---
title: "DeepChem - Air Market"
description: "When you want to predict something about a molecule, half the work is deciding how to represent it. This gives you many featurizers and ready-made datasets so you can try options quickly, with tradit…"
canonical: "https://airmarket.ai/app/deepchem"
---

[Air Market](/) / [Data & Analytics](/category/data) / DeepChem

Skill by [K-Dense](/@k-dense-ai)

# DeepChem

Try many molecular representations before committing to one

## What this does

When you want to predict something about a molecule, half the work is deciding how to represent it. This gives you many featurizers and ready-made datasets so you can try options quickly, with traditional models or graph neural networks. Reach for it for fast experiments; other tools fit better for graph-first PyTorch work or for benchmark data alone.

### Top 3 things it does for you

- Predict a property like toxicity or ADMET
- Compare different ways of featurizing molecules
- Benchmark against MoleculeNet datasets

## Information

**DeepChem at a glance**

|  |  |
| --- | --- |
| Kind | Skill |
| Publisher | [K-Dense](/@k-dense-ai) |
| Category | [Data & Analytics](/category/data) |
| Works with | Agent Skills - an open standard supported by 40+ agents |
| Version | 1.4 |
| Size | 74 KB |
| Licence | MIT |
| Repository | [k-dense-ai/scientific-agent-skills](https://github.com/k-dense-ai/scientific-agent-skills/tree/0e451065e3308e9902d8229e17d2028359b2bbaf/skills/deepchem) |
| GitHub stars | 34,239 (as of Nov 2026) |

## Security report

**Verified.** AIR scanned this exact version of DeepChem and flagged nothing. AIR's verdict: **safe**.

**What DeepChem's check was run against**

|  |  |
| --- | --- |
| Commit | 0e451065e3308e9902d8229e17d2028359b2bbaf |
| Content hash | f9bbe30d8154773f99d5deff77194eed93bf7792a48c636f1cecfc4f7a57782f |
| Files read | [Browse the files at this exact commit](https://github.com/k-dense-ai/scientific-agent-skills/blob/0e451065e3308e9902d8229e17d2028359b2bbaf/skills/deepchem/SKILL.md) |

A scan is named by the exact content it read, not by a version number. A different version is a different artifact, and nothing here applies to a version AIR has not scanned.

[Read the full security report for DeepChem](/security/deepchem)

## About DeepChem

This covers molecular machine learning with diverse featurizers and pre-built datasets. It suits property prediction such as ADMET and toxicity, using either traditional machine learning or graph neural networks, and it brings MoleculeNet benchmarks along with it.

It is aimed at quick experiments: extensive featurization options, diverse molecular representations, and pre-trained models to start from. For graph-first PyTorch workflows, use torchdrug; for benchmark datasets on their own, use pytdc.

## What's inside

- SKILL.md - instructions
- references/api_reference.md - reference
- references/core_capabilities.md - reference
- references/typical_workflows.md - reference
- references/workflows.md - reference
- scripts/graph_neural_network.py - script
- scripts/predict_solubility.py - script
- scripts/transfer_learning.py - script

## Questions

### Is DeepChem safe to install?

AIR scanned this exact version of DeepChem and flagged nothing. AIR's verdict: safe. The verdict is named by the content that was read, at commit 0e451065e330, so it cannot drift onto a version nobody scanned. The full report is at https://airmarket.ai/security/deepchem.

### How do I install DeepChem?

Open https://airmarket.ai/app/deepchem on Air Market and use the install action: Air Market hands Claude a prompt naming this exact skill, and Claude sets it up. Source, pinned to the exact commit this listing describes: https://github.com/k-dense-ai/scientific-agent-skills/tree/0e451065e3308e9902d8229e17d2028359b2bbaf/skills/deepchem. Install from that link, not the branch.

## Related on Air Market

- [More Data & Analytics listings](/category/data)
- [Everything by K-Dense](/@k-dense-ai)

---

Canonical URL: <https://airmarket.ai/app/deepchem>