Find open-source science resources

From https://anndata.readthedocs.io/en/latest/ "Python package for handling annotated data matrices in memory and on disk, positioned between pandas and xarray."

A list of values for class levels. Created in the context of the OpenEduHub

A 1.7B-parameter causal language model distilled from Qwen3-30B-A3B on 6,122 STEM chain-of-thought samples using discrepancy-informed knowledge distillation. The training objective emphasizes proof structure, detects reasoning pivot tokens through token-level divergence dynamics, smooths…

DeepTaxa is a hybrid CNN-BERT deep learning framework for multi-rank taxonomic classification of 16S rRNA gene sequences. It predicts all seven Linnaean ranks from domain to species in a single forward pass and provides pre-trained checkpoints for full-length 16S and V3-V4 amplicons.

The ASURI (Analysis of SUrvival and patients RIsk prediction based on gene signatures) package discovers marker genes that are related to risk prediction capabilities and to a clinical variable of interest. It uses two main steps, including subsampling glmnet and unicox. The package implements robust functions to discover survival markers related to a clinical phenotype and to predict a risk score, allowing to study the patient's risk based on the gene signatures. Several plots are provided to visualise the relevance of the genes, the risk score, and patient stratification, as well as a robust version of the Kaplan-Meier curves.

Next-generation benchmark for data-driven global weather models with standardized evaluation framework and curated datasets for ML forecasting (Google Research, 2024)

Computational fluid dynamics in JAX, enabling differentiable Navier-Stokes simulations with automatic differentiation for ML-accelerated CFD research, supporting turbulence modeling, convection-diffusion, and complex boundary conditions on CPUs and GPUs (Google Research, 947+ stars)

A list of pipeline resources.

A much faster analytical implementation of chromVAR, with additional features, used to infer TF activity from (bulk or single-cell) ATAC-seq data and motif annotations (or binding probabilities). The package also includes the CVnorm normalization method based on the chromVAR logic.

Fine-tuned ESM-2 650M with LoRA for predicting protein subcellular localization (10 classes).

Exon-intron split analysis (EISA) uses ordinary RNA-seq data to measure changes in mature RNA and pre-mRNA reads across different experimental conditions to quantify transcriptional and post-transcriptional regulation of gene expression. For details see Gaidatzis et al., Nat Biotechnol 2015. doi: 10.1038/nbt.3269. eisaR implements the major steps of EISA in R.

standR is an user-friendly R package providing functions to assist conducting good-practice analysis of Nanostring's GeoMX DSP data. All functions in the package are built based on the SpatialExperiment object, allowing integration into various spatial transcriptomics-related packages from Bioconductor. standR allows data inspection, quality control, normalization, batch correction and evaluation with informative visualizations.

PhenoVisionL is a Vision Transformer (ViT-Large) model fine-tuned to detect leaf phenological states in plant photographs: green leaves, colored (senescent) leaves, and breaking leaf buds. It was trained on 165,988 iNaturalist records of deciduous woody plants using a two-stage semi-supervised…

PhenoVision is a Vision Transformer (ViT-Large) model fine-tuned to detect flowers and fruits in plant photographs. It was trained on 1.5 million human-annotated iNaturalist images and has been used to generate over 30 million new phenology records across 119,000+ plant species, vastly expanding…

A cross-platform and ultrafast toolkit for FASTA/Q file manipulation in Golang.

GO Rules are a way of documenting the set of filters and reports that should apply to GAF annotation data. Some rules are expressed as SPARQL on a triplestore, some are code in the GAF parsing software, ontobio.

This package implements functions to analyze multi-omics epigenetic data. Data of fragment type and base type are supported by epiSeeker. It provides functions to retrieve the nearest genes around the peak, annotate genomic region of the peak, statistical methods to estimate the significance of overlap among peak data sets, and motif analysis. It incorporates the GEO database for users to compare their own dataset with those deposited in the database. The comparison can be used to infer cooperative regulation and thus can be used to generate hypotheses. Several visualization functions are implemented to summarize the coverage of the peak experiment, average profile and heatmap of peaks binding to TSS regions, genomic annotation, distance to TSS, overlap of peaks or genes, and the single-base resolution epigenetic data by considering the strand, motif, and additional information.

> NEXUS domain specialist for medical Q&A and clinical reasoning — lightweight & uncensored.

The scDiagnostics package provides diagnostic plots to assess the quality of cell type assignments from single cell gene expression profiles. The implemented functionality allows to assess the reliability of cell type annotations, investigate gene expression patterns, and explore relationships between different cell types in query and reference datasets allowing users to detect potential misalignments between reference and query datasets. The package also provides visualization capabilities for diagnostics purposes.

> NEXUS domain specialist for medical Q&A and clinical reasoning — lightweight & uncensored.

Tools to compute and visualize overlaps between gene sets or genomic regions. Venn diagrams with proportional areas are provided, while UpSet plots are recommended for larger numbers of sets. The package supports GRanges and GRangesList inputs, and integrates with analysis workflows for ChIP-seq, ATAC-seq, and other genomic interval data. It generates clean, interpretable, and publication-ready figures.

Uses quadratic programming for signature refitting, i.e., to decompose the mutation catalog from an individual tumor sample into a set of given mutational signatures (either Alexandrov-model signatures or Shiraishi-model signatures), computing weights that reflect the contributions of the signatures to the mutation load of the tumor.

A package for creating fast and accurate interatomic potentials.

Learning operators in Fourier space

IDPO is used to describe structural aspects of an IDP/IDR, self-functions and functions directly associated with their disordered state. GO is used to describe functional aspects of an IDP/IDR.

Toolkit for identification and statistical testing of RNA editing signals from within R. Provides support for identifying sites from bulk-RNA and single cell RNA-seq datasets, and general methods for extraction of allelic read counts from alignment files. Facilitates annotation and exploratory analysis of editing signals using Bioconductor packages and resources.

Google DeepMind's official collection of agentic science skills accelerating scientific workflows with better grounding and higher token efficiency, integrating insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools (2026)

Ensemble of automated QM workflows that can be run through jupyter notebooks, command lines and yaml files.

Deep learning-based bioacoustic monitoring framework for automated bird species identification from audio recordings, supporting 6,000+ species globally with real-time analysis, batch processing, and API deployment; foundational tool in biodiversity research, conservation biology, and ecological acoustic monitoring (Cornell Lab of Ornithology, 1.5K+ stars, MIT License)

This package provides modalities to analyze tumor evolution from whole genome sequencing data. In particular, it provides estimates of mutation densities at genomic segments and uses these to time the origin of the tumor.

Performs unbiased cell type recognition from single-cell RNA sequencing data, by leveraging reference transcriptomic datasets of pure cell types to infer the cell of origin of each single cell independently.

The scDblFinder package gathers various methods for the detection and handling of doublets/multiplets in single-cell sequencing data (i.e. multiple cells captured within the same droplet or reaction volume). It includes methods formerly found in the scran package, the new fast and comprehensive scDblFinder method, and a reimplementation of the Amulet detection method for single-cell ATAC-seq.

This package is a parser to import HiC data into R. It accepts several type of data: tabular files, Cooler `.cool` or `.mcool` files, Juicer `.hic` files or HiC-Pro `.matrix` and `.bed` files. The HiC data can be several files, for several replicates and conditions. The data is formated in an InteractionSet object.

Peak Detection in Mass Spectrometry data is one of the important preprocessing steps. The performance of peak detection affects subsequent processes, including protein identification, profile alignment and biomarker identification. Using Continuous Wavelet Transform (CWT), this package provides a reliable algorithm for peak detection that does not require any type of smoothing or previous baseline correction method, providing more consistent results for different spectra. See <doi:10.1093/bioinformatics/btl355} for further details.

Manipulation and analysis of geometric objects.

R-package with shiny interface, provides a framework for the analysis of transcriptomics, proteomics and/or metabolomics data. The interface offers a guided experience for the user, from the definition of the experimental design to the integration of several omics table together. A report can be generated with all settings and analysis results.

`muscat` provides various methods and visualization tools for DS analysis in multi-sample, multi-group, multi-(cell-)subpopulation scRNA-seq data, including cell-level mixed models and methods based on aggregated “pseudobulk” data, as well as a flexible simulation platform that mimics both single and multi-sample scRNA-seq data.

SimBu can be used to simulate bulk RNA-seq datasets with known cell type fractions. You can either use your own single-cell study for the simulation or the sfaira database. Different pre-defined simulation scenarios exist, as are options to run custom simulations. Additionally, expression values can be adapted by adding an mRNA bias, which produces more biologically relevant simulations.

Distilling Boltz: Flow Maps for Fast All-Atom Cofolding

An interactive platform that performs statistical analyses on metabolomics datasets and allows visualising results with ease. The interface gives users autonomy in creating figures suited to their reporting and publication needs.

karyoploteR creates karyotype plots of arbitrary genomes and offers a complete set of functions to plot arbitrary data on them. It mimicks many R base graphics functions coupling them with a coordinate change function automatically mapping the chromosome and data coordinates into the plot coordinates. In addition to the provided data plotting functions, it is easy to add new ones.

Simulations of spiking neural networks.

BgeeCall allows to generate present/absent gene expression calls without using an arbitrary cutoff like TPM<1. Calls are generated based on reference intergenic sequences. These sequences are generated based on expression of all RNA-Seq libraries of each species integrated in Bgee (https://bgee.org).

Compare differential gene expression results with those from known cellular perturbations (such as gene knock-down, overexpression or small molecules) derived from the Connectivity Map. Such analyses allow not only to infer the molecular causes of the observed difference in gene expression but also to identify small molecules that could drive or revert specific transcriptomic alterations.

Open-source biomedical AI platform integrating multimodal foundation models (BioMedGPT, PharmolixFM, LangCell) with agentic workflows and 45+ Claude Code skills for drug discovery, protein engineering, and single-cell omics analysis (PharMolix & Tsinghua AIR, 1K+ stars, 2023-2026)

Utilities for working with CSV/Tab-delimited files.

Long-context generative genomic foundation model using 6-mer tokenization for DNA sequence modeling and generation, with v2 model families for prokaryote and eukaryote genomes and pretrained weights available on HuggingFace (GenerTeam, 460+ stars, MIT License, 2025-2026)