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 1,401–1,450

An algorithm for improved plasmid assembly in metagenomes. SCAPP assembles plasmids from metagenomic assembly graphs.

Subtype and Stage Inference, or SuStaIn, is an algorithm for discovery of data-driven groups or "subtypes" in chronic disorders. This repository is the Python implementation of SuStaIn, with the option to describe the subtype progression patterns using either the event-based model, the piecewise linear z-score model or the scored events model.

PyInteraph2 and PyInKnife2 to analyze networks in protein structural ensembles. PyInKnife2 is a set of Python scripts to run an updated version of the PyInKnife pipeline [ for Protein Structure Network (PSN) analysis using PyInteraph2.

A webserver for predicting protein-protein interactions.

ppx provides a simple, programmatic means to access proteomics data that are publicly available in ProteomeXchange partner repositories.

Unbiased estimation of nucleotide diversity and divergence in the presence of missing data. pixy is a command-line tool for painlessly and correctly estimating average nucleotide diversity within (π) and between (dxy) populations from a VCF. In particular, pixy facilitates the use of VCFs containing invariant (AKA monomorphic) sites, which are essential for the correct computation of π and dxy in the face of missing data (i.e. always). Unbiased estimation of nucleotide diversity within and between populations.

Automated repurposing of public peptide LC-MS data for machine learning applications.

metaMIC is a fully automated tool for identifying and correcting misassemblies of (meta)genomic assemblies with the following three steps. Firstly, metaMIC extracts various types of features from the alignment between paired-end sequencing reads and the assembled contigs. Secondly, the features extracted in the first step will be used as input of a random forest classifier for identifying misassembled metagenomic assemblies. Thirdly, metaMIC will localize misassembly breakpoints for each misassembled contig and then correct misassemblies by splitting into parts at the breakpoints.

Integrating millions of single cells using batch-aware triplet neural networks. INtegration of millions of Single Cells using batch-aware Triplet networks. insct is a deep learning algorithm which calculates an integrated embedding for scRNA-seq data. With insct, you can:. a, INSCT learns a data representation, which integrates cells across batches. The goal of the network is to minimize the distance between Anchor and Positive while maximizing the distance between Anchor and Negative. Anchor and Positive pairs consist of transcriptionally similar cells from different batches. The Negative is a transcriptomically dissimilar cell sampled from the same batch as the Anchor. b, Principal components of three data points corresponding to Anchor, Positive and Negative are fed into three identical neural networks, which share weights. The triplet loss function is used to train the network weights and the two-dimensional embedding layer activations represent the integrated embedding.

Building a Knowledge Graph from public databases and scientific literature to extract associations between chemicals and diseases. FORUM is an open knowledge network aiming at supporting metabolomics results interpretation in biomedical sciences and automated reasoning. Containing more than 8 billion statements, it federates data from several life-science resources such as PubMed, ChEBI and PubMed. Leveraging the bridges in this linked dataset, we automatically extract associations between compound and biomedical concepts, using literature metadata enrichment. Find more about the method in our preprint here: BioXiv.

FEATS is a Python tool for performing downstream analysis on Single-Cell RNA-seq datasets.

Improved protein-nucleic acid binding site prediction using protein-language-model-informed equivariant deep graph neural networks.

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.

DeepLncLoc is a deep learning framework for long non-coding RNA subcellular localization prediction based on subsequence embedding.

DeepFrag is a deep convolutional neural network that guides ligand optimization by extending a ligand with a molecular fragment, such that the resulting extension is also highly complementary to the receptor.

DDIEM is a Drug Database for inborn errors of metabolism. DDIEM database is a database on therapeutic strategies for inborn errors of metabolism. These strategies are classified by mechanism and outcome in DDIEM Ontology. DDIEM uses this ontology to categprise the experimental treatments that have been proposed or applied. It includes descriptions of the phenotypes addressed by the treatment and drugs participating in treatment and procedures.

CHEER is a hierarchical model, which can learn the species masking feature via deep learning classifier, for new RNA virus taxonomy classification.

BioLearn is an open-source library for the curation, harmonization, and systematic evaluation of aging biomarkers. It provides tools to load data from public sources and run common aging clocks with a few lines of code.

APA-Scan detects the potential Alternative Polyadenylation (APA) events in the downstream 3'-UTR of a gene among two different biological conditions. APA-Scan is a python tool which can be downloaded directly from github. Python (version 3.0 or higher) is required to be installed on users machine to run APA-Scan. It can work on Windows, Linux and Mac platform.

Repository for transferGWAS, a deep learning method for performing genome-wide association studies on full medical imaging data.

Efficient TWAS Tool with Nonparametric Bayesian eQTL Weights of 49 Tissue Types from GTEx V8.

Toffee – A highly efficient, lossless file format for DIA-MS | A library for fast access to Time of Flight SWATH-MS data — toffee latest documentation | Free document hosting provided by Read the Docs

Minimizing the number of optimizations for efficient community dynamic flux balance analysis. Dynamic FBA for use with COBRAPy metabolic models.

Processing and analysis of large-scale spatial transcriptomics data.

Sparse Correlation Network Investigation for Compositional Data.

Batch effect removal in large-scale, multi-source omics data integration.

A function-based gut microbiome health index

MQuad (Mixture Model for Mitochondrial Mutation detection in single-cell omics data) is a tool that detects mitochondrial mutations that are informative for clonal substructure inference. MQuad enables clonal substructure discovery using single cell mitochondrial variants. It uses a binomial mixture model to assess the heteroplasmy of mtDNA variants among background noise.

An open-source computational pipeline for robust nanobody humanization.

A Python package for HiChIP data processing and quality control pipeline.

A framework for the annotation and prioritization of non-coding regulatory variants in whole-genome sequencing. Genomic Regulatory Elements ENcyclopedia. This is the home of the GREEN-DB and companion tools (GREEN-VARAN). Genomic Regulatory Elements ENcyclopedia Database A collection of ~2.4M regulatory regions in the human genome, with information about controlled genes, tissues of activity and associated phenotypes. GREEN-DB is available for free for academic usage in a Zenodo repository.

FL-QSAR is a federated learning based QSAR prototype for collaborative drug discovery. FL-QSAR is an horizontal federated-learning based QSAR framework that enables clients to simulate the scenario of n clients with and without HFL(horizontal federated-learning). FL-QSAR is also a demo framework designed to help users better understanding the workflow and the underline mechanism of applying HFL for QSAR modeling. Meanwhile, FL-QSAR can be easily extended to other deep learning algorithms for solving various drug-related learning tasks.

ELEPHANT is an interactive platform for cell tracking in 4D that seamlessly integrates annotation, deep learning, and proofreading.

Metagenomics is a culture-independent method for studying the microbes inhabiting a particular environment. Comparing the composition of samples (functionally/taxonomically), either from a longitudinal study or cross-sectional studies can provide clues into how the microbiota has adapted to the environment. However, a recurring challenge is that key metadata about the sample and molecular methods used to extract and sequence the genetic material are often missing from sequence records, making it difficult to account for confounding factors. Nevertheless, this missing metadata may be found in the narrative of publications describing the research. This respository offers a new metagenomics annotations pipeline that regularly enrich up-to-date ENA and MGnify metagenomics studies with metadata extracted from research articles in EuropePMC. These metadata are now available for researchers to explore and retrieve in the MGnify and Europe PMC websites, and Europe PMC annotations API.

DeeReCT-APA is a tool for prediction of alternative polyadenylation site usage through deep learning.

Fast and Reliable Tool for QSAR. Transformer CNN for QSAR/QSPR modelling. The repository contains the source code for a new Transformer-CNN method described in our paper http://arxiv.org/abs/1911.06603. First, we trained the Transformer model on SMILES canonicalization task, e.g., given an arbitrary SMILES, the model converts it to a canonical one. Second, we use the internal representation of the Transformer (the output of the encoding stack with shape (BATCH, LENGTH, EMBEDDING)) as SMILES embeddings and build upon them CharNN model (Convolution and HighWay as it is done in DeepChem). The resulting model works both in classification and regression settings

A biologically drop-connect deep neural network model for prioritizing disease risk variants and genes. Population studies such as GWAS have identified a variety of genomic variants associated with human diseases. To further understand potential mechanisms of disease variants, recent statistical methods associate functional omic data (e.g., gene expression) with genotype and phenotype and link variants to individual genes. However, how to interpret molecular mechanisms from such associations, especially across omics is still challenging. To address this, we develop an interpretable deep learning method, Varmole to simultaneously reveal genomic functions and mechanisms while predicting phenotype from genotype. In particular, Varmole embeds multi-omic networks into a deep neural network architecture and prioritizes variants, genes and regulatory linkages via drop-connect without needing prior feature selections.

a library for the analysis and visualization of long-read transcriptomes. swan is a tool for visualizing and analyzing transcript isoforms.

A Platform for Structural Variant Visual Validation and Automated Filtering. samplot is a command line tool for rapid, multi-sample structural variant visualization. samplot takes SV coordinates and bam files and produces high-quality images that highlight any alignment and depth signals that substantiate the SV. 1000 genomes high coverage crams.

Identification of foods containing compounds with specific pharmacological properties. Phytebyte is an extensible software framework used to train machine learning models to identify bioactive compounds found in food. The use case captured in 'run.py' is training models using known drug compounds that target a specific gene, and identifying plant compounds in FooDB that may behave similarly.

Penguin is a tool for predicting pseudouridine sites in direct RNA nanopore sequencing data. The penguin tool needs as input a fast5 path and if you don't provide a sam file you have to provide a reference genome to align to so the tool can create the sam file. If no bed file is provided a default one is included and will be used. The tool will then id all fast5 files and create coordinate file with ids of files that are modified.

Pancreatlas is applying an adaptable framework to map the human pancreas in health and disease.

De Novo Molecule Identification from NMR Spectra. Molecule identification from NMR spectrum using de novo molecule generator. This code is for reference only as it requires MPI and Gaussian environment which is hard to ensure among different clusters. Also, for the NMR spectrum prediction part, we have used a Gaussain encapsulation package which we can not make public for now. Replacing this part by a traditional Gaussian code or other NMR spectrum prediction method would solve the problem.

A user-friendly, comprehensive microbial genome annotation pipeline. Easy-to-use pipeline for the comprehensive metabolic annotation of microbial genomes. MicrobeAnnotator uses an iterative approach to annotate microbial genomes (Bacteria, Archaea and Virus) starting from proteins predicted using your favorite ORF prediction tool, e.g. Prodigal. The iterative approach is composed of three or five main steps (depending on the flavor of MicrobeAnnotator you run).

Screening for inborn errors of metabolism using untargeted metabolomics and out-of-batch controls. This repository contains code and datasets used for the article Using Out-of-Batch Reference Populations to Improve Untargeted Metabolomics for Screening Inborn Errors of Metabolism published in MDPI Metabolites:.

A high-performance and stand-alone ensemble binning method to recover individual genomes from complex microbial communities.

MAnorm2 for quantitatively comparing groups of ChIP-seq samples. To pre-process a set of ChIP-seq samples. MAnorm2_utils is designed to coordinate with MAnorm2, an R package for differential analysis with ChIP-seq signals between two or more groups of replicate samples. MAnorm2_utils is primarily used for processing a set of ChIP-seq samples into a regular table recording the read abundances and enrichment states of a list of genomic bins in each of these samples.

JASMINE (Jointly Accurate Sv Merging with Intersample Network Edges) is an automated pipeline for alignment and SV calling in long-read datasets. The tool is used to merge structural variants (SVs) across samples. Each sample has a number of SV calls, consisting of position information (chromosome, start, end, length), type and strand information, and a number of other values. Jasmine represents the set of all SVs across samples as a network, and uses a modified minimum spanning forest algorithm to determine the best way of merging the variants such that each merged variants represents a set of analogous variants occurring in different samples.

DeepDrug is a general graph-based deep learning framework for drug-drug/protein interaction prediction.

CpG Transformer for imputation of single-cell methylomes.