Find open-source science resources

SQUARNA is a tool for RNA secondary structure prediction. It can take a single RNA sequence or an alignment of sequences as input. SQUARNA handles pseudoknots and can predict alternative structures. SQUARNA allows structural restraints and chemical probing data as additional input and is available at https://github.com/febos/SQUARNA and https://larnal.imol.institute/.

🩺 HealthGPT-Pro: A High-Performance Multimodal Large Language Model for Medical Understanding and Analysis

Ontology representation of the [International Committee on Taxonomy of Viruses (ICTV)](https://ictv.global/) for the [EVORA project](https://evora-project.eu/)

This ontology describes sensors, actuators and observations, and related concepts. It does not describe domain concepts, time, locations, etc. these are intended to be included from other ontologies via OWL imports.

Graph neural network library for PyTorch enabling molecular modeling, materials discovery, protein interaction networks, and scientific knowledge graph learning (23.7k+ stars)

Meta's comprehensive ML ecosystem for materials/chemistry with 118M+ DFT calculations, EquiformerV2 models achieving top Matbench Discovery performance

A binary healthy hard coral vs bleached hard coral classifier built on top of the ReefNet species LoRA model BobDerBaum/bioclip-2.5-vith14-reefnet-lora, which provides the fine-tuned vision-encoder LoRA adapters. Only a small linear head is trained on top (frozen backbone + LoRA + 2-way linear…

A LoRA fine-tune of imageomics/bioclip-2.5-vith14 trained contrastively on the ReefNet 1.0 coral-reef species dataset (ReefNet/ReefNet-1.0), 92-class global curated split (train 48,312 / image-val 32,792 / image-test 33,090 / source-val 8,074; split cache 56ea94e36f9f).

PyTorch-based embedding instance segmentation algorithm optimized for accurate, efficient, and portable cell and nucleus segmentation across fluorescence and brightfield microscopy images, achieving state-of-the-art speed and accuracy with lightweight model sizes suitable for edge deployment (224+ stars, Apache 2.0)

Toolbox for comparative genomics of MAGs

A library for processing, analyzing and modeling spectroscopic data.

A lightweight language model designed to answer science questions clearly and accurately in English.

Chemical Information from the Web.

!Nucleus Resynthesis

Microsoft's generative model for sampling protein equilibrium conformations 100,000× faster than MD simulations, predicting domain motions, local unfolding and cryptic binding pockets on a single GPU (Science 2025)

Unified Python framework for extracellular electrophysiology, standardizing interfaces to 10+ ML-based spike sorting algorithms including Kilosort for reproducible neural spike sorting workflows (792+ stars, actively maintained)

PseudoScope is an automated, locally-executable computational pipeline designed specifically for comprehensive Pseudomonas aeruginosa genomic surveillance. It integrates seven essential analysis modules into a single, cohesive workflow: FASTA QC (assembly quality metrics), MLST (Oxford scheme), PAST serotyping (O-antigen typing), AMRFinderPlus (antimicrobial resistance gene detection), ABRicate (multi-database screening for resistance, virulence, plasmids, biocides), Ultimate Reporter (gene-centric integration with interactive HTML), and Visualisation Dashboard (publication-ready interactive plots including PCA, networks, boxplots). PseudoScope runs entirely locally (or on HPC clusters), protects data privacy, and produces beautiful interactive reports in minutes.

Kleboscope is an automated, locally‑executable computational pipeline designed specifically for comprehensive Klebsiella pneumoniae genomic surveillance. It addresses the growing threat of multidrug‑resistant and hypervirulent K. pneumoniae by integrating eight essential analysis modules into a single, cohesive workflow. Kleboscope offers two complementary report views: Gene‑centric – each gene is shown with all genomes that contain it, together with its frequency, enabling rapid cross‑genome pattern discovery; and Sample‑centric – each isolate gets its own interactive box with typing badges (MLST, K‑locus, O‑locus, hypervirulence), per‑database tables (AMR, Virulence, BACMET, Plasmids), and full mutation details – perfect for clinical reports and patient‑level investigations.

Acausal modeling framework for automatically parallelized scientific machine learning (1.5k+ stars)

Differential abundance testing in microbiome data challenges both parametric and non-parametric statistical methods, due to its sparsity, high variability and compositional nature. Microbiome-specific statistical methods often assume classical distribution models or take into account compositional specifics. These produce results that range within the specificity vs sensitivity space in such a way that type I and type II error that are difficult to ascertain in real microbiome data when a single method is used. Recently, a consensus approach based on multiple differential abundance (DA) methods was recently suggested in order to increase robustness. With dar, you can use dplyr-like pipeable sequences of DA methods and then apply different consensus strategies. In this way we can obtain more reliable results in a fast, consistent and reproducible way.

Java framework for processing biological data.

A Python script that converts positional information from a SAM dataset into interval format with 0-based start and 1-based end. CIGAR string of SAM format is used to compute the end coordinate.

High-throughput extensible toolkit for processing FASTQ data. The goal of this package is to empower users to quickly build out small programmatic 'kernels' to define any FASTQ processing task they may need. Builds on Intel TBB’s flow graph to orchestrate concurrent I/O and data processing; throughput can be as fast as compression and disk speed allows. The package also ships with a suite of predefined kernels for common FASTQ tasks.

A two-step desktop GUI application for RNA-seq differential gene expression (DEG) analysis. Step 1 reads raw GDC/TCGA STAR gene-count files together with a GDC sample sheet, matches samples to a Tumor/Normal design, and runs PyDESeq2 to produce normalized counts and DEG statistics. Step 2 generates publication-style volcano plots, MA plots, summary bar charts, and expression heatmaps (with optional gene labeling) from the results, exportable as PNG, PDF, SVG, or TIFF. Requires no coding from the user.

Scientific Computing for Chemists with Python is a Jupyter book teaching basic python in chemistry skills, including relevant libraries, and applies them to solving chemical problems.

AI coding assistant for JupyterLab with agent mode, supporting arbitrary LLM providers (2025+)

An R interface to the HISAT2 spliced short-read aligner by Kim et al. (2015). The package contains wrapper functions to create a genome index and to perform the read alignment to the generated index.

SpaceTrooper performs Quality Control analysis using data driven GLM models of Image-Based spatial data, providing exploration plots, QC metrics computation, outlier detection. It implements a GLM strategy for the detection of low quality cells in imaging-based spatial data (Transcriptomics and Proteomics). It additionally implements several plots for the visualization of imaging based polygons through the ggplot2 package.

Agent-agnostic research infrastructure providing AI agents with a structured scientific workspace for deep PDF parsing, hybrid semantic/keyword literature search, citation-graph analysis, topic discovery, and academic writing workflows; natively integrates with Claude Code, Codex, Cursor, Cline, and AgentSkills.io (530+ stars, MIT License, 2026)

Package fills a helper package role for whole gDR suite. It helps to support good development practices by keeping style requirements and style tests for other packages. It also contains build helpers to make all package requirements met.

Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model; official code for the Nature Neuroscience paper and Meta blog post on brain-AI communication (Meta FAIR, 894+ stars, CC BY-NC 4.0, 2026)

Python Materials Genomics: robust materials analysis library defining classes for structures and molecules with support for many electronic structure codes; foundational toolkit powering the Materials Project (Berkeley Lab, 1.8K+ stars)

For a convenient overview and download list, visit our model page for this model.

seqlib is a type-safe Rust library for working with DNA and RNA sequences.

Open-source SDK for working with quantum computers at the level of extended quantum circuits, operators, and primitives, enabling quantum algorithm development for quantum chemistry, materials science, and optimization research (IBM, 7.4K+ stars, Apache 2.0)

Web-based platform for discovering professional contacts, organizations, and business email addresses using advanced search and filtering capabilities.

A package to 'build' collections of materials properties from the output of computational materials calculations.

StaphScope is an automated, locally-executable computational pipeline designed specifically for comprehensive Staphylococcus aureus genomic surveillance. It addresses the critical bottleneck in MRSA research by integrating seven essential genotyping methods into a single, cohesive workflow.

Winnow recalibrates confidence scores and provides FDR control for de novo peptide sequencing (DNS) workflows. This repository hosts a calibrator trained on the HeLa Single Shot dataset as referenced in our paper: De novo peptide sequencing rescoring and FDR estimation with Winnow.

Winnow recalibrates confidence scores and provides FDR control for de novo peptide sequencing (DNS) workflows. This repository hosts a pretrained, general-purpose calibrator that maps raw InstaNovo model confidences and complementary features (mass error, retention time, beam features, fragment…

Deep learning atomistic model across elements, temperatures, and pressures

Large transformer-based single-cell foundation model pretrained on 50 million cells for robust gene network inference, expression denoising, cell embedding, and zero-shot label prediction, leveraging ESM2 protein embeddings and bidirectional transformer architecture (Cantini Lab, 148+ stars, GPL-3.0)

Parallel computing with task scheduling.

Biomedical AI agents

Benchmark evaluating AI agents for end-to-end automated research from re-discovery to new-discovery, with 40 real-science tasks across 10 disciplines, curated datasets from published papers, and expert-curated multimodal rubrics (170+ stars, MIT License)

COSMOS (Causal Oriented Search of Multi-Omic Space) is a method that integrates phosphoproteomics, transcriptomics, and metabolomics data sets based on prior knowledge of signaling, metabolic, and gene regulatory networks. It estimated the activities of transcrption factors and kinases and finds a network-level causal reasoning. Thereby, COSMOS provides mechanistic hypotheses for experimental observations across mulit-omics datasets.

Local-first, conversational AI research partner for multi-omics analysis with CLI, desktop app, and 95+ reproducible skills; keeps raw data local while routing natural-language requests to Python/R/CLI tools with persistent memory, autonomous analysis paths, and multi-method consensus workflows (TianGzlab, 155+ stars, Apache 2.0, 2026)