agentleFS
NVIDIAKnown publisherNVIDIA/dgx-spark-playbooks/nvidia/station-healthcare-agent/assets/skills/molecular-viz/SKILL.md

molecular-viz

Skill1.5k starsChanged 2 months agoApache-2.0View on GitHub

Visualize drug-protein complexes using build_viewer.py, PubChem, and OpenFold3 NIM. Use when asked to show a molecular structure, drug target, or protein visualization.

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 48 mentionsNov 2026: 2 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the NVIDIA/dgx-spark-playbooks repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about NVIDIA/dgx-spark-playbooks

The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 50

Talked about on GitHub (50 times).

On GitHub · 50

45 more on GitHub

The file

Files
SKILL.md

Molecular Visualization

Generate 3D protein-ligand visualizations using the build_viewer.py script. The script handles the full pipeline:

  1. Drug SMILES -- looked up automatically from PubChem
  2. Protein target -- resolved from a built-in drug-target table (or pass --sequence manually)
  3. Structure prediction -- protein + drug sent to OpenFold3 NIM for co-structure prediction
  4. 3D viewer -- self-contained HTML with jQuery + 3Dmol.js inlined, saved to canvas

Usage

Simplest form (target auto-resolved):

python /sandbox/clinical-intelligence/scripts/build_viewer.py --drug metformin

With explicit sequence (for drugs not in the built-in table):

python /sandbox/clinical-intelligence/scripts/build_viewer.py --drug drugname --sequence AMINOACIDSEQ --title "Custom Title"

Options

FlagRequiredDescription
--drugYesDrug name for PubChem SMILES lookup (e.g. metformin)
--sequenceNoAmino acid sequence of protein target. Auto-resolved if omitted.
--titleNoCustom viewer title
--outputNoCustom output path (defaults to ~/.openclaw/canvas/{drug}_complex.html)
--openfold-hostNoOverride OpenFold3 host IP (defaults to 172.17.0.1)

Built-in drug targets

The script knows these drugs and auto-resolves their protein targets:

DrugTarget protein
metforminInsulin B-chain
atorvastatinHMG-CoA reductase
rosuvastatinHMG-CoA reductase
lisinoprilACE
enalaprilACE
losartanAngiotensin II receptor type 1
amlodipineL-type calcium channel Cav1.2
empagliflozinSGLT2
semaglutideGLP-1 receptor

For any drug in this table, just pass --drug and the script does the rest.

Drugs NOT in the table

If the drug is not listed, the script exits with an error and prints the list of known drugs. In that case, you need to provide --sequence explicitly. Tell the user the drug is not in the built-in table and that you need a protein target sequence to proceed.

Drugs that cannot be visualized

Biologics, enzyme mixtures, or complex formulations that PubChem cannot resolve to a single SMILES (e.g. pancrelipase, insulin glargine) will still get protein-only structure prediction -- the script handles this gracefully by predicting without a ligand.

Output

The script saves an HTML viewer to canvas. Link it in your response as a markdown hyperlink:

[View 3D structure](http://localhost:18789/__openclaw__/canvas/metformin_complex.html)

Confidence Scores

The viewer header displays OpenFold3 scores:

  • Confidence -- overall prediction confidence (higher = better)
  • pLDDT -- per-residue local confidence (0-100, >70 is good)
  • pTM -- predicted template modeling score (0-1)
  • ipTM -- interface predicted TM-score (complexes only, measures protein-ligand interface quality)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.