MétaCan
Menu
Back to cohort
Record W4226097934 · doi:10.1186/s12920-022-01166-3

GeneTerpret: a customizable multilayer approach to genomic variant prioritization and interpretation

2022· article· en· W4226097934 on OpenAlexafffund
Roozbeh Manshaei, Sean DeLong, Veronica Andric, Esha Joshi, John B. A. Okello, Priya Dhir, Cherith Somerville, Kirsten M. Farncombe, Kelsey Kalbfleisch, Rebekah Jobling, Stephen W. Scherer, Raymond H. Kim, S. Mohsen Hosseini

Bibliographic record

VenueBMC Medical Genomics · 2022
Typearticle
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicGenomics and Rare Diseases
Canadian institutionsToronto General HospitalUniversity Health NetworkSickKids FoundationUniversity of TorontoHospital for Sick ChildrenYork UniversityTed Rogers Centre for Heart Research
FundersHospital for Sick ChildrenWellcome Trust
KeywordsDECIPHERComputer scienceBottleneckGenomicsComputational biologyData miningGenomeInformation retrievalBioinformaticsGeneticsBiologyGene

Abstract

fetched live from OpenAlex

BACKGROUND: Variant interpretation is the main bottleneck in medical genomic sequencing efforts. This usually involves genome analysts manually searching through a multitude of independent databases, often with the aid of several, mostly independent, computational tools. To streamline variant interpretation, we developed the GeneTerpret platform which collates data from current interpretation tools and databases, and applies a phenotype-driven query to categorize the variants identified in the genome(s). The platform assigns quantitative validity scores to genes by query and assembly of the genotype-phenotype data, sequence homology, molecular interactions, expression data, and animal models. It also uses the American College of Medical Genetics and Genomics (ACMG) criteria to categorize variants into five tiers of pathogenicity. The final output is a prioritized list of potentially causal variants/genes. RESULTS: We tested GeneTerpret by comparing its performance to expert-curated genes (ClinGen's gene-validity database) and variant pathogenicity reports (DECIPHER database). Output from GeneTerpret was 97.2% and 83.5% concordant with the expert-curated sources, respectively. Additionally, similar concordance was observed when GeneTerpret's performance was compared with our internal expert-interpreted clinical datasets. CONCLUSIONS: GeneTerpret is a flexible platform designed to streamline the genome interpretation process, through a unique interface, with improved ease, speed and accuracy. This modular and customizable system allows the user to tailor the component-programs in the analysis process to their preference. GeneTerpret is available online at https://geneterpret.com .

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.010
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.013
Threshold uncertainty score0.044

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.010
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0030.001
Science and technology studies0.0010.001
Scholarly communication0.0030.002
Open science0.0030.004
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0130.004

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.008
GPT teacher head0.228
Teacher spread0.220 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueBMC Medical GenomicsSame topicGenomics and Rare DiseasesFrench-language works237,207