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
License
Source
Type
9,874 resources indexed
Showing 8,201–8,250
G-PGS is a GPU-accelerated pipeline designed to calculate polygenic scores (PGS) for an individual genome against an entire catalog of genetic risk scores, transforming this output into clinically useful disease risk modules.
PoolParty is a Python package that automates and structures the design of complex oligo pools/DNA sequence libraries, making oligo pool design transparent and reproducible for functional genomics assays.
agtools is a Python framework for manipulating assembly graphs, facilitating downstream analyses in metagenomics. It provides command-line and Python interfaces to parse, convert, filter, and analyze graph formats like GFA.
ChromBERT-tools is a toolkit designed to generate context-specific, regulation-informed embeddings of transcription regulators. It supports end-to-end workflows for enhancing transcription regulation modeling and inferring regulatory roles in different cell types.
InterMap is a Python package designed for accelerating the detection of interaction fingerprints (IFPs) from large-scale Molecular Dynamics (MD) trajectories, crucial for studying biomolecular interactions.
An R package implementing the DIVAS framework for multi-modal data integration, designed to identify jointly shared, partially shared, and individual variations across multi-omics data types. It is particularly useful for identifying complex markers and pathways associated with diseases like COVID-19.
RevelioPlots is an interactive web application that assesses the quality of AI-predicted protein structures. It combines statistical pLDDT score analysis with an interactive, confidence-colored Ramachandran plot to link local reliability to stereochemical feasibility.
LoReMINE is an automated end-to-end pipeline designed to mine natural products from microbial genomes. It processes long-read sequencing data to generate assemblies, classify taxa, and predict biosynthetic gene clusters (BGCs).
conMItion is an R package designed to estimate Conditional Mutual Information (CMI) for multi-omics data, allowing researchers to identify associations between biological factors while statistically adjusting for specified confounding variables.
pyKinaXe is a Python package providing automated, end-to-end analysis for peptide microarray data (PamChip®). It profiles kinase activity by extracting kinase information and quantifying phosphorylation kinetics from raw microarray images.
MKado is a comprehensive Python toolkit designed for performing McDonald-Kreitman (MK) tests to analyze patterns of natural selection from aligned coding sequences. It implements both standard MK tests and various extensions, providing tools for estimating the fraction of adaptive substitutions ($\alpha$).
SuperSurv is an R package that provides a unified framework for building, evaluating, and interpreting ensemble machine learning models for right-censored survival data. It implements techniques like stacking and integrates interpretability tools such as SHAP values and Restricted Mean Survival Time (RMST) contrasts.
SNPWay is an end-to-end web server and R package designed for streamlined SNP-to-function and pathway over-representation analysis. It translates variant lists (like SNPs) into functional hypotheses by combining various annotation and enrichment steps.
sxLaep is a resource-efficient framework designed for high-throughput enzyme pre-screening from large-scale metagenomic sequences. It uses lightweight physicochemical features to rapidly predict enzymatic sequences, filtering datasets before resource-intensive annotation.
G-VEP is a GPU-accelerated framework designed to massively parallelize the annotation process for clinical whole-genome sequencing (WGS) variants, significantly reducing computational bottlenecks compared to standard tools like VEP.
Antimony is a human-readable, plain-text language used for defining and sharing biochemical models, supporting conversions to and from SBML. It enables comprehensive model specifications combining kinetic reactions, flux balance analysis, and uncertainty modeling.
TSUMUGI is a platform that identifies gene networks linked to complex organismal phenotypes, specifically using gene-phenotype associations derived from comprehensive knockout mouse data.
LDscore is a cloud-based web application integrated into NCI LDlink, designed for scalable analysis of genetic data. It performs Linkage Disequilibrium Score (LD) regression to estimate heritability and genetic correlations between complex traits.
SCOT+ is an unsupervised software suite that uses Optimal Transport (OT) to align cells and features across disparate single-cell multi-omics datasets. It provides a unified framework for accurate multi-omics single-cell data alignment.
Yomix is an interactive, omics-agnostic tool designed for the visualization and exploration of low-dimensional embeddings derived from diverse omics datasets. It allows users to define regions of interest and compute feature signatures for rapid data comparison.
fetchm is a command-line Python tool designed for bacterial comparative genomics. It automates the retrieval, standardization, and integration of genomic metadata (from NCBI Genome) and biological context (from BioSample) records for large-scale comparative studies.
baktfold is a fast, sensitive command-line tool for functional annotation of protein sequences across the microbial tree of life using structural information. It processes protein sequences and exports results in standard formats like GFF3 and JSON.
GLiNER-BioMed is a suite of models designed for open biomedical named entity recognition (NER). It utilizes both uni- and bi-encoder architectures to efficiently extract entities like genes, proteins, and sequences from biomedical text.
AMRgen is an R package designed for systematic antimicrobial resistance (AMR) genotype-phenotype analysis. It integrates genomic and antimicrobial susceptibility testing data to model and visualize associations between AMR genes and resistance phenotypes.
DoReMiTra is an R/Bioconductor data package that provides a unified collection of curated transcriptomic datasets related to radiation exposure (neutron, x-ray, gamma ray). It facilitates reproducible analysis, visualization, and biomarker discovery in radiation transcriptomics.
A cross-platform, open-source library for neuroscientists to automatically extract standardized electrophysiological features (eFeatures) from time series data (e.g., voltage traces). It combines a C++ core with a Python interface for reproducible analysis of neuronal activity.
A web-based tool that converts open-source eLabFTW electronic laboratory notebook records into Annotated Research Contexts (ARCs). It automatically retrieves and reorganizes metadata, protocols, and attachments into ISA-compliant, FAIR digital objects.
IDAP is a modular pipeline designed for precision oncology that integrates multiple evidence sources (OncoKB, PubMed, knowledge graphs, ClinicalTrials.gov) to prioritize therapeutic hypotheses from genetic variants.
CCycDB is an integrative knowledgebase designed for accurate metagenomic profiling of microbial carbon cycling processes. It contains functional gene families and sequences to link microbial communities to complex biogeochemical cycles.
A novel k-mer-based metagenomic profiling tool that utilizes genome coverage information by splitting the reference genomes into chunks and stores k-mers in a modified and optimized Compact Bit-Sliced Signature Index for fast alignment-free sequence searching. KMCP combines k-mer similarity and genome coverage information to reduce the false positive rate of k-mer-based taxonomic classification and profiling methods.
An R package that introduces the 'plate plot' method for visualizing complex results from network meta-analysis (NMA), allowing simultaneous display of multiple efficacy and uncertainty metrics in a single, compact graphic.
A bioinformatics resource providing resources and methodology for characterizing the genomic and functional diversity of the marine bacterial genus *Pseudoalteromonas*. It utilizes whole-genome sequencing and phylogenomic inference to study bacterial diversification in bivalve microbiomes.
A framework-agnostic Python toolkit that provides structured and reliable cross-validation methods (including grouped, temporal, and spatial splits) for mitigating data leakage in medical machine learning applications.
TAIX-Ray is a large-scale, comprehensive dataset of bedside chest radiographs and structured radiologic reports. It facilitates automated AI model development for pathology detection and severity assessment in critical care settings.
A paired dataset containing potato tuber samples collected in Hokkaido, Japan. It combines multi-sensory data (RGB-D point clouds, ground measurements, SfM reconstructions) to benchmark and train algorithms for 3D phenotyping and data completion.
SPATULA is a Python package designed to compute the continuous symmetry ordering (PGOP) of neighboring particles. It analyzes local particle arrangements, which is crucial for understanding the development of order in crystalline or condensed phase systems.
A framework-agnostic Python toolkit for robust cross-validation in medical machine learning. It supports numerous CV methods, detects data leakage, and provides structure-aware evaluation for biomedical data.
NeuroAIHub is an AI-driven web framework that automates the discovery and structured exploration of neuroradiology datasets. It provides a continuously curated database, enabling natural-language dataset retrieval and standardized metadata management.
A consolidated, harmonized data resource containing overlapping continuous glucose monitoring (CGM) and insulin pump dosing records for Type 1 Diabetes management, designed for algorithmic development.
cxt is a transformer-based language model designed for population genetics, inferring pairwise coalescent times (TMRCA) from genotype data. It reframes the inference of coalescence times as a language translation problem, predicting coalescent events conditioned on local mutational context.
mdxplain is a high-level Python API designed for analyzing large molecular dynamics (MD) simulation datasets. It provides unified workflows for calculating structural features, performing dimensionality reduction, and identifying key structural patterns and conformational states.
The MRS4Brain Toolbox is an open-source, MATLAB-based platform for analyzing preclinical MR spectroscopic imaging data (proton and deuterium). It provides integrated workflows for preprocessing, quantification, and metabolic map analysis using a GUI.
DySTrack is an open-source Python tool designed for smart microscopy, enabling automated feedback control to track dynamic biological samples, such as migrating cells or developing tissues. It serves as a modular bridge connecting commercial microscope acquisition software to advanced Python image analysis pipelines.
DposFinder is a deep learning framework that uses transformer architecture (ESM-2) to predict phage-derived polysaccharide depolymerases and their associated host bacterial capsular serotypes. It aids in the large-scale discovery of enzymes relevant for phage therapy against antibiotic-resistant bacteria.
ChloroScan is a bioinformatics pipeline designed to extract eukaryotic plastid genomes from metagenomic data. It uses deep learning and automated binning to recover high-quality plastid-containing metagenome-assembled genomes (MAGs) from protist-size-fraction metagenomes.
pEYES is an open-source Python package designed for researchers to perform quantitative, systematic comparisons of eye-movement detection algorithms (fixations and saccades). It provides implementations of multiple widely used algorithms and offers over 20 metrics to evaluate performance against ground-truth human-annotated eye-tracking data.
BDI-Kit is an open-source toolkit designed for biomedical data harmonization. It provides a Python API and an AI-assisted chat interface to integrate and transform diverse biomedical datasets.
Copick is an open-source API and tool suite for cryo-electron tomography (cryoET) data, providing standardized, scalable access and collaborative annotation/analysis features for complex biological datasets.
graphpancake is an open-source Python package that generates molecular graphs for small organic molecules by translating quantum mechanical data (DFT/WFT) into graph representations. It is designed for cheminformatics pipelines, enabling advanced predictive modeling like QSAR.
Lancet2 is an open-source somatic variant caller designed for short-read sequencing data. It improves variant detection using partial order multiple sequence alignment and offers optimized scoring via explainable machine learning models.