A structure-based, alignment-free embedding approach for proteins. Can be used as input to machine learning algorithms.

A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).

Get protein embeddings from protein sequences

Python client for the Open Targets REST API at targetvalidation.org

A new approach for representing biological sequences

Python dependency management and packaging made easy.

Assessment of the quality of protein folds and protein-protein interaction interfaces using statistical potentials

Pipeline to extract protein interfaces from Interactome3d structures

A script that computationally designs a vaccine

Predict Host Pathogen Protein Protein Interactions using 3D Fully Convolutional Neural Networks

A fast python class for reading 2-bit files (used by UCSC genome browser)

C-library for calculating Solvent Accessible Surface Areas

A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)

An implementation of Knowledge-aware attention networks (KAN) for protein-protein extraction task

dataset for MutaBindv2.0

matter.farm, 7x7 beijing project w/ Sean Raspet

intro to machine learning - reverse engineering phenomena