Find open-source science resources

Framework for processing and visualization of chromatographically separated and single-spectra mass spectral data. Imports from AIA/ANDI NetCDF, mzXML, mzData and mzML files. Preprocesses data for high-throughput, untargeted analyte profiling.

Open-source implementation of AlphaEvolve's evolutionary coding agent paradigm, enabling LLMs to autonomously discover and optimize algorithms through iterative evolution, matching the approach behind DeepMind's breakthrough matrix multiplication discovery (6.2K+ stars, 2025)

!Screenshot 2026-07-05 at 2.33.47 AM

This package implements sampling, iteration, and input of FASTQ files. The package includes functions for filtering and trimming reads, and for generating a quality assessment report. Data are represented as DNAStringSet-derived objects, and easily manipulated for a diversity of purposes. The package also contains legacy support for early single-end, ungapped alignment formats.

### Model Overview TabPFN-3 is a transformer-based foundation model that uses in-context-learning to solve tabular prediction problems in a forward pass. Inference code can be found at https://github.com/PriorLabs/TabPFN. More details can be found in the Model Report.

This repository contains LoRA finetunes of DiffusionGemma (image-conditioned discrete-diffusion LLM) for radiology visual question answering, each paired with an autoregressive Gemma-4 finetune as a controlled baseline. It corresponds to the paper Discrete Diffusion Language Models for Interactive…

Interactive explorer for single-cell transcriptomics data enabling visualization of UMAP/t-SNE embeddings, differential expression analysis, and cross-dataset comparison through a fast web-based interface; widely adopted for exploring atlas-scale single-cell datasets and integrating with AI/ML analysis workflows (773+ stars, MIT License)

Interactive browser for the complete Human Phenotype Ontology (~19,800 terms), with a graph-based term explorer and a clinical profile analyzer for phenotype similarity, differential diagnosis, and gene prioritization.

Multi-agent system for drug-discovery gene target validation. LangGraph agents over an MCP data layer (~26 data sources, ~44 tools) score evidence across six independent lenses (genetics, biology, safety, clinical, commercial, regulatory) into a provenanced dossier. Configurable local/cloud LLM routing with full Langfuse/OTEL traceability.

Fine-tuned gSelformer-MV-Dyn model for predicting dynamic surface tension (DST) curves from SMILES, temperature, and concentration.

LLM papers for scientific discovery

"rhinotypeR" is designed to automate the comparison of sequence data against prototype strains, streamlining the genotype assignment process. By implementing predefined pairwise distance thresholds, this package makes genotype assignment accessible to researchers and public health professionals. This tool enhances our epidemiological toolkit by enabling more efficient surveillance and analysis of rhinoviruses (RVs) and other viral pathogens with complex genomic landscapes. Additionally, "rhinotypeR" supports comprehensive visualization and analysis of single nucleotide polymorphisms (SNPs) and amino acid substitutions, facilitating in-depth genetic and evolutionary studies.

Toolkit for large-scale whole-slide image processing supporting 22+ patch encoders (UNI, CONCH, Virchow, H-Optimus-0, etc.), slide encoders (TITAN, GigaPath, PRISM, CHIEF, Madeleine, Feather), tissue segmentation, and multi-GPU inference with end-to-end pipeline and smart resume for standardized deployment of computational pathology foundation models (Mahmood Lab, Harvard Medical School, 553+ stars)

A classification of subjects in Hochschule (universities of applied sciences)

A controlled vocbualry of higher education resource types

NanoMethViz is a toolkit for visualising methylation data from Oxford Nanopore sequencing. It can be used to explore methylation patterns from reads derived from Oxford Nanopore direct DNA sequencing with methylation called by callers including nanopolish, f5c and megalodon. The plots in this package allow the visualisation of methylation profiles aggregated over experimental groups and across classes of genomic features.

A native MLX port of OpenMed/privacy-filter-multilingual-v2 for Apple Silicon PII detection and de-identification with OpenMed. This is the unquantized BF16 reference artifact. For the 8-bit sibling, see OpenMed/privacy-filter-multilingual-v2-mlx-8bit.

simPIC is a package for simulating single-cell ATAC-seq count data. It provides a user-friendly, well documented interface for data simulation. Functions are provided for parameter estimation, realistic scATAC-seq data simulation, and comparing real and simulated datasets.

A native MLX port of OpenMed/privacy-filter-multilingual-v2, affine-quantized to 8-bit for faster and smaller Apple Silicon PII detection with OpenMed. For the unquantized BF16 reference, see OpenMed/privacy-filter-multilingual-v2-mlx.

The EVORAO Ontology provides a structured and harmonized vocabulary for describing shareable pathogens as characterized biological materials, along with their derived products and associated services, organized into collections. Developed within the EVORA project, it supports consistent metadata annotation across research infrastructures, promoting findability, accessibility, interoperability, and reusability (FAIR). By aligning with relevant standards and ontologies, EVORAO facilitates cross-domain collaboration, integration, and sharing of pathogenic resources and services to enhance pandemic preparedness and response. While initially focused on virology, EVORAO is designed to be extensible and also supports metadata harmonization for other pathogens. [from repository]

Family of large language models for materials research via continued pretraining of LLaMA-2/3 on ~30B materials science tokens, outperforming commercial LLMs on materials science tasks while identifying "adaptation rigidity" in overtrained models; includes MatNLP benchmark and CIF crystal generation capabilities (IIT Delhi M3RG, MIT License)

Polymathic AI's large omnimodal foundation model for astronomical surveys, seamlessly integrating 39 distinct data modalities including imaging, spectra, photometry, and catalog entries for similarity search, property prediction, and generative modeling across legacy surveys (MIT)

Democratizing AlphaFold3: PyTorch reimplementation to accelerate protein structure prediction research

The barbieQ package provides a series of robust statistical tools for analysing barcode count data generated from cell clonal tracking (i.e., lineage tracing) experiments. In these experiments, an initial cell and its offspring collectively form a clone (i.e., lineage). A unique barcode sequence, incorporated into the DNA of the inital cell, is inherited within the clone. This one-to-one mapping of barcodes to clones enables clonal tracking of their behaviors. By counting barcodes, researchers can quantify the population abundance of individual clones under specific experimental perturbations. barbieQ supports barcode count data preprocessing, statistical testing, and visualization.

Galaxy Tool Shed repositories maintained and developed by the GalaxyP community

!ESMC ProtHash Banner

!Python

PomBase manages gene and phenotype data related to Fission Yeast. FYECO contains experimental conditions relevant to fission yeast biology. The FYECO namespace shows up in data ingests from PomBase.

In gene therapy, stem cells are modified using viral vectors to deliver the therapeutic transgene and replace functional properties since the genetic modification is stable and inherited in all cell progeny. The retrieval and mapping of the sequences flanking the virus-host DNA junctions allows the identification of insertion sites (IS), essential for monitoring the evolution of genetically modified cells in vivo. A comprehensive toolkit for the analysis of IS is required to foster clonal trackign studies and supporting the assessment of safety and long term efficacy in vivo. This package is aimed at (1) supporting automation of IS workflow, (2) performing base and advance analysis for IS tracking (clonal abundance, clonal expansions and statistics for insertional mutagenesis, etc.), (3) providing basic biology insights of transduced stem cells in vivo.

compareMS2 is a tool for comparing sets of (tandem) mass spectra for clustering samples, molecular phylogenetics, identification of biological species or tissues, and quality control. compareMS2 currently consumes Mascot Generic Format, or MGF, and produces output in a variety of common image and distance matrix formats.

🤗 Blog | 📄 Paper | 💻 Code | 🌐 FineMed | 🩺 DoctoBERT

🤗 Blog | 📄 Paper | 💻 Code | 🌐 FineMed | 🩺 DoctoBERT

This package addresses two broad areas. It allows for in-depth analysis of spatial transcriptomic data by identifying tissue neighbourhoods. These are contiguous regions of tissue surrounding individual cells. 'CatsCradle' allows for the categorisation of neighbourhoods by the cell types contained in them and the genes expressed in them. In particular, it produces Seurat objects whose individual elements are neighbourhoods rather than cells. In addition, it enables the categorisation and annotation of genes by producing Seurat objects whose elements are genes.

Builds prediction interval for cell type annotation using conformal inference and conformal risk control. It provides two main methods. The first one gives prediction intervals with coverage guarantees based on standard conformal inference. The second one instead gives hierarchical prediction intervals that are consistent with the cell ontology.

Pretrained time series foundation model for zero-shot forecasting across diverse scientific and real-world domains; tokenizes continuous time series into discrete bins to train transformer language models on large-scale corpora, achieving strong zero-shot generalization and competitive performance with task-specific supervised models on climate, energy, and health benchmarks (5.3K+ stars, Apache 2.0, 2024-2026)

Medical time series foundation model pretrained on 454B time points from heterogeneous clinical corpora spanning ICU physiological signals and hospital EHR, with continuous-time rotary positional encoding, frequency-specialized Mixture-of-Experts, and neural ODE extrapolation for zero-shot forecasting across irregular and multimodal temporal health data (Microsoft, 399+ stars, MIT License)

Semi-automated research assistant for academic research and software development, supporting Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication (Galaxy-Dawn, 4.5K+ stars, MIT License, 2026)

Gene regulatory networks model the underlying gene regulation hierarchies that drive gene expression and observed phenotypes. Epiregulon infers TF activity in single cells by constructing a gene regulatory network (regulons). This is achieved through integration of scATAC-seq and scRNA-seq data and incorporation of public bulk TF ChIP-seq data. Links between regulatory elements and their target genes are established by computing correlations between chromatin accessibility and gene expressions.

MCP server, CLI, and agent skills for searching and downloading academic papers from multiple open sources (arXiv, PubMed, bioRxiv, Semantic Scholar, OpenAlex, CORE, Europe PMC, etc.) with unified, deduplicated, LLM-friendly retrieval and an OA-first download fallback chain (OpenAGS, 1.9K+ stars, MIT License, 2025)

98B-parameter frontier generative model jointly reasoning over protein sequence, structure, and function, trained on 2.78 billion proteins; generated a novel fluorescent protein (esmGFP) with only 58% sequence identity to known GFPs (EvolutionaryScale, 2024)

'HuBMAP' provides an open, global bio-molecular atlas of the human body at the cellular level. The `datasets()`, `samples()`, `donors()`, `publications()`, and `collections()` functions retrieves the information for each of these entity types. `*_details()` are available for individual entries of each entity type. `*_derived()` are available for retrieving derived datasets or samples for individual entries of each entity type. Data files can be accessed using `bulk_data_transfer()`.

Curated open dataset collection of 602M+ observational and perturbational single-cell profiles for accelerating virtual cell model creation, integrating Tahoe-100M and scBaseCount data with Google Cloud Marketplace distribution (Arc Institute, 2025-2026)

Parameter/topology editor and molecular simulator with visualization capability.

ClustIRR analyzes repertoires of B- and T-cell receptors. It starts by identifying communities of immune receptors with similar specificities, based on the sequences of their complementarity-determining regions (CDRs). Next, it employs a Bayesian probabilistic models to quantify differential community occupancy (DCO) between repertoires, allowing the identification of expanding or contracting communities in response to e.g. infection or cancer treatment.

msqrob2 provides a robust linear mixed model framework for assessing differential abundance in MS-based Quantitative proteomics experiments. Our workflows can start from raw peptide intensities or summarised protein expression values. The model parameter estimates can be stabilized by ridge regression, empirical Bayes variance estimation and robust M-estimation. msqrob2's hurde workflow can handle missing data without having to rely on hard-to-verify imputation assumptions, and, outcompetes state-of-the-art methods with and without imputation for both high and low missingness. It builds on QFeature infrastructure for quantitative mass spectrometry data to store the model results together with the raw data and preprocessed data.

The Ontology for Biomarkers of Clinical Interest (OBCI) formally defines biomarkers for diseases, phenotypes, and effects.

In recent years a wealth of biological data has become available in public data repositories. Easy access to these valuable data resources and firm integration with data analysis is needed for comprehensive bioinformatics data analysis. biomaRt provides an interface to a growing collection of databases implementing the BioMart software suite (<https://www.ensembl.org/info/data/biomart/index.html>). The package enables retrieval of large amounts of data in a uniform way without the need to know the underlying database schemas or write complex SQL queries. The most prominent examples of BioMart databases are maintained by Ensembl, which provides biomaRt users direct access to a diverse set of data and enables a wide range of powerful online queries from gene annotation to database mining.