CognitionBioChem
A structural pharmacology workbench for cognition-related CNS targets, built so that a displayed number must trace to a computation. Runs Boltz-2 locally for structure prediction, validates chemistry with RDKit, enforces a provenance record on every value, and reports eight studies pre-registered under content hashes before any data was seen. Its headline result is negative: designed peptides did not separate from composition-matched shuffles of their own amino acids.
Topics
Details
- License:
- Apache-2.0
- Maturity:
- Mature
- Cost:
- Free of charge
- Tool Type:
- command-line tool, web application
- Operating Systems:
- Linux, Mac
- Programming Languages:
- JavaScript, Python
- Added:
- 8/20/2026
- Last Updated:
- 8/20/2026
Operations
Data Inputs & Outputs
Protein structure prediction
Inputs
Outputs
Validation
Inputs
Outputs
Structure analysis
Inputs
Outputs
Documentation
Terms of use
https://github.com/hopejsh/CognitionBioChem/blob/main/NOTICEThe `license` field above is Apache-2.0, which covers this project's code, but the repository is not single-licensed. It redistributes third-party scientific data that keeps its own terms: CC BY 4.0 (UniProt, AlphaFold DB), CC BY-SA 3.0 (ChEMBL-derived files -- SHARE-ALIKE, so reuse carries an obligation onward), CC0 1.0 (RCSB depositions) and MIT (Boltz-2 model outputs). NOTICE lists which files fall under which.
Citation instructions
https://github.com/hopejsh/CognitionBioChem/blob/main/docs/REGISTRATION.mdDownloads
- Source codeVersion: 1.0.0https://github.com/hopejsh/CognitionBioChem/archive/refs/tags/v1.0.0.tar.gz