pdb-database

这段内容是审核时保存的快照。外部来源才是完整且最新的版本。

---
name: pdb-database
description: >
  Use when you want to search for or download experimentally-determined 3D
  structures for biomolecules (proteins, nucleic acids, bound ligands).
  Supports searching by sequence similarity, structure similarity, chemical
  and other attributes. Also use to get metadata about biomolecular structure
  experiments.
---

# RCSB Protein Data Bank skill

## Prerequisites

1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
    `uv` is installed and on PATH.
2.  **User Notification**: If .licenses/pdb_database_LICENSE.txt does not
    already exist in the workspace root directory then (1) prominently notify
    the user to check the terms at https://www.rcsb.org/pages/usage-policy, then
    (2) create the file recording the notification text and timestamp.

## Core Rules

-   **Always prefer to use the provided scripts**. Only as a last resort use
    `curl`, `urllib`, raw HTTP requests, or any other method to access PDB APIs.
    The scripts automatically enforce required rate limits.
-   **Always redirect output to a file**. Parse output with e.g. `jq`, `grep`,
    or a short Python snippet. Do NOT print large API responses to stdout to
    avoid truncation.
-   **Notification**: If this skill is used, ensure this is mentioned in the
    output.
-   **Explain your queries** On completing a task that used PDB JSON/GraphQL
    queries, explain in clear language what your query did so the user can
    correct any bad assumptions.

## Attribute-based search workflow

1.  **Fetch the relevant schema** to discover searchable attribute names. For
    structure attributes: `uv run scripts/fetch_schema.py --api search_structure
    --output schema_structure.txt` For chemical attributes: `uv run
    scripts/fetch_schema.py --api search_chemical --output schema_chemical.txt`

2.  **Grep the schema** to find relevant attributes. Grep one keyword at a time
    and examine many lines — there are lots of similar attributes and you must
    choose the **best match** for the user's intent.

3.  **Compose and run a JSON search query** using the discovered attributes: `uv
    run scripts/search_pdb.py --query '<JSON>' --return_type <RETURN_TYPE>
    --output results.json` Pass the `--count_only` flag to get just the number
    of matching entries.

### For step 2: some basic PDB concepts (helpful for attribute choice)

-   **Entity**: A unique molecule found in a structure.
-   **Instance / Chain**: A particular copy of an entity. E.g. if a structure
    contains two protein chains with the same sequence, they are the same entity
    but different instances / chains.
-   **Assembly**: A biologically relevant collection of instances / chains. This
    may be the same as the deposited structure, a subset, or multiple copies.
-   **Label vs Auth**: Polymer instances get letter labels ("A", "B", "AA") and
    their monomers are numbered. There are author-assigned ("auth") and
    PDB-internal ("label") schemes. The label scheme is more consistent and is
    always used in scripts and APIs. However, users and papers may refer to the
    author scheme (clarify which scheme is being used if necessary).
-   **Chemical component**: A small molecule / monomer, with an ID matching
    `[A-Z]{1,3}`
-   **Primary citation**: The main publication about a structure. Prefer
    `primary_citation` attributes over `citation` attributes.
-   **Resolution**: Frequently used measure of structure quality (lower is
    better). Usually prefer `rcsb_entry_info.resolution_combined`, which
    accounts for different experimental methods.

### For step 3: Example queries

```bash
# Non-human proteins published in Nature, newest first
uv run scripts/search_pdb.py --query '{ "type": "group", "logical_operator": "and", "nodes": [ { "type": "terminal", "service": "text", "parameters": { "operator": "exact_match", "negation": true, "value": "Homo sapiens", "attribute": "rcsb_entity_source_organism.taxonomy_lineage.na