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.
Filters
Health
Domain(1)
Language
License
Source
Type
48 of 9,874 resources
Analysis pipeline for the consistent, reproducible and high-resolution structural analysis of bacterial peptidoglycans.
This tutorial aims to illustrate the process of ligand parameterization for a small molecule, step by step, using the BioExcel Building Blocks library (biobb). The particular example used is the Ibuprofen small compound (3-letter code IBP, Drugbank code DB01050), a non-steroidal anti-inflammatory drug (NSAID) derived from propionic acid.
PP-MAPS is an open-source workflow designed to extract and aggregate dynamic pharmacophore signatures from molecular dynamics (MD) trajectories of protein-peptide complexes. It helps characterize protein-peptide interactions critical for drug discovery by producing per-residue interaction frequencies and pharmacophore heatmaps.
BioMetAll is a command line application to allow the identification of metal-binding sites in proteins from backbone preorganization.
An automated framework that maps small organic molecules from SMILES strings into standardized Martini 3 coarse-grained force field models for molecular dynamics simulations.
ProteoRift is an end-to-end deep attention-based multitask deep-network designed for predicting multiple peptide properties (length, missed cleavages, modification status) directly from mass spectrometry spectra. It integrates into a pipeline to significantly reduce the search space for peptide identification, achieving speedups of 8x to 12x.
NaviDiv is a web application designed to monitor and manage chemical diversity in the generative design of molecules. It provides multi-metric analysis, real-time visualization, and adaptive constraint generation to guide molecular optimization while preserving chemical diversity.
TransBindpMHCI is a transformer-based model designed for predicting MHC-I peptide binding, which is crucial for identifying immunogenic neoantigens in cancer immunotherapy.
gisttools is a Python package and set of Jupyter notebooks designed to compute the free energy of solvation of molecules on a 3D grid using Grid Inhomogeneous Solvation Theory (GIST). It allows for detailed analysis of solvation energetics (energy and entropy contributions) around proteins and small molecules.
DGraph is a simple utility to visualize a Distance Graph in two dimensions. Targeted for Biotech use, but is entirely general.
AutoGraph performs autonomous graph based clustering on metabolite conformers to reduce redundancy from configuration space. AutoGraph prioritizes autonomation, simplicity, and practicality.
A Python script to predict peptide MHC binding and presentation with BERT model. Improves MHC-peptide class II interaction prediction with transformer and multiple instance learning.
COVID-19 Knowledge Extractor (COKE) is a tool and a web portal to extract drug - target protein associations from the CORD-19 corpus of scientific publications on COVID-19.
DrugSimDB is a comprehensive database of multi-modal drug similarity measures by integrating variety of heterogenous datasets.
A Deep Learning Framework for Drug Synergy Prediction. Drug combination therapies have been a viable strategy for the treatment of complex diseases such as cancer due to increased efficacy and reduced side effects.
Prediction of phosphoglycerylated lysine residues using structural properties of amino acids. The train and test datasets used for implementing PhoglyStruct are .mat files by the names 'train' and 'test' respectively (the three features namely tau, pc and ph are not present in train and test but in the .mat files 'original_train' and 'original_test' has all the features which can be viewed for reference). The codes in this repository are in two categories. One is based on commercial software (Matlab), while the other on non-commercial software (Octave).
Natural Product-likeness calculator v-2.1 : calculates natural product-likeness of small molecules based on open-data of natural products.
pyKinaXe is a Python package providing automated, end-to-end analysis for peptide microarray data (PamChip®). It profiles kinase activity by extracting kinase information and quantifying phosphorylation kinetics from raw microarray images.
TorsiFlex is an automatic generator of torsional conformers. Application to the twenty proteinogenic amino acids. TorsiFlex is an user-friendly program written in Python 3. It was designed to seek the conformers of a given molecule by using a combined low-level/high-level (LL/HL) methodology.
Pandoomain is a Snakemake pipeline for analyzing genomic and protein domain context, revealing diversity and novel toxins. It automates genome acquisition, protein identification, domain annotation, and gene neighborhood analysis.
An optimized FM-index library for nucleotide and amino acid search. A fast, AVX2 accelerated FM-index library that utilizes windows of SIMD registers to quickly locate exact match kmers in genetic data. This FM-index is highly optimized for both nucleotide and amino sequences, but is unsuitable for general text.
Deep Fingerprint Learn (DFPL) is an aI for predicting chemical-effect associations at the universe level. Link molecular structures of chemicals (in form of topological fingerprints) with multiple targets.
a Web Tool for Data Retrieval to Interpret Somatic Variants in Cancer. Please enter your mutation's gene name, peptide change, and coding strand change.
In silico model for predicting IL-2 inducing peptides in human.
The Software Tool for Peptide Specificity Analysis (PeSA) is an open-source software designed as a tool to use in the analysis of peptide arrays, permutation arrays and OPALs. The analysis can be used to generate motifs to share the results as a position-specific scoring matrix (PSSM).
Populating Chemical Space with Peptides using a Genetic Algorithm. In drug discovery one uses chemical space as a concept to organize molecules according to their structures and properties. One often would like to generate new possible molecules at a specific location in chemical space marked by a molecule of interest. Herein we report the peptide design genetic algorithm (PDGA, code available at https: github.com reymondgroup PeptideDesignGA), a computational tool capable of producing peptide sequences of various chain topologies (linear, cyclic polycyclic or dendritic) in proximity of any molecule of interest in a chemical space defined by MXFP, an atom-pair fingerprint describing molecular shape and pharmacophores. We show that PDGA generates high similarity analogs of bioactive peptides, including in selected cases known active analogs, as well as of non-peptide targets.
Generating antiviral peptides using Generative Adversarial Network. Antiviral peptide predictions using GAN.
Bioinformatic pipeline to predict MHC-I-restricted T cell epitopes in mice. NeoAntigens Prediction @ CNB (NAP-CNB) is a tool for the prediction of neoantigenic peptides from tumoral RNA-seq or peptide sequences. NAP-CNB uses variant calling methods with models trained on recurrent neuronal networks (RNN) to produce a list of putative neoantigens.
DockQ is a software tool for assessing the quality of modeled biomolecules, including proteins, nucleic acids, and small molecules. The tool has been reimplemented in pure Python, featuring improved portability, speed, and novel functionalities like automatic chain mapping and calculations for multiple interfaces.
Web server for predicting SAM binding residues of a protein from its amino acid sequence.
A multi-source ensemble predictor for prioritizing sgRNAs in CRISPR/Cas9 protein knockouts. GuidePro:A multi-source ensemble predictor for prioritizing sgRNAs in CRISPR/Cas9 protein knockouts. GuidePro is a two-layer ensemble predictor that enables the integration of multiple predictive methods and feature sets to predict sgRNA efficiency for the CRISPR Cas9 protein knockouts.
D3Similarity is A Ligand-Based Approach for Predicting Drug Targets and for Virtual Screening of Active Compounds Against COVID-19. D3Similarity was developed with two purposes based on the two-dimensional and three-dimensional similarity of molecular structure, one is for predicting target proteins for active compounds observed from experimental studies, and another is for virtual screening via 2D and 3D similarity evaluation. To this end, we developed a database composed of the bioactive molecules with known targets or/and well-explored mechanism related to the whole process of coronavirus infection, replication and release. “TargetPrediction” is for predicting target proteins, while “VirtualScreening” is for virtual screening against target proteins based on the 2D or 3D similarity evaluation.
In silico tool for predicting and designing Blood-Brain Barrier Penetrating Peptides.
Pathogenicity prediction of human missense variants based on protein sequence, structure and dynamics | computationally predicting effects of saturation mutagenesis | In silico saturation mutagenesis | perform a complete scan of all possible 19 amino acid substitutions at each site on a human sequence. See example: H-Ras
Peptipedia v2.0 is a peptide sequence database and web platform that facilitates peptide research and machine learning applications. It features expanded sequence data, enhanced functional activity classifications, and user-friendly machine learning tools for peptide annotation.
DTI-Voodoo is a computational method that combines molecular features and ontology-encoded phenotypic effects of drugs with protein protein interaction networks, and uses a graph neural networks to predict drug-target interactions.
BtToxin_Digger is a comprehensive and high-throughput pipeline for mining toxin protein genes from Bacillus thuringiensis. BtToxin_Digger is a Bt toxin mining tool which integrated BLAST, HMM (Hidden Markov Model) and SVM (Supporting Vector Machine) prediction modules.
CovPepDock is a web application for covalent flexible peptide docking in Rosetta.
CoV3D is a web r resource for structures of coronavirus proteins and their recognition by antibodies and other molecules. It contains high resolution coronavirus protein structures.
EMBER is a tool for multi-label prediction of kinase-substrate phosphorylation events through deep learning.
DeepDrug is a general graph-based deep learning framework for drug-drug/protein interaction prediction.
A pipeline for the prediction of virulence factors and antimicrobial resistance genes in metagenomic data.
COSS (CompOmics Spectral Searching ) is a user-friendly spectral library search tool capable of processing large spectral libraries and supporting multiple file formats.
Automated annotation of amino acid biosynthesis | Abstract GapMind is a web-based tool for annotating amino acid biosynthesis in bacteria and archaea ( http: papers.genomics.lbl gov gaps ). GapMind incorporates many variant pathways and 130 different reactions, and it analyzes a genome in just 15 seconds. To avoid error-prone “transitive” annotations, GapMind relies primarily on a database of experimentally-characterized proteins. GapMind correctly handles fusion proteins and split proteins, which often cause errors for “best hit” approaches. To improve GapMind’s coverage, we examined genetic data from 35 bacteria that grow in minimal media and we filled many gaps in amino acid biosynthesis pathways.
An R package for fast genome-wide prediction of antimicrobial peptides. It is fast and user-friendly method to predict antimicrobial peptides (AMPs) from any given size protein dataset. ampir uses a supervised statistical machine learning approach to predict AMPs.
USE (Universal Spectrum Explorer) A standalone (web-)application for cross-resource spectrum comparison. The Universal Spectrum Explorer (USE) is a web-based tool based for cross-resource (peptide) spectrum visualization and comparison (https://www.proteomicsdb.org/use/).
A Genome-Mining Tool for Class-Independent RiPP Discovery. Bioinformatic application for the detection of RREs in protein sequences of interest. Install the included conda environment with "conda env create -f RREfinder.yml" Or make sure the following packages/programs are installed and in your path. Databases need to be downloaded independently from https://zenodo.org/record/3733240#.XoRkIUEzbCI. Please download all the files, except the folder with the seed sequences, and place them into the data/database folder within the downloaded repository. RREFinder accepts both protein .fasta files and .genbank files. Alternatively, you can use '--antismash ripp' and let the --infile point to a .final.gbk file from antiSMASH analysis. This way all the antiSMASH RiPP gene clusters will be analyzed.