligand SMILES from PDB EMDB search structures(query) cryo EM structures (prefer for GPCRs, ion channels) alphafold get prediction(qualifier) AlphaFold DB fallback Phase 3.5: Docking Validation (NVIDIA NIM) If PDB + SDF available: use get diffdock info(protein=PDB, ligand=SDF, num poses=10) . If only sequence + SMILES: use NvidiaNIM boltz2(polymers=[...], ligands=[...]) . Dock a known reference inhibitor first to validate the binding pocket geometry before running candidates. Phase 4: Compound Expansion 4.1 4.3 Search Based Expansion Use 3 5 diverse actives as seeds, similarity threshold 70 85%: ChEMBL search similar molecules(molecule=SMILES, similarity=70) PubChem search compounds by similarity(smiles, threshold=0.7) ChEMBL search substructure(smiles=core scaffold) STITCH get chemical protein interactions(identifier=gene, species=9606) 4.4 De Novo Generation (NVIDIA NIM) GenMol scaffold hopping with masked regions: MolMIM controlled analog generation: Phase 5: ADMET Filtering Apply sequentially (all tools accept smiles=[list] ): 1. Physicochemical : ADMETAI predict physicochemical properties Lipinski violations <= 1, QED 0.3, MW 200 600 2. Bioavailability : ADMETAI predict bioavailability oral bioavailability 0.3 3. Toxicity : ADMETAI predict toxicity AMES < 0.5, hERG < 0.5, DILI < 0.5 4. CYP : ADMETAI predict CYP interactions flag CYP3A4 inhibitors 5. Alerts : ChEMBL search compound structural alerts no PAINS Include a filter funnel summary in the report showing pass/fail counts at each stage. Phase 6: Candidate Docking & Prioritization Composite score: docking confidence (40%) + ADMET score (30%) + similarity to known active (20%) + novelty (10%, not in ChEMBL + novel scaffold bonus). Evidence tiers for candidates: T1 (3 stars): Experimental IC50/Ki < 100 nM T2 (2 stars): Docking within 5% of reference OR IC50 100 1000 nM T3 (1 star): 80% similarity to T1 compound T4 (0 stars): 70 80% similarity, scaffold match only T5 (no stars): Generated molecule, ADMET passed, no docking Deliver top 20 candidates with: Rank, ID, SMILES, docking score, ADMET score, overall score, source, evidence tier. Phase 6.5: Literature Evidence PubMed search articles(query="[TARGET] inhibitor SAR") peer reviewed EuropePMC search articles(query, source="PPR") preprints (not peer reviewed) openalex search works(query) citation analysis Fallback Chains Programmatic Access (Beyond Tools) When ToolUniverse tools return limited compound sets, access chemical databases directly: See tooluniverse data wrangling skill for format cookbook and pagination patterns. NVIDIA NIM Runtime Notes AlphaFold2: 5 15 min (async, max ~2000 AA). ESMFold: ~30 sec (max 1024 AA). DiffDock: ~1 2 min/ligand. Boltz2: ~2 5 min. GenMol/MolMIM: ~1 3 min. Always check: import os; nvidia available = bool(os.environ.get("NVIDIA API KEY")) For large expansions ( 500 compounds): batch in chunks of 100, prioritize top candidates for docking. Reference Files [WORKFLOW DETAILS.md](./WORKFLOW DETAILS.md) Phase by phase procedures, code patterns, screening protocols [TOOLS REFERENCE.md](./TOOLS REFERENCE.md) Complete tool reference with parameters and fallback chains [REPORT TEMPLATE.md](./REPORT TEMPLATE.md) Report file template and evidence grading system [EXAMPLES.md](./EXAMPLES.md) End to end workflow examples (EGFR, novel target, lead optimization) [CHECKLIST.md](./CHECKLIST.md) Pre delivery verification checklist

tooluniverse-binder-discovery