Python package for graph neural networks in chemistry and biology
- deep-learning
- graph-neural-networks
- dgl
- cheminformatics
89,073 visible repositories in the index
25–48 of 76 · Most stars
Python package for graph neural networks in chemistry and biology
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
A Go package for engineering organisms.
Generation of protein sequences and evolutionary alignments via discrete diffusion models
C++ library and cmdline tools for parsing and manipulating VCF files with python and zig bindings
OmegaFold Release Code
Generative biopolymer design with rich conditioning.
A tool for semi-automatic cell type classification
Official repository for the ProteinGym benchmarks
A Practical and Efficient NCBI Taxonomy Toolkit, also supports creating NCBI-style taxdump files for custom taxonomies like GTDB/ICTV
Sequential regulatory activity predictions with deep convolutional neural networks.
A dependency-free cross-platform swiss army knife for PDB files.
Benchmarking analysis of data integration tools
Open Frontier Biomolecular Intelligence
Native R and Python sample-deletion robustness for omics: candidate certificates, minimum deletion bounds, Bioconductor model refits and donor-level pseudobulk
Schema and generated objects for biolink data model and upper ontology
RNA-seq prediction with deep convolutional neural networks.
MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction (Bioinformatics)
Pan-Cancer Integrative Histology-Genomic Analysis via Multimodal Deep Learning - Cancer Cell
Haplotype-aware CNV analysis from single-cell RNA-seq, ATAC-seq, and multiome
scPerturb: A resource and a python/R tool for single-cell perturbation data
MOGONET (Multi-Omics Graph cOnvolutional NETworks) is a novel multi-omics data integrative analysis framework for classification tasks in biomedical applications.
Open source tumor evidence matching for sequencing labs and hospitals without molecular tumor boards. Research prototype; oncologist review required.
OpenBioLink is a resource and evaluation framework for evaluating link prediction models on heterogeneous biomedical graph data.