dnbaker

dashing

Fast and accurate genomic distances using HyperLogLog

sketch

C++ Implementations of sketch data structures with SIMD Parallelism, including Python bindings

bonsai

Bonsai: Fast, flexible taxonomic analysis and classification

dashing2

Dashing 2 is a fast toolkit for k-mer and minimizer encoding, sketching, comparison, and indexing.

minicore

Fast and memory-efficient clustering + coreset construction, including fast distance kernels for Bregman and f-divergences.

bioseq

Tokenizers and Machine Learning Models for biological sequence data

vec

Type-generic SIMD library for optimized generic code generation

aesctr

C++ implementation of AES-CTR PRNG using SIMD, based on Samuel Neves' Implementation

wmh

Weighted Minhash Code

fastiota

Fast std::iota for contiguous memory using SIMD operations

libsimdsampling

Data- and processor- parallelism for fast weighted sampling

fgc

libkl

Kernels for fast vectorized KL divergence + related

dashing2-experiments

libtorch-kseq-demo

Demo using libtorch and one-hot encoding for fastx files

dashing2-binaries

Binaries for releases for Dashing2

minicore-experiments

Experiments for minicore: fast scRNA-seq clustering with various distances

scavenger

Rust spatial/single-cell genomics

tilt

Biased dataloaders for PyTorch and related utilities

bioconda-recipes

Conda recipes for the bioconda channel.

dashing-binaries

distmat

2-dimensional distance matrix for holding distances of arbitrary types.

dnbaker

einops

Simplistic API for deep learning tensor operations

FFHT

Fast Fast Hadamard Transform

megadepth

BigWig and BAM utilities

minilsh

Python bindings for Locality-Sensitive Hashers, built on the minicore C++ library.

pathml

Tools for computational pathology

ProtTrans

ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.

rust-tokenizers

Rust-tokenizer offers high-performance tokenizers for modern language models, including WordPiece, Byte-Pair Encoding (BPE) and Unigram (SentencePiece) models