Literature DB >> 34042937

Peel Learning for Pathway-Related Outcome Prediction.

Yuantong Li1, Fei Wang2, Mengying Yan3, Edward Cantu4, Fan Nils Yang5, Hengyi Rao6, Rui Feng7.   

Abstract

MOTIVATION: Traditional regression models are limited in outcome prediction due to their parametric nature. Current deep learning methods allow for various effects and interactions and have shown improved performance, but they typically need to be trained on a large amount of data to obtain reliable results. Gene expression studies often have small sample sizes but high dimensional correlated predictors so that traditional deep learning methods are not readily applicable.
RESULTS: In this paper, we proposed peel learning, a novel neural network that incorporates the prior relationship among genes. In each layer of learning, overall structure is peeled into multiple local substructures. Within the substructure, dependency among variables is reduced through linear projections. The overall structure is gradually simplified over layers and weight parameters are optimized through a revised backpropagation. We applied PL to a small lung transplantation study to predict recipients' post-surgery primary graft dysfunction using donors' gene expressions within several immunology pathways, where PL showed improved prediction accuracy compared to conventional penalized regression, classification trees, feed-forward neural network, and a neural network assuming prior network structure. Through simulation studies, we also demonstrated the advantage of adding specific structure among predictor variables in neural network, over no or uniform group structure, which is more favorable in smaller studies. The empirical evidence is consistent with our theoretical proof of improved upper bound of PL's complexity over ordinary neural networks.
AVAILABILITY AND IMPLEMENTATION: PL algorithm was implemented in Python and the open-source code and instruction will be available at https://github.com/Likelyt/Peel-Learning.
© The Author(s) (2021). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  deep learning; genetic pathway; graph structure; high dimensional data; neural network

Year:  2021        PMID: 34042937      PMCID: PMC9502230          DOI: 10.1093/bioinformatics/btab402

Source DB:  PubMed          Journal:  Bioinformatics        ISSN: 1367-4803            Impact factor:   6.931


  16 in total

1.  Report of the ISHLT Working Group on Primary Lung Graft Dysfunction part I: introduction and methods.

Authors:  Jason D Christie; Dirk Van Raemdonck; Marc de Perrot; Mark Barr; Shaf Keshavjee; Selim Arcasoy; Jonathan Orens
Journal:  J Heart Lung Transplant       Date:  2005-10       Impact factor: 10.247

2.  Classification with correlated features: unreliability of feature ranking and solutions.

Authors:  Laura Tolosi; Thomas Lengauer
Journal:  Bioinformatics       Date:  2011-05-16       Impact factor: 6.937

Review 3.  Deep learning.

Authors:  Yann LeCun; Yoshua Bengio; Geoffrey Hinton
Journal:  Nature       Date:  2015-05-28       Impact factor: 49.962

4.  A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data.

Authors:  Yunchuan Kong; Tianwei Yu
Journal:  Bioinformatics       Date:  2018-11-01       Impact factor: 6.937

5.  A general model for the genetic analysis of pedigree data.

Authors:  R C Elston; J Stewart
Journal:  Hum Hered       Date:  1971       Impact factor: 0.444

6.  Preprocurement In Situ Donor Lung Tissue Gene Expression Classifies Primary Graft Dysfunction Risk.

Authors:  Edward Cantu; Mengying Yan; Yoshikazu Suzuki; Taylor Buckley; Vito Galati; Neha Majeti; Christian A Bermudez; Joshua M Diamond; Jason D Christie; Rui Feng
Journal:  Am J Respir Crit Care Med       Date:  2020-10-01       Impact factor: 21.405

7.  Construct validity of the definition of primary graft dysfunction after lung transplantation.

Authors:  Jason D Christie; Scarlett Bellamy; Lorraine B Ware; David Lederer; Denis Hadjiliadis; James Lee; Nancy Robinson; A Russell Localio; Keith Wille; Vibha Lama; Scott Palmer; Jonathan Orens; Ann Weinacker; Maria Crespo; Ejigaehu Demissie; Stephen E Kimmel; Steven M Kawut
Journal:  J Heart Lung Transplant       Date:  2010-07-22       Impact factor: 10.247

8.  Impact of human donor lung gene expression profiles on survival after lung transplantation: a case-control study.

Authors:  M Anraku; M J Cameron; T K Waddell; M Liu; T Arenovich; M Sato; M Cypel; A F Pierre; M de Perrot; D J Kelvin; S Keshavjee
Journal:  Am J Transplant       Date:  2008-08-22       Impact factor: 8.086

9.  PASNet: pathway-associated sparse deep neural network for prognosis prediction from high-throughput data.

Authors:  Jie Hao; Youngsoon Kim; Tae-Kyung Kim; Mingon Kang
Journal:  BMC Bioinformatics       Date:  2018-12-17       Impact factor: 3.169

10.  KEGG for representation and analysis of molecular networks involving diseases and drugs.

Authors:  Minoru Kanehisa; Susumu Goto; Miho Furumichi; Mao Tanabe; Mika Hirakawa
Journal:  Nucleic Acids Res       Date:  2009-10-30       Impact factor: 16.971

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.