Find open-source science resources

A directory of tools, AI models, datasets, and research resources for biotech, bioinformatics, and other scientific fields. Aggregated from curated GitHub awesome-lists, HuggingFace, bio.tools, Bioconductor, and more.

1,529 of 9,874 resources

Showing 1,301–1,350

CheSPI (Chemical shift Secondary structure Population Inference) is a tool for a simple and efficient method that provides unbiased and sensitive aggregate measures of local structure and disorder.

DiNetxify is a Python package for three-dimensional disease network analysis based on electronic health record data. It offers comprehensive modular functions for 3D network analysis, data handling, and visualization, optimized for large-scale EHR datasets.

BnpC is a non-parametric method to cluster individual cells into clones and infer their genotypes based on their noisy mutation profiles. BnpC employs a Chinese Restaurant Process prior to handle the unknown number of clonal populations. The model introduces a combination of Gibbs sampling, a modified non-conjugate split-merge move and Metropolis-Hastings updates to explore the joint posterior space of all parameters. Furthermore, it employs a novel estimator, which accounts for the shape of the posterior distribution, to predict the clones and genotypes.

BATMAN is a novel tool for batch effect correction (integration) of single-cell RNA-Seq datasets.

autodE is a Python module designed for the automated calculation of reaction profiles from just SMILES strings of reactant(s) and product(s).

ATAV is a comprehensive platform for population-scale genomic analyses. ATAV stores variant and per site coverage data for all samples in a centralized database, which is efficiently queried by ATAV to support diagnostic analyses for trios and singletons, as well as rare-variant collapsing analyses for finding disease associations in complex diseases.

Accurate identification of RNA-binding proteins using machine learning techniques.

web-based visualization of Arabidopsis thaliana iCLIP and RNA-seq data in an interactive python framework. SEQing: interactive web-based tool for visualization of iCLIP and RNA-seq data. The file requirements.txt can be used to install all needed needed dependencies for the project. Python 3.5 or higher is required and we recommend to setup a virtual environment for this project. If your current python points to a python2 version, please put python3 instead of just python before running SEQing

PHOSforUS is a fully biophysical parameter-based protein phosphorylation site predictor.

Genetic profiling of 2,683 Vietnamese genomes from non-invasive prenatal testing data. VCF file of our variant call set: https://drive.google.com/file/d/1iyeuaz5w6uSVP9UyV6DjSc-GvMrYYMyr/view?usp=sharing. The analysis pipeline can be run following instructions in the Python script pipeline.py.

An integrated, customizable microbial genome evaluation and annotation pipeline. Pipeline for major biological analyses. MetaSanity v1.1.1 - 2020 version. MetaSanity v1.1.1 provides a unified workflow for genome assessment and functional annotation that combines all outputs into a single queryable database – all within an easily distributed Docker image

Community predictions of hubs in gene regulatory networks. Abstract Summary Hub transcription factors, regulating many target genes in gene regulatory networks (GRNs), play important roles as disease regulators and potential drug targets. However, while numerous methods have been developed to predict individual regulator-gene interactions from gene expression data, few methods focus on inferring these hubs. We have developed ComHub, a tool to predict hubs in GRNs. ComHub makes a community prediction of hubs by averaging over predictions by a compendium of network inference methods. Benchmarking ComHub to the DREAM5 challenge data and an independent data set of human gene expression, proved a robust performance of ComHub over all data sets. Lastly, we implemented ComHub to work with both predefined networks and to do standard network inference, which we believe will make it generally applicable

A wisdom of the crowd-based Gene Ontology annotation tool | Abstract Motivation Protein function prediction tools vary widely in their methodologies, resulting in different sets of GO terms being correctly predicted. Ideally, multiple tools are combined to achieve a higher recall of GO terms while increasing precision. Results CrowdGO combines input predictions from any number of tools and combines them based on the Gene Ontology Directed Acyclic Graph. Using each GO terms information content, the semantic similarity between GO predictions of different tools, and a Support Vector Machine model, it achieves improved precision and recall compared to each of the tools separately (Figure 1). Availability CrowdGO can be found at https: gitlab.com mreijnders CrowdGO

An Open Source Unsupervised Algorithm for Discovery of Spontaneous Behaviors | Behavioral segmentation of open field in DeepLabCut, or B-SOID ("B-side"), is an unsupervised learning algorithm written in MATLAB that serves to discover behaviors that are not pre-defined by users | B-SOID: Behavioral segmentation of open field in DeepLabCut

A Flexible Command-Line Tool for the Detection of Giant Virus Signatures in Omic Data. ViralRecall is a flexible command-line tool for detecting signatures of giant viruses (NCLDV) in genomic data. Version 2 has been updated to focus more on NCLDV compared to version 1, but the original options are still available.

YeastMate is a tool for the automated detection and segmentation of S. cerevisae cells and their mating and budding events, as well as a subclassification of the cells involved in these events into mother and daughter cells.

ATAC-seq with unique molecular identifiers improves quantification and footprinting. This pipeline is used for UMI-ATAC-seq raw data processing, including removing the sequencing adapters, extracting UMIs from the original FASTQ read1 file, removing ME sequences and using the UMIs to remove PCR duplicates.

tysserand is a Python library to reconstruct spatial networks from spatially resolved omics experiments. It is intended as a common tool where the bioinformatics community can add new methods to reconstruct networks, choose appropriate parameters, clean resulting networks and pipe data to other libraries.

STonKGs is a Sophisticated Transformer that can be jointly trained on biomedical text and knowledge graphs. This multimodal Transformer combines structured information from KGs with unstructured text data to learn joint representations.

Spotiflow is a deep learning method for accurate spot detection in microscopy images, particularly useful for spatial transcriptomics. It uses stereographic flow regression to achieve subpixel-accurate localizations and is available as a Python library and a napari plugin.

A Multi-functional Software for Sequence Processing and Data Extraction.

Multi-task self-supervised learning for cell type classification. Rapidly generated scRNA-seq datasets enable us to understand cellular differences and the function of each individual cell at single-cell resolution.

scCNR reconstructs signal transduction networks from single-cell protein quantification data by treating stochastic variation as natural perturbations. The tool is available as a Python module and can be used to analyze cell population-specific signaling differences.

SAPLING: Suffix Array Piecewise Linear INdex for Genomics. A method for achieving faster suffix array queries compared to binary search.

SAINT stands for Self-Attention Augmented Inception-Inside-Inception Network Improves Protein Secondary Structure Prediction.

Rossmann-toolbox is a deep learning-based protocol for the prediction and design of cofactor specificity in Rossmann-fold proteins.

Improving binding affinity prediction by leveraging molecular mechanics energies with a 3D Convolutional Neural Network.

Protein and ligand multiconformer modeling for X-ray crystallographic and single-particle cryo-EM density maps. qFit is a collection of programs for modeling multi-conformer protein structures. Electron density maps obtained from high-resolution X-ray diffraction data are a spatial and temporal average of all conformations within the crystal. qFit evaluates an extremely large number of combinations of sidechain conformers, backbone fragments and small-molecule ligands to locally explain the electron density.

a python package for RNA-Seq workflows. pyrpipe: python rna-seq pipeliner. Example to identify orphan transcripts in maize by pyrpipe. A python package for RNA-Seq workflows — pyrpipe 0.0.1 documentation. pyrpipe (Pronounced as "pyre-pipe") is a python package to easily develop bioinformatic or any other computational pipelines in pure python. pyrpipe provides an easy-to-use framework for importing any UNIX command in python. pyrpipe comes with specialized classes and functions to easily code RNA-Seq processing workflows. pyrpipe (Pronounced as "pyre-pipe") is a python package to easily develop RNA-Seq analyses workflow by integrating popular RNA-Seq analysis programs in an object oriented manner. pyrpipe can be used on local computers or on HPC environments to manage analysis of RNA-Seq data.

an open-source tool for exploring 3D super-resolution data. Localization-based super-resolution microscopy techniques such as PALM, STORM, and PAINT are increasingly critical tools for biological discovery. These methods generate lists of single fluorophore positions that capture nanoscale structural details of subcellular organisation, but to develop biological insight, we must post-process and visualize this data in a meaningful way. A large number of algorithms have been developed for localization post-processing, transforming point data into representations which approximate traditional microscopy images, and performing specific quantitative analysis directly on points. Implementations of these algorithms typically stand in isolation, necessitating complex workflows involving multiple different software packages

Pseudofinder is a bioinformatics tool that detects pseudogene candidates from annotated genbank files of bacterial and archaeal genomes.

A Novel Method for Classification and Feature Selection. An Application in Metabolomics Studies. Here we provide a python code for the "Primal-Dual for Classification with Rejection (PD-CR)" method.\ This method works on Spyder 3.3.6.\ Users will need to have some experience in coding to use the scripts.\ The code is currently usable with ".csv" files following a specific organization (see Test datasets for an example). Users may need to modify the scripts to use PD-CR on new files.

Automating parameter selection to avoid implausible biological pathway models. Parameter advising for biological pathway creation algorithms. Pathway parameter advising is described in the following preprint:. Pathway parameter advising was written and tested using Python 3.6 and requires the packages networkx and numpy. The runPPA.sh and setupPGD.sh scripts require git. These scripts have only been tested in a Linux environment initially

PanClassif is a machine learning classifier pipeline for TCGA pancancer classification. It is a complete machine learning pipeline package to work with TCGA cancer RNA-seq gene count data.

Accurate identification of splice junctions using Oxford Nanopore sequencing.

A Python framework for analyzing multi-layer biological networks using diffusion algorithms. A Python package for analyzing harmonized biological networks through diffusion algorithms. systems-biology knowledge-graph network-analysis diffusion-network network-biology. Results of the MultiPaths publication. A Python package for network analysis through diffusion label propagation algorithms.

A hybrid deep learning-based approach for predicting miRNA targets.

MetaLogo is a tool for making sequence logos. It can take multiple sequences as input, automatically identify the homogeneity and heterogeneity among sequences and cluster them into different groups given any wanted resolution, finally output multiple aligned sequence logos in one figure. Grouping can also be specified by users, such as grouping by lengths, grouping by sample Id, etc. Compared to conventional sequence logo generator, MetaLogo can display the total sequence population in a more detailed, dynamic and informative view.

Whole-genome doubling-aware copy number phylogenies for cancer evolution with MEDICC2. Chromosomal instability (CIN) and somatic copy number alterations (SCNA) play a key role in the evolutionary process that shapes cancer genomes. SCNAs comprise many classes of clinically relevant events, such as localised amplifications, gains, losses, loss-of-heterozygosity (LOH) events, and recently discovered parallel evolutionary events revealed by multi-sample phasing. These events frequently appear jointly with whole genome doubling (WGD), a transformative event in tumour evolution, which generates tetraploid or near-tetraploid cells. WGD events are often clonal, occuring before the emergence of the most recent common ancestor, and have been associated with increased CIN, poor patient outcome and are currently being investigated as potential therapeutic targets

A web platform for protein dynamic residue networks and modal analysis. Interactive homology modeling pipeline. A platform for the analysis of molecular dynamics trajectories using dynamic residue network analysis, perturbation response scanning, essential dynamics, dynamic cross-correlation, and for large-scale motion analysis of protein complexes using normal mode analysis.

Learning genotype-phenotype maps from multiplex assays of variant effect. learning genotype-phenotype maps from multiplex assays of variant effect — mavenn 0.24 documentation.

A Machine Learning Model for Predicting the Pathogenicity of Missense Variants.

Automated image analysis for developmental phenotyping of mouse embryos. LAMA (Lightweight Analysis of Morphological Abnormalities). Welcome to LAMA, an open source pipeline to automatically identify embryo dysmorphology from 3D volumetric images.

A web resource for structural classification of protein kinases and their inhibitors. Use the following command to create a virtual enviroment and install the necessary packages.

iQcell is a platform for predicting the effect of gene perturbations on developmental trajectories using single-cell RNA-seq data.

Exploiting deep learning embeddings of protein sequences to predict the localisation of peroxisomal proteins. In-Pero: Prediction of sub-peroxisomal localisation using deep learning embeddings and

InterLabelGO+ is a hybrid protein function prediction tool that integrates deep learning and alignment-based methods, incorporating a novel loss function to address label dependency and imbalance. It achieved a strong performance in the CAFA5 challenge and is freely available on GitHub.

Python package for matrix storage and operations on hetnets

HEMnet is a deep learning automated cancer diagnosis software using molecular labelling to improve pathological annotation of Haematoxylin and Eosin (H&E) stained tissue.