Generalized information criteria for personalized gene network inference

Identifying individual genomic characteristics is a critical focus in personalized therapies. To reveal targets in such therapies, we considered personalized gene network analysis using kernel-based L1-type regularization methods. In kernel-based L1-type regularized modeling, selecting optimal regul...

Full description

Saved in:
Bibliographic Details
Main Authors: Heewon Park, Seiya Imoto, Sadanori Konishi
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Genetics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fgene.2025.1583756/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850114036114391040
author Heewon Park
Heewon Park
Heewon Park
Heewon Park
Seiya Imoto
Sadanori Konishi
author_facet Heewon Park
Heewon Park
Heewon Park
Heewon Park
Seiya Imoto
Sadanori Konishi
author_sort Heewon Park
collection DOAJ
description Identifying individual genomic characteristics is a critical focus in personalized therapies. To reveal targets in such therapies, we considered personalized gene network analysis using kernel-based L1-type regularization methods. In kernel-based L1-type regularized modeling, selecting optimal regularization parameters is crucial because edge selection and weight estimation depend heavily on such parameters. Furthermore, selecting a kernel bandwidth that controls sample weighting is vital for personalized modeling. Although cross-validation and information criteria (i.e., AIC and BIC) are often used for parameter selection, such traditional techniques are computationally expensive or unsuitable for approaches based on estimation techniques other than maximum likelihood estimation. To overcome these issues, we introduced a novel evaluation criterion in line with the generalized information criterion (GIC), which relaxes the assumption of maximum likelihood estimation, making it suitable for personalized gene network analysis based on various estimation techniques. Monte Carlo simulations demonstrated that the proposed GIC outperforms existing evaluation criteria in terms of edge selection and weight estimation. Acute myeloid leukemia (AML) drug sensitivity-specific gene network analysis revealed critical molecular interactions to uncover ALM drugs resistant mechanism. Notably, PIK3CD activation and RARA/RELA suppression are crucial markers for improving AML chemotherapy efficacy. We also applied our strategy for gastric cancer drug sensitivity analysis and uncovered personalized therapeutic targets. We expect that the proposed sample specific GIC will be a useful tool for evaluating personalized modeling, including in sample characteristic-specific gene networks analysis.
format Article
id doaj-art-b03bfff41a194075ba2223c2d5c9b45f
institution OA Journals
issn 1664-8021
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Genetics
spelling doaj-art-b03bfff41a194075ba2223c2d5c9b45f2025-08-20T02:36:59ZengFrontiers Media S.A.Frontiers in Genetics1664-80212025-06-011610.3389/fgene.2025.15837561583756Generalized information criteria for personalized gene network inferenceHeewon Park0Heewon Park1Heewon Park2Heewon Park3Seiya Imoto4Sadanori Konishi5School of Mathematics, Statistics and Data Science, Sungshin Women’s University, Seoul, Republic of KoreaData Science Center, Sungshin Women’s University, Seoul, Republic of KoreaHuman Genome Center, Institute of Medical Science, University of Tokyo, Bunkyo, JapanM&D Data Science Center, Institute of Science Tokyo, Tokyo, JapanHuman Genome Center, Institute of Medical Science, University of Tokyo, Bunkyo, JapanDepartment of Mathematics, Faculty of Science and Engineering, Chuo University, Hachioji, JapanIdentifying individual genomic characteristics is a critical focus in personalized therapies. To reveal targets in such therapies, we considered personalized gene network analysis using kernel-based L1-type regularization methods. In kernel-based L1-type regularized modeling, selecting optimal regularization parameters is crucial because edge selection and weight estimation depend heavily on such parameters. Furthermore, selecting a kernel bandwidth that controls sample weighting is vital for personalized modeling. Although cross-validation and information criteria (i.e., AIC and BIC) are often used for parameter selection, such traditional techniques are computationally expensive or unsuitable for approaches based on estimation techniques other than maximum likelihood estimation. To overcome these issues, we introduced a novel evaluation criterion in line with the generalized information criterion (GIC), which relaxes the assumption of maximum likelihood estimation, making it suitable for personalized gene network analysis based on various estimation techniques. Monte Carlo simulations demonstrated that the proposed GIC outperforms existing evaluation criteria in terms of edge selection and weight estimation. Acute myeloid leukemia (AML) drug sensitivity-specific gene network analysis revealed critical molecular interactions to uncover ALM drugs resistant mechanism. Notably, PIK3CD activation and RARA/RELA suppression are crucial markers for improving AML chemotherapy efficacy. We also applied our strategy for gastric cancer drug sensitivity analysis and uncovered personalized therapeutic targets. We expect that the proposed sample specific GIC will be a useful tool for evaluating personalized modeling, including in sample characteristic-specific gene networks analysis.https://www.frontiersin.org/articles/10.3389/fgene.2025.1583756/fullmodel evaluationpersonalized gene networkgeneralized information criteriaacute myeloid leukemiagastri cancer
spellingShingle Heewon Park
Heewon Park
Heewon Park
Heewon Park
Seiya Imoto
Sadanori Konishi
Generalized information criteria for personalized gene network inference
Frontiers in Genetics
model evaluation
personalized gene network
generalized information criteria
acute myeloid leukemia
gastri cancer
title Generalized information criteria for personalized gene network inference
title_full Generalized information criteria for personalized gene network inference
title_fullStr Generalized information criteria for personalized gene network inference
title_full_unstemmed Generalized information criteria for personalized gene network inference
title_short Generalized information criteria for personalized gene network inference
title_sort generalized information criteria for personalized gene network inference
topic model evaluation
personalized gene network
generalized information criteria
acute myeloid leukemia
gastri cancer
url https://www.frontiersin.org/articles/10.3389/fgene.2025.1583756/full
work_keys_str_mv AT heewonpark generalizedinformationcriteriaforpersonalizedgenenetworkinference
AT heewonpark generalizedinformationcriteriaforpersonalizedgenenetworkinference
AT heewonpark generalizedinformationcriteriaforpersonalizedgenenetworkinference
AT heewonpark generalizedinformationcriteriaforpersonalizedgenenetworkinference
AT seiyaimoto generalizedinformationcriteriaforpersonalizedgenenetworkinference
AT sadanorikonishi generalizedinformationcriteriaforpersonalizedgenenetworkinference