PathExpSurv: pathway expansion for explainable survival analysis and disease gene discovery.
Disease genes
Model interpretability
Neural nerworks
Pathways
Survival analysis
Journal
BMC bioinformatics
ISSN: 1471-2105
Titre abrégé: BMC Bioinformatics
Pays: England
ID NLM: 100965194
Informations de publication
Date de publication:
15 Nov 2023
15 Nov 2023
Historique:
received:
17
07
2023
accepted:
16
10
2023
medline:
27
11
2023
pubmed:
16
11
2023
entrez:
16
11
2023
Statut:
epublish
Résumé
In the field of biology and medicine, the interpretability and accuracy are both important when designing predictive models. The interpretability of many machine learning models such as neural networks is still a challenge. Recently, many researchers utilized prior information such as biological pathways to develop neural networks-based methods, so as to provide some insights and interpretability for the models. However, the prior biological knowledge may be incomplete and there still exists some unknown information to be explored. We proposed a novel method, named PathExpSurv, to gain an insight into the black-box model of neural network for cancer survival analysis. We demonstrated that PathExpSurv could not only incorporate the known prior information into the model, but also explore the unknown possible expansion to the existing pathways. We performed downstream analyses based on the expanded pathways and successfully identified some key genes associated with the diseases and original pathways. Our proposed PathExpSurv is a novel, effective and interpretable method for survival analysis. It has great utility and value in medical diagnosis and offers a promising framework for biological research.
Sections du résumé
BACKGROUND
BACKGROUND
In the field of biology and medicine, the interpretability and accuracy are both important when designing predictive models. The interpretability of many machine learning models such as neural networks is still a challenge. Recently, many researchers utilized prior information such as biological pathways to develop neural networks-based methods, so as to provide some insights and interpretability for the models. However, the prior biological knowledge may be incomplete and there still exists some unknown information to be explored.
RESULTS
RESULTS
We proposed a novel method, named PathExpSurv, to gain an insight into the black-box model of neural network for cancer survival analysis. We demonstrated that PathExpSurv could not only incorporate the known prior information into the model, but also explore the unknown possible expansion to the existing pathways. We performed downstream analyses based on the expanded pathways and successfully identified some key genes associated with the diseases and original pathways.
CONCLUSIONS
CONCLUSIONS
Our proposed PathExpSurv is a novel, effective and interpretable method for survival analysis. It has great utility and value in medical diagnosis and offers a promising framework for biological research.
Identifiants
pubmed: 37968615
doi: 10.1186/s12859-023-05535-2
pii: 10.1186/s12859-023-05535-2
pmc: PMC10648621
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
434Subventions
Organisme : National Key Research and Development Program of China
ID : 2020YFA0712402
Organisme : National Key Research and Development Program of China
ID : 2020YFA0712402
Organisme : National Key Research and Development Program of China
ID : 2020YFA0712402
Organisme : National Key Research and Development Program of China
ID : 2020YFA0712402
Organisme : National Natural Science Foundation of China
ID : 12231018
Organisme : National Natural Science Foundation of China
ID : 12231018
Organisme : National Natural Science Foundation of China
ID : 12231018
Organisme : National Natural Science Foundation of China
ID : 12231018
Informations de copyright
© 2023. The Author(s).
Références
BMC Urol. 2017 Sep 18;17(1):86
pubmed: 28923030
Oncol Lett. 2022 May;23(5):142
pubmed: 35340558
J Hematol Oncol. 2022 Jan 6;15(1):2
pubmed: 34991659
Mol Med. 2020 Apr 5;26(1):27
pubmed: 32248791
Mol Cancer. 2010 Aug 21;9:221
pubmed: 20727204
J Neuropathol Exp Neurol. 2010 Jun;69(6):606-22
pubmed: 20467331
Stat Med. 2011 May 10;30(10):1105-17
pubmed: 21484848
Biomed Pharmacother. 2017 Jun;90:659-664
pubmed: 28415045
NPJ Syst Biol Appl. 2016 Mar 03;2:16002
pubmed: 28725467
Stat Med. 2020 Dec 30;39(30):4605-4620
pubmed: 32974946
Int J Mol Med. 2020 Apr;45(4):1187-1194
pubmed: 32124954
Thyroid. 2015 Apr;25(4):425-36
pubmed: 25647164
Brief Bioinform. 2022 Jan 17;23(1):
pubmed: 34498681
Comput Struct Biotechnol J. 2021 May 01;19:2719-2725
pubmed: 34093987
Allergy Asthma Immunol Res. 2020 Nov;12(6):1012-1028
pubmed: 32935492
Bone. 2013 Jan;52(1):145-56
pubmed: 23032104
PLoS One. 2021 Mar 4;16(3):e0247837
pubmed: 33662042
Breast Cancer Res Treat. 2009 Mar;114(1):85-96
pubmed: 18409060
Front Genet. 2021 Aug 20;12:709514
pubmed: 34490040
Stat Med. 1995 Jan 15;14(1):73-82
pubmed: 7701159
Epigenomics. 2019 Jan;11(1):1635-1651
pubmed: 30089404
Dis Markers. 2021 Jun 15;2021:5510780
pubmed: 34221185
Exp Hematol. 2008 May;36(5):545-558
pubmed: 18439488
Mol Ther Nucleic Acids. 2019 Sep 6;17:138-149
pubmed: 31255976
BMC Med Res Methodol. 2018 Feb 26;18(1):24
pubmed: 29482517
Front Oncol. 2019 Oct 25;9:1117
pubmed: 31709184
Protein Pept Lett. 2018 Feb 8;24(12):1084-1095
pubmed: 29173143
PLoS Comput Biol. 2018 Apr 10;14(4):e1006076
pubmed: 29634719