Find open-source science resources

All-atom generative world model for all-to-all biomolecular interaction design, enabling cross-modality generation of proteins, nucleic acids, small molecules, and cyclic peptides with fine-grained epitope-level control and 2-4 orders of magnitude faster design throughput than modality-specific baselines (316+ stars, Apache 2.0)

scToppR provides an easy-to-use API wrapper for the ToppGene web platform, used for gene ontology and functional enrichment research. The package also integrates visualization tools, making it a convenient tool directly connecting ToppGene to code-based workflows in R. The tool can also easily save results into different formats.

Multi-modal foundation model for biomolecular structure prediction (proteins, small molecules, DNA, RNA, glycans) achieving SOTA across benchmarks, with optional MSA/template support (Chai Discovery, 2024)

transmogR provides the tools needed to crate a new reference genome or reference transcriptome, using a set of variants. Variants can be any combination of SNPs, Insertions and Deletions. The intended use-case is to enable creation of variant-modified reference transcriptomes for incorporation into transcriptomic pseudo-alignment workflows, such as salmon.

Taking a set of sequence motifs as PWMs, test a set of sequences for over-representation of these motifs, as well as any positional features within the set of motifs. Enrichment analysis can be undertaken using multiple statistical approaches. The package also contains core functions to prepare data for analysis, and to visualise results.

Statistical and computational method to analyze the co-expression of gene pairs at single cell level. It provides the foundation for single-cell gene interactome analysis. The basic idea is studying the zero UMI counts' distribution instead of focusing on positive counts; this is done with a generalized contingency tables framework. COTAN can effectively assess the correlated or anti-correlated expression of gene pairs. It provides a numerical index related to the correlation and an approximate p-value for the associated independence test. COTAN can also evaluate whether single genes are differentially expressed, scoring them with a newly defined global differentiation index. Moreover, this approach provides ways to plot and cluster genes according to their co-expression pattern with other genes, effectively helping the study of gene interactions and becoming a new tool to identify cell-identity marker genes.

Self-hostable scientific claim-verification and literature-review tool combining Semantic Scholar retrieval, bibliometric scoring, and LLM-based evidence synthesis for large-batch validation workflows

Deep learning framework for molecular docking extending AutoDock Vina with convolutional neural network scoring functions, achieving superior virtual screening enrichment and pose prediction across diverse target classes; widely adopted in pharmaceutical structure-based drug design (J. Cheminformatics, 915+ stars, actively maintained)

cfDNA fragments carry important features for building cancer sample classification ML models, such as fragment size, and fragment end motif etc. Analyzing and visualizing fragment size metrics, as well as other biological features in a curated, standardized, scalable, well-documented, and reproducible way might be time intensive. This package intends to resolve these problems and simplify the process. It offers two sets of functions for cfDNA feature characterization and visualization.

This package builds on existing tools and adds some simple but extremely useful capabilities for working wth ChIP-Seq data. The focus is on detecting differential binding windows/regions. One set of functions focusses on set-operations retaining mcols for GRanges objects, whilst another group of functions are to aid visualisation of results. Coercion to tibble objects is also implemented.

Learnable latent embeddings for joint behavioral and neural analysis, enabling consistent and interpretable mapping of neural activity to behavior across modalities, species, and experiments (EPFL & Harvard, 1K+ stars)

First system progressively surpassing human SOTA on frontier AI tasks (183.7%, 1.9%, 7.9% improvements), month-long autonomous discovery with 20,000+ GPU hours

'OSTA.data' is a companion package for the "Orchestrating Spatial Transcriptomics Analysis" (OSTA) with Bioconductor online book. Throughout OSTA, we rely on a set of publicly available datasets that cover different sequencing- and imaging-based platforms, such as Visium, Visium HD, Xenium (10x Genomics) and CosMx (NanoString). In addition, we rely on scRNA-seq (Chromium) data for tasks, e.g., spot deconvolution and label transfer (i.e., supervised clustering). These data been deposited in an Open Storage Framework (OSF) repository, and can be queried and downloaded using functions from the 'osfr' package. For convenience, we have implemented 'OSTA.data' to query and retrieve data from our OSF node, and cache retrieved Zip archives using 'BiocFileCache'.

Toolbox for larger-than-memory scientific computing and visualization, providing efficient out-of-core data structures using files or shared memory, for dense and sparse vectors, matrices, and arrays, with applications to nonuniformly sampled signals and images.

The package implements an algorithm for fast gene set enrichment analysis. Using the fast algorithm allows to make more permutations and get more fine grained p-values, which allows to use accurate stantard approaches to multiple hypothesis correction.

This package implements a variety of methods for batch correction in single-cell RNA sequencing (scRNA-seq) data. It incorporates quantitative metrics (e.g. Wasserstein distance, Adjusted Rand Index) to evaluate their performance. Furthermore, the package assists users in identifying and applying the optimal method for specific datasets.

A novel framework to correct for batch effects prior to any downstream analysis in microbiome data based on Projection to Latent Structures Discriminant Analysis. The main method is named “PLSDA-batch”. It first estimates treatment and batch variation with latent components, then subtracts batch-associated components from the data whilst preserving biological variation of interest. PLSDA-batch is highly suitable for microbiome data as it is non-parametric, multivariate and allows for ordination and data visualisation. Combined with centered log-ratio transformation for addressing uneven library sizes and compositional structure, PLSDA-batch addresses all characteristics of microbiome data that existing correction methods have ignored so far. Two other variants are proposed for 1/ unbalanced batch x treatment designs that are commonly encountered in studies with small sample sizes, and for 2/ selection of discriminative variables amongst treatment groups to avoid overfitting in classification problems. These two variants have widened the scope of applicability of PLSDA-batch to different data settings.

International association of users & developers of open source Perl tools for bioinformatics, genomics and life sciences.

Cython + HTSlib == fast VCF parsing; even faster parsing than pyVCF.

Provides hurdle negative binomial models for differential expression analysis with long-read RNA-Seq data.

Automated academic illustration generation for AI scientists, converting research papers into publication-ready figures using VLMs and diffusion models with iterative refinement (PKU & Google Research, 6.2K+ stars, 2026)

Provides a streamlined workflow for clustering and visualizing gene expression patterns, particularly from time-series RNA-Seq and single-cell experiments. The package is designed to integrate seamlessly within the Bioconductor ecosystem by operating directly on standard data classes such as `SummarizedExperiment` and `SingleCellExperiment`. It implements common clustering algorithms (e.g., k-means, fuzzy c-means) and generates a suite of publication-ready visualizations to explore co-expressed gene modules. Functions are also included to facilitate the visualization of clustering results derived from other popular tools.

This tutorial aims to illustrate the process of extracting structural and dynamical properties from a DNA MD trajectory helical parameters, step by step, using the BioExcel Building Blocks library (biobb). The particular example used is the Drew Dickerson Dodecamer sequence -CGCGAATTCGCG- (PDB code 1BNA). The trajectory used is a 500ns-long MD simulation taken from the BigNASim database (NAFlex_DDD_II entry).

First multi-domain generative foundation model for the natural sciences built on a unified scientific grammar, encoding proteins, antibodies, small molecules, chemical reactions, materials, and their spatial interactions into a shared token vocabulary; enables unified generation, prediction, and design across domains under a purely autoregressive paradigm (134+ stars, Apache 2.0, 2026)

Autonomous AI scientist research

A powerful, high-performance bioinformatics framework for discovering, evaluating, and verifying microRNA (miRNA) interactions across DNA, RNA, and protein target sequences. The mirnaprotpred package provides two core modules: SeqFinder: A discovery engine to find all potential miRNA interactions across a genome or target sequence. Validator: A targeted verification engine to test specific, user-provided miRNAs against a target sequence. Both modules are powered by a shared, rigorous biological engine that evaluates exact seed matching, wobble pairing, AU-rich context, and RNAduplex thermodynamic stability.

PhantasusLite – a lightweight package with helper functions of general interest extracted from phantasus package. In parituclar it simplifies working with public RNA-seq datasets from GEO by providing access to the remote HSDS repository with the precomputed gene counts from ARCHS4 and DEE2 projects.

DeepMind's graph neural network for materials exploration, discovering 2.2M new crystal structures (380K most stable) equivalent to 800 years of traditional research, with 520K+ materials dataset open-sourced (Nature 2023)

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.

Cross-domain foundation model for continuum dynamics trained on 19 physical scenarios spanning 63 variables, featuring adaptive compute via stride modulation and patch jittering for long-run stability (Polymathic AI, 293+ stars, MIT License)

Meta FAIR's foundation model of vision, audition, and language for in-silico neuroscience, predicting fMRI brain responses to naturalistic multimodal stimuli (video, audio, text) through unified Transformer architecture mapped to the cortical surface (2026)

Inference of ligand-receptor (L-R) interactions from single-cell expression (transcriptomics/proteomics) data. SingleCellSignalR v2 inferences rely on the statistical model we introduced in the BulkSignalR package as well as the original SingleCellSignalR LR-score (both are available). SingleCellSignalR v2 can be regarded as a wrapper to BulkSignalR fundamental classes. This also enables v2 users to work with any species, whereas only Mus musculus & Homo sapiens were available before in SingleCellSignalR v1.

Inference of ligand-receptor (LR) interactions from bulk expression (transcriptomics/proteomics) data, or spatial transcriptomics. BulkSignalR bases its inferences on the LRdb database included in our other package, SingleCellSignalR available from Bioconductor. It relies on a statistical model that is specific to bulk data sets. Different visualization and data summary functions are proposed to help navigating prediction results.

Provides a reproducible and modular workflow for absolute microbial quantification using spike-in controls. Supports both single spike-in taxa and synthetic microbial communities with user-defined spike-in volumes and genome copy numbers. Compatible with 'phyloseq' and 'TreeSummarizedExperiment' (TSE) data structures. The package implements methods for spike-in validation, preprocessing, scaling factor estimation, absolute abundance conversion, bias correction, and normalization. Facilitates downstream statistical analyses with 'DESeq2', 'edgeR', and other Bioconductor-compatible methods. Visualization tools are provided via 'ggplot2', 'ggtree', and related packages. Includes detailed vignettes, case studies, and function-level documentation to guide users through experimental design, quantification, and interpretation.

Autonomous multi-agent AI scientist that mirrors a PhD workflow: literature review → grounded hypothesis → real ML experiments → self-critique → write-up; features a deterministic harness with frozen-metric scoring, edit allowlists, and a verified registry to make reward-hacking and hallucination impossible, plus 108 unit tests runnable without API keys or GPUs (461+ stars, MIT License, 2026)

Package to analyze transcription factor enrichment in a gene set using data from ChIP-Seq experiments.

103B-parameter open-source medical language model with 1/32 Mixture-of-Experts architecture, achieving HealthBench-leading performance among open-source models with only 6.1B active parameters; jointly developed by Ant Group and Zhejiang Province Health Information Center (MIT License)

Foundation model for universal prompt-driven medical image segmentation extending SAM3 to clinical imaging, supporting 2D public benchmarks and 3D training/evaluation with text and box prompts; pretrained weights available on HuggingFace (189+ stars)

Numerical differential equation solving in JAX

Google's open multimodal medical LLM family built on Gemma 3, including a 4B multimodal model handling medical images (radiology, pathology, dermatology) alongside text and a 27B text model for clinical reasoning; trained on de-identified medical data with checkpoints and inference code released under Apache 2.0 (1.6K+ stars)

The scECODA R package provides a complete workflow for the analysis and visualization of compositional data, primarily focusing on cell type proportions derived from single-cell data. It implements specialized methods, such as the Centered Log-Ratio (CLR) transformation, to properly analyze proportional data while avoiding the biases introduced by the compositional constraint. The package encapsulates data management, transformation, and analysis into a single SummarizedExperiment object, offering downstream tools for dimensionality reduction via PCA, calculating critical metrics like the Adjusted Rand Index (ARI) and Modularity to quantify sample grouping quality, and generating high-quality visualizations like heatmaps and scatter plots.

DenoIST identifies and removes contamination in Image-based Spatial Transcriptomics data, using a transposed poisson mixture model with local neighbourhood offsets to infer genes that are likely to be due to neighbourhood contamination rather than endogenous expression.

Arc Institute's 40B-parameter genome foundation model trained on 9 trillion nucleotides from all domains of life, supporting 1M base pair context for generalist DNA/RNA/protein prediction and design (Nature 2026)

A single molecule sequence assembler for genomes large and small.

MeLSI (Metric Learning for Statistical Inference) is a novel machine learning method for microbiome data analysis that learns optimal distance metrics to improve statistical power in detecting group differences. Unlike traditional distance metrics (Bray-Curtis, Euclidean, Jaccard), MeLSI adapts to the specific characteristics of your dataset to maximize separation between groups. The method uses an ensemble of weak learners to identify which microbial features drive group differences, providing both improved statistical power and biological interpretability through feature importance weights.

Have you ever index sorted cells in a 96 or 384-well plate and then sequenced using Sanger sequencing? If so, you probably had some struggles to either check the electropherogram of each cell sequenced manually, or when you tried to identify which cell was sorted where after sequencing the plate. Scifer was developed to solve this issue by performing basic quality control of Sanger sequences and merging flow cytometry data from probed single-cell sorted B cells with sequencing data. scifer can export summary tables, 'fasta' files, electropherograms for visual inspection, and generate reports.

A multitude of tools for comparative genomics, focused on large-scale analyses of biological data. SynExtend includes tools for working with syntenic data, clustering massive network structures, and estimating functional relationships among genes.

Fudan University's cascade machine learning forecasting system for 15-day global weather prediction, employing a 3D Earth-specific transformer with hard-constraint techniques to achieve state-of-the-art accuracy against traditional NWP and AI baselines

Diffusion-based document OCR framework replacing autoregressive decoding with block-level parallel diffusion decoding, enabling high-accuracy text recognition in scientific PDFs (613+ stars, MIT License)

Genome-wide association studies (GWAS) are widely used to investigate the genetic basis of diseases and traits, but they pose many computational challenges. We developed an R package SNPRelate to provide a binary format for single-nucleotide polymorphism (SNP) data in GWAS utilizing CoreArray Genomic Data Structure (GDS) data files. The GDS format offers the efficient operations specifically designed for integers with two bits, since a SNP could occupy only two bits. SNPRelate is also designed to accelerate two key computations on SNP data using parallel computing for multi-core symmetric multiprocessing computer architectures: Principal Component Analysis (PCA) and relatedness analysis using Identity-By-Descent measures. The SNP GDS format is also used by the GWASTools package with the support of S4 classes and generic functions. The extended GDS format is implemented in the SeqArray package to support the storage of single nucleotide variations (SNVs), insertion/deletion polymorphism (indel) and structural variation calls in whole-genome and whole-exome variant data.