-
Oxford Nanopore Technologies
- Oxford, UK
Lists (11)
Sort Name ascending (A-Z)
antibodies
Antibody structure prediction related goodiesbioinformatics
A competitor for Biopython?comp-chem
epidemiology
mac-tools
ml-engineering
Tools for ML engineeringobsidian
protein generative models
Stars
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
Hydra is a framework for elegantly configuring complex applications
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
The machine learning toolkit for time series analysis in Python
Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍
Code for the ProteinMPNN paper
Generation of protein sequences and evolutionary alignments via discrete diffusion models
Diffusion-based all-atom protein generative model.
Lightweight, super fast C/C++ (& Python) library for sequence alignment using edit (Levenshtein) distance.
Bilingual Language Model for Protein Sequence and Structure
GDTW is a Python/C++ library that performs dynamic time warping. It is based on a paper by Dave Deriso and Stephen Boyd.
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Scripts. config, and snakefiles for seasonal-flu nextstrain builds
✌🏻 Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures (NeurIPS 2022)
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Data science interview questions and answers
Convert Machine Learning Code Between Frameworks
Fitness landscape exploration sandbox for biological sequence design.
Materials for the Hugging Face Diffusion Models Course
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.