PASNet: Pathway-associated sparse deep neural network for prognosis prediction from high-throughput data

Jie Hao, Youngsoon Kim, Taekyung Kim, Mingon Kang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background: Predicting prognosis in patients from large-scale genomic data is a fundamentally challenging problem in genomic medicine. However, the prognosis still remains poor in many diseases. The poor prognosis may be caused by high complexity of biological systems, where multiple biological components and their hierarchical relationships are involved. Moreover, it is challenging to develop robust computational solutions with high-dimension, low-sample size data. Results: In this study, we propose a Pathway-Associated Sparse Deep Neural Network (PASNet) that not only predicts patients' prognoses but also describes complex biological processes regarding biological pathways for prognosis. PASNet models a multilayered, hierarchical biological system of genes and pathways to predict clinical outcomes by leveraging deep learning. The sparse solution of PASNet provides the capability of model interpretability that most conventional fully-connected neural networks lack. We applied PASNet for long-term survival prediction in Glioblastoma multiforme (GBM), which is a primary brain cancer that shows poor prognostic performance. The predictive performance of PASNet was evaluated with multiple cross-validation experiments. PASNet showed a higher Area Under the Curve (AUC) and F1-score than previous long-term survival prediction classifiers, and the significance of PASNet's performance was assessed by Wilcoxon signed-rank test. Furthermore, the biological pathways, found in PASNet, were referred to as significant pathways in GBM in previous biology and medicine research. Conclusions: PASNet can describe the different biological systems of clinical outcomes for prognostic prediction as well as predicting prognosis more accurately than the current state-of-the-art methods. PASNet is the first pathway-based deep neural network that represents hierarchical representations of genes and pathways and their nonlinear effects, to the best of our knowledge. Additionally, PASNet would be promising due to its flexible model representation and interpretability, embodying the strengths of deep learning. The open-source code of PASNet is available at https://github.com/DataX-JieHao/PASNet.

Original languageEnglish (US)
Article number510
JournalBMC Bioinformatics
Volume19
Issue number1
DOIs
StatePublished - Dec 17 2018

Fingerprint

Neural Pathways
Prognosis
High Throughput
Pathway
Throughput
Neural Networks
Prediction
Glioblastoma
Biological systems
Medicine
Learning
Biological Phenomena
Neural Networks (Computer)
Survival
Nonparametric Statistics
Biological Systems
Brain Neoplasms
Sample Size
Genes
Area Under Curve

Keywords

  • Glioblastoma multiforme
  • Long-term survival prediction
  • Pathway-based analysis
  • Prognosis prediction
  • Sparse deep neural network
  • TCGA

ASJC Scopus subject areas

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

PASNet : Pathway-associated sparse deep neural network for prognosis prediction from high-throughput data. / Hao, Jie; Kim, Youngsoon; Kim, Taekyung; Kang, Mingon.

In: BMC Bioinformatics, Vol. 19, No. 1, 510, 17.12.2018.

Research output: Contribution to journalArticle

@article{e0cbf7eb4fd544bebc9afadcc5c309ad,
title = "PASNet: Pathway-associated sparse deep neural network for prognosis prediction from high-throughput data",
abstract = "Background: Predicting prognosis in patients from large-scale genomic data is a fundamentally challenging problem in genomic medicine. However, the prognosis still remains poor in many diseases. The poor prognosis may be caused by high complexity of biological systems, where multiple biological components and their hierarchical relationships are involved. Moreover, it is challenging to develop robust computational solutions with high-dimension, low-sample size data. Results: In this study, we propose a Pathway-Associated Sparse Deep Neural Network (PASNet) that not only predicts patients' prognoses but also describes complex biological processes regarding biological pathways for prognosis. PASNet models a multilayered, hierarchical biological system of genes and pathways to predict clinical outcomes by leveraging deep learning. The sparse solution of PASNet provides the capability of model interpretability that most conventional fully-connected neural networks lack. We applied PASNet for long-term survival prediction in Glioblastoma multiforme (GBM), which is a primary brain cancer that shows poor prognostic performance. The predictive performance of PASNet was evaluated with multiple cross-validation experiments. PASNet showed a higher Area Under the Curve (AUC) and F1-score than previous long-term survival prediction classifiers, and the significance of PASNet's performance was assessed by Wilcoxon signed-rank test. Furthermore, the biological pathways, found in PASNet, were referred to as significant pathways in GBM in previous biology and medicine research. Conclusions: PASNet can describe the different biological systems of clinical outcomes for prognostic prediction as well as predicting prognosis more accurately than the current state-of-the-art methods. PASNet is the first pathway-based deep neural network that represents hierarchical representations of genes and pathways and their nonlinear effects, to the best of our knowledge. Additionally, PASNet would be promising due to its flexible model representation and interpretability, embodying the strengths of deep learning. The open-source code of PASNet is available at https://github.com/DataX-JieHao/PASNet.",
keywords = "Glioblastoma multiforme, Long-term survival prediction, Pathway-based analysis, Prognosis prediction, Sparse deep neural network, TCGA",
author = "Jie Hao and Youngsoon Kim and Taekyung Kim and Mingon Kang",
year = "2018",
month = "12",
day = "17",
doi = "10.1186/s12859-018-2500-z",
language = "English (US)",
volume = "19",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - PASNet

T2 - Pathway-associated sparse deep neural network for prognosis prediction from high-throughput data

AU - Hao, Jie

AU - Kim, Youngsoon

AU - Kim, Taekyung

AU - Kang, Mingon

PY - 2018/12/17

Y1 - 2018/12/17

N2 - Background: Predicting prognosis in patients from large-scale genomic data is a fundamentally challenging problem in genomic medicine. However, the prognosis still remains poor in many diseases. The poor prognosis may be caused by high complexity of biological systems, where multiple biological components and their hierarchical relationships are involved. Moreover, it is challenging to develop robust computational solutions with high-dimension, low-sample size data. Results: In this study, we propose a Pathway-Associated Sparse Deep Neural Network (PASNet) that not only predicts patients' prognoses but also describes complex biological processes regarding biological pathways for prognosis. PASNet models a multilayered, hierarchical biological system of genes and pathways to predict clinical outcomes by leveraging deep learning. The sparse solution of PASNet provides the capability of model interpretability that most conventional fully-connected neural networks lack. We applied PASNet for long-term survival prediction in Glioblastoma multiforme (GBM), which is a primary brain cancer that shows poor prognostic performance. The predictive performance of PASNet was evaluated with multiple cross-validation experiments. PASNet showed a higher Area Under the Curve (AUC) and F1-score than previous long-term survival prediction classifiers, and the significance of PASNet's performance was assessed by Wilcoxon signed-rank test. Furthermore, the biological pathways, found in PASNet, were referred to as significant pathways in GBM in previous biology and medicine research. Conclusions: PASNet can describe the different biological systems of clinical outcomes for prognostic prediction as well as predicting prognosis more accurately than the current state-of-the-art methods. PASNet is the first pathway-based deep neural network that represents hierarchical representations of genes and pathways and their nonlinear effects, to the best of our knowledge. Additionally, PASNet would be promising due to its flexible model representation and interpretability, embodying the strengths of deep learning. The open-source code of PASNet is available at https://github.com/DataX-JieHao/PASNet.

AB - Background: Predicting prognosis in patients from large-scale genomic data is a fundamentally challenging problem in genomic medicine. However, the prognosis still remains poor in many diseases. The poor prognosis may be caused by high complexity of biological systems, where multiple biological components and their hierarchical relationships are involved. Moreover, it is challenging to develop robust computational solutions with high-dimension, low-sample size data. Results: In this study, we propose a Pathway-Associated Sparse Deep Neural Network (PASNet) that not only predicts patients' prognoses but also describes complex biological processes regarding biological pathways for prognosis. PASNet models a multilayered, hierarchical biological system of genes and pathways to predict clinical outcomes by leveraging deep learning. The sparse solution of PASNet provides the capability of model interpretability that most conventional fully-connected neural networks lack. We applied PASNet for long-term survival prediction in Glioblastoma multiforme (GBM), which is a primary brain cancer that shows poor prognostic performance. The predictive performance of PASNet was evaluated with multiple cross-validation experiments. PASNet showed a higher Area Under the Curve (AUC) and F1-score than previous long-term survival prediction classifiers, and the significance of PASNet's performance was assessed by Wilcoxon signed-rank test. Furthermore, the biological pathways, found in PASNet, were referred to as significant pathways in GBM in previous biology and medicine research. Conclusions: PASNet can describe the different biological systems of clinical outcomes for prognostic prediction as well as predicting prognosis more accurately than the current state-of-the-art methods. PASNet is the first pathway-based deep neural network that represents hierarchical representations of genes and pathways and their nonlinear effects, to the best of our knowledge. Additionally, PASNet would be promising due to its flexible model representation and interpretability, embodying the strengths of deep learning. The open-source code of PASNet is available at https://github.com/DataX-JieHao/PASNet.

KW - Glioblastoma multiforme

KW - Long-term survival prediction

KW - Pathway-based analysis

KW - Prognosis prediction

KW - Sparse deep neural network

KW - TCGA

UR - http://www.scopus.com/inward/record.url?scp=85058516008&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058516008&partnerID=8YFLogxK

U2 - 10.1186/s12859-018-2500-z

DO - 10.1186/s12859-018-2500-z

M3 - Article

C2 - 30558539

AN - SCOPUS:85058516008

VL - 19

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 1

M1 - 510

ER -