OncoDigger Prioritizes Mutation-Associated Genes in Cancer-Specific PubMed Abstracts

Abstract OncoDigger is a biomedical text-mining tool designed to identify and rank genes associated with user-defined queries across cancer-specific PubMed literature. This study systematically evaluates OncoDigger's performance in prioritizing genes associated with mutation-focused literature and examines the factors underlying its results. Ranking involves no gene-specific mutation extraction, so concordance with IntOGen measures agreement with a driver catalogue, not mutation-reporting accuracy. Using the query "mutation mutations", we analyzed PubMed abstract collections representing 19 cancer types and evaluated the top 10 ranked genes per cancer against the IntOGen cancer-driver catalogue. Across 190 gene–cancer pairs, 93.7% (178/190) involved genes recognized as drivers in at least one cancer, while 78.9% (150/190) matched drivers of the corresponding cancer type. Exact cancer-type concordance exceeded that of a pooled, cancer-blind control (53.2%), which by construction returns one list for all cancers, by 25.8 percentage points and CancerMine (60.0%) by 18.9 percentage points. Controlled comparisons identified cancer-specific document retrieval and gene-name quality control as principal contributors to performance, whereas the full scoring formula provided only a small, statistically nonsignificant improvement over matched gene counting. Sensitivity analyses supported the stability of the principal findings. These results provide evidence of OncoDigger's effectiveness for cancer-specific, mutation-focused gene prioritization from published literature. By providing traceable gene rankings and distinguishing literature associations from driver genes called in tumour-sequencing cohorts, OncoDigger offers an accessible and reproducible resource for exploring cancer-associated genes. Availability: The web application is available at https://oncodigger.com. Code, data, and reproducibility materials are available at https://github.com/jfataphd/OncoDigger-gene-prioritization (release v1.3, archived at Zenodo, https://doi.org/10.5281/zenodo.23774746).

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-02
DOI
https://doi.org/10.21203/rs.3.rs-11556965/v1
Primary Topic
Biomedical Text Mining and Ontologies
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

OncoDigger Prioritizes Mutation-Associated Genes in Cancer-Specific PubMed Abstracts

Jimmie E. Fata
1 links
Research Square
Biomedical Text Mining and Ontologies
preprint

OncoDigger Prioritizes Mutation-Associated Genes in Cancer-Specific PubMed Abstracts

Jimmie E. Fata
preprint en

Abstract

Abstract OncoDigger is a biomedical text-mining tool designed to identify and rank genes associated with user-defined queries across cancer-specific PubMed literature. This study systematically evaluates OncoDigger's performance in prioritizing genes associated with mutation-focused literature and examines the factors underlying its results. Ranking involves no gene-specific mutation extraction, so concordance with IntOGen measures agreement with a driver catalogue, not mutation-reporting accuracy. Using the query "mutation mutations", we analyzed PubMed abstract collections representing 19 cancer types and evaluated the top 10 ranked genes per cancer against the IntOGen cancer-driver catalogue. Across 190 gene–cancer pairs, 93.7% (178/190) involved genes recognized as drivers in at least one cancer, while 78.9% (150/190) matched drivers of the corresponding cancer type. Exact cancer-type concordance exceeded that of a pooled, cancer-blind control (53.2%), which by construction returns one list for all cancers, by 25.8 percentage points and CancerMine (60.0%) by 18.9 percentage points. Controlled comparisons identified cancer-specific document retrieval and gene-name quality control as principal contributors to performance, whereas the full scoring formula provided only a small, statistically nonsignificant improvement over matched gene counting. Sensitivity analyses supported the stability of the principal findings. These results provide evidence of OncoDigger's effectiveness for cancer-specific, mutation-focused gene prioritization from published literature. By providing traceable gene rankings and distinguishing literature associations from driver genes called in tumour-sequencing cohorts, OncoDigger offers an accessible and reproducible resource for exploring cancer-associated genes. Availability: The web application is available at https://oncodigger.com. Code, data, and reproducibility materials are available at https://github.com/jfataphd/OncoDigger-gene-prioritization (release v1.3, archived at Zenodo, https://doi.org/10.5281/zenodo.23774746).

Research Square
College of Staten Island (US)
Good health and well-being
Biomedical Text Mining and Ontologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
OncoDigger Prioritizes Mutation-Associated Genes in Cancer-Specific PubMed Abstracts — Jimmie E. Fata · Research Square (2026) | TGRS Research Map | TGRS