Skill UI

Access RCSB PDB to search biomolecular structures via text, sequence, or geometry queries, download coordinate files in PDB/mmCIF/Binary formats, retrieve metadata, and batch-process entries for drug discovery, protein engineering, and structural biology pipelines.

Query the STRING REST API to retrieve protein-protein interaction networks, map identifiers, visualize evidence-weighted edges, and run GO/KEGG/Pfam enrichment for systems biology analysis.

TorchDrug is a PyTorch-native toolbox for building graph neural networks tailored to molecules, proteins, and biomedical knowledge graphs, covering property prediction, generation, retrosynthesis, and knowledge graph reasoning with curated datasets and models.

Direct REST API access to UniProt for searching proteins, fetching FASTA sequences, mapping identifiers, selecting annotations, and streaming large datasets within Python workflows.

Query InterPro for protein family, domain, and GO annotations via a REST API with Python helpers, enabling function prediction, domain architecture mapping, and evolutionary classification insights for proteomic workflows.

Run OpenMM-powered molecular dynamics simulations and MDAnalysis trajectory workflows to build protein or small-molecule systems, minimize energy, equilibrate conditions, and characterize RMSD/RMSF, contacts, and free-energy surfaces for structural biology or drug studies.

A comprehensive toolkit for reconstructing and analyzing the evolutionary history of biological sequences (genes, proteins, genomes). The standard workflow includes multiple sequence alignment using MAFFT, robust maximum likelihood tree inference with IQ-TREE 2 and FastTree, and advanced visualization/manipulation using ETE3. This skill is essential for studies in viral phylodynamics, microbial genomics, protein family evolution, and molecular clock dating.

This skill provides comprehensive functionality for querying, comparing, and calculating nutritional data from a structured food database. Users can perform precise searches by food name or nutritional criteria (e.g., high protein, low GI). It supports calculating total nutrient intake based on specific portions, suggesting foods for various health conditions (like diabetes or high blood pressure), and performing detailed comparative analysis between multiple food items.

Provides direct REST API access to UniProt, the premier resource for protein sequence and functional information. This skill enables users to search proteins by name, gene, or accession number, retrieve sequences in FASTA format, perform cross-database ID mapping (e.g., Ensembl, RefSeq), and analyze functional annotations (GO terms) for building comprehensive bioinformatics pipelines.

Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons, predict O-glycosylation hotspots, and access curated glycoengineering tools for antibody optimization and vaccine design.

Run and analyze molecular dynamics simulations using OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, perform energy minimization, NVT equilibration, production MD, and analyze trajectories including RMSD, RMSF, contact maps, and free energy surfaces.

Python bindings to OpenMS for computational mass spectrometry. Analyze proteomics and metabolomics LC-MS/MS data: feature detection, peptide and protein identification, label-free and isobaric quantification, adduct and accurate-mass annotation, plus ready-to-run workflow scripts.