REINVENT4 molecular design as MCP tools — sampling, transfer learning, and staged RL with interactive scoring-function design — plus skills for validation, job status, analysis, and custom scoring components. Requires a locally built GPU Docker container (see README).
Plugin solitarius-mcp from marketplace solitarius in lcmd-epfl/Solitarius-mcp. Commands read from the repo's manifest — 1 month ago.
analyzeEvaluate and characterize a set of generated SMILES across multiple quality dimensions (physicochemical, druglikeness, scaffold diversity, structural alerts, similarity to reference). Use after sampling or RL to assess molecule quality.
custom-componentGenerate a custom scoring component plugin (comp_*.py) for REINVENT4 RL. Use when the user needs a scoring function not available as a built-in component.
job-statusCheck the status of a running or completed REINVENT4 job (TL or RL). Use when the user asks about job progress, status, or results.
rlRun reinforcement learning with REINVENT4 to optimize molecular properties via a scoring function. Use when the user wants to optimize, score, or run RL/staged learning for molecule design.
sampleGenerate molecules from a REINVENT4 prior model. Use when the user wants to sample, generate, or explore chemical space from a trained model.
transfer-learnFine-tune a REINVENT4 prior model on a focused SMILES dataset (transfer learning). Use when the user wants to train, fine-tune, or adapt a model to a specific chemical series.
validateValidate REINVENT4 input SMILES files and TOML configs before launching jobs. Use when the user wants to check, validate, or verify their inputs.
reinvent4connects to: ${SOLITARIUS_MCP_URL:-http://127.0.0.1:8081/sse}
Full Domino Data Lab platform support — workspaces, jobs, model deployment, experiment tracking, GenAI tracing, Spark/Ray/Dask, and app deployment for data science teams
26 skills · 4 commands · 3 agents · 1 MCP server
Evidence-backed BioPharma research workflows over Maven Bio's drug, trial, company, and deal knowledge graph. Skills for competitive pipelines, indication landscapes, asset profiles, deal and financing activity, and evidence synthesis grounded in FDA, SEC, clinical, and press sources. Requires a Maven Bio account.
16 skills · 1 agent · 1 MCP server
Query the KEGG bioinformatics database — pathways, genes, compounds, drugs, enzymes, diseases, reactions, and more via 34 read-only MCP tools. No API key required.
1 skill · 3 commands · 1 agent · 1 MCP server
Create narrated Mandarin math and science tutorial videos or interactive explainers from problem statements and images.
1 skill
Data Science Team — 10 agents: Cast, Feat, Fit, Score, Drift, Vect, Tune, Plot, Clean, Eval
Science-based learning exercises for deliberate skill development during AI-assisted coding
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.