PyTorch

Ankhagemagician/Ankh

Ankh is a state-of-the-art protein language model for general-purpose protein modeling and engineering tasks.

MolTranskexinhuang12345/MolTrans

A transformer-based model for predicting drug-target interactions using substructural pattern mining and augmented transformer encoders.

torchaxgoogle/torchax

A PyTorch frontend for JAX that enables running PyTorch code on TPUs and provides seamless PyTorch-JAX interoperability.

Backpropbackprop-ai/backprop

A Python library that simplifies using, finetuning, and deploying state-of-the-art machine learning models for various AI tasks.

AtomAIpycroscopy/atomai

A PyTorch-based Python package for deep and machine learning analysis of microscopy data, designed for domain scientists.

CellSAMvanvalenlab/cellSAM

A foundation model for cell segmentation that achieves state-of-the-art performance across diverse cellular targets and imaging modalities.

Ultrackroyerlab/ultrack

A scalable cell tracking method for 2D, 3D, and multichannel timelapse recordings, robust under segmentation uncertainty.

Datasetanalysiscenter/dataset

A Python library for building lazy data processing and machine learning workflows that handle datasets larger than memory.

MSDAbupt-ai-cz/Meta-SelfLearning

A benchmark dataset and meta self-learning method for multi-source domain adaptation in scene text recognition.

e2calibuzh-rpg/e2calib

A tool for calibrating event cameras by converting event data to images and using standard image-based calibration toolboxes.

PyTorch Connectomicszudi-lin/pytorch_connectomics

A PyTorch-based segmentation toolbox for electron microscopy connectomics, enabling neural structure analysis in 3D volumes.

BeautyNetcms-flash/beauty-net

A simple, flexible, and extensible object-oriented template for PyTorch projects.

ChemMLhachmannlab/chemml

A Python machine learning and informatics suite for analyzing, mining, and modeling chemical and materials data.

MolGPTdevalab/molgpt

A transformer-based model for unconditional and conditional molecular generation using GPT architecture trained on chemical datasets.

MotionNetpxiangwu/MotionNet

A deep learning model for joint perception and motion prediction in autonomous driving using bird's eye view maps.

EDS_NLPaphp/edsnlp

A modular NLP framework for extracting information from French clinical notes, compatible with spaCy and PyTorch.

nn_builderp-christ/nn_builder

A Python library that builds neural networks with minimal boilerplate code for PyTorch and TensorFlow.

OpenBioLinkOpenBioLink/OpenBioLink

A resource and evaluation framework for benchmarking link prediction models on large-scale, heterogeneous biomedical knowledge graphs.

scPRINTcantinilab/scPRINT

A large transformer foundation model for single-cell RNA sequencing data analysis, including gene network inference, denoising, and cell annotation.

ChatDrugchao1224/ChatDrug

A conversational AI framework for editing small molecules, peptides, and proteins using retrieval-augmented generation and domain feedback.

TransformerCPIlifanchen-simm/transformerCPI

A deep learning model using transformer architecture to predict compound-protein interactions from molecular and protein sequences.

dbmdz BERT modelsdbmdz/berts

A collection of pre-trained BERT, DistilBERT, ELECTRA, GPT-2, and ConvBERT models for multiple languages, including German, Italian, Turkish, and historic texts.

open-solution-data-science-bowl-2018neptune-ml/open-solution-data-science-bowl-2018

Open-source implementation of the winning solution for the 2018 Data Science Bowl Kaggle competition using PyTorch and U-Net.

DrugBANpeizhenbai/DrugBAN

A deep bilinear attention network framework with adversarial domain adaptation for interpretable drug-target interaction prediction.

graph-2-textdiegma/graph-2-text

A PyTorch implementation combining Graph Convolutional Networks with OpenNMT-py for structured data to text generation.

PyTorch Geometric Signed DirectedSherylHYX/pytorch_geometric_signed_directed

A PyTorch Geometric extension library for signed and directed graph neural networks, embedding, and clustering methods.

neural-dreamProGamerGov/neural-dream

A PyTorch implementation of the DeepDream algorithm for generating psychedelic, dream-like images from neural network activations.

Legend of ElyaScottcjn/legend-of-elya-n64

A training pipeline to generate four distinct AI NPC personality weight bundles for a Zelda-style N64 game, enabling byte-level transformer inference on the console's CPU.

Spotiflowweigertlab/spotiflow

A deep learning-based, threshold-agnostic, subpixel-accurate 2D and 3D spot detection method for fluorescence microscopy and spatial transcriptomics.

Sinabssynsense/sinabs

A PyTorch-based deep learning library for building and training spiking convolutional neural networks with hardware deployment support.

GeneCompassxCompass-AI/GeneCompass

A knowledge-informed cross-species foundation model pre-trained on over 120 million human and mouse single-cell transcriptomes to decipher universal gene regulatory mechanisms.

jax-resnetn2cholas/jax-resnet

Flax implementations and pretrained checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX.

SeiFunctionLab/sei-framework

A deep learning framework for predicting chromatin profiles and sequence regulatory activities from DNA sequences and variants.

GitHub repositorypeiyunh/WYSIWYG

A 3D object detection method that exploits visibility information from LiDAR point clouds to improve accuracy.

CellPLMOmicsML/CellPLM

A pre-trained language model for single-cell RNA sequencing data that encodes cell-cell relations and accelerates inference for downstream tasks.

PassGPTjavirandor/passgpt

A GPT-2 model trained from scratch on password leaks for password modeling, generation, and strength estimation.