Find open-source science resources

CBN2Path package provides a unifying interface to facilitate CBN-based quantification, analysis and visualization of cancer progression pathways.

Descriptor library containing a variety of fingerprinting techniques, including the Smooth Overlap of Atomic Positions (SOAP).

Fast FASTQ filtering by matching reads against one or more regex patterns.

Scaling efficient, expressive, and general SE(3)-equivariant graph attention transformers for atomic systems and machine-learned interatomic potentials (MIT License, 2026)

Battlefield is a Swiss-army toolkit originally developed to define and extract spatial spots from specific tissue regions—such as front regions, niche borders, invasive margins, and cluster interfaces—using spatial transcriptomics data or clustered tissue maps. It has since been extended to support trajectory selection and layer inspection, and now provides a collection of low-level utilities for spatial transcriptomics analysis. These utilities are primarily intended to be reused within higher-level analytical packages. It is designed to work with sequencing-based platforms such as Visium at several resolutions and Visium HD(binned).

This package provides Bioconductor-friendly wrappers for RNA velocity calculations in single-cell RNA-seq data. We use the basilisk package to manage Conda environments, and the zellkonverter package to convert data structures between SingleCellExperiment (R) and AnnData (Python). The information produced by the velocity methods is stored in the various components of the SingleCellExperiment class.

The package prepares input scATAC-seq data and adapts for copy number variance profiling with InferCNV package usage. It has also various paramters to control the analysis (e.g. external normal reference usage, meta-cells, bin size, etc) and custom plot visualizations.

Pretrained machine-learned force field for (bio)molecular simulations combining the fast SO3krates neural network for semi-local interactions with universal pairwise force fields for short-range repulsion, long-range electrostatics, and dispersion interactions; supports geometry optimization, NVT/NPT/NVE MD, fine-tuning, ASE calculator, and JAX-MD integration (JACS 2025, 218+ stars, MIT License)

Analysis and plotting of array CGH data. Allows usage of Circular Binary Segementation, wavelet-based smoothing (both as in Liu et al., and HaarSeg as in Ben-Yaacov and Eldar), HMM, GLAD, CGHseg. Most computations are parallelized (either via forking or with clusters, including MPI and sockets clusters) and use ff for storing data.

Functions for forward population genetic simulation in asexual populations, with special focus on cancer progression. Fitness can be an arbitrary function of genetic interactions between multiple genes or modules of genes, including epistasis, order restrictions in mutation accumulation, and order effects. Fitness (including just birth, just death, or both birth and death) can also be a function of the relative and absolute frequencies of other genotypes (i.e., frequency-dependent fitness). Mutation rates can differ between genes, and we can include mutator/antimutator genes (to model mutator phenotypes). Simulating multi-species scenarios and therapeutic interventions, including adaptive therapy, is also possible. Simulations use continuous-time models and can include driver and passenger genes and modules. Also included are functions for: simulating random DAGs of the type found in Oncogenetic Trees, Conjunctive Bayesian Networks, and other cancer progression models; plotting and sampling from single or multiple realizations of the simulations, including single-cell sampling; plotting the parent-child relationships of the clones; generating random fitness landscapes (Rough Mount Fuji, House of Cards, additive, NK, Ising, and Eggbox models) and plotting them.

Duchifat-2.3-Instruct is a state-of-the-art, instruction-tuned Large Language Model developed by TopAI. As the flagship of the Duchifat series, this model represents a fundamental breakthrough in how Hebrew is processed, reasoned, and generated in the LLM era.

Determine sample ploidy via flow cytometry histogram analysis. Reads Flow Cytometry Standard (FCS) files via the flowCore bioconductor package, and provides functions for determining the DNA ploidy of samples based on internal standards.

This repository contains the PyTorch model weights for MarS-FM (Markov Space Flow Matching) trained on the MD-CATH dataset. This model was introduced in the ICLR 2026 paper: MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models.

An extensive set of data (pre-)processing and analysis methods and tools for metabolomics and other omics, with a strong emphasis on statistics and machine learning. This toolbox allows the user to build extensive and standardised workflows for data analysis. The methods and tools have been implemented using class-based templates provided by the struct (Statistics in R Using Class-based Templates) package. The toolbox includes pre-processing methods (e.g. signal drift and batch correction, normalisation, missing value imputation and scaling), univariate (e.g. ttest, various forms of ANOVA, Kruskal–Wallis test and more) and multivariate statistical methods (e.g. PCA and PLS, including cross-validation and permutation testing) as well as machine learning methods (e.g. Support Vector Machines). Ontology terms have been integrated to provide standardised definitions for the different methods, inputs and outputs.

!image

Dataset and benchmarking framework integrating histology and spatial transcriptomics, enabling multimodal analysis of whole-slide images with matched spatial gene expression for advancing computational pathology and tissue microenvironment research (Mahmood Lab, Harvard Medical School, 411+ stars)

spatialFDA is a package to calculate spatial statistics metrics. The package takes a SpatialExperiment object and calculates spatial statistics metrics using the package spatstat. Then it compares the resulting functions across samples/conditions using functional additive models as implemented in the package refund. Furthermore, it provides exploratory visualisations using functional principal component analysis, as well implemented in refund.

An issue on the Vertebrate Breed Ontology GitHub issue tracker

Imports transcript-level abundance, estimated counts and transcript lengths, and summarizes into matrices for use with downstream gene-level analysis packages. Average transcript length, weighted by sample-specific transcript abundance estimates, is provided as a matrix which can be used as an offset for different expression of gene-level counts.

lisaClust provides a series of functions to identify and visualise regions of tissue where spatial associations between cell-types is similar. This package can be used to provide a high-level summary of cell-type colocalization in multiplexed imaging data that has been segmented at a single-cell resolution.

The core function of this R package is to provide the implementation of the well-cited and well-reviewed QUBIC algorithm, aiming to deliver an effective and efficient biclustering capability. This package also includes the following related functions: (i) a qualitative representation of the input gene expression data, through a well-designed discretization way considering the underlying data property, which can be directly used in other biclustering programs; (ii) visualization of identified biclusters using heatmap in support of overall expression pattern analysis; (iii) bicluster-based co-expression network elucidation and visualization, where different correlation coefficient scores between a pair of genes are provided; and (iv) a generalize output format of biclusters and corresponding network can be freely downloaded so that a user can easily do following comprehensive functional enrichment analysis (e.g. DAVID) and advanced network visualization (e.g. Cytoscape).

This package provides functions to browse the harmonized metadata for large omics databases. This package also supports data navigation if the metadata incorporates ontology.

Retrieves condition-specific variants in RNA-seq data (SNVs, alternative-splicings, indels). It has been developed as a post-treatment of 'KisSplice' but can also be used with user's own data.

Single-cell mRNA sequencing can uncover novel cell-to-cell heterogeneity in gene expression levels in seemingly homogeneous populations of cells. However, these experiments are prone to high levels of technical noise, creating new challenges for identifying genes that show genuine heterogeneous expression within the population of cells under study. BASiCS (Bayesian Analysis of Single-Cell Sequencing data) is an integrated Bayesian hierarchical model to perform statistical analyses of single-cell RNA sequencing datasets in the context of supervised experiments (where the groups of cells of interest are known a priori, e.g. experimental conditions or cell types). BASiCS performs built-in data normalisation (global scaling) and technical noise quantification (based on spike-in genes). BASiCS provides an intuitive detection criterion for highly (or lowly) variable genes within a single group of cells. Additionally, BASiCS can compare gene expression patterns between two or more pre-specified groups of cells. Unlike traditional differential expression tools, BASiCS quantifies changes in expression that lie beyond comparisons of means, also allowing the study of changes in cell-to-cell heterogeneity. The latter can be quantified via a biological over-dispersion parameter that measures the excess of variability that is observed with respect to Poisson sampling noise, after normalisation and technical noise removal. Due to the strong mean/over-dispersion confounding that is typically observed for scRNA-seq datasets, BASiCS also tests for changes in residual over-dispersion, defined by residual values with respect to a global mean/over-dispersion trend.

Fully autonomous medical image segmentation research system that generates complete manuscripts end-to-end from datasets with zero human intervention, beating strongest baselines on 24 of 31 datasets and achieving T1-T2 tier manuscript quality in double-blind evaluations (USTC & Shanghai AI Lab, 2026)

A frontier protein-language generative model — because proteins deserve better small talk.

Unified latent diffusion transformer that jointly generates periodic crystals and non-periodic molecules, scaling to 500M parameters with SOTA results on QM9, MP20, and GEOM-DRUGS (Meta FAIR, ICML 2025, 310+ stars)

The EMI ontology is used to structure spectrum annotation provenance by reusing the PROV-O ontology (a W3C recommendation) and sample and observation data by applying the SOSA ontology. EMI reuses the SOSA ontology as a data schema for struturing the Sample and Observation data. SOSA (Sensor, Observation, Sample, and Actuator) is a subset of SSN (Semantic Sensor Network Ontology) that is a W3C recommendation. [from homepage]

AstraZeneca's industrial-grade retrosynthetic planning tool using MCTS to recursively decompose molecules into purchasable precursors, with multi-step route scoring and support for custom one-step models (v4.0, 2024)

UBio-MolFM is a foundation model suite for molecular modeling, specifically designed for bio-systems. This model, UBio-MolFM-V1 (Stage 3), is built on the E2Former-V2 linear-scaling equivariant transformer architecture. Refer to the technique report for more details: UBio-MolFM (arXiv:2602.17709).

Fine-tuned version of google/gemma-4-E4B-it across three professional domains — Medical, Legal, and Finance — using QLoRA (4-bit NF4) with Optuna-tuned hyperparameters, trained on Kaggle T4 GPU.

Scalable agentic training environment for code-centric reasoning in biomedical data science

This is an R package for interfacing with the BIOM file format. This package includes basic tools for reading biom-format files, accessing and subsetting data tables from a biom object (which is more complex than a single table), as well as limited support for writing a biom-object back to a biom-format file. The design of this API is intended to match the python API and other tools included with the biom-format project, but with a decidedly "R flavor" that should be familiar to R users. This includes S4 classes and methods, as well as extensions of common core functions/methods.

Stamps Seurat, SingleCellExperiment, and SummarizedExperiment objects with a persistent metadata passport. For Seurat objects the passport is stored in the misc slot; for SingleCellExperiment and SummarizedExperiment objects it is stored in the metadata slot. Tracks animal info, experiment details, lineage (parent/child relationships), RDS registry numbers, processing logs, and custom fields. Includes an interactive Shiny gadget to fill and update the passport, and a read mode to print the full passport to console. The passport persists inside the RDS file with no external files needed.

Open Parser for Systematic IUPAC nomenclature

The Context and Measurement Ontology (COMO) contains ontological terms to describe the context for various types of experimental data and measurements. It is useful in its current state for several different environmental microbiology projects. This ontology is used in multiple CORAL (Contextual Ontology-based Repository Analysis Library) deployments.

An issue on the Information Artifact Ontology GitHub issue tracker

Implements a DelayedArray backend for reading and writing dense or sparse arrays in the TileDB format. The resulting TileDBArrays are compatible with all Bioconductor pipelines that can accept DelayedArray instances.

L1 (Learning Unit 1) is the first language model from Lunit and Lunit Consortium, purpose-built for the medical domain. Derived from Gravity-16B-A3B-Base, L1 is designed for clinical reasoning and decision support.

Improved equivariant Transformer for 3D atomic graphs (ICLR2024)

A test harness for bsseq loading of Biscuit output, summarization of WGBS data over defined regions and in mappable samples, with or without imputation, dropping of mostly-NA rows, age estimates, etc.

A series of statistical models using count generating distributions for background modelling, feature and sample QC, normalization and differential expression analysis on GeoMx RNA data. The application of these methods are demonstrated by example data analysis vignette.

> Note: This checkpoint was donated to Huggingface-science to support open medical AI research

CodonTranslator is a protein-conditioned codon sequence generation model trained on the representative-only data_v3 release.

A frontier protein-language generative model — because proteins deserve better small talk.

!Banner.

Lightweight Expression displaYer (plotter / viewer) of SummarizedExperiment object in R. This package provides a quick and easy Shiny-based GUI to empower a user to use a SummarizedExperiment object to view

Point mutations occurring in a genome can be divided into 96 categories based on the base being mutated, the base it is mutated into and its two flanking bases. Therefore, for any patient, it is possible to represent all the point mutations occurring in that patient's tumor as a vector of length 96, where each element represents the count of mutations for a given category in the patient. A mutational signature represents the pattern of mutations produced by a mutagen or mutagenic process inside the cell. Each signature can also be represented by a vector of length 96, where each element represents the probability that this particular mutagenic process generates a mutation of the 96 above mentioned categories. In this R package, we provide a set of functions to extract and visualize the mutational signatures that best explain the mutation counts of a large number of patients.