Find open-source science resources

RepEnrich is a method to estimate repetitive element enrichment using high-throughput sequencing data.

[@crazyhottommy](https://github.com/crazyhottommy)'s notes on various steps and considerations when doing RNA-seq analysis.

Automated strain separation of low-complexity metagenomes

Crystal property prediction

Computation Pipeline library for python widely used in science and bioinformatics.

Spike detection and clustering-based spike sorting.

qam is a Python library and command-line tool to compute 3D surface-distances for evaluating liver ablation/tumor completeness based on segmentation images.

Pythonic access to the UCSC Genome database.

NanoSV is a software package that can be used to identify structural genomic variations in long-read sequencing data, such as data produced by Oxford Nanopore Technologies’ MinION, GridION or PromethION instruments, or Pacific Biosciences RSII or Sequel sequencers.

Automatic Filtering, Trimming, Error Removing and Quality Control for fastq data.

Molecule validation and standardization based on [RDKit](http://www.rdkit.org/).

Prediction of mRNA subcellular localization using deep recurrent neural networks | RNATracker is a deep learning approach to learn mRNA subcellular localization patterns and to infer its outcome. It operates on the cDNA of the longest isoformic protein-coding transcript of a gene with or without its corresponding secondary structure annnotations. The learning targets are fractions/percentage of the transcripts being localized to a fixed set of subcellular compartments of interest

A port of [pyVCF](https://github.com/jamescasbon/PyVCF) using Cython for speed.

Tool to generate a count matrix for expression data in Galaxy. generate_count_matrix reads in one or more input text files with expression counts and produces a single combined file. Each input will have a column in the matrix containing expression values. The column containing gene (or feature) names should be identical for all input count files.

Automate common SAM & BAM conversions.

This desktop application enables users to upload DICOM data along with associated clinical information to QP-Insights—the data management platform of the UPV Reference Node within EUCAIM.

This module provides a command line tool to validate DICOM SEG files against predefined requirements specified in an Excel file. It contains components for finding relevant DICOM files, loading and parsing validation requests and applying validation rules. The main validation process checks each DICOM file for compliance with the Type 1, 1C, 2, 2C and 3 attributes specified in the requirements file. A detailed report is generated highlighting issues such as missing, invalid or conditionally required attributes, including file paths and affected DICOM tags. The tool is designed to ensure data integrity and compliance with DICOM standards.

A tool that checks the clinical metadata quality (validity, completeness), the integrity between images and clinical metadata provided as well as their accuracy, the de-identification protocol applied, and existence of annotation together with the consistency between the images and the annotation files and informs the user on corrective actions prior to data upload.

Automatically detects duplicate and near-duplicate DICOM image series in large medical imaging datasets. Uses a tiered pipeline combining DICOM metadata analysis, SHA-based pixel hashing, and image similarity metrics (SSIM, cosine, MAD) to identify exact copies, re-exported series, and near-identical acquisitions. All findings are reported for human expert review — no files are modified or deleted automatically. For scenarios requiring strict, image-level deduplication based on pixel content, fully agnostic to metadata changes, consider using [https://bio.tools/image_duplicate_check_tool]

CompuCell3D is a multiscale multicellular virtual tissue modeling and simulation environment. CompuCell3D is written in C++ and provides Python bindings for model and simulation development in Python.

Miniconda is a minimal Python distribution that includes the Conda package and environment manager plus only essential dependencies. It provides a lightweight way to create isolated environments and install Python packages as needed, without the large preinstalled package set of Anaconda.

Implemented by GIBI230, this tool is a Docker-based software designed for extracting radiomic features from 3D medical images in NIfTI format using the PyRadiomics library (if DICOM images, the DICOM to NIFTI converter must be run before using this tool). It streamlines the radiomics calculation process by generating a structured CSV file containing all extracted variables from medical images. The dockerized software enables users to configure parameters like filters, bin width, resampling spacing, and normalization settings can be specified. The output radiomic variables provide quantitative information for further analysis in medical imaging research and machine learning applications. Specially important the parameter selection of the band width. For robust and reproducible results, a bin width of 5 is commonly recommended, but it should be adjusted based on image resolution, modality, and noise levels.

The tool is designed to perform radiomics harmonization on large and heterogeneous datasets, where the risk of over-harmonization is present. Instead of directly applying harmonization based on predefined batch labels, the tool first identifies groups of batches that share similar characteristics through clustering of the radiomics data. It then performs harmonization using these cluster-derived labels. The tool allows the harmonization of radiomics variables using two methods: (1) original ComBat (Rabinovic, 2007) method, where each original batch group is considered for the harmonization process and (2) cluster-based ComBat method, where batch groups with similar radiomics characteristics form clusters and the latter are being considered for the harmonization process.

This preprocessing tool is design for 2D digital mammograms in DICOM format. It standardizes and harmonizes images through a configurable pipeline that includes spatial reorientation, pseudo-3D stacking, isotropic resampling, intensity normalization, optional denoising, contrast enhancement, and mask processing (if available).

The tool performs by deep learning an automatic segmentation of the possible neuroblastoma tumours on Contrast Enhanced CT images (CE-CTs). Model architecture is Unet-based with residual operations, atrous dilation convolution and specific batch generator. It applies preprocessing steps as RAS conversion, resizing, z-score normalization, patching; and postprocessing operations. It takes DICOM images as input and generates tumoral masks in DICOM SEG or NIFTI formats.

The tool performs an automatic segmentation of the possible glioblastoma tumours on MRI images and its subregions: necrosis (Intratumoral necrotic core), edema (Peritumoral vasogenic edema), enhancing (Contrast-enhancing tumor region), total (Total tumor including edema and necrosis by a single model) and total-fused (Total tumor fusioning of necrosis+edema+enhancing). It applies preprocessing steps as skull stripping, intra-patient registration, z-score normalization, patching, among others. It takes DICOM images as input and generates tumoral masks in DICOM SEG or NIFTI formats.

The tool performs an automatic segmentation of the possible DIPG tumours on MR images. DIPG (Diffuse Intrinsic Pontine Glioma), or more recently, DMG (Diffuse Midline Glioma) is a H3 K27M–mutant pediatric brainstem cancer detected in T1W and Flair/T2-weighted magnetic resonance images. The tool includes a complete workflow from DICOM images to DICOM seg tumoral masks.

This tool is specifically designed and validated for automated detection and segmentation of neuroblastic tumours in T2-weighted magnetic resonance images (T2-MR) using deep learning. It processes DICOM or NIfTI input data and outputs in NIFTI or DICOM SEG. TRAINING & VALIDATION COHORTS: Initial Development (Veiga-Canuto 2022): -Training: 106 patients, 5-fold CV (median DSC 0.965 ± 0.018). -Internal validation: 26 patients (median DSC 0.918 ± 0.067). -Sources: La Fe (Spain), SIOPEN HR-NBL1/LINES, St. Anna (Austria), Pisa (Italy). -Mean age: 37.6 ± 39.3 months. -Median tumor volume: 116,518 mm³. External Validation (Veiga-Canuto 2023): -300 patients, 535 independent T2 MRI scans (486 at diagnosis, 49 post-chemotherapy). -Performance: median DSC 0.997 (0.944–1.000), 94% successful detection. -Sources: 12 European countries (HR-NBL1/SIOPEN 119, LINES/SIOPEN 107, German Registry 62, others 12). -Heterogeneous data: 1.5T (435), 3T (100); Siemens (318), Philips (109), GE (105), Canon (3).

The tool is designed to perform a customisable image pre-processing to reduce noise and inhomogeneity field effect, thus improving image quality and reproducibility of radiomics features. This tool consists of two independent steps: one for denoising using one of the 5 integrated filters (Bilateral Filter, Anisotropic Diffusion Filter (ADF), Curvature Flow Filter (CFF), SUSAN and Non Local Means (NLM)), and another for the ANTs N4 and another for the ANT's N4 bias correction filter. The parameter configuration of this tool has been optimised for TW1, T2W, DWI and DCE sequences in neuroblastoma (NB) and paediatric brain tumours, but it can also be configured with some of their parameters using a JSON parameter configuration file.

A tool based on artificial intelligence that is able to perform a categorisation of MRI series by using standardized DICOM tags. The categorisation includes the type of sequence (e.g. spin echo, gradient echo), the weighting (e.g. T1W, T2W, DCE, ...), the presence of fat suppression and the detection of non-relevant / junk series (e.g. localizers, calibrations, screenshots...).

Tool that aims to validate visually the chronological order and logical consistency of dates associated with a patient's medical history. It generates a timeline visualization for each patient from an Excel file and highlights rule violations. Status : Containerized

The tool performs a DICOM quality check in terms of correct number of files per sequence, corrupted files, precise directory hierarchy, separated dynamic series merging them, interest series filtering/selection by specific series description lists and diffusion sequence identification by b-values. It applies the desired changes to the dataset and generates a report containing information about the selected sequences, corrupted files, missing files and merged files. Status: Deployed

Membrane Protein-Lipid Interaction Database. A large-scale experimentally validated dataset of 80685 residue-level lipid contact annotations across 4712 membrane proteins derived from PDB crystal and cryo-EM structures. Provides pre-computed binary contact labels, continuous distance values, sequence-identity-based cluster assignments, and ready-made train-validation-test splits for machine learning.

FlavoTyper is a bioinformatics tool that performs in silico serotyping of Flavobacterium psychrophilum genome assemblies.

MONAI Label is an intelligent open source image labeling and learning tool that enables users to create annotated datasets and build AI annotation models for clinical evaluation. MONAI Label enables application developers to build labeling apps in a serverless way, where custom labeling apps are exposed as a service through the MONAI Label Server.

metagWGS is a workflow dedicated to the analysis of metagenomic data. It allows assembly, taxonomic annotation, and functional annotation of predicted genes. Since release 2.3, binning step with the possibility of cross-alignment is included. It has been developed in collaboration with several CATI BIOS4biol agents. Funded by Antiselfish Project (Labex Ecofect), ExpoMicoPig project (France Futur elevage) and SeqOccIn project (CPER - Occitanie Toulouse / FEDER), ATB_Biofilm funded by PNREST Anses, France genomique (ANR-10-INBS-09-08) and Resalab Ouest.

xnattools is a python package with a set of modules for performing various operations on data stored in XNAT servers. The main purpose is to provide one standardized platform for running operations on XNAT servers. The package currently contains four tools that use this platform: dicom to nifty conversion, thumbnail generation from dicom, DICOM header data collection, in bulk downloading of a project.

Python package for biodatafuse project.

AmsterdamUMCdb is a database of de-identified health data related to tens of thousands of intensive care unit admissions, including demographics, vital signs, laboratory tests and medications.

SciAgentKit is an MCP-native toolkit that connects AI agents to reproducible computational drug-discovery workflows. It integrates established tools for molecular analysis, protein-structure assessment, binding-site detection, molecular docking, molecular dynamics, trajectory analysis and scientific reporting.

NIM Studio is a local-first platform for neuroinformatics, BIDS organization, metadata generation, duplicate auditing, and scalable research data management.

Reactr is an modularized, Snakemake workflow for automated, species-agnostic characterization of gene families from sequence to experimental design. Given a query protein sequence and NCBI taxonomy IDs (or RefSeq assembly accessions), reactr retrieves genomic data and runs comprehensive analysis across 4 integrated tiers: (1) evolutionary analysis, including homolog detection, domain-based clustering, multiple sequence alignment, and phylogenetic inference; (2) synteny and selection analysis, detecting collinear blocks and calculating Ka/Ks ratios; (3) structural and regulatory characterization, including motif discovery, chromosomal mapping, biochemical property prediction, subcellular localization prediction, and promoter analysis; and (4) experimental design tools, generating PCR primers and scored CRISPR gRNAs for lab validation. Reactr bridges computational prediction and experimental validation, thus enabling rapid transition from genomic discovery to functional studies.

Predicting the effect of mutations on protein-RNA binding with Deep Learning | This repository contains all DeepCLIP Python code | A context-aware neural network for modeling and predicting protein binding to nucleic acids using only sequence input | DeepCLIP is a neural network with shallow convolutional layers connected to a bidirectional LSTM layer

Plant Compound Extractor is a desktop application that builds a ready-to-use, deduplicated library of 3D ligand structures for a given plant. It queries multiple natural-product and chemical databases (COCONUT, LOTUS, Wikidata, PubChem, PlantaeDB, USDA Dr. Duke's, KNApSAcK and IMPPAT) in parallel, resolves each compound against PubChem for a canonical structure, and falls back to direct source retrieval when needed. Retrieved structures are then converted to 3D using RDKit, with configurable conformer generation and physicochemical filters (molecular weight, rotatable bonds, ring size, etc.). It can also process a manually supplied compound list, or convert an existing folder of 2D structures to 3D.

Pan.bio is a cloud genomics platform for pipeline execution, exploratory analysis, and clinical variant interpretation. Workflows runs validated Nextflow and nf-core pipelines including Sarek, rnaseq, scrnaseq, mag, ampliseq, chipseq and atacseq without local installation. Notebooks provides Python and R sessions with a preinstalled bioinformatics stack, importing public data from GEO, SRA and IPG by accession and reading Workflows outputs directly. VAIC applies ACMG/AMP variant classification with gene-specific rule sets from CanVIG-UK and ClinGen ENIGMA, with automated evidence criteria implemented for BRCA1 and BRCA2. Cohorts provides federated analysis of patient data within a Trusted Research Environment.

PhonaLab is a browser-based platform for acoustic analysis of voice recordings, aimed at speech-language pathologists, voice clinicians, and researchers. It computes validated multiparametric acoustic indices — including the Acoustic Voice Quality Index (AVQI), Acoustic Breathiness Index (ABI), smoothed cepstral peak prominence (CPPS), and glottal-to-noise excitation ratio (GNE) — from sustained-vowel and connected-speech recordings, using Praat algorithms via the Parselmouth interface. Audio is processed in memory and not stored. Interface available in English, Brazilian Portuguese, and Spanish.