GE-IA-NAM: gene-environment interaction analysis via imaging-assisted neural additive model.
Saved in:
| Title: | GE-IA-NAM: gene-environment interaction analysis via imaging-assisted neural additive model. |
|---|---|
| Authors: | Li J; Department of Biostatistics, Yale School of Public Health, New Haven, CT 06511, United States., Xu Y; School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China., Ma S; Department of Biostatistics, Yale School of Public Health, New Haven, CT 06511, United States., Fang K; Department of Statistics and Data Science, School of Economics, Xiamen University, Xiamen 361005, China. |
| Source: | Bioinformatics (Oxford, England) [Bioinformatics] 2025 Sep 01; Vol. 41 (9). |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: Oxford University Press Country of Publication: England NLM ID: 9808944 Publication Model: Print Cited Medium: Internet ISSN: 1367-4811 (Electronic) Linking ISSN: 13674803 NLM ISO Abbreviation: Bioinformatics Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Oxford : Oxford University Press, c1998- |
| MeSH Terms: | Gene-Environment Interaction* , Deep Learning* , Lung Neoplasms*/genetics , Skin Neoplasms*/genetics , Melanoma*/genetics, Datasets as Topic ; Humans ; Age Factors ; Sex Factors ; Smoking |
| Abstract: | Motivation: Gene-environment (G-E) interaction analysis is crucial in cancer research, offering insights into how genetic and environmental factors jointly influence cancer outcomes. Most existing G-E interaction methods are regression-based, which may lack flexibility to capture complex data patterns. Recent advances have investigated deep neural network-based G-E models. However, these methods may be more vulnerable to information deficiency due to challenges such as limited sample size and high dimensionality. Apart from genetic and environmental data, pathological images have emerged as a widely accessible and informative resource for cancer modeling, presenting its potential to enhance G-E modeling. Results: We propose the pathological imaging-assisted neural additive model for G-E analysis (GE-IA-NAM). The flexible and interpretable additive network architecture is adopted to account for individualized effects associated with genetic factors, environmental factors, and their interactions. To improve G-E modeling, an assisted-learning strategy is investigated, which adopts a joint analysis to integrate information from pathological images. Simulations and the analysis of lung and skin cancer datasets from The Cancer Genome Atlas demonstrate the competitive performance of the proposed method. Availability and Implementation: Python code implementing the proposed method is available at https://github.com/Mr-maoge/NAM-IA-GE. The data that support the findings in this article are openly available in TCGA (The Cancer Genome Atlas) at https://portal.gdc.cancer.gov/. (© The Author(s) 2025. Published by Oxford University Press.) |
| References: | Bioinformatics. 2023 Aug 1;39(8):. (PMID: 37610338) Sci Rep. 2020 Sep 14;10(1):15030. (PMID: 32929170) Genet Epidemiol. 2023 Apr;47(3):261-286. (PMID: 36807383) Nat Rev Genet. 2005 Apr;6(4):287-98. (PMID: 15803198) Bioinformatics. 2024 Aug 2;40(8):. (PMID: 39073893) Proc Natl Acad Sci U S A. 2021 Sep 7;118(36):. (PMID: 34480002) Nat Rev Genet. 2024 Nov;25(11):768-784. (PMID: 38806721) Biometrics. 2023 Dec;79(4):3883-3894. (PMID: 37132273) Sci Transl Med. 2012 Oct 24;4(157):157ra143. (PMID: 23100629) Brief Bioinform. 2022 Jan 17;23(1):. (PMID: 34791021) Brief Bioinform. 2022 Jan 17;23(1):. (PMID: 34791014) Neural Netw. 2022 Mar;147:81-102. (PMID: 34995952) Bioinformatics. 2021 Oct 25;37(20):3546-3552. (PMID: 33974036) Cancers (Basel). 2019 Apr 24;11(4):. (PMID: 31022926) Bioinformatics. 2023 Aug 1;39(8):. (PMID: 37490475) Proc Mach Learn Res. 2021 Apr;130:10-18. (PMID: 36092461) Can J Stat. 2022 Mar;50(1):59-85. (PMID: 35530428) Commun Biol. 2022 Nov 12;5(1):1238. (PMID: 36371468) Biostatistics. 2015 Apr;16(2):326-38. (PMID: 25406332) Comput Stat Data Anal. 2023 Oct;186:. (PMID: 39555004) Bioinformatics. 2009 Feb 1;25(3):401-5. (PMID: 19073588) Biometrics. 2020 Mar;76(1):23-35. (PMID: 31424088) |
| Grant Information: | 12571313 National Natural Science Foundation of China; 72071169 National Natural Science Foundation of China; 82204153 National Natural Science Foundation of China; 22JJD910001 MOE Project of Key Research Institute of Humanities and Social Sciences |
| Entry Date(s): | Date Created: 20250829 Date Completed: 20250925 Latest Revision: 20250925 |
| Update Code: | 20250926 |
| PubMed Central ID: | PMC12452269 |
| DOI: | 10.1093/bioinformatics/btaf481 |
| PMID: | 40880282 |
| Database: | MEDLINE |
Full Text 
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | Motivation: Gene-environment (G-E) interaction analysis is crucial in cancer research, offering insights into how genetic and environmental factors jointly influence cancer outcomes. Most existing G-E interaction methods are regression-based, which may lack flexibility to capture complex data patterns. Recent advances have investigated deep neural network-based G-E models. However, these methods may be more vulnerable to information deficiency due to challenges such as limited sample size and high dimensionality. Apart from genetic and environmental data, pathological images have emerged as a widely accessible and informative resource for cancer modeling, presenting its potential to enhance G-E modeling.<br />Results: We propose the pathological imaging-assisted neural additive model for G-E analysis (GE-IA-NAM). The flexible and interpretable additive network architecture is adopted to account for individualized effects associated with genetic factors, environmental factors, and their interactions. To improve G-E modeling, an assisted-learning strategy is investigated, which adopts a joint analysis to integrate information from pathological images. Simulations and the analysis of lung and skin cancer datasets from The Cancer Genome Atlas demonstrate the competitive performance of the proposed method.<br />Availability and Implementation: Python code implementing the proposed method is available at https://github.com/Mr-maoge/NAM-IA-GE. The data that support the findings in this article are openly available in TCGA (The Cancer Genome Atlas) at https://portal.gdc.cancer.gov/.<br /> (© The Author(s) 2025. Published by Oxford University Press.) |
|---|---|
| ISSN: | 1367-4811 |
| DOI: | 10.1093/bioinformatics/btaf481 |