OpenBioMed

Find the most suitable skill for a given biomedical task. Use this skill when: (1) You are unsure which skill to use for a specific biomedical task, (2) You want to discover available skills for a particular domain, (3) You need to compare multiple skills for a given use case.

Generate diverse druggable molecules for a given target or disease using OpenBioMed's AI-powered drug discovery tools. Use this skill when: (1) Generating drug candidates, molecules, or compounds for a target/disease, (2) Performing structure-based drug design or de novo drug design, (3) Finding or creating molecules that bind to a specific protein target, (4) Discovering potential drugs for a disease name, (5) Designing molecules with specific properties (LogP, QED, docking scores). The skill handles target identification, structure retrieval, molecule generation, and in silico evaluation.

Analyze potential drug-drug interactions (DDI) for up to 5 drugs using KEGG DDI database. Use this skill when: (1) Checking interactions between multiple medications, (2) Assessing DDI risk for drug combinations, (3) Understanding interaction mechanisms and severity, (4) Analyzing CYP enzyme involvement in DDIs.

Generate comprehensive drug development progress reports for disease therapeutic targets. Use when user asks about target drug pipeline, clinical trials, or research progress. Triggers on phrases like "target report", "drug development progress", "clinical trial summary", "靶点报告", "药物研发进展", "竞品分析", "专利分析".

Create new biomedical skills or improve existing ones for the OpenBioMed toolkit. Use this skill when: (1) Creating a new skill from scratch, (2) Capturing a workflow as a reusable skill, (3) Automating a biomedical task, (4) Improving an existing skill. This skill guides through an interactive process: define intent → design workflow → validate with real data → iterate → evaluate.

Query ChEMBL database for bioactivity data on drug-like compounds. Use this skill when: (1) Finding compounds active against a protein target (target-based search), (2) Getting bioactivity profile for a molecule (molecule-based search), (3) Finding drugs for a disease indication (indication-based search).

Identify the IUPAC name of a molecule using BioT5 question answering model. Use this skill when: (1) User wants to find the IUPAC name of a molecule, (2) User asks "What is the IUPAC name?" or "What's the systematic name?", (3) User provides a SMILES string and wants the IUPAC nomenclature.

Query KEGG database for drug information, pathway analysis, and disease-drug-target discovery. Use this skill when: (1) Looking up drug information including efficacy, targets, metabolism, and interactions, (2) Analyzing metabolic or signaling pathways to retrieve genes, compounds, and modules, (3) Discovering disease-associated drugs, genes, and pathways for drug repurposing.

Query a molecule's biochemical significance and roles in biology and chemistry using BioT5 multi-modal model. Use this skill when: (1) Understanding a molecule's biological roles and functions, (2) Describing a molecule's chemical significance and applications, (3) Getting natural language explanations of molecular properties, (4) Summarizing what a molecule is used for or its metabolic relevance.

Query STRING database for protein-protein interactions with confidence scores. Use this skill when: (1) Finding interaction partners for a protein of interest, (2) Retrieving confidence scores for protein-protein interactions, (3) Building protein interaction networks for pathway analysis.

Predict protein function and properties from amino acid sequence using BioT5. Use this skill when: (1) You have a protein sequence and want to understand its biological function, (2) You need to identify enzyme activity, pathway involvement, or molecular interactions, (3) You want a concise description of protein properties from sequence alone.

Analyze protein-ligand interactions in PDB structures using PLIP (Protein-Ligand Interaction Profiler). Use this skill when: (1) Analyzing binding interactions from a PDB structure file, (2) Identifying hydrogen bonds, hydrophobic contacts, π-stacking, salt bridges, and water bridges, (3) Generating 3D visualizations of protein-ligand complexes, (4) Creating interaction summary reports for drug discovery.

Predict protein subcellular localization from amino acid sequence using BioT5. Use this skill when: (1) You have a protein sequence and want to know where it localizes in the cell, (2) You need to identify cellular compartment (nucleus, cytoplasm, membrane, etc.), (3) You want quick localization prediction without experimental data.

Generate diverse lead compounds for a specific protein target using structure-based drug design with MolCraft. Use this skill when: (1) Designing drug candidates for a known protein target (PDB ID or disease name), (2) Generating structurally diverse molecules with optimized binding affinity, (3) Filtering candidates based on user-defined criteria (docking, ADMET, drug-likeness), (4) Iteratively refining leads through regeneration when criteria are not met.

Modify molecules based on natural language descriptions using MolT5/BioT5 models. Use this skill when: (1) User wants to modify a molecule to improve specific properties (solubility, potency, etc.), (2) User provides a molecule and asks to "make it more X" or "improve Y", (3) User wants to generate molecule variants guided by text descriptions. Triggers on phrases like "modify this molecule", "edit the molecule", "make it more soluble", "improve drug-likeness", "change the molecule to", "optimize this compound".

Query UniProt database for protein sequences, metadata, and search by criteria. Use this skill when: (1) Looking up protein information by UniProt accession ID, (2) Searching proteins by gene name, organism, function, or disease, (3) Retrieving comprehensive protein metadata including domains, PTMs, and annotations.

面向生物医药问答场景的“疾病到创新药综合分析”技能。用于回答“某疾病有哪些创新药/前沿药/在研药/新机制药”等问题，输出疾病-靶点-药物-临床进展-机制趋势的一体化证据报告。适用于联合本地数据库适配代码与公开数据库 API（ChEMBL、ClinicalTrials、Search）进行多数据库查询、去重归一、创新性筛选与结构化报告生成的任务。

Expert-in-the-loop retrosynthetic planning workflow. Use when you need to break down complex target molecules into available starting materials, design synthetic routes, or collaborate with a human chemist to refine a proposed synthesis pathway.

Predict comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties for drug candidate molecules using GraphMVP ensemble models. Use this skill when: (1) Predicting blood-brain barrier penetration, (2) Assessing side effect profiles, (3) Estimating Caco-2 permeability, half-life, or LD50 toxicity, (4) Evaluating drug-likeness and safety of molecules.

Antibody design using IgGM model. Use this skill when: (1) Epitope-conditioned de novo antibody design, (2) Antibody affinity maturation, (3) Using antigen PDB structure and epitope information. For binding affinity evaluation, use prodigy.

Antibody-related structure prediction using tfold model. Use this skill when: (1) Predict antibody and nanobody structure of a given sequence, (2) Predict antigen-antibody complex structure of given sequences, (3) Using local GPU resources. For binding affinity evaluation, use prodigy.

Protein complex binding affinity prediction. Use this skill when: (1) Predict the binding affinity score, (2) Using protein complex structure.

Search biomedical literature from PubMed and bioRxiv for research papers. Use this skill when: (1) Finding research papers on a specific topic or disease, (2) Retrieving recent preprints from bioRxiv, (3) Getting paper titles, abstracts, and metadata, (4) Literature review for drug discovery or biomedical research.

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets and metadata, (3) Training machine learning models on single-cell data, (4) Performing large-scale cross-dataset analyses.

Analyze drug candidate molecules for drug-likeness, ADMET properties, and safety profiles. Use this skill when: (1) Evaluating a molecule's potential as a drug candidate, (2) Checking drug-likeness scores (QED, Lipinski), (3) Predicting blood-brain barrier penetration, (4) Assessing side effects and ADMET properties, (5) Comparing multiple molecules for lead optimization.

Propose high-fitness and high-diversity mutants of the VP1 capsid protein of Adeno-Associated Virus (AAV) through multi-round iterative optimization.

Propose high-fluorescence and high-diversity mutants of Green Fluorescent Protein (GFP) through multi-round iterative optimization.

All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or ligands, (3) Want all-atom diffusion (not just backbone), (4) Require precise binding geometries, (5) Using YAML-based configuration. For structure validation, use boltz-2.

Query PubChem database for chemical structures, similar compounds, and bioactivity data. Use this skill when: (1) Converting drug name to molecular structure (SMILES, SDF), (2) Finding similar compounds for lead optimization, (3) Querying bioactivity data against protein targets, (4) Getting compounds active in specific assays.

Retrieve proteins with similar structures, sequences, or from the same family. Use this skill when: (1) Finding similar proteins or homologs, (2) Searching for proteins with similar 3D structure, (3) Performing sequence similarity search, (4) Discovering proteins in the same family.

Use this skill when a task involves Geneformer workflows, especially TranscriptomeTokenizer input preparation, tokenized `.dataset` generation, cell or gene classification with `Classifier`, embedding extraction with `EmbExtractor`, and in silico perturbation analysis with `InSilicoPerturber`.

Use this skill when a task involves the LangCell project for single-cell language-cell modeling, especially zero-shot cell type annotation, few-shot annotation, LangCell-CE finetuning, Geneformer-style tokenization, or preparing text descriptions for candidate cell identities and multimodal cell-text matching workflows.

Use this skill when a task involves the local scGPT project in /DATA/disk0/zhaosy/home/scGPT, especially scGPT preprocessing and binning, checkpoint vocabulary matching, cell embedding extraction, reference mapping, fine-tuning scGPT for integration or annotation, or using scGPT tutorials for GRN, perturbation, multiomics, and reference mapping workflows.

Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics deconvolution with DestVI.

Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type annotation.

Use this skill when a task involves the local SToFM project in /DATA/disk0/zhaosy/home/SToFM, especially preprocessing spatial transcriptomics data for SToFM, generating cell embeddings with the cell encoder plus SE(2) Transformer pipeline, handling spatial coordinates, or preparing SToFM embeddings for downstream region segmentation or cell type annotation.

Load spatial transcriptomics data from Visium, Xenium, MERFISH, Slide-seq, and other platforms using Squidpy and SpatialData. Use this skill when: (1) Loading Visium spatial transcriptomics data from Space Ranger output, (2) Loading Xenium single-cell resolution spatial data, (3) Loading MERFISH, CosMx, or other spatial platforms, (4) Converting between SpatialData and AnnData formats.

Structure prediction using Boltz-2, an open biomolecular structure predictor. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using local GPU resources. For protein complex binding affinity evaluation, use prodigy.

Analyze protein mutations by retrieving protein data, explaining mutation effects, predicting protein structure, and visualizing results. Use this skill when the user asks about protein mutations, wants to understand mutation effects, or needs to analyze genetic variants. Triggers on phrases like "analyze mutation", "explain mutation", "what does this mutation do", "protein variant analysis".