Article

GhostBuster: A Deep-Learning-based, Literature-Unbiased Gene Prioritization Tool for Gene Annotation Prediction

2025-06-27

Abstract excerpt

All genes are not equal before literature. Despite the explosion of genomic data, a significant proportion of human protein-coding genes remain poorly characterized (“ghost genes”). Due to sociological dynamics in research, scientific literature disproportionately focuses on already well-annotated genes, reinforcing existing biases (bandwagon effect). This literature bias often permeates machine learning (ML) mode...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: dbe03560-735c-58b5-8573-33375586b0a3
DOI: 10.1101/2025.06.22.660948

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

GhostBuster: A Deep-Learning-based, Literature-Unbiased Gene Prioritization Tool for Gene Annotation PredictionDOI 10.1101/2025.06.22.660948Read

pBRIT: gene prioritization by correlating functional and phenotypic annotations through integrative data fusion.Semantic proximity Read

Systematic Evaluation of Molecular Networks for Discovery of Disease Genes.Semantic proximity Read

GCDPipe: risk gene, cell type, and drug ranking for complex traitsSemantic proximity Read

Supervised-learning is an accurate method for network-based gene classificationSemantic proximity Read

Knowledge Inclusive Machine Learning for Disease Gene PrioritisationSemantic proximity Read

genepanel.iobio - an easy to use web tool for generating disease- and phenotype-associated gene listsSemantic proximity Read

Prioritizing candidate disease genes by network-based boosting of genome-wide association data.Semantic proximity Read

Genepanel.iobio - an easy to use web tool for generating disease- and phenotype-associated gene lists.Semantic proximity Read

The Implicitome: A Resource for Rationalizing Gene-Disease Associations.Semantic proximity Read

A heterogeneous graph neural network for candidate gene prediction in endometriosis.Semantic proximity Read

XG-PUL: A Network-Based Framework for Disease Gene Prioritization Using Graph Representation Learning and Positive-Unlabeled LearningSemantic proximity Read

The FABRIC Cancer Portal: A Ranked Catalogue of Gene Selection in Tumors over the Human Coding GenomeSemantic proximity Read