Find open-source science resources

Open software framework for Engineering AI built on transformer building blocks, enabling teams to build, train, and operate industrial simulation models across engineering verticals; includes ready-to-use recipes for CFD (AB-UPT on DrivAerML), external aerodynamics, and heat transfer (234+ stars, ENPL non-commercial license, 2026)

This tool estimates the completeness of KEGG pathway modules from the presence or absence of KEGG orthologues (KOs)

Heretic-abliterated version of Qwen/Qwen2.5-0.5B-Instruct for the Evolva drug discovery pipeline.

HantaBERT fine-tunes DNABERT-2 on hantavirus RNA sequences for three simultaneous classification tasks: species/lineage, host, and geographic origin. A single forward pass produces predictions for all three tasks along with a 768-dimensional embedding suitable for phylogenetic visualization.

Fast and accurate protein structure search using a learned 3Di structural alphabet (VQ-VAE) that discretizes tertiary interactions into structural tokens, enabling protein-universe-scale structural alignment at sequence-search speeds (4-5 orders of magnitude faster than DALI/TM-align) and underpinning many AI4S tools such as SaProt, ESMAtlas search, and AFDB clustering pipelines (Steinegger Lab, Nature Biotechnology 2023)

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

First agentic LLM for autonomous data science with end-to-end pipeline from data to analyst-grade reports

All-atom generative world model for all-to-all biomolecular interaction design, enabling cross-modality generation of proteins, nucleic acids, small molecules, and cyclic peptides with fine-grained epitope-level control and 2-4 orders of magnitude faster design throughput than modality-specific baselines (316+ stars, Apache 2.0)

Xinghe1-9B (杏核) is a specialized large language model fine-tuned for the formalization, computational derivation, and clinical reasoning of Huangdi Neijing. It is based on the Qwen3.5-9B-Instruct architecture and trained using the V3 Double-Purity SFT dataset.

An international LGBTQ+ linked data vocabulary

scToppR provides an easy-to-use API wrapper for the ToppGene web platform, used for gene ontology and functional enrichment research. The package also integrates visualization tools, making it a convenient tool directly connecting ToppGene to code-based workflows in R. The tool can also easily save results into different formats.

Pretrained LDARNet (~2M params) with learnable DNA tokenization (dynamic chunking + BiMamba-2).

Pretrained LDARNet (~110M params) with learnable DNA tokenization (dynamic chunking + BiMamba-2).

Perform fast functional enrichment on feature lists (like genes or proteins) using the hypergeometric distribution. Tailored for speed, this package is ideal for interactive platforms such as Shiny. It supports the retrieval of functional data from sources like GO, KEGG, Reactome, Bioplanet and WikiPathways. By downloading and preparing data first, it allows for rapid successive tests on various feature selections without the need for repetitive, time-consuming preparatory steps typical of other packages.

Multi-modal foundation model for biomolecular structure prediction (proteins, small molecules, DNA, RNA, glycans) achieving SOTA across benchmarks, with optional MSA/template support (Chai Discovery, 2024)

# Overview This is the CellHermes model, based on the LLaMA-3.1-8B-instruct architecture developed by Meta, fine-tuned using single-cell RNA sequencing (scRNA-seq) datasets from CellxGene and PPI network from BioGRID. CellHermes is an innovative framework for adapting existing large language models…

transmogR provides the tools needed to crate a new reference genome or reference transcriptome, using a set of variants. Variants can be any combination of SNPs, Insertions and Deletions. The intended use-case is to enable creation of variant-modified reference transcriptomes for incorporation into transcriptomic pseudo-alignment workflows, such as salmon.

Taking a set of sequence motifs as PWMs, test a set of sequences for over-representation of these motifs, as well as any positional features within the set of motifs. Enrichment analysis can be undertaken using multiple statistical approaches. The package also contains core functions to prepare data for analysis, and to visualise results.

It is a web-application for visual and interactive gene expression analysis. Phantasus is based on Morpheus – a web-based software for heatmap visualisation and analysis, which was integrated with an R environment via OpenCPU API. Aside from basic visualization and filtering methods, R-based methods such as k-means clustering, principal component analysis or differential expression analysis with limma package are supported.

Statistical and computational method to analyze the co-expression of gene pairs at single cell level. It provides the foundation for single-cell gene interactome analysis. The basic idea is studying the zero UMI counts' distribution instead of focusing on positive counts; this is done with a generalized contingency tables framework. COTAN can effectively assess the correlated or anti-correlated expression of gene pairs. It provides a numerical index related to the correlation and an approximate p-value for the associated independence test. COTAN can also evaluate whether single genes are differentially expressed, scoring them with a newly defined global differentiation index. Moreover, this approach provides ways to plot and cluster genes according to their co-expression pattern with other genes, effectively helping the study of gene interactions and becoming a new tool to identify cell-identity marker genes.

Self-hostable scientific claim-verification and literature-review tool combining Semantic Scholar retrieval, bibliometric scoring, and LLM-based evidence synthesis for large-batch validation workflows

The FRBR-aligned Bibliographic Ontology (FaBiO) is an ontology for describing entities that are published or potentially publishable (e.g., journal articles, conference papers, books), and that contain or are referred to by bibliographic references.

An ontology that enables the metadata properties of the DataCite Metadata Schema Specification (i.e., a list of metadata properties for the accurate and consistent identification of a resource for citation and retrieval purposes) to be described in RDF.

An ontology that provides a structured vocabulary written of document components, both structural (e.g., block, inline, paragraph, section, chapter) and rhetorical (e.g., introduction, discussion, acknowledgements, reference list, figure, appendix).

An ontology that enables characterization of the nature or type of citations, both factually and rhetorically.

Deep learning framework for molecular docking extending AutoDock Vina with convolutional neural network scoring functions, achieving superior virtual screening enrichment and pose prediction across diverse target classes; widely adopted in pharmaceutical structure-based drug design (J. Cheminformatics, 915+ stars, actively maintained)

Deep learning with spiking neural networks in Python, providing gradient-based training of SNNs via PyTorch autodifferentiation for brain-inspired computing and neuromorphic research, with online learning capabilities and extensive tutorials (1.9K+ stars, actively maintained)

Parallel Computing and Scientific Machine Learning: MIT 18.337J/6.338J course materials (1.9k+ stars)

cfDNA fragments carry important features for building cancer sample classification ML models, such as fragment size, and fragment end motif etc. Analyzing and visualizing fragment size metrics, as well as other biological features in a curated, standardized, scalable, well-documented, and reproducible way might be time intensive. This package intends to resolve these problems and simplify the process. It offers two sets of functions for cfDNA feature characterization and visualization.

This package builds on existing tools and adds some simple but extremely useful capabilities for working wth ChIP-Seq data. The focus is on detecting differential binding windows/regions. One set of functions focusses on set-operations retaining mcols for GRanges objects, whilst another group of functions are to aid visualisation of results. Coercion to tibble objects is also implemented.

Learnable latent embeddings for joint behavioral and neural analysis, enabling consistent and interpretable mapping of neural activity to behavior across modalities, species, and experiments (EPFL & Harvard, 1K+ stars)

A set of tools to for machine and deep learning in R from amino acid and nucleotide sequences focusing on adaptive immune receptors. The package includes pre-processing of sequences, unifying gene nomenclature usage, encoding sequences, and combining models. This package will serve as the basis of future immune receptor sequence functions/packages/models compatible with the scRepertoire ecosystem.

This repository contains Chemistry fine-tuned Qwen3-4B checkpoints from the local SciKnowEval-style generalization setup.

First system progressively surpassing human SOTA on frontier AI tasks (183.7%, 1.9%, 7.9% improvements), month-long autonomous discovery with 20,000+ GPU hours

'OSTA.data' is a companion package for the "Orchestrating Spatial Transcriptomics Analysis" (OSTA) with Bioconductor online book. Throughout OSTA, we rely on a set of publicly available datasets that cover different sequencing- and imaging-based platforms, such as Visium, Visium HD, Xenium (10x Genomics) and CosMx (NanoString). In addition, we rely on scRNA-seq (Chromium) data for tasks, e.g., spot deconvolution and label transfer (i.e., supervised clustering). These data been deposited in an Open Storage Framework (OSF) repository, and can be queried and downloaded using functions from the 'osfr' package. For convenience, we have implemented 'OSTA.data' to query and retrieve data from our OSF node, and cache retrieved Zip archives using 'BiocFileCache'.

PlantGeneAnn is a plant genome foundation model that enables the prediction of various plant genomic elements at single-nucleotide resolution. The model is built upon the PlantBiMoE architecture with a 1D U-Net segmentation head, specifically designed for automated plant genome annotation.

Tools For analyzing Illumina Infinium DNA methylation arrays. SeSAMe provides utilities to support analyses of multiple generations of Infinium DNA methylation BeadChips, including preprocessing, quality control, visualization and inference. SeSAMe features accurate detection calling, intelligent inference of ethnicity, sex and advanced quality control routines.

Toolbox for larger-than-memory scientific computing and visualization, providing efficient out-of-core data structures using files or shared memory, for dense and sparse vectors, matrices, and arrays, with applications to nonuniformly sampled signals and images.

The package implements an algorithm for fast gene set enrichment analysis. Using the fast algorithm allows to make more permutations and get more fine grained p-values, which allows to use accurate stantard approaches to multiple hypothesis correction.

Computational toolbox for large scale Calcium Imaging Analysis, including movie handling, motion correction, source extraction, spike deconvolution and result visualization, using machine learning for automated neuron detection and activity inference in two-photon and one-photon calcium imaging data (723+ stars, actively maintained)

33 lightweight, standalone models that predict discrete Alzheimer's-disease–related phenotypes (e.g. medication use, APOE genotype, vascular pathology, sex) from SomaScan plasma proteomics. The full list is in phenotypes.tsv.

69 lightweight, standalone models that predict continuous Alzheimer's-disease–related phenotypes (cognition, neuropathology burden, motor/functional measures, demographics, a genetic risk score, and longitudinal change) from SomaScan plasma proteomics.

This repository contains a drop-in, Hugging Face–compatible checkpoint converted from https://huggingface.co/microsoft/llava-med-v1.5-mistral-7b. You can load it with the exact same code you use for the original model—no extra conversion steps required.

👋 Join our LiGHT community. 📖 Check out the MeditronFO blog and MeditronFO preprint. 🔜 If you are a clinician join the MOOVE initiative here.

Sexo-FR is a French-language conversational language model that provides reliable, caring, and evidence-based sexual health information (information en santé sexuelle). It is part of a French public-health initiative whose goal is to make trustworthy sexual-health information more accessible to the…

This package implements a variety of methods for batch correction in single-cell RNA sequencing (scRNA-seq) data. It incorporates quantitative metrics (e.g. Wasserstein distance, Adjusted Rand Index) to evaluate their performance. Furthermore, the package assists users in identifying and applying the optimal method for specific datasets.

👋 Join our LiGHT community. 📖 Check out the MeditronFO blog and MeditronFO preprint. 🔜 If you are a clinician join the MOOVE initiative here.

A novel framework to correct for batch effects prior to any downstream analysis in microbiome data based on Projection to Latent Structures Discriminant Analysis. The main method is named “PLSDA-batch”. It first estimates treatment and batch variation with latent components, then subtracts batch-associated components from the data whilst preserving biological variation of interest. PLSDA-batch is highly suitable for microbiome data as it is non-parametric, multivariate and allows for ordination and data visualisation. Combined with centered log-ratio transformation for addressing uneven library sizes and compositional structure, PLSDA-batch addresses all characteristics of microbiome data that existing correction methods have ignored so far. Two other variants are proposed for 1/ unbalanced batch x treatment designs that are commonly encountered in studies with small sample sizes, and for 2/ selection of discriminative variables amongst treatment groups to avoid overfitting in classification problems. These two variants have widened the scope of applicability of PLSDA-batch to different data settings.

International association of users & developers of open source Perl tools for bioinformatics, genomics and life sciences.