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
Language(1)
License
Source
Type(1)
1,529 of 9,874 resources
Showing 1,451–1,500
CancerVar is a web server for improved evidence-based clinical interpretation for cancer somatic mutations. CancerVar is a bioinformatics software tool for clinical interpretation of somatic variants.
Balrog is a prokaryotic gene finder based on a Temporal Convolutional Network.
Assembline is a multi-step protocol for integrative structural modeling of macromolecular complexes based on electron microscopy, cross-linking mass spectrometry and other data. The protocols is based on our Xlink Analyzer and external software: Integrative Modeling Plafform (IMP), Python Modeling Interface (PMI), UCSF Chimera, and imp-sampcon. Comparing to other methods, Assembline enables efficient sampling of conformational space through a multi-step procedure, provides new modeling restraints, and includes a unique configuration system for setting up the modelling project.
Ad hoc learning of fragmentation patterns in mass spectra detects post-translationally modified peptides prior to database search. Deep learning model (Temporal conv net, using dilated conv layers) detects post-translational modified peptides based on their ms/ms spectrum.
> MEDIUM CONFIDENCE! | > CORRECT NAME OF TOOL COULD ALSO BE 'jats:list-item' | A quantitative method for proteome reallocation using minimal regulatory interventions | Regulation based Proteome Minimization (ReProMin) | Three files are needed for the analysis:
An interpretable recurrent neural network model with attention mechanism for peptide-HLA class II binding prediction. A sequence-based pan model for peptide-MHC II binding affinity prediction.
A deep convolutional neural network toolkit for epigenomics. SDK for deep learning based processing of Atac-seq data. AtacWorks is a deep learning toolkit for track denoising and peak calling from low-coverage or low-quality ATAC-Seq data. AtacWorks trains a deep neural network to learn a mapping between noisy (low coverage/low quality) ATAC-Seq data and matching clean (high coverage/high quality) ATAC-Seq data from the same cell type. Once this mapping is learned, the trained model can be applied to improve other noisy ATAC-Seq datasets
Deciphering active prophages from metagenomes. PropagAtE (Prophage Activity Estimator) uses genomic coordinates of integrated prophage sequences and short sequencing reads to estimate if a given prophage was in the lysogenic (dormant) or lytic (active) stage of infection.
A method to map and interpret pleiotropic loci using summary statistics of multiple traits. Pleiotropic Locus Exploration and Interpretation using Optimal test.
PeakBot is a python package for peak-picking in LC-HRMS profile mode data. It uses local-maxima in the LC-HRMS dataset each of which is then exported as a standarized two-dimensional area (rt x mz), which is used as the input for a machine-learning CNN model that reports whether the local-maxima is a chromatographic peak with left/right isomeric compounds or a signal of the background.
Drug2ways is a Python package for reasoning over paths on large-scale biological networks for drug discovery.
ANANSE is a computational approach to infer enhancer-based gene regulatory networks (GRNs) and to use these GRNs to identify the key transcription factors in cell fate determination.
Structural variant detection from haploid and diploid genome assemblies. SVIM-asm - Structural variant identification method (Assembly edition). SVIM-asm (pronounced SWIM-assem) is a structural variant caller for haploid or diploid genome-genome alignments. It analyzes a given sorted BAM file (preferably from minimap2) and detects five different variant classes between the query assembly and the reference: deletions, insertions, tandem and interspersed duplications and inversions.
ProteInfer is an approach for predicting the functional properties of protein sequences using deep neural networks.
Accurate and Versatile 3D Segmentation of Plant Tissues at Cellular Resolution. PlantSeg is a tool for cell instance aware segmentation in densely packed 3D volumetric images. The pipeline uses a two stages segmentation strategy (Neural Network + Segmentation). The pipeline is tuned for plant cell tissue acquired with confocal and light sheet microscopy. Pre-trained models are provided.
deepManReg is a deep manifold-regularized learning model for improving phenotype prediction from multi-modal data.
A GUI-based Python framework for segmentation, tracking and cell cycle annotations of microscopy data.
A convolutional neural network for highly accurate, label-free segmentation of yeast microscopy images. Laboratory of the Physics of Biological Systems ‐ EPFL.
Pout2Prot converts Percolator output files to protein group and subgroup files using Occam's razor or anti-Occam's razor. These output files can directly be used in Prophane for further downstream taxonomic and functional analysis
Non-parametric modelling of temporal and spatial counts data from RNA-seq experiments. GPcounts is Gaussian process regression package for counts data with negative binomial and zero-inflated negative binomial likelihoods described in the paper "Non-parametric modelling of temporal and spatial counts data from RNA-seq experiments". It is implemented using the GPflow library.
EpiDope is a deep neural network for linear B-cell epitope prediction.
CoPTR is a tool for accurate and robust inference of microbial growth dynamics from metagenomic sequencing.
Metaproteomic Least Common Ancestor Analysis for Taxonomic Inference Using Specialized Sequence Assemblies. The METATRYP software consists of:. METATRYP allows users to investigate the occurrence of tryptic peptides within the protein coding sequences predicted from genomes and metagenomes. METATRYP allows users to investigate the occurrance of tryptic peptides within the protein coding sequences predicted from genomes. Testing for the Corona-2 (COVID-19) virus has utilized RNA and antibody analytical methodologies to date. METATRYP allows users to investigate the occurrence of tryptic peptides within the protein coding sequences predicted from genomes and metagenomes.
Summary Visualisations of Gene Ontology Terms with GO-Figure!. GO-Figure! offers a simple solution for command-line plotting of informative summary visualisations of lists of GO terms, designed to support exploratory data analyses and multiple dataset comparisons.
TDimpute is a novel transfer learning-based neural network to impute missing gene expression data from DNA methylation data. In the tool, the pan-cancer dataset from TCGA was utilized for training a general model for all cancers, which was then fine-tuned on the target cancer dataset for imputation.
pypgatk is a Python library part of the ProteoGenomics Analysis Toolkit. It provides different bioinformatics tools for proteogenomics data analysis
Large-scale tandem mass spectrum clustering using fast nearest neighbor searching. The falcon spectrum clustering tool uses advanced algorithmic techniques for highly efficient processing of millions of MS/MS spectra. First, high-resolution spectra are binned and converted to low-dimensional vectors using feature hashing. Next, the spectrum vectors are used to construct nearest neighbor indexes for fast similarity searching. The nearest neighbor indexes are used to efficiently compute a sparse pairwise distance matrix without having to exhaustively compare all spectra to each other. Finally, density-based clustering is performed to group similar spectra into clusters.
An open-source Python package for the visual annotation of proteomics data with sequence specific knowledge.
PPanGGOLiN is a software suite used to create and manipulate prokaryotic pangenomes from a set of either genomic DNA sequences or provided genome annotations. It is designed to scale up to tens of thousands of genomes. It has the specificity to partition the pangenome using a statistical approach rather than using fixed thresholds which gives it the ability to work with low-quality data such as Metagenomic Assembled Genomes (MAGs) or Single-cell Amplified Genomes (SAGs) thus taking advantage of large scale environmental studies and letting users study the pangenome of uncultivable species
scDART (single cell Deep learning model for ATAC-Seq and RNA-Seq Trajectory integration) is a scalable deep learning framework that embed the two data modalities of single cells, scRNA-seq and scATAC-seq data, into a shared low-dimensional latent space while preserving cell trajectory structures. Furthermore, scDART learns a nonlinear function represented by a neural network encoding the cross-modality relationship simultaneously when learning the latent space representations of the integrated dataset.
A deep-learning framework for protein subcellular and suborganellar localization prediction with residue-level interpretation. MULocDeep is a deep learning model for protein localization prediction at both sub-cellular level and sub-organellar level. It also has the ability to interpret localization mechanism at a amino acid resolution. Users can go to our webserver at xxx.xxx for localiztion prediction and visualization. This repository is for running MuLocDeep locally. A protein localization prediction tool at sub-cellular and sub-organellar levels. MULocDeep: An Interpretable Deep Learning Model for Protein Localization Prediction at the Sub-organelle Resolution (in submission).
Identifying signaling genes in spatial single cell expression data. MESSI (Mixture of Experts for Spatial Signaling genes Identification) is a predictive framework to identify signaling genes active in cell-cell interaction. It jointly models gene interactions within and between cells, using the recently developed spatial single cell expression data. MESSI combines the ability to subdivide cell types with multi-task learning to accurately infer the expression of a set of response genes based on signaling genes and to provide useful biological insights about key signaling genes and cell subtypes.
Mantis is a homology-based protein function annotation tool that integrates multiple reference data sources. It uses multiple high-quality data sources as a reference, however custom reference data sources can also be added. Mantis does not use a pre-built database, instead, it dynamically integrates the multiple sources into a consensus-driven output. Mantis is extensively customizable and is available on Linux.
Integration of machine learning and pan-genomics expands the biosynthetic landscape of RiPP natural products. decRiPPter (Data-driven Exploratory Class-independent RiPP TrackER). Alexander M. Kloosterman, Peter Cimermancic, Somayah S. Elsayed, Chao Du, Michalis Hadjithomas, Mohamed S. Donia, Michael A. Fischbach, Gilles P. van Wezel, and Marnix H. Medema. decRiPPter is a genome mining tool for detection of novel biosynthetic gene clusters (BGCs) of ribosomally synthesized and post-translationally modified peptides (RiPPs). Number of operons with antismash overlap. Nr of operons with known RiPP domains.
A platform for live cell multiplex imaging reveals cell phenotypic transition dynamics inherently missing in snapshot data. M-TRACK is a live cell imaging analysis tool
Reference-free Cell-type Annotation for Single-cell Transcriptomics using Deep Learning with a Weighted Graph Neural Network. To addresses this challenge, we developed a reference-free cell-type annotation method, namely scDeepSort, using a state-of-the-art deep learning algorithm, i.e. a modified graph neural network (GNN) model. Recent advance in single-cell RNA sequencing (scRNA-seq) has enabled large-scale transcriptional characterization of thousands of cells in multiple complex tissues, in which accurate cell type identification becomes the prerequisite and vital step for scRNA-seq studies.
DeepTE is aimed to classify transposons with unknown classification via Convolutional Neural Network. A computational method for de novo classification of transposons with convolutional neural network.
SOMDE: A scalable method for identifying spa-tially variable genes with self-organizing map. A scalable method for identifying spatially variable genes with self-organizing map. Algorithm for finding gene spatial pattern based on Gaussian process accelerated by SOM.
Redesign and Expansion of the Prediction on Kinase-specific Phosphorylation Sites.
metabolic complementarity applied to genomes of large-scale microbiotas for the identification of keystone species. From annotated genomes to metabolic screening in large scale microbiotas. Metage2metabo is a Python3 (Python >= 3.6) tool to perform graph-based metabolic analysis starting from annotated genomes (reference genomes or metagenome-assembled genomes). It uses Pathway Tools in a automatic and parallel way to reconstruct metabolic networks for a large number of genomes. The obtained metabolic networks are then analyzed individually and collectively in order to get the added value of metabolic cooperation in microbiota over individual metabolism and to identify and screen interesting organisms among all. m2m — metage2metabo documentation. Free document hosting provided by Read the Docs
Kallisto and Alevin (and possibly other tools) output an MTX file and associated labels that are not consistent with the old-style 10X, meaning that routines designed to parse those files cannot be used. This tool transforms (in the mathematical sense) the matrix, and reformats the genes file (essentially duplicating the column) to match those earlier conventions.
D-SCRIPT is a deep learning method for predicting a physical interaction between two proteins given just their sequences. It generalizes well to new species and is robust to limitations in training data size. Its design reflects the intuition that for two proteins to physically interact, a subset of amino acids from each protein should be in con-tact with the other. The intermediate stages of D-SCRIPT directly implement this intuition, with the penultimate stage in D-SCRIPT being a rough estimate of the inter-protein contact map of the protein dimer. This structurally-motivated design enhances the interpretability of the results and, since structure is more conserved evolutionarily than sequence, improves generalizability across species.
ANN-SoLo (Approximate Nearest Neighbor Spectral Library) is a spectral library search engine for fast and accurate open modification searching.
Ultra-high throughput single-cell RNA sequencing by combinatorial fluidic indexing. Cell atlas projects and single-cell CRISPR screens hit the limits of current technology, as they require cost-effective profiling for millions of individual cells
Detection of m6A from direct RNA sequencing using a Multiple Instance Learning framework.
Visualization of Very Large High-Dimensional Data Sets as Minimum Spanning Trees | Visualize big high-dimensional data | tmap is a very fast visualization library for large, high-dimensional data sets | We suggest using faerun to plot the data layed out by tmap. But you can of course also use matplotlib (which might be to slow for large data sets and doesn't provide interactive features). Following, an example plot produced with tmap and matplotlib
A Scanpy extension for analyzing single-cell T-cell receptor sequencing data. Scirpy: A Scanpy extension for analyzing single-cell immune-cell receptor sequencing data. Scirpy is a scalable python-toolkit to analyse T cell receptor (TCR) or B cell receptor (BCR) repertoires from single-cell RNA sequencing (scRNA-seq) data. It seamlessly integrates with the popular scanpy library and provides various modules for data import, analysis and visualization. Tutorials — scirpy documentation.
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.
A repository of unique short Open Reading Frames identified by both experimental and computational approaches for gene-level and meta-analysis. MetamORF: A repository of unique short Open Reading Frames identified by both experimental and computational approaches for gene-level and meta analysis.