← Plugin catalog
Education & Research

DeepMedChem

Deep MedChem v0.1.1

Molecular similarity search

Create a free account to save this plugin.

Competitor profile

Developer declarations; not independently tested. Listing last checked Nov 4, 2026. Package observed Nov 3, 2026.

Declared capabilities

  • Read

Declared limitations

  • A molecule name alone must not cause an invented structure
  • Unsupported property and price constraints
  • Requests beyond the guest limit

Not specified in the available declarations: pricing & account requirements.

Onboarding example

Find 20 molecules similar to aspirin, SMILES CC(=O)Oc1ccccc1C(=O)O, in Enamine REAL.

View package source →

Description

From the marketplace listing

Search public make-on-demand chemical spaces, such as Enamine REAL, for purchasable molecules similar to a structure you supply as SMILES. Choose fingerprint (Morgan/Tanimoto), 3D shape or electrostatic (ESP) similarity. Results appear as an interactive structure grid with scores, list prices and a CSV export. Searches run one SMILES against one database and return up to 20 hits. Guest access needs no account. Scores describe structural similarity, not biological activity or safety, and results are a bounded shortlist rather than every match.

Language: English · Automatically detected from descriptions.

Changes

No changes recorded yet. Follow this plugin to keep track of future changes.

First seen Oct 28, 2026. Last seen Nov 4, 2026.

Keywords

Files & skills

File archives

Plugin package5 files · 66.8 KBBrowse files →
Skill instructions
chemical-space-search2.67 KB

View saved version →

---
name: chemical-space-search
description: Search public DeepMedChem chemical spaces for molecules similar to a supplied structure, and explain the scope of the results.
---
# Chemical space search

Use the DeepMedChem MCP tools for catalog discovery and molecular similarity search.

1. Call catalog for current database IDs, pricing and guest limits.
2. Use one verified SMILES per search. If only a name is supplied, resolve it using a reliable source available in the client, or ask for SMILES. Never invent a structure.
3. Choose morgan for fingerprint/Tanimoto similarity, shape for shape cosine, or esp for electrostatic cosine. Search one database at a time, at most 20 hits.
4. Preserve product IDs, returned vendor catalog IDs, SMILES, scores, metric, database and release. Platform product IDs are API identities; an internal hash is not a vendor catalog ID. Report missing prices as unavailable; do not invent currency, vendor contacts or availability.
5. In hosts that support MCP Apps, similarity_search renders its own interactive grid of the returned structures (with scores, prices, CSV export and a link to the vendor's general catalogue page). Do not draw, generate or fetch molecule pictures by other means, and do not retype hits into a table when the grid is shown: markdown corrupts stereo SMILES such as [C@@H]. To show an earlier result again, call render_results with its result_id.
6. Explain that hits are a bounded shortlist, not all matches, a global optimum or proof of biological activity. Use the returned links.cheese URL for the search; do not replace it with a homepage or reconstruct it. A job= link opens saved results without another search; an older run=0 link only prefills the form.
7. The grid can download its displayed hits as CSV. The guest MCP does not support SDF or other file exports, substructure constraints, property/price filters, name resolution, property calculations, UMAP, or procurement contacts. Explain missing capabilities before searching; do not substitute unconstrained similarity for requested constraints. Client-side analysis is allowed only with an available execution tool, and must be labelled as analysis of returned hits.
8. Ask for clarification when a chemical constraint is ambiguous. Do not make repeated searches to bypass guest limits. Run searches one at a time, never in parallel: guest capacity is shared and parallel calls return a busy error. On a busy error, wait briefly and retry that one search once; on repeated capacity/timeout errors, explain the failure and avoid retry loops.

For broader authenticated workflows, direct the user to https://cheese.deepmedchem.com and the DeepMedChem Python SDK. Never ask users to paste API keys into chat.

Release notes

Initial directory submission of DeepMedChem for ChatGPT: guest molecular similarity search using Morgan, shape and ESP methods, with a results grid, CSV export and saved CHEESE links. Package 0.1.1 corrects the support URL and category and includes five positive and three negative review cases.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package license
MIT
Package author
Deep MedChem
Keywords
See keywords
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Read

Package observed Nov 3, 2026.

Technical details
First seen
Oct 28, 2026 · 12:00 UTC
Last seen
Nov 4, 2026 · 06:00 UTC
Collection status
Collected

plugin_asdk_app_6ace45caacf0819194fd9a0a63e74873

Download plugin data (JSON)