Comprehensive collection of computational tools used in STRC variant analysis and hearing loss genetics research. All tools are freely accessible to enable independent genetic variant research.
Predicts 3D structures of protein complexes (protein-protein, protein-DNA, protein-ligand)
Provides predicted 3D protein structures for nearly every known protein
Untrained algorithm predicting the folding stability impact of amino acid substitutions.
Integrates mCSM and SDM into a consensus prediction of protein stability upon mutation.
Analyzes mutational impacts on protein dynamics and vibrational entropy.
Evaluates the effect of mutations on protein folding and protein-protein interactions.
Predicts 3D protein structure from amino acid sequence alone
Calculates empirical energy terms for evaluating wild-type and mutant protein stability.
Jointly estimates absolute folding stability (DeltaG) and equilibrium structural ensembles.
Predicts intrinsic disorder from protein sequence
Interactive 3D protein structure visualization
Predicts GPI-anchor signal presence
Predicts N-linked glycosylation sites (NXS/NXT motifs)
Predicts changes in thermodynamic stability caused by single site mutations.
Publication-quality 3D protein structure rendering
Predicts 3D structures and models complex multi-protein biological assemblies.
Python wrapper automating high-throughput free energy calculations for variants.
Calculates the difference in stability based on environment-specific amino acid substitution tables.
Predicts \Delta\DeltaG using quantitative structure-activity relationship (QSAR) models.
Builds 3D protein models by homology to known experimental structures
Predicts signal peptide presence and type (Sec/SPI, Sec/SPII, Tat/SPI)
Predicts stability and binding affinity changes utilizing graph-based spatial signatures.
High-resolution imaging and transcriptomics mapping genetic expression strictly to brain anatomy.
Predicts pathogenicity of missense variants (amino acid substitutions)
Evaluates coding and non-coding variants utilizing a Bayesian modeling framework.
Scores all variant types: missense, synonymous, intronic, intergenic, UTR, splice
Open-source, crowd-sourced database for clinical interpretation of variants in cancer.
Genomic language model leveraging the Mamba architecture with reverse-complement equivariance.
Meta-predictor combining functional VEP scores with clinical allele frequencies.
Uses deep neural networks to score the deleteriousness of genetic variants.
Multi-species modeling tool employing byte pair encoding and refined transformer configurations.
Evaluates missense variants using zero-shot protein language modeling.
Maps viral and human fitness landscapes via deep generative models.
Uses unsupervised spectral approaches to aggregate functional annotations into a single score.
40-billion parameter genomic foundation model predicting and generating tasks across DNA and RNA.
Database of gene and protein expression across species and biological conditions.
Integrates multiple kernel learning to predict the functional consequences of SNVs.
Facilitates the annotation of variants based on their functional consequences.
AI-assisted ACMG/AMP variant classification
Open-source, web-based platform for highly accessible and reproducible genomic data analysis.
Exhaustive, expert-curated database of germline mutations underlying inherited human diseases.
Spatial omics atlas mapping all human proteins across tissues, blood, and single cells.
Genomic sequence model utilizing implicit convolutions to achieve million-token data contexts.
Automated application of ACMG/AMP criteria (PVS1, PS1-4, PM1-6, PP1-5, BA1, BS1-4, BP1-7)
Estimates the fitness consequences of non-coding mutations.
Calculates missense badness, PolyPhen-2, and constraint metrics for variant scoring.
AI-driven genomic intelligence platform indexing variants from over 11 million full-text articles.
Prioritizes rare non-synonymous SNVs via recurrent neural networks.
Assesses the specific fitness effects and loss-of-function potential of genetic variants.
Unified foundation model pre-trained on 9 trillion base pairs for molecular phenotype prediction.
Platform supporting the systematic identification and prioritization of therapeutic drug targets.
Comprehensive resource detailing how genetic variation directly affects drug response.
Evaluates missense variants by integrating 3D protein structures and primate genomics.
Ensemble score from 13 tools: MutPred, FATHMM, VEST, PolyPhen, SIFT, PROVEAN, MutationAssessor, MutationTaster, LRT, GERP, SiPhy, phyloP, phastCons
Annotates variants and predicts their localized structural and sequence ontology impacts.
Analyzes variants for broad phenotypic and functional impacts in scalable cloud environments.
Scalable platform enabling researchers to run bioinformatics tools securely on Google/Azure clouds.
Random forest classifier predicting the statistical probability of a variant being pathogenic.
Aggregates: ClinVar, gnomAD, REVEL, CADD, SpliceAI, conservation scores, literature
30+ predictor scores per variant: REVEL, CADD, SIFT, PolyPhen-2, MutationTaster, FATHMM, GERP, PhyloP, PhastCons, AlphaMissense, and more
Clusters genomic positions by functional annotations to estimate fitness consequences.
Predicts missense variant pathogenicity employing a sophisticated graph neural network.
Flexible command-line toolset for the storage, annotation, and dynamic filtering of sequence variants.
Tissue-specific contextual filter estimating the probability of aberrant splicing events.
Intron-centric aberrant splicing caller utilizing empirical RNA-seq data.
Detects splice sites in genomic DNA sequences using maximal dependence decomposition.
High-throughput alternative splicing prediction platform.
Modular modeling framework predicting the usage of cassette exons.
Evaluates 5' and 3' splice site strength employing the Maximum Entropy Principle.
Neural network approach to locating consensus splice sites in primary DNA sequence.
Predicts splice site strength and aberrant usage across multiple mammalian tissues.
Predicts the percentage of spliced-in (PSI) events across different tissues.
Bioinformatics pipeline utilizing statistical thresholds for deep splicing analysis.
Predicts splice site creation/disruption from DNA sequence
Deep convolutional neural network for splice site prediction in whole genomes.
Predicts cell-type-specific epigenetic and transcriptional profiles from raw DNA sequence.
Deep learning-based sequence model for predicting the chromatin effects of sequence alterations.
Encyclopedia of DNA elements providing massive functional genomic datasets.
Maps DNA sequences to RNA expression and chromatin states using transformer networks.
Comprehensive database of tissue-specific gene expression and eQTLs.
Explores functional annotations of the noncoding genome at specific haplotype blocks.
Computational method modeling the magnitude and shape of genome-wide DNase profiles.
Identifies functional DNA features and regulatory elements in non-coding genomic regions.
Atlas of human epigenomes mapping regulatory elements across multiple cell types.
Organ-specific machine-learning architecture for prioritizing regulatory variants.
Allele Frequency Aggregator analyzing dbSNP data across diverse populations.
Variant browser providing allele frequencies for over 868 million variants from whole genomes.
Prospective genome biobank offering summary statistics for ~260,000 Japanese individuals.
High-quality database containing 9.04 million SNVs from 141,431 healthy Chinese individuals.
Gene-disease validity curation (is STRC definitively linked to hearing loss?)
Historical exome aggregation consortium (largely superseded by gnomAD).
The National Project of Bio-Big Data in South Korea, projecting 1 million sequenced genomes.
Leiden Open Variation Database providing locus-specific gene variant data.
Comprehensive repertoire integrating 154 million genetic variants from South Asians.
Massive biomedical database containing over 500,000 sequenced genomes.
Foundational archive for single nucleotide polymorphisms and multiple small-scale variations.
Population allele frequencies across diverse ancestries
Variant search across 70K+ rare disease cases
Interactive web application for prioritizing clinically implicated variants via ancestry composition.
Archives variant classifications from clinical labs and research groups
Registry of 400,000+ clinical studies worldwide
Maps genomic variants (especially CNVs/SVs) to clinical phenotypes
Drug-Gene Interaction Database mapping genes to potential therapeutic compounds.
Extensively curated database of human genome-wide association studies and summary statistics.
Comprehensive gene-disease relationship catalog
Resource providing uniformly processed gene counts from over 137k GEO/SRA RNA-seq samples.
Variant Effect Predictor (VEP) — predict consequences of variants
Visualize any genomic region with dozens of annotation tracks
Protein sequences (reviewed SwissProt + unreviewed TrEMBL)
Catalog of natural and engineered AAV capsids
Tracks gene therapy clinical trials globally
Supervised machine learning suite predicting patient genotypes strictly from audiometric data.
Repository of clinical trial parameters for dual-AAV gene therapy treating OTOF mutations.
Variant classifications specific to hearing loss genes
Single-nucleus RNAseq atlas of human inner ear development (1st and 2nd trimesters).
Complete list of deafness genes and loci
High-throughput in vivo screening database identifying and validating AAV vectors for the inner ear.
Gene Expression Analysis Resource for comparing in vivo cochlear data to in vitro organoids.
Multiple sequence alignment (MSA) of protein or DNA sequences
Estimates the evolutionary conservation of amino and nucleic acid positions using precise phylogeny.
Predicts 3D structural conformations and mutation fitness landscapes from evolutionary sequence covariation.
Ortholog clusters across 2,000+ species
Scoring algorithm for amino acid conservation taking into account stochastic evolutionary processes.
Compiles functionally and clinically relevant information to interpret SV pathogenicity quickly.
Primary structural variant caller utilizing read-depth signals from whole-genome sequencing.
Advanced copy number estimator and variant caller designed for large-scale cohort analysis.
Command-line tool calculating the pathogenicity of germline duplications and large deletions.
Integrates paired-end and split-read analyses to discover precise genomic rearrangements.
Broad Institute pipeline for robustly detecting germline copy number variants in WES and WGS data.
Rapid structural variant caller tailored specifically for high-throughput clinical sequencing pipelines.
Versatile tool for converting genome coordinates in various file formats (BAM, BED, VCF).
Checks sequence variant nomenclature according to strict, up-to-date HGVS guidelines.
Validates HGVS sequence descriptions and flawlessly maps transcript/genomic variant data.
Repository providing comprehensive access to worldwide life sciences articles and preprints.
Finds the best-matching sentences given a query via a cutting-edge neural embedding approach.
Web-based system utilizing AI and machine learning for document classification and literature triage.
Advanced semantic search engine linking genomic variant data in PubMed, PMC, and dbSNP.
Search biomedical literature (abstracts and full text)
Text-mining tool annotating entire articles with key biological entities (genes, mutations, diseases).
AI-backed search engine focusing entirely on scientific literature and citation graphs.
Complex NLP algorithm extracting sequence variants across both protein and gene levels.
All tools are designed for independent research. Most databases are free with academic access. The complete methodology is documented to enable reproduction by any family facing similar variant uncertainty.