Skip to content

struct-os DomainOS

Status: Scaffold (routing wired, skills pending)
Engine: struct-os
Domain: Protein structure (AlphaFold, RosettaFold, docking, molecular dynamics)

Protein-structure DomainOS: structure prediction (AlphaFold / RosettaFold), docking, molecular dynamics, and binding-pocket analysis. Empty-shell scaffold -- routing is wired with status=scaffold and degrades to the pubmed + chembl MCP fallback until skills are built.

Field Value
Product struct-os
Engine id struct-os
Intent key struct_os
Repository Hordago-Labs/struct-os
Plugin struct-os
Maturity (registry) Scaffold (routing wired, skills pending)

Overview

Protein-structure DomainOS: structure prediction (AlphaFold / RosettaFold), docking, molecular dynamics, and binding-pocket analysis. Empty-shell scaffold -- routing is wired with status=scaffold and degrades to the pubmed + chembl MCP fallback until skills are built.

Scientific approach

struct-os structures every run as 5 phases. Gates marked HITL require an explicit human-in-the-loop approval before the run advances.

# Phase Gate HITL
1 Sequence Prep Prepare and validate input sequence(s). No
2 Structure Prediction Predict structure (AlphaFold/RosettaFold). No
3 Docking Dock ligands / partners. No
4 Molecular Dynamics Run MD refinement. No
5 Binding-Pocket Analysis Characterize binding pockets. Yes

Capabilities & evidence objects

Domain tools / skills

  • alphafold
  • rosettafold
  • docking
  • molecular-dynamics

Evidence objects

Object Role Consumer
result.json planned co-writer

Canonical artifacts (5-artifact contract)

Planned

The 5-artifact contract below is the target shape. Canonical-artifact emission is tracked as inherited debt (Wave 3C) and is not yet guaranteed.

Artifact Description
result.json Structured primary result payload for the domain run.
report.md Human-readable narrative summary of the analysis.
provenance.json Tool versions, reference data, and algorithm lineage for reproducibility.
gate_status.json Per-phase gate pass/fail decisions.
session_summary.json Session metadata for replay and audit.

Standalone quickstart

Zero platform dependency

This quickstart runs the DomainOS standalone. The Hordago platform is not required; platform composition is opt-in (see Composition below).

  1. Install the standalone struct-os plugin (Hordago-Labs/struct-os) -- no Hordago platform required.
  2. Invoke the domain skill with a struct-os intent (see the intent keywords below).
  3. Review the emitted artifacts under the run's output directory.

Intent keywords (route to this engine):

protein structure \bprotein structure\b alphafold docking molecular dynamics rosettafold protein folding structural prediction binding pocket homology model

Worked example

AlphaFold structure prediction (planned surface)

A user asks to predict a protein structure and identify a binding pocket. The planned surface prepares the sequence, predicts structure, docks a ligand, and refines with MD. Until skills land, requests degrade to the pubmed + chembl MCP fallback.

Validation & benchmarks

Benchmarks

  • Planned: CASP-style TM-score / lDDT evaluation

Reproducibility. Planned: provenance.json will pin model weights and MSA database version.

Reference

MCP fallback servers (used when the plugin is unavailable): pubmed, chembl

Source documents

  • Scaffold-domains ledger (struct-os): references/scaffold-domains.md

Composition

Platform opt-in

struct-os runs standalone. When composed under the Hordago platform it gains cross-domain routing, the Shared Compiler gate, and evidence-audit provenance enforcement. Platform composition is opt-in; the quickstart above has zero platform dependency.

Cross-domain dependencies

Engine Relationship
aiDevops Consumes protein-embedding models produced by MLos.