Find open-source science resources

Efficient foundation model and benchmark for multi-species genome understanding with context-aware nucleotide representations, improving upon DNABERT for diverse genomic task transfer learning (UIUC MAGICS Lab, 484+ stars)

The PIUMA package offers a tidy pipeline of Topological Data Analysis frameworks to identify and characterize communities in high and heterogeneous dimensional data.

Fast, modular, and accurate de novo design of protein binders based on the Protenix foundation model, achieving 17-82% nanomolar hit rates across diverse targets with 2-6× improvement over prior methods like AlphaProteo and RFdiffusion (229+ stars, Apache 2.0)

AI-human collaborative research platform where a human researcher works with a team of LLM agents via team and individual meetings to perform scientific research; demonstrated by designing new SARS-CoV-2 nanobodies with wet-lab validation

Pairwise SNP distance matrix from a FASTA sequence alignment

The Structstrings package implements the widely used dot bracket annotation for storing base pairing information in structured RNA. Structstrings uses the infrastructure provided by the Biostrings package and derives the DotBracketString and related classes from the BString class. From these, base pair tables can be produced for in depth analysis. In addition, the loop indices of the base pairs can be retrieved as well. For better efficiency, information conversion is implemented in C, inspired to a large extend by the ViennaRNA package.

Deep equivariant generative model predicting ligand-specific protein-ligand complex structures with dynamic receptor conformational flexibility, enabling accurate docking for flexible protein targets

This package addresses two broad areas. It allows for in-depth analysis of spatial transcriptomic data by identifying tissue neighbourhoods. These are contiguous regions of tissue surrounding individual cells. 'CatsCradle' allows for the categorisation of neighbourhoods by the cell types contained in them and the genes expressed in them. In particular, it produces Seurat objects whose individual elements are neighbourhoods rather than cells. In addition, it enables the categorisation and annotation of genes by producing Seurat objects whose elements are genes.

MAPFX is an end-to-end toolbox that pre-processes the raw data from MPC experiments (e.g., BioLegend's LEGENDScreen and BD Lyoplates assays), and further imputes the ‘missing’ infinity markers in the wells without those measurements. The pipeline starts by performing background correction on raw intensities to remove the noise from electronic baseline restoration and fluorescence compensation by adapting a normal-exponential convolution model. Unwanted technical variation, from sources such as well effects, is then removed using a log-normal model with plate, column, and row factors, after which infinity markers are imputed using the informative backbone markers as predictors. The completed dataset can then be used for clustering and other statistical analyses. Additionally, MAPFX can be used to normalise data from FFC assays as well.

Creates a muti-graph web page which allows the interactive exploration of differential analysis tests. The graphical web interface presents results as a table which is integrated with five interactive graphs: MA-plot, volcano plot, box plot, lines plot and cluster heatmap. Graphical aspect and information represented in the graphs can be customized by means of user controls. Final graphics can be exported as PNG format.

Official implementation of the second-generation fully autonomous scientific discovery system, extending the original with agentic tree search and reduced template dependency to achieve workshop-level accepted papers (6.7K+ stars, 2025)

First fully autonomous open-ended scientific discovery system with official implementation: hypothesis→experiment→writing→review simulation (13.8K+ stars, 2024)

Shanghai AI Lab's deep learning-based global weather forecasting model pushing skillful forecasts beyond 10 days lead, with open-source inference code and pretrained ONNX model weights (arXiv 2023)

Cross-modal self-supervised foundation model for galaxies by Polymathic AI, jointly embedding multi-band galaxy imaging and optical spectra into a shared latent space to enable zero/few-shot redshift estimation, galaxy property prediction, morphology classification, and cross-modal similarity search (MNRAS Letters 2024)

ECMWF's unified framework and command-line tool to run AI-based weather forecasting models (GraphCast, Aurora, Pangu, NeuralGCM, FourCastNet) with operational ECMWF data infrastructure, enabling standardized inference and benchmarking across state-of-the-art meteorological AI systems (ECMWF, 576+ stars)

Trainable, memory-efficient PyTorch reproduction and retraining of AlphaFold2 providing new insights into its learning dynamics and out-of-distribution generalization; widely used as the open-source AlphaFold2 backbone underpinning many downstream protein structure prediction and design pipelines (Columbia AlQuraishi Lab & OpenFold Consortium, Nature Methods 2024)

Generative AI framework for inverse design of 3D RNA structure and function using geometric deep learning, learning design rules from 3D structures to capture complex tertiary interactions (pseudoknots, non-canonical base pairs) with expert-level accuracy for designing functional RNAs including aptamers and ribozymes (bioRxiv 2025)

Gene signatures of TB progression, TB disease, and other TB disease states have been validated and published previously. This package aggregates known signatures and provides computational tools to enlist their usage on other datasets. The TBSignatureProfiler makes it easy to profile RNA-Seq data using these signatures and includes common signature profiling tools including ASSIGN, GSVA, and ssGSEA. Original models for some gene signatures are also available. A shiny app provides some functionality alongside for detailed command line accessibility.

Statial is a suite of functions for identifying changes in cell state. The functionality provided by Statial provides robust quantification of cell type localisation which are invariant to changes in tissue structure. In addition to this Statial uncovers changes in marker expression associated with varying levels of localisation. These features can be used to explore how the structure and function of different cell types may be altered by the agents they are surrounded with.

Python-centric Cookiecutter for Molecular Computational Chemistry Packages by [MolSSL](https://molssi.org/)

Multimodal whole-slide pathology foundation model jointly pretrained on H&E histology and diagnostic text reports, enabling zero-shot cancer subtyping, biomarker prediction, and multimodal reasoning across diverse cancer types (Mahmood Lab, 341+ stars)

An R Package for Geneset Enrichment Workflows.

Large-scale identification and advanced visualization of sets of conserved noncoding elements.

This package provides functionality for interactive visualization of RNA-seq datasets based on Principal Components Analysis. The methods provided allow for quick information extraction and effective data exploration. A Shiny application encapsulates the whole analysis.

xCell2 provides methods for cell type enrichment analysis using cell type signatures. It includes three main functions - 1. xCell2Train for training custom references objects from bulk or single-cell RNA-seq datasets. 2. xCell2Analysis for conducting the cell type enrichment analysis using the custom reference. 3. xCell2GetLineage for identifying dependencies between different cell types using ontology.

The analysis and visualization of alternative splicing (AS) events from RNA sequencing data remains challenging. SpliceWiz is a user-friendly and performance-optimized R package for AS analysis, by processing alignment BAM files to quantify read counts across splice junctions, IRFinder-based intron retention quantitation, and supports novel splicing event identification. We introduce a novel visualization for AS using normalized coverage, thereby allowing visualization of differential AS across conditions. SpliceWiz features a shiny-based GUI facilitating interactive data exploration of results including gene ontology enrichment. It is performance optimized with multi-threaded processing of BAM files and a new COV file format for fast recall of sequencing coverage. Overall, SpliceWiz streamlines AS analysis, enabling reliable identification of functionally relevant AS events for further characterization.

This packages provides C++ header files for developers wishing to create R packages that processes BAM files. ompBAM automates file access, memory management, and handling of multiple threads 'behind the scenes', so developers can focus on creating domain-specific functionality. The included vignette contains detailed documentation of this API, including quick-start instructions to create a new ompBAM-based package, and step-by-step explanation of the functionality behind the example packaged included within ompBAM.

This package provides functions for the analysis of data generated by the multiplex substrate profiling by mass spectrometry for proteases (MSP-MS) method. Data exported from upstream proteomics software is accepted as input and subsequently processed for analysis. Tools for statistical analysis, visualization, and interpretation of the data are provided.

Provides a collection of additional compression filters for HDF5 datasets. The package is intended to provide seamless integration with rhdf5, however the compiled filters can also be used with external applications.

Bedgraph files generated by Bisulfite pipelines often come in various flavors. Critical downstream step requires summarization of these files into methylation/coverage matrices. This step of data aggregation is done by Methrix, including many other useful downstream functions.

Provide functions for retrieving, exploratory analyzing and visualizing the Human Protein Atlas data. HPAanalyze is designed to fullfill 3 main tasks: (1) Import, subsetting and export downloadable datasets; (2) Visualization of downloadable datasets for exploratory analysis; and (3) Working with the individual XML files. This package aims to serve researchers with little programming experience, but also allow power users to use the imported data as desired.

Full spaCy pipeline and models for scientific/biomedical documents, enabling named entity recognition, abbreviation resolution, and UMLS linking for scientific literature mining (1.9K+ stars, Apache 2.0)

Detection of biases in the usage of immunoglobulin (Ig) genes is an important task in immune repertoire profiling. IgGeneUsage detects aberrant Ig gene usage between biological conditions using a probabilistic model which is analyzed computationally by Bayes inference. With this IgGeneUsage also avoids some common problems related to the current practice of null-hypothesis significance testing.

scBubbletree is a quantitative method for the visual exploration of scRNA-seq data, preserving key biological properties such as local and global cell distances and cell density distributions across samples. It effectively resolves overplotting and enables the visualization of diverse cell attributes from multiomic single-cell experiments. Additionally, scBubbletree is user-friendly and integrates seamlessly with popular scRNA-seq analysis tools, facilitating comprehensive and intuitive data interpretation.

Autonomous multi-agent research loop for model architecture discovery that ran 1,773 experiments over 20,000 GPU hours and produced 106 state-of-the-art linear-attention architectures, surpassing human-designed baselines including Mamba2 and DeltaNet (1.1K+ stars, Apache 2.0)

Volcano plots represent a useful way to visualise the results of differential expression analyses. Here, we present a highly-configurable function that produces publication-ready volcano plots. EnhancedVolcano will attempt to fit as many point labels in the plot window as possible, thus avoiding 'clogging' up the plot with labels that could not otherwise have been read. Other functionality allows the user to identify up to 4 different types of attributes in the same plot space via colour, shape, size, and shade parameter configurations.

Vizualize, analyze and explore networks using Cytoscape via R. Anything you can do using the graphical user interface of Cytoscape, you can now do with a single RCy3 function.

This package implements a metabolic network analysis pipeline to identify an active metabolic module based on high throughput data. The pipeline takes as input transcriptional and/or metabolic data and finds a metabolic subnetwork (module) most regulated between the two conditions of interest. The package further provides functions for module post-processing, annotation and visualization.

GladiaTOX R package is an open-source, flexible solution to high-content screening data processing and reporting in biomedical research. GladiaTOX takes advantage of the tcpl core functionalities and provides a number of extensions: it provides a web-service solution to fetch raw data; it computes severity scores and exports ToxPi formatted files; furthermore it contains a suite of functionalities to generate pdf reports for quality control and data processing.

iSEEu (the iSEE universe) contains diverse functionality to extend the usage of the iSEE package, including additional classes for the panels, or modes allowing easy configuration of iSEE applications.

iSEEfier provides a set of functionality to quickly and intuitively create, inspect, and combine initial configuration objects. These can be conveniently passed in a straightforward manner to the function call to launch iSEE() with the specified configuration. This package currently works seamlessly with the sets of panels provided by the iSEE and iSEEu packages, but can be extended to accommodate the usage of any custom panel (e.g. from iSEEde, iSEEpathways, or any panel developed independently by the user).

Defines a S4 class that is based on SingleCellExperiment. In addition to the usual gene layer the object can also store data for immune genes such as HLAs, Igs and KIRs at allele and functional level. The package is part of a workflow named single-cell ImmunoGenomic Diversity (scIGD), that firstly incorporates allele-aware quantification data for immune genes. This new data can then be used with the here implemented data structure and functionalities for further data handling and data analysis.

This package provides functionality to run a number of tasks in the differential expression analysis workflow. This encompasses the most widely used steps, from running various enrichment analysis tools with a unified interface to creating plots and beautifying table components linking to external websites and databases. This streamlines the generation of comprehensive analysis reports.

flowcatchR is a set of tools to analyze in vivo microscopy imaging data, focused on tracking flowing blood cells. It guides the steps from segmentation to calculation of features, filtering out particles not of interest, providing also a set of utilities to help checking the quality of the performed operations (e.g. how good the segmentation was). It allows investigating the issue of tracking flowing cells such as in blood vessels, to categorize the particles in flowing, rolling and adherent. This classification is applied in the study of phenomena such as hemostasis and study of thrombosis development. Moreover, flowcatchR presents an integrated workflow solution, based on the integration with a Shiny App and Jupyter notebooks, which is delivered alongside the package, and can enable fully reproducible bioimage analysis in the R environment.

This package provides functions for an Interactive Differential Expression AnaLysis of RNA-sequencing datasets, to extract quickly and effectively information downstream the step of differential expression. A Shiny application encapsulates the whole package. Support for reproducibility of the whole analysis is provided by means of a template report which gets automatically compiled and can be stored/shared.

Tools for manipulating paired ranges and working with Hi-C data in R. Functionality includes manipulating/merging paired regions, generating paired ranges, extracting/aggregating interactions from `.hic` files, and visualizing the results. Designed for compatibility with plotgardener for visualization.

Intuitive framework for identifying spatially variable genes (SVGs) and differential spatial variable pattern (DSP) between conditions via edgeR, a popular method for performing differential expression analyses. Based on pre-annotated spatial clusters as summarized spatial information, DESpace models gene expression using a negative binomial (NB), via edgeR, with spatial clusters as covariates. SVGs are then identified by testing the significance of spatial clusters. For multi-sample, multi-condition datasets, we again fit a NB model via edgeR, incorporating spatial clusters, conditions and their interactions as covariates. DSP genes-representing differences in spatial gene expression patterns across experimental conditions-are identified by testing the interaction between spatial clusters and conditions.

Provides tools for large-scale protein motif analysis and visualization in R. PMScanR facilitates the identification of motifs using external tools like PROSITE's ps_scan (handling necessary file downloads and execution) and enables downstream analysis of results. Key features include parsing scan outputs, converting formats (e.g., to GFF-like structures), generating motif occurrence matrices, and creating informative visualizations such as heatmaps, sequence logos (via seqLogo/ggseqlogo). The package also offers an optional Shiny-based graphical user interface for interactive analysis, aiming to streamline the process of exploring motif patterns across multiple protein sequences.

The package provides different distances measurements to calculate the difference between genesets. Based on these scores the genesets are clustered and visualized as graph. This is all presented in an interactive Shiny application for easy usage.

Biocaml aims to be a high-performance user-friendly library for Bioinformatics.