PULCHRA Protein Structure Rebuild

SkillDev tools

Rebuilds incomplete protein PDB structures with PULCHRA for downstream docking and simulation preparation.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the PULCHRA Protein Structure Rebuild skill

What this skill tells your AI

The instructions your AI receives, as published by internscience/molclaw in skills/L1_tools/molclaw-pulchura-rebuild/SKILL.md and read by ahel’s review.

Note:

  • Local files are not directly accessible by the server. Please upload them to the server using molclaw-file-transfer before execution.
  • For PDB file inputs, it is recommended to preprocess them using molclaw-pdbfixer before execution.
  • Please refer to skill molclaw-scp-server to complete tool invocation.

Usage

1. Protein PDB Rebuild with PULCHRA

The description of tool pulchura_rebuild.

Rebuilds incomplete protein PDB structures with PULCHRA for structure preparation workflows before docking or simulation.
Args:
    input_pdbs (str | List[str]): One input PDB path or a list of input PDB paths.
    mode (str): Rebuild mode in {'full','backbone','sidechain','hydrogen'}, default 'full'.
    optimize_hbond (bool): Enable hydrogen-bond optimization (-q), default False.
    detect_cis_pro (bool): Enable cis-proline detection (-p), default False.
    verbose (bool): Print verbose PULCHRA logs (-v), default False.
    preserve_coords (bool): Preserve original coordinates (-f), default False.
    dry_run (bool): Validate inputs and create run directory without executing rebuild, default False.
Return:
    status (str): 'success', 'partial_success', or 'error'.
    msg (str): Human-readable execution summary.
    output_dir (str): Run-specific directory under tool_result/pulchura_rebuild_result.
    mode (str): Effective rebuild mode used for this run.
    requested_input_count (int): Number of input files requested by caller.
    succeeded_count (int): Number of inputs rebuilt successfully.
    failed_count (int): Number of inputs that failed validation or rebuild.
    rebuilt_pdb_files (List[str]): Paths to rebuilt PDB files.
    failed_inputs (List[Dict[str, str]]): Per-input failure details with input_pdb and error.

How to use tool pulchura_rebuild :

response = await client.session.call_tool(
    "pulchura_rebuild",
    arguments={
        "input_pdbs": "/path/to/input.pdb",
        "mode": "full",
        "optimize_hbond": False,
        "detect_cis_pro": False,
        "verbose": False,
        "preserve_coords": False,
        "dry_run": False
    }
)
result = client.parse_result(response)
rebuilt_pdb_files = result["rebuilt_pdb_files"]

Example parameter sets
# 1) Main mode
{
    "input_pdbs": "/path/to/input.pdb",
    "mode": "full",
    "optimize_hbond": True,
    "detect_cis_pro": False,
    "verbose": False,
    "preserve_coords": False,
    "dry_run": False
}

# 2) Variant mode
{
    "input_pdbs": "relative/path/to/frame_0.pdb",
    "mode": "backbone",
    "optimize_hbond": False,
    "detect_cis_pro": False,
    "verbose": False,
    "preserve_coords": False,
    "dry_run": True
}

Signals

GitHub stars
33
Forks
3
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
molclaw-pulchura-rebuild
Source
github.com/internscience/molclaw