Find open-source science resources

Evaluating multimodal autonomous agents in realistic scientific workflows across real scientific software environments (KAlgebra, Celestia, Grass GIS, Lean 4, etc.) with VM-based evaluation infrastructure and agent trajectories

Structure prediction and design of proteins with noncanonical amino acids, enabling AI-powered modeling of synthetic biology constructs and expanded genetic code systems (133+ stars, 2025)

Subgroup classification is a basic task in genomic data analysis, especially for gene expression and DNA methylation data analysis. It can also be used to test the agreement to known clinical annotations, or to test whether there exist significant batch effects. The cola package provides a general framework for subgroup classification by consensus partitioning. It has the following features: 1. It modularizes the consensus partitioning processes that various methods can be easily integrated. 2. It provides rich visualizations for interpreting the results. 3. It allows running multiple methods at the same time and provides functionalities to straightforward compare results. 4. It provides a new method to extract features which are more efficient to separate subgroups. 5. It automatically generates detailed reports for the complete analysis. 6. It allows applying consensus partitioning in a hierarchical manner.

The core functionality of the package is to provide coordinates of genes on the BioCarta pathway images and to provide methods to add self-defined graphics to the genes of interest.

A new clustering algorithm, "binary cut", for clustering similarity matrices of functional terms is implemeted in this package. It also provides functions for visualizing, summarizing and comparing the clusterings.

This package can easily make heatmaps which are produced by the ComplexHeatmap package into interactive applications. It provides two types of interactivities: 1. on the interactive graphics device, and 2. on a Shiny app. It also provides functions for integrating the interactive heatmap widgets for more complex Shiny app development.

GREAT (Genomic Regions Enrichment of Annotations Tool) is a type of functional enrichment analysis directly performed on genomic regions. This package implements the GREAT algorithm (the local GREAT analysis), also it supports directly interacting with the GREAT web service (the online GREAT analysis). Both analysis can be viewed by a Shiny application. rGREAT by default supports more than 600 organisms and a large number of gene set collections, as well as self-provided gene sets and organisms from users. Additionally, it implements a general method for dealing with background regions.

This package implements infrastructures for ontology analysis by offering efficient data structures, fast ontology traversal methods, and elegant visualizations. It provides a robust toolbox supporting over 70 methods for semantic similarity analysis.

Genome level Trellis graph visualizes genomic data conditioned by genomic categories (e.g. chromosomes). For each genomic category, multiple dimensional data which are represented as tracks describe different features from different aspects. This package provides high flexibility to arrange genomic categories and to add self-defined graphics in the plot.

Enriched heatmap is a special type of heatmap which visualizes the enrichment of genomic signals on specific target regions. Here we implement enriched heatmap by ComplexHeatmap package. Since this type of heatmap is just a normal heatmap but with some special settings, with the functionality of ComplexHeatmap, it would be much easier to customize the heatmap as well as concatenating to a list of heatmaps to show correspondance between different data sources.

Logistic Factor Analysis is a method for a PCA analogue on Binomial data via estimation of latent structure in the natural parameter. The main method estimates genetic population structure from genotype data. There are also methods for estimating individual-specific allele frequencies using the population structure. Lastly, a structured Hardy-Weinberg equilibrium (HWE) test is developed, which quantifies the goodness of fit of the genotype data to the estimated population structure, via the estimated individual-specific allele frequencies (all of which generalizes traditional HWE tests).

GCAT is an association test for genome wide association studies that controls for population structure under a general class of trait models. This test conditions on the trait, which makes it immune to confounding by unmodeled environmental factors. Population structure is modeled via logistic factors, which are estimated using the `lfa` package.

Scientific equation discovery with agentic AI, elevating LLMs from equation proposers to autonomous scientists that write code, analyze data, implement equations, and optimize based on experimental feedback; outperforms baselines by 6-35% across four science disciplines with robustness to noise and out-of-domain generalization (GAIR-NLP / SJTU, 49+ stars, Apache 2.0)

Epialleles are specific DNA methylation patterns that are mitotically and/or meiotically inherited. This package calls and reports cytosine methylation as well as frequencies of hypermethylated epialleles at the level of genomic regions or individual cytosines in next-generation sequencing data using binary alignment map (BAM) files as an input. Among other things, this package can also extract and visualise methylation patterns and assess allele specificity of methylation.

This package runs the GADGETS method to identify epistatic effects in nuclear family studies. It also provides functions for permutation-based inference and graphical visualization of the results.

This package allows interactive viewing of package maintainer information. The Bioconductor Package Maintainer Application sends yearly verification emails to accept Bioconductor policies; this application also depicts maintainer status on opting in and if the email is deemed valid.

scFeatures constructs multi-view representations of single-cell and spatial data. scFeatures is a tool that generates multi-view representations of single-cell and spatial data through the construction of a total of 17 feature types. These features can then be used for a variety of analyses using other software in Biocondutor.

Foundation model for joint segmentation, detection, and recognition of biomedical objects across nine imaging modalities, with v2 introducing BoltzFormer architecture for end-to-end 3D inference (Microsoft, Nature Methods 2025)

DNA sequence analysis

A generic but comprehensive bacterial annotation pipeline, built with Nextflow, with nice graphical options for investigating results.

A Shiny application to explore the TCGA Diagnostic Image Database.

Computes Multiple Co-Inertia Analysis (MCIA), a dimensionality reduction (jDR) algorithm, for a multi-block dataset using a modification to the Nonlinear Iterative Partial Least Squares method (NIPALS) proposed in (Hanafi et. al, 2010). Allows multiple options for row- and table-level preprocessing, and speeds up computation of variance explained. Vignettes detail application to bulk- and single cell- multi-omics studies.

Open-source toolkit and benchmark for learning-based theorem proving in Lean, providing programmatic Lean interaction, a 98K+ theorem dataset extracted from 217 Lean projects, and ReProver—the first retrieval-augmented LLM-based theorem prover for Lean—with reproducible training pipelines underpinning much subsequent Lean prover research (Caltech & NVIDIA, NeurIPS 2023 Outstanding Paper, Datasets & Benchmarks)

Package performs summarization of replicates, filtering by frequency, several different options for imputing missing data, and a variety of options for transforming, batch correcting, and normalizing data.

The package comprises a set of pretrained machine learning models to predict basic immune cell types. This enables all users to quickly get a first annotation of the cell types present in their dataset without requiring prior knowledge. scAnnotatR also allows users to train their own models to predict new cell types based on specific research needs.

SCENIC+ is a python package to build gene regulatory networks (GRNs) using combined or separate single-cell gene expression (scRNA-seq) and single-cell chromatin accessibility (scATAC-seq) data.

This package contains functionality to run differential gene co-expression across two different conditions. The algorithm is inspired by Voigt et al. 2017 and finds Conserved, Specific and Differentiated genes (hence the name CSD). This package include efficient and variance calculation by bootstrapping and Welford's algorithm.

Design primers for targeted single-cell RNA-seq used by TAP-seq. Create sequence templates for target gene panels and design gene-specific primers using Primer3. Potential off-targets can be estimated with BLAST. Requires working installations of Primer3 and BLASTn.

Discrete diffusion framework for generative protein sequence design over evolutionary-scale databases, supporting unconditional generation, evolutionary-guided conditional design, motif scaffolding, and intrinsically disordered region generation through order-agnostic autoregressive diffusion, enabling sequence-only protein design without structural priors (Microsoft Research, Nature Communications 2024)

CebraEM is a bioinformatics tool for analyzing and processing large-scale imaging data, providing a pipeline for segmentation, annotation, and analysis with support for both Linux and Windows environments. It includes modules for core functionality, annotation, and network analysis, requiring specific dependencies and a conda environment for execution.

The package aims to identify miRNA sponge or ceRNA modules in heterogeneous data. It provides several functions to study miRNA sponge modules at single-sample and multi-sample levels, including popular methods for inferring gene modules (candidate miRNA sponge or ceRNA modules), and two functions to identify miRNA sponge modules at single-sample and multi-sample levels, as well as several functions to conduct modular analysis of miRNA sponge modules.

an automated workflow for the generation and storage of DFT calculations for organic molecules.

ICML 2025 drug discovery generalist using masked discrete diffusion and fragment-based generation with molecular context guidance (NVIDIA)

Open-source, platform-independent, community-supported software for describing and comparing microbial communities

DeepMind's Olympiad-level geometry theorem prover combining neural language model with symbolic deduction engine, AlphaGeometry2 solves 84% of IMO geometry problems (42/50) at gold-medalist level (Nature 2024)

Standard data-centric AI package for data quality and machine learning, automatically detecting label errors, outliers, and dataset issues to improve scientific dataset reliability and model performance (11K+ stars, MIT License)

SpotClean is a computational method to adjust for spot swapping in spatial transcriptomics data. Recent spatial transcriptomics experiments utilize slides containing thousands of spots with spot-specific barcodes that bind mRNA. Ideally, unique molecular identifiers at a spot measure spot-specific expression, but this is often not the case due to bleed from nearby spots, an artifact we refer to as spot swapping. SpotClean is able to estimate the contamination rate in observed data and decontaminate the spot swapping effect, thus increase the sensitivity and precision of downstream analyses.

TEKRABber is made to provide a user-friendly pipeline for comparing orthologs and transposable elements (TEs) between two species. It considers the orthology confidence between two species from BioMart to normalize expression counts and detect differentially expressed orthologs/TEs. Then it provides one to one correlation analysis for desired orthologs and TEs. There is also an app function to have a first insight on the result. Users can prepare orthologs/TEs RNA-seq expression data by their own preference to run TEKRABber following the data structure mentioned in the vignettes.

a specification for describing analysis workflows and tools that are portable and scalable across a variety of software and hardware environments, from workstations to cluster, cloud, and high performance computing (HPC) environments.

mitch is an R package for multi-contrast enrichment analysis. At it’s heart, it uses a rank-MANOVA based statistical approach to detect sets of genes that exhibit enrichment in the multidimensional space as compared to the background. The rank-MANOVA concept dates to work by Cox and Mann (https://doi.org/10.1186/1471-2105-13-S16-S12). mitch is useful for pathway analysis of profiling studies with one, two or more contrasts, or in studies with multiple omics profiling, for example proteomic, transcriptomic, epigenomic analysis of the same samples. mitch is perfectly suited for pathway level differential analysis of scRNA-seq data. We have an established routine for pathway enrichment of Infinium Methylation Array data (see vignette). The main strengths of mitch are that it can import datasets easily from many upstream tools and has advanced plotting features to visualise these enrichments.

A batteries-included toolkit for the GPU-accelerated OpenMM molecular simulation engine.

A seamless interface to the MEME Suite family of tools for motif analysis. 'memes' provides data aware utilities for using GRanges objects as entrypoints to motif analysis, data structures for examining & editing motif lists, and novel data visualizations. 'memes' functions and data structures are amenable to both base R and tidyverse workflows.

`tidyCoverage` framework enables tidy manipulation of collections of genomic tracks and features using `tidySummarizedExperiment` methods. It facilitates the extraction, aggregation and visualization of genomic coverage over individual or thousands of genomic loci, relying on `CoverageExperiment` and `AggregatedCoverage` classes. This accelerates the integration of genomic track data in genomic analysis workflows.

Prokka: rapid prokaryotic genome annotation. Prokka is one of the most cited annotation command line tools for microbial genome annotations.

Webapp for generating conformers

The CNVMetrics package calculates similarity metrics to facilitate copy number variant comparison among samples and/or methods. Similarity metrics can be employed to compare CNV profiles of genetically unrelated samples as well as those with a common genetic background. Some metrics are based on the shared amplified/deleted regions while other metrics rely on the level of amplification/deletion. The data type used as input is a plain text file containing the genomic position of the copy number variations, as well as the status and/or the log2 ratio values. Finally, a visualization tool is provided to explore resulting metrics.

A library for building, manipulating, analyzing and automatic design of molecules, including a genetic algorithm.

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)