Find open-source science resources
A directory of tools, AI models, datasets, and research resources for biotech, bioinformatics, and other scientific fields. Aggregated from curated GitHub awesome-lists, HuggingFace, bio.tools, Bioconductor, and more.
Filters
Health
Domain
Language(1)
License
Source
Type(1)
1,529 of 9,874 resources
Showing 1,501–1,529
Graph convolutional networks for drug response prediction.
Spatially resolved single-cell deconvolution of bulk RNA-seq using Bulk2Space.
a Customized Proteogenomic Workflow for Neoantigen Prediction and Selection | ProGeo-neo requires a Linux operation system (centos6) with Python (V2.7) , Perl and Java installed
A Unifying Toolbox for Quantification of Neuronal Anatomy. This repository hosts the scripts that were used to assemble the figures of the SNT publication. The ImageJ framework for quantification of neuronal anatomy. These scripts are intended to run from a Fiji installation subscribed to the Neuroanatomy update site, as detailed in the SNT documentation. Scripts relying on sciview/Cx3D functionality, also require the optional subscription to the SciView-Unstable update site. Since data is frequently downloaded from external servers, an internet connection is required. SNT is ImageJ's framework for semi-automated tracing, visualization, quantitative analyses and modeling of neuronal morphology.
A Python package for mass spectrometry data processing and visualization | Python package for efficient MS/MS spectrum processing and visualization | spectrum_utils is a Python package for efficient MS/MS spectrum processing and visualization
Unsupervised Topological Alignment for Single-Cell Multi-Omics Integration. UnionCom software is available on the Python package index (PyPI), latest version 0.2.1.
Command tool for metagenomic binning with semi-supervised deep learning using information from reference genomes.
DeepPhospho is a tool to accelerate DIA phosphoproteome profiling by Deep Learning. It is used for the prediction of fragment ion intensity and retention time for phosphopeptides. DeepPhospho is a hybrid deep neural network combining LSTM and transformer modules and it is specifically developed for accurate prediction of fragment ion intensity and indexed retention time (iRT) for any given phosphopeptide.
DeepCDR is a hybrid graph convolutional network for cancer drug response prediction. It takes both multi-omics data of cancer cell lines and drug structure as inputs and predicts the drug sensitivity (binary or contineous IC50 value). DeepCDR is a hybrid graph convolutional network for cancer drug response prediction. It takes both multi-omics data of cancer cell lines and drug structure as inputs and predicts the drug sensitivity (binary or contineous IC50 value). This work has been accepted to ECCB2020 and was also published in the journal Bioinformatics.
Cobolt is a method developed for modeling multi-omic single-cell sequencing datasets. It provides an integrated analysis of multi-omic data by learning a latent representation shared by the different data modalities. Cobolt jointly models these multiple modalities via a novel application of Multimodal Variational Autoencoder to a hierarchical generative model. It uses a probablity model that is robust to sparse counts and high numbers of features, therefore works for omics such as chromatin accessibility or methylation status.
a deep generative model for unsupervised removal of background noise from scRNA-seq datasets. CellBender is a software package for eliminating technical artifacts from high-throughput single-cell RNA sequencing (scRNA-seq) data. Welcome to CellBender’s documentation! — CellBender documentation. Free document hosting provided by Read the Docs. Stephen J Fleming, John C Marioni, and Mehrtash Babadi. CellBender remove-background: a deep generative model for unsupervised removal of background noise from scRNA-seq datasets. bioRxiv 791699; doi: https://doi.org/10.1101/791699.
MultiiVI is a part of the scvi-tools framework and carries out integration of paired/unpaired multiome data, missing modality imputation, normalization of other cell- and sample-level confounding factors
integrating spatial location, tissue morphology and gene expression to find cell types, cell-cell interactions and spatial trajectories within undissociated tissues. a downstream analysis toolkit for Spatial Transcriptomics data.
Improved mass spectral similarity scoring through learning of structural relationships. Spec2vec is a novel spectral similarity score inspired by a natural language processing algorithm -- Word2Vec. Where Word2Vec learns relationships between words in sentences, spec2vec does so for mass fragments and neutral losses in MS/MS spectra. The spectral similarity score is based on spectral embeddings learnt from the fragmental relationships within a large set of spectral data. Analysis and benchmarking of mass spectra similarity measures using gnps data set.
Automatic generation of gene cluster comparison figures. Gene cluster comparison figure generator. A d3 chart for generating gene cluster comparison figures. clinker is a pipeline for easily generating publication-quality gene cluster comparison figures. Given a set of GenBank files, clinker will automatically extract protein translations, perform global alignments between sequences in each cluster, determine the optimal display order based on cluster similarity, and generate an interactive visualisation (using clustermap.js) that can be extensively tweaked before being exported as an SVG file. clustermap.js is an interactive, reusable d3 chart designed to visualise homology between multiple gene clusters.
UniVI is a Python toolkit for multimodal single-cell data integration using a mixture-of-experts β-variational autoencoder. It integrates heterogeneous measurements, including gene expression, chromatin accessibility and surface-protein abundance, into a shared latent representation. UniVI supports paired and partially observed multimodal datasets, cross-modal imputation, data denoising, synthetic data generation and reference-to-query mapping. It provides training and evaluation workflows, fitted preprocessing transformations and reproducible tutorials for single-cell multi-omics analysis.
Web framework for integrating and running antimicrobial resistance (AMR) prediction models on genomic data. Users upload sequencing reads (Illumina or ONT), an assembly or a Bakta annotation; Cocos discovers which registered models can be applied to the sample, runs the assembly, annotation and gene extraction each model needs, and returns resistance predictions with their provenance (PROV-O, RO-Crate) and a trust level. Models are plug-ins described in RDF with the AMRF application profile and validated with SHACL, so new models can be added without changing the code.
A community-driven Python library for bioinformatics, providing versatile data structures, algorithms and educational resources.
Biophysical reaction-diffusion transport solver and research-only sanctuary dynamics CLI for compact EGFR-mutant NSCLC under osimertinib. Computes perivascular penetration and evolutionary sanctuary profiles; it is not a clinical decision system or treatment recommendation.
Reproducible Python command-line assay for inferring frequency-dependent subclonal payoff matrices and evolutionary dynamics from spatial transcriptomics, with research-only adaptive-therapy simulations. Not a clinical decision system.
Biophysical reaction-diffusion and evolutionary game engine resolving the post-ADAURA osimertinib cessation dilemma via microvascular sanctuaries and the Composite Resistance Index (CRI).
ToxTempAssistant helps scientists document cell-based toxicological test methods more efficiently. Based on the ToxTemp template from OECD Guidance Document 211, the tool guides users through 77 structured questions to create clear, standardised test method descriptions. Using large language models, ToxTempAssistant extracts and organises information from uploaded documents, turning manual data entry into an expert-review process. Its goal is to reduce the documentation burden and support the wider acceptance of New Approach Methodologies.
Web application for analysing medical imaging research data in the browser, without local installation or coding. Supports automatic and interactive segmentation of organs, bones and muscles in CT and MRI (including TotalSegmentator, MOOSE, MRSegmentator and MuscleMap models), manual editing of segmentation masks, synthetic CT and brain MRI generation (MAISI-v2), structured research reports from chest and abdominal CT, and quantitative PET/SPECT measurements with longitudinal and group comparisons. Accepts DICOM and NIfTI input. For research use only; not a medical device.
Syndat computes quality metrics for synthetic tabular data and visualizes how closely it reproduces the real data. It implements three base metrics: Jensen-Shannon distance for feature distributions, normalized correlation difference for inter-feature relationships, and discriminator AUC from a cross-validated Random Forest classifier, and aggregates them into normalized 0-100 distribution, correlation and discrimination scores. It also provides stratified visualizations (raincloud, GOF, trajectory plots) for clinical subgroups.
Python toolkit for processing , analyising and visualising high-speed AFM (Atomic Force Microscopy) video data.
spaCR links pooled CRISPR-Cas9 perturbations to single-cell spatial phenotypes in high-content microscopy images. It segments cells, nuclei, pathogens and organelles with Cellpose, measures morphology, intensity, texture and colocalization features into a SQLite project, trains image and measurement classifiers, maps sequencing reads to wells and gRNAs, and estimates per-guide and per-gene effects by regression.