GeezerVison

Popular repositories Loading

1. USearchMolecules USearchMolecules Public

   Large Multi-Modal Chem-Informatics dataset of 7B+ molecules with fingerprints and 3D conformers for drug discovery

   Python 112 11

2. AffineGaps AffineGaps Public

   Exact biosequence alignment and folding on GPUs — Needleman-Wunsch, Smith-Waterman, Levenshtein, Zuker, and Sankoff with Gotoh adjustments and traceback

   Mojo 35 1

3. FasterFASTA FasterFASTA Public

   Faster FASTA and FASTQ file processing command line tool - parsing, sorting, deduplication, transliteration, filter, and stats

   Rust 32 2

4. SmallField SmallField Public

   Small-molecule 3D conformers generation from SMILES on GPU — one CUDA warp per molecule — 100,000+ conformers/s on 8x GPUs

   C++ 5 1

5. USearchWiki USearchWiki Public

   Heavily enriched Wikipedia dataset, extending the HuggingFace's FineWiki with late-interaction (ColBERT-style) and auto-regressive (LLM-style) embeddings and additional metadata

   Python