← Latest products

I wrote a GPU-less billion-vector DB for molecule search (live demo)

CHEESE synthon-native molecular search. Input a SMILES string (or pick one molecule from the examples) and it returns up to 100k molecules closest in 3-D shape or electrostatic similarity – from 10+ billion scale databases — typically in under 5-10 s.

Visit cheese-new.deepmedchem.comexternal site

Reactions (1)

Similar products

by description similarity

  1. TuringDB

    github.com

    The fastest analytical in-memory graph database in C++

    Hacker News7 pts

  2. OctaneDB

    github.com

    Fast, Open-Source Vector Database for Python

    Hacker News33 pts

  3. ParqDB

    search.parqdb.io

    Vector search in the browser from Parquet over HTTP"

    Hacker News26 pts

  4. Fast Thermodynamic Calculations in Python

    dlr-institute-of-future-fuels.github.io

    I built gaspype, a Python library for fast thermodynamic calculations, like equilibrium reactions.

    Hacker News59 pts

  5. NanoVector

    github.com

    A 120KB zero-dependency vector search engine in C and SIMD

    Hacker News10 pts