Statistical testing for uncertainty of P-NET by DeepLIFT

Abstract In precision medicine, deep learning models have become essential for identifying biomarkers and predicting diagnosis and prognosis of diseases. Although these models have demonstrated considerable success in producing accurate prognostic and diagnostic predictions, their opaque decision-ma...

Full description

Saved in:
Bibliographic Details
Main Authors: Taewan Goo, Chanhee Lee, Sangyeon Shin, Haeyoung Kim, Taesung Park
Format: Article
Language:English
Published: Springer 2025-06-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-025-07156-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434316836175872
author Taewan Goo
Chanhee Lee
Sangyeon Shin
Haeyoung Kim
Taesung Park
author_facet Taewan Goo
Chanhee Lee
Sangyeon Shin
Haeyoung Kim
Taesung Park
author_sort Taewan Goo
collection DOAJ
description Abstract In precision medicine, deep learning models have become essential for identifying biomarkers and predicting diagnosis and prognosis of diseases. Although these models have demonstrated considerable success in producing accurate prognostic and diagnostic predictions, their opaque decision-making processes pose challenges for meaningful biological interpretation. In response, biologically informed neural networks (BINNs), such as P-NET, have been introduced to integrate biological domain knowledge. These models commonly employ measures like SHAP and DeepLIFT to determine the importance of their nodes. However, existing models are limited because they rely on importance estimates that does not consider statistical significance of these estimates. This study proposes a novel statistical testing approach designed to address these limitations. Specifically, it introduces two permutation tests–label and gene permutation test–aimed at identifying significant genes and pathways. Our findings show that this framework can measure the statistical significance of genes and pathways. Additionally, significant pathways are biologically associated with the metastasis mechanism of cancer, thereby enhancing both the interpretability and reliability of BINN-derived insights. This approach confidence in model outputs, thereby advancing the clinical applicability of BINNs in precision medicine.
format Article
id doaj-art-08fc32caaaf243a7be21249c075b327a
institution Kabale University
issn 3004-9261
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-08fc32caaaf243a7be21249c075b327a2025-08-20T03:26:43ZengSpringerDiscover Applied Sciences3004-92612025-06-017611110.1007/s42452-025-07156-1Statistical testing for uncertainty of P-NET by DeepLIFTTaewan Goo0Chanhee Lee1Sangyeon Shin2Haeyoung Kim3Taesung Park4Interdisciplinary Program in Bioinformatics, Seoul National UniversityInterdisciplinary Program in Bioinformatics, Seoul National UniversityInterdisciplinary Program in Bioinformatics, Seoul National UniversityInterdisciplinary Program in Bioinformatics, Seoul National UniversityInterdisciplinary Program in Bioinformatics, Seoul National UniversityAbstract In precision medicine, deep learning models have become essential for identifying biomarkers and predicting diagnosis and prognosis of diseases. Although these models have demonstrated considerable success in producing accurate prognostic and diagnostic predictions, their opaque decision-making processes pose challenges for meaningful biological interpretation. In response, biologically informed neural networks (BINNs), such as P-NET, have been introduced to integrate biological domain knowledge. These models commonly employ measures like SHAP and DeepLIFT to determine the importance of their nodes. However, existing models are limited because they rely on importance estimates that does not consider statistical significance of these estimates. This study proposes a novel statistical testing approach designed to address these limitations. Specifically, it introduces two permutation tests–label and gene permutation test–aimed at identifying significant genes and pathways. Our findings show that this framework can measure the statistical significance of genes and pathways. Additionally, significant pathways are biologically associated with the metastasis mechanism of cancer, thereby enhancing both the interpretability and reliability of BINN-derived insights. This approach confidence in model outputs, thereby advancing the clinical applicability of BINNs in precision medicine.https://doi.org/10.1007/s42452-025-07156-1Biologically informed neural networksP-NETExplainable AIStatistical significance test
spellingShingle Taewan Goo
Chanhee Lee
Sangyeon Shin
Haeyoung Kim
Taesung Park
Statistical testing for uncertainty of P-NET by DeepLIFT
Discover Applied Sciences
Biologically informed neural networks
P-NET
Explainable AI
Statistical significance test
title Statistical testing for uncertainty of P-NET by DeepLIFT
title_full Statistical testing for uncertainty of P-NET by DeepLIFT
title_fullStr Statistical testing for uncertainty of P-NET by DeepLIFT
title_full_unstemmed Statistical testing for uncertainty of P-NET by DeepLIFT
title_short Statistical testing for uncertainty of P-NET by DeepLIFT
title_sort statistical testing for uncertainty of p net by deeplift
topic Biologically informed neural networks
P-NET
Explainable AI
Statistical significance test
url https://doi.org/10.1007/s42452-025-07156-1
work_keys_str_mv AT taewangoo statisticaltestingforuncertaintyofpnetbydeeplift
AT chanheelee statisticaltestingforuncertaintyofpnetbydeeplift
AT sangyeonshin statisticaltestingforuncertaintyofpnetbydeeplift
AT haeyoungkim statisticaltestingforuncertaintyofpnetbydeeplift
AT taesungpark statisticaltestingforuncertaintyofpnetbydeeplift