An Open Source Machine Learning Framework for Everyone

Accelerated BLAST compatible local sequence aligner.

python module to plot beautiful and highly customizable genome browser tracks

A Variant Call Format reader for Python.

Depth-weighted De-Mixing

Tools for making plots of genomic datasets in a genome-browser-like format

Hybridization probe design for targeted genomic sequencing of diverse and hypervariable viral taxa

Implementation of data dimensionality reduction algorithms SVD and CUR without using library functions.

A GPT-style large language model (LLM) with no positional embeddings (NoPE).

An autoscaling Bloom filter with ultra-low memory footprint for PHP

ncER dataset

Proximal Enrichment By Approximated Sampling

AmiGO is a dataset of high-quality samples for protein function prediction.

An ESM2 Transformer fine-tuned to predict protein function from amino acid sequences.

The CAFA 5 dataset with protein sequence GO term and taxonomy annotations.