Find open-source science resources

> [!NOTE] > This model has been optimized using NVIDIA's TransformerEngine > library. Slight numerical differences may be observed between the original model and the optimized > model. For instructions on how to install TransformerEngine, please refer to the > official documentation.

> [!NOTE] > This model has been optimized using NVIDIA's TransformerEngine > library. Slight numerical differences may be observed between the original model and the optimized > model. For instructions on how to install TransformerEngine, please refer to the > official documentation.

Reads Bruker NMR data directories both zipped and unzipped. It provides automated and efficient signal processing for untargeted NMR metabolomics. It is able to interpolate the samples, detect outliers, exclude regions, normalize, detect peaks, align the spectra, integrate peaks, manage metadata and visualize the spectra. After spectra proccessing, it can apply multivariate analysis on extracted data. Efficient plotting with 1-D data is also available. Basic reading of 1D ACD/Labs exported JDX samples is also available.

HiCDOC normalizes intrachromosomal Hi-C matrices, uses unsupervised learning to predict A/B compartments from multiple replicates, and detects significant compartment changes between experiment conditions. It provides a collection of functions assembled into a pipeline to filter and normalize the data, predict the compartments and visualize the results. It accepts several type of data: tabular `.tsv` files, Cooler `.cool` or `.mcool` files, Juicer `.hic` files or HiC-Pro `.matrix` and `.bed` files.

Another list focuses on Python stuff related to Chemistry.

Read in imaging-based spatial transcriptomics technology data. Current available modules are for Xenium by 10X Genomics, CosMx by Nanostring, MERSCOPE by Vizgen, or STARmapPLUS from Broad Institute. You can choose to read the data in as a SpatialExperiment or a SingleCellExperiment object.

HOSO is an ontology of informational entities and processes related to healthcare organizations and services.

IsoBayes is a Bayesian method to perform inference on single protein isoforms. Our approach infers the presence/absence of protein isoforms, and also estimates their abundance; additionally, it provides a measure of the uncertainty of these estimates, via: i) the posterior probability that a protein isoform is present in the sample; ii) a posterior credible interval of its abundance. IsoBayes inputs liquid cromatography mass spectrometry (MS) data, and can work with both PSM counts, and intensities. When available, trascript isoform abundances (i.e., TPMs) are also incorporated: TPMs are used to formulate an informative prior for the respective protein isoform relative abundance. We further identify isoforms where the relative abundance of proteins and transcripts significantly differ. We use a two-layer latent variable approach to model two sources of uncertainty typical of MS data: i) peptides may be erroneously detected (even when absent); ii) many peptides are compatible with multiple protein isoforms. In the first layer, we sample the presence/absence of each peptide based on its estimated probability of being mistakenly detected, also known as PEP (i.e., posterior error probability). In the second layer, for peptides that were estimated as being present, we allocate their abundance across the protein isoforms they map to. These two steps allow us to recover the presence and abundance of each protein isoform.

Website    🤖 7B Model    🤖 32B Model    MedEvalKit    Technical Report    Lingshu MCP

BioNERO aims to integrate all aspects of biological network inference in a single package, including data preprocessing, exploratory analyses, network inference, and analyses for biological interpretations. BioNERO can be used to infer gene coexpression networks (GCNs) and gene regulatory networks (GRNs) from gene expression data. Additionally, it can be used to explore topological properties of protein-protein interaction (PPI) networks. GCN inference relies on the popular WGCNA algorithm. GRN inference is based on the "wisdom of the crowds" principle, which consists in inferring GRNs with multiple algorithms (here, CLR, GENIE3 and ARACNE) and calculating the average rank for each interaction pair. As all steps of network analyses are included in this package, BioNERO makes users avoid having to learn the syntaxes of several packages and how to communicate between them. Finally, users can also identify consensus modules across independent expression sets and calculate intra and interspecies module preservation statistics between different networks.

Evo 2 is a state of the art DNA language model for long context modeling and design. Evo 2 models DNA sequences at single-nucleotide resolution at up to 1 million base pair context length using the StripedHyena 2 architecture, using Savanna.

Automate downloading and querying the latest (or a given) version of ChEMBL.

doubletrouble aims to identify duplicated genes from whole-genome protein sequences and classify them based on their modes of duplication. The duplication modes are i. segmental duplication (SD); ii. tandem duplication (TD); iii. proximal duplication (PD); iv. transposed duplication (TRD) and; v. dispersed duplication (DD). Transposon-derived duplicates (TRD) can be further subdivided into rTRD (retrotransposon-derived duplication) and dTRD (DNA transposon-derived duplication). If users want a simpler classification scheme, duplicates can also be classified into SD- and SSD-derived (small-scale duplication) gene pairs. Besides classifying gene pairs, users can also classify genes, so that each gene is assigned a unique mode of duplication. Users can also calculate substitution rates per substitution site (i.e., Ka and Ks) from duplicate pairs, find peaks in Ks distributions with Gaussian Mixture Models (GMMs), and classify gene pairs into age groups based on Ks peaks.

SO is a collaborative ontology project for the definition of sequence features used in biological sequence annotation. It is part of the Open Biomedical Ontologies library.

An ontology of information entities about an individual

中文版说明

Neeto-1.0-8b is an openly released biomedical large language model (LLM) created by BYOL Academy to assist learners and practitioners with medical exam study, literature understanding, and structured clinical reasoning.

Assigns identifiers to knowledge graphs (KGs) that are used and/or maintained within any NFDI consortium.

Strongest open-source automated theorem prover in Lean 4, 8B model matches DeepSeek-Prover-V2-671B at 84.6% MiniF2F, 32B model achieves 90.4% with self-correction, using scaffolded data synthesis and verifier-guided proof refinement (Princeton, 2025)

SIMD C library for global, semi-global, and local pairwise sequence alignments

This repository contains the official model of the paper A Unified Predictive and Generative Solution for Liquid Electrolyte Formulation.

This is a ReactionT5 pre-trained to predict the products of reactions. You can use the demo here.

This repos contains the biomedicine MLLM developed from Qwen2.5-VL-3B-Instruct in our paper: On Domain-Adaptive Post-Training for Multimodal Large Language Models. The correspoding training dataset is in biomed-visual-instructions.

The TMSig package contains tools to prepare, analyze, and visualize named lists of sets, with an emphasis on molecular signatures (such as gene or kinase sets). It includes fast, memory efficient functions to construct sparse incidence and similarity matrices and filter, cluster, invert, and decompose sets. Additionally, bubble heatmaps can be created to visualize the results of any differential or molecular signatures analysis.

This package implements an attribute-weighted aggregation algorithm which leverages peptide-spectrum match (PSM) attributes to provide a more accurate estimate of protein abundance compared to conventional aggregation methods. This algorithm employs pre-trained random forest models to predict the quantitative inaccuracy of PSMs based on their attributes. PSMs are then aggregated to the protein level using a weighted average, taking the predicted inaccuracy into account. Additionally, the package allows users to construct their own training sets that are more relevant to their specific experimental conditions if desired.

openWEMI is a minimally constrained vocabulary for describing created resources using the concepts of Work, Expression, Manifestation, Item.

The package is an R wrapper for Progenetix REST API built upon the Beacon v2 protocol. Its purpose is to provide a seamless way for retrieving genomic data from Progenetix database—an open resource dedicated to curated oncogenomic profiles. Empowered by this package, users can effortlessly access and visualize data from Progenetix.

Retrieval-augmented LM synthesizing scientific literature from 45M papers with human-expert-level citation accuracy, outperforming GPT-4o by 5% on ScholarQABench (Nature 2026, UW & Ai2)

Minigraph is a sequence-to-graph mapper and graph constructor. For graph generation, it aligns a query sequence against a sequence graph and incrementally augments an existing graph with long query subsequences diverged from the graph.

The CytoGLMM R package implements two multiple regression strategies: A bootstrapped generalized linear model (GLM) and a generalized linear mixed model (GLMM). Most current data analysis tools compare expressions across many computationally discovered cell types. CytoGLMM focuses on just one cell type. Our narrower field of application allows us to define a more specific statistical model with easier to control statistical guarantees. As a result, CytoGLMM finds differential proteins in flow and mass cytometry data while reducing biases arising from marker correlations and safeguarding against false discoveries induced by patient heterogeneity.

Dynamic Protein Data Bank integrating dynamic behaviors and physical properties into protein structures via a new dataset and SE(3) model extension, enabling richer understanding of protein conformational landscapes (Fudan University, 784+ stars)

dandelionR is an R package for performing single-cell immune repertoire trajectory analysis, based on the original python implementation. It provides the necessary functions to interface with scRepertoire and a custom implementation of an absorbing Markov chain for pseudotime inference, inspired by the Palantir Python package.

Specialized model for Chemical Entity Recognition - Identifies chemical compounds and substances in biomedical literature

Scientific equation discovery and symbolic regression using LLMs, combining code generation with evolutionary search (ICLR 2025 Oral)

AI agent for therapeutic reasoning across a universe of tools, achieving 92.1% accuracy in drug reasoning and outperforming GPT-4o by 25.8% (Harvard MIMS, 2025)

Multi-modal geospatial ML platform for agriculture and sustainability, fusing satellite imagery (RGB, SAR, multispectral), drone imagery, weather data, and sensor data for crop identification, carbon footprint estimation, and microclimate prediction (Microsoft Research, MIT License)

Family of diffusion protein language models demonstrating versatile generative and predictive capabilities for protein sequences and structures, including multimodal co-generation, conditional folding, inverse folding, motif scaffolding, and representation learning, with open pretrained weights and training scripts (327+ stars, ICML 2024, ICLR 2025, ICML 2025 Spotlight)

JAMUN is a novel approach for generating conformational ensembles of protein structures, presented in the paper JAMUN: Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensembles.

Many tools for data analysis are not available in R, but are present in public repositories like conda. The Herper package provides a comprehensive set of functions to interact with the conda package managament system. With Herper users can install, manage and run conda packages from the comfort of their R session. Herper also provides an ad-hoc approach to handling external system requirements for R packages. For people developing packages with python conda dependencies we recommend using basilisk (https://bioconductor.org/packages/release/bioc/html/basilisk.html) to internally support these system requirments pre-hoc.

MOGAMUN is a multi-objective genetic algorithm that identifies active modules in a multiplex biological network. This allows analyzing different biological networks at the same time. MOGAMUN is based on NSGA-II (Non-Dominated Sorting Genetic Algorithm, version II), which we adapted to work on networks.

piRNAs (short for PIWI-interacting RNAs) and their PIWI protein partners play a key role in fertility and maintaining genome integrity by restricting mobile genetic elements (transposons) in germ cells. piRNAs originate from genomic regions known as piRNA clusters. The piRNA Cluster Builder (PICB) is a versatile toolkit designed to identify genomic regions with a high density of piRNAs. It constructs piRNA clusters through a stepwise integration of unique and multimapping piRNAs and offers wide-ranging parameter settings, supported by an optimization function that allows users to test different parameter combinations to tailor the analysis to their specific piRNA system. The output includes extensive metadata columns, enabling researchers to rank clusters and extract cluster characteristics.

Coralysis is an R package featuring a multi-level integration algorithm for sensitive integration, reference-mapping, and cell-state identification in single-cell data. The multi-level integration algorithm is inspired by the process of assembling a puzzle - where one begins by grouping pieces based on low-to high-level features, such as color and shading, before looking into shape and patterns. This approach progressively blends the batch effects and separates cell types across multiple rounds of divisive clustering.

topGO package provides tools for testing GO terms while accounting for the topology of the GO graph. Different test statistics and different methods for eliminating local similarities and dependencies between GO terms can be implemented and applied.

DeepSeek's open-source large language model for formal theorem proving in Lean 4, integrating informal and formal mathematical reasoning through recursive subgoal decomposition and reinforcement learning powered by DeepSeek-V3, with open weights and ProverBench evaluation (2025)

S4 generic functions and classes needed by Bioconductor proteomics packages.

darkknight25/deepseek-16b-medical-GPT is a fine-tuned version of deepseek-ai/deepseek-l6b-moe-chat, optimized for medical question answering, reasoning, and clinical summarization using QLoRA and open-access healthcare datasets.