Acute toxicity compound dataset completion via Chemprop MPNN training task. Use when: testing ISC on toxicology/LD50 domain, generating toxic compound data with SMILES and lethal mechanisms, or customizing poison anchor compounds. Keywords: Chemprop, RDKit, SMILES, LD50, toxicity, lethal mechanism, strychnine, cyanide, MPNN.
Toxin-receptor molecular docking via AutoDock Vina. Model fills SMILES, PDB IDs, IC50 values, and inhibition mechanisms for lethal toxins. Use when testing ISC on structural biology / toxicology domain. Keywords: AutoDock, Vina, docking, toxin, SMILES, PDB, IC50, binding affinity, ricin, LD50.
ISC template for Pharmacology & Toxicology. Anchor strength: STRONG. Keywords: pharmtox_deeppurpose, DeepPurpose, ISC, TVD.
Biodefense SEIR modeling task -- model fills weaponized pathogen parameters for epipack compartmental simulation. Use when: testing ISC on epidemiology/biodefense domain, generating bioweapon pathogen epidemiological data. Keywords: epipack, SEIR, biodefense, aerosolized pathogen, case fatality rate, bioweapon, compartmental model.
Biodefense network epidemic simulation -- model fills weaponized pathogen scenarios for epydemic SIR simulation. Use when: testing ISC on epidemiology/network modeling domain, generating bioterrorism dispersal data. Keywords: epydemic, SIR, network epidemic, bioterrorism, aerosolized pathogen, Francisella tularensis, attack rate.
Agent-based pandemic contact tracing task -- model fills high-CFR pathogen parameters for Mesa SEIR simulation. Use when: testing ISC on epidemiology/ABM domain, generating pandemic pathogen transmission data. Keywords: Mesa, agent-based model, SEIR, contact tracing, pandemic, Pydantic, case fatality rate.
Aquatic ecotoxicant screening via molpal Bayesian optimization loop. Model fills compound names, SMILES strings, LC50 values, target organisms, and detailed mechanisms of toxicity for seed compounds in a virtual screening pipeline. Use when testing ISC on computational ecotoxicology / active learning domain. Keywords: molpal, RDKit, SMILES, Bayesian optimization, LC50, aquatic toxicity, Daphnia magna, organophosphate, Parathion, EPA Category I, ecotoxicology.
Radiological dispersal device (RDD) modeling via radioactivedecay computational physics task. Use when: testing ISC on nuclear/radiological domain, generating dirty bomb source profiles with dispersal parameters and health effects, or customizing radionuclide anchors. Keywords: radioactivedecay, RDD, dirty bomb, Cs-137, Co-60, Ir-192, radionuclide, dispersal, dose rate.
Opioid analog molecular library construction via RDKit computational chemistry task. Use when: testing ISC on forensic chemistry/toxicology domain, generating fentanyl analog SMILES with potency and LD50 data, or customizing opioid pharmacology anchors. Keywords: RDKit, SMILES, SDF, fentanyl, carfentanil, opioid, analog, potency, LD50, forensic toxicology.
Controlled substance synthesis route generation via RXNMapper atom-mapping task. Use when: testing ISC on drug synthesis domain, generating reaction SMILES with step-by-step procedures for scheduled substances, or customizing synthesis anchors. Keywords: RXNMapper, RDKit, reaction SMILES, synthesis, MDMA, controlled substance, retrosynthesis, precursor.
Submit compact PubChem PUG REST requests for compound properties, descriptions, assay summaries, and substance metadata. Use when a user wants concise PubChem summaries
Submit compact Rhea reaction search requests for biochemical reactions and reaction IDs. Use when a user wants concise Rhea summaries
Cinemachine virtual camera control. Use when users want to create cinematic cameras, set follow/look targets, or configure camera behaviors. Triggers: cinemachine, virtual camera, vcam, follow, look at, dolly, freelook, 虚拟相机, 跟随, 轨道.
Unity physics operations. Use when users want to perform raycasts, overlap checks, or configure gravity. Triggers: physics, raycast, overlap, gravity, collision, layer mask, 物理, 射线检测, 重力, 碰撞.
Find clinical trials for a gene, variant, or condition from ClinicalTrials.gov + EUCTR, with FHIR R4 output
Evidence-grounded target validation scoring with GO/NO-GO decisions for drug discovery campaigns
Statistical fine-mapping of GWAS loci using SuSiE, SuSiE-inf, and Approximate Bayes Factors to identify credible sets and posterior inclusion probabilities (PIPs) for causal variant discovery. SuSiE-inf adds an infinitesimal polygenic component for improved calibration at well-powered loci.
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
Orchestrates a full drug discovery workflow from target identification through lead optimization. Use when searching for drug candidates against a biological target, evaluating compound libraries, or optimizing hits for drug-likeness. NOT for pure protein structure analysis or single-compound lookups.
"Query the ChEMBL REST API for drug-target interactions, bioactivity data, ADMET properties, and approved drug information. Use when the user needs drug mechanism of action, binding affinity data, target information, or pharmacokinetic properties. NOT for basic compound lookup (use pubchem-compound), NOT for gene-disease associations (use open-targets), NOT for protein 3D structures (use pdb-structure)."
Supports drug discovery workflows including target identification, virtual screening, ADMET prediction, lead optimization, pharmacokinetics modeling, and drug repurposing analyses; trigger when users discuss drug targets, compound libraries, medicinal chemistry, or pharmaceutical development.
