# Drug Bioactivity Assay

> Fetch biological assays and target proteins a chemical has been tested against via PubChem.

- **Type:** Skill
- **Install:** `agentstack add skill-learningmatter-mit-atomisticskills-drug-bioactivity-assay`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [learningmatter-mit](https://agentstack.voostack.com/s/learningmatter-mit)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [learningmatter-mit](https://github.com/learningmatter-mit)
- **Source:** https://github.com/learningmatter-mit/AtomisticSkills/tree/main/.agents/skills/drug-bioactivity-assay
- **Website:** https://arxiv.org/abs/2605.24002

## Install

```sh
agentstack add skill-learningmatter-mit-atomisticskills-drug-bioactivity-assay
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Bioactivity and Assay Data Retrieval

## Goal
To programmatically retrieve the testing history of a specific chemical compound against biological targets using PubChem's Assay Summary endpoint. This skill allows filtering for "Active" outcomes, providing assay IDs (AIDs), target GeneIDs, and micromolar activity values to assess a compound's promiscuity or target specificity.

## Instructions

### 1. Extract All Assays
Retrieve all assays for a given compound (CID), regardless of outcome:

```bash
# Env: base-agent
python .agents/skills/drug-bioactivity-assay/scripts/get_assays.py \
  --cid 2244 \
  --limit 50 \
  --outdir research/aspirin_assays \
  --output aspirin_all_assays.json
```

### 2. Extract Only 'Active' Results
Use the `--active_only` flag to strictly return assays where the compound was marked as "Active" or showed positive binding/inhibition.

```bash
# Env: base-agent
python .agents/skills/drug-bioactivity-assay/scripts/get_assays.py \
  --cid 5291 \
  --active_only \
  --limit 50 \
  --outdir research/imatinib_assays \
  --output imatinib_active_assays.json
```

**Parameters**:
* `--cid`: PubChem CID of the target molecule (e.g., 5291 for Imatinib).
* `--outdir`: Directory to save the resulting JSON file.
* `--active_only`: (Optional) Flag to strictly filter results to assays where the test outcome was "Active".
* `--limit`: (Optional) Maximum number of assays to retrieve (default: 1000) to keep JSON sizes manageable.
* `--output`: (Optional) Output filename (default: `assay_summary.json`).

## Examples

We can test extracting known active targets for the cancer drug Imatinib (CID: 5291).

```bash
# Env: base-agent
python .agents/skills/drug-bioactivity-assay/scripts/get_assays.py \
  --cid 5291 \
  --active_only \
  --limit 20 \
  --outdir .agents/skills/drug-bioactivity-assay/examples/imatinib \
  --output assays_imatinib_active.json
```

## Constraints
- **Assay Availability**: Compounds with no biological testing history in PubChem will return 0 results.
- **Reporting Variations**: High-throughput screening (HTS) assay results often lack explicit target GeneIDs or quantitative Activity Values compared to confirmatory literature assays. The script retrieves whatever is available natively in the column.
- **Network Limits**: PubChem can sporadically drop connections when rendering very large assay summaries. The script automatically handles connection drops and `HTTP 503` blocking via exponential backoff.

---
---

**Author:** Bowen Deng
**Contact:** [GitHub @learningmatter-mit](https://github.com/learningmatter-mit)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [learningmatter-mit](https://github.com/learningmatter-mit)
- **Source:** [learningmatter-mit/AtomisticSkills](https://github.com/learningmatter-mit/AtomisticSkills)
- **License:** MIT
- **Homepage:** https://arxiv.org/abs/2605.24002

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-learningmatter-mit-atomisticskills-drug-bioactivity-assay
- Seller: https://agentstack.voostack.com/s/learningmatter-mit
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.