Salmon: Survival analysis learning with multi-omics neural networks on breast cancer

Zhi Huang, Xiaohui Zhan, Shunian Xiang, Travis S. Johnson, Bryan Helm, Christina Y. Yu, Jie Zhang, Paul Salama, Maher Rizkalla, Zhi Han, Kun Huang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Improved cancer prognosis is a central goal for precision health medicine. Though many models can predict differential survival from data, there is a strong need for sophisticated algorithms that can aggregate and filter relevant predictors from increasingly complex data inputs. In turn, these models should provide deeper insight into which types of data are most relevant to improve prognosis. Deep Learning-based neural networks offer a potential solution for both problems because they are highly flexible and account for data complexity in a non-linear fashion. In this study, we implement Deep Learning-based networks to determine how gene expression data predicts Cox regression survival in breast cancer. We accomplish this through an algorithm called SALMON (Survival Analysis Learning with Multi-Omics Neural Networks), which aggregates and simplifies gene expression data and cancer biomarkers to enable prognosis prediction. The results revealed improved performance when more omics data were used in model construction. Rather than use raw gene expression values as model inputs, we innovatively use eigengene modules from the result of gene co-expression network analysis. The corresponding high impact co-expression modules and other omics data are identified by feature selection technique, then examined by conducting enrichment analysis and exploiting biological functions, escalated the interpretation of input feature from gene level to co-expression modules level. Our study shows the feasibility of discovering breast cancer related co-expression modules, sketch a blueprint of future endeavors on Deep Learning-based survival analysis. SALMON source code is available at https://github.com/huangzhii/SALMON/.

Original languageEnglish (US)
Article number166
JournalFrontiers in Genetics
Volume10
Issue numberMAR
DOIs
StatePublished - Jan 1 2019

Fingerprint

Salmon
Survival Analysis
Learning
Breast Neoplasms
Gene Expression
Precision Medicine
Feasibility Studies
Tumor Biomarkers
Health
Genes
Neoplasms

Keywords

  • Breast cancer
  • Co-expression analysis
  • Cox regression
  • Deep Learning
  • Multi-omics
  • Neural networks
  • Survival prognosis

ASJC Scopus subject areas

  • Molecular Medicine
  • Genetics
  • Genetics(clinical)

Cite this

Huang, Z., Zhan, X., Xiang, S., Johnson, T. S., Helm, B., Yu, C. Y., ... Huang, K. (2019). Salmon: Survival analysis learning with multi-omics neural networks on breast cancer. Frontiers in Genetics, 10(MAR), [166]. https://doi.org/10.3389/fgene.2019.00166

Salmon : Survival analysis learning with multi-omics neural networks on breast cancer. / Huang, Zhi; Zhan, Xiaohui; Xiang, Shunian; Johnson, Travis S.; Helm, Bryan; Yu, Christina Y.; Zhang, Jie; Salama, Paul; Rizkalla, Maher; Han, Zhi; Huang, Kun.

In: Frontiers in Genetics, Vol. 10, No. MAR, 166, 01.01.2019.

Research output: Contribution to journalArticle

Huang, Z, Zhan, X, Xiang, S, Johnson, TS, Helm, B, Yu, CY, Zhang, J, Salama, P, Rizkalla, M, Han, Z & Huang, K 2019, 'Salmon: Survival analysis learning with multi-omics neural networks on breast cancer', Frontiers in Genetics, vol. 10, no. MAR, 166. https://doi.org/10.3389/fgene.2019.00166
Huang, Zhi ; Zhan, Xiaohui ; Xiang, Shunian ; Johnson, Travis S. ; Helm, Bryan ; Yu, Christina Y. ; Zhang, Jie ; Salama, Paul ; Rizkalla, Maher ; Han, Zhi ; Huang, Kun. / Salmon : Survival analysis learning with multi-omics neural networks on breast cancer. In: Frontiers in Genetics. 2019 ; Vol. 10, No. MAR.
@article{2b33a3dfc7544c219207f730d51a2337,
title = "Salmon: Survival analysis learning with multi-omics neural networks on breast cancer",
abstract = "Improved cancer prognosis is a central goal for precision health medicine. Though many models can predict differential survival from data, there is a strong need for sophisticated algorithms that can aggregate and filter relevant predictors from increasingly complex data inputs. In turn, these models should provide deeper insight into which types of data are most relevant to improve prognosis. Deep Learning-based neural networks offer a potential solution for both problems because they are highly flexible and account for data complexity in a non-linear fashion. In this study, we implement Deep Learning-based networks to determine how gene expression data predicts Cox regression survival in breast cancer. We accomplish this through an algorithm called SALMON (Survival Analysis Learning with Multi-Omics Neural Networks), which aggregates and simplifies gene expression data and cancer biomarkers to enable prognosis prediction. The results revealed improved performance when more omics data were used in model construction. Rather than use raw gene expression values as model inputs, we innovatively use eigengene modules from the result of gene co-expression network analysis. The corresponding high impact co-expression modules and other omics data are identified by feature selection technique, then examined by conducting enrichment analysis and exploiting biological functions, escalated the interpretation of input feature from gene level to co-expression modules level. Our study shows the feasibility of discovering breast cancer related co-expression modules, sketch a blueprint of future endeavors on Deep Learning-based survival analysis. SALMON source code is available at https://github.com/huangzhii/SALMON/.",
keywords = "Breast cancer, Co-expression analysis, Cox regression, Deep Learning, Multi-omics, Neural networks, Survival prognosis",
author = "Zhi Huang and Xiaohui Zhan and Shunian Xiang and Johnson, {Travis S.} and Bryan Helm and Yu, {Christina Y.} and Jie Zhang and Paul Salama and Maher Rizkalla and Zhi Han and Kun Huang",
year = "2019",
month = "1",
day = "1",
doi = "10.3389/fgene.2019.00166",
language = "English (US)",
volume = "10",
journal = "Frontiers in Genetics",
issn = "1664-8021",
publisher = "Frontiers Media S. A.",
number = "MAR",

}

TY - JOUR

T1 - Salmon

T2 - Survival analysis learning with multi-omics neural networks on breast cancer

AU - Huang, Zhi

AU - Zhan, Xiaohui

AU - Xiang, Shunian

AU - Johnson, Travis S.

AU - Helm, Bryan

AU - Yu, Christina Y.

AU - Zhang, Jie

AU - Salama, Paul

AU - Rizkalla, Maher

AU - Han, Zhi

AU - Huang, Kun

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Improved cancer prognosis is a central goal for precision health medicine. Though many models can predict differential survival from data, there is a strong need for sophisticated algorithms that can aggregate and filter relevant predictors from increasingly complex data inputs. In turn, these models should provide deeper insight into which types of data are most relevant to improve prognosis. Deep Learning-based neural networks offer a potential solution for both problems because they are highly flexible and account for data complexity in a non-linear fashion. In this study, we implement Deep Learning-based networks to determine how gene expression data predicts Cox regression survival in breast cancer. We accomplish this through an algorithm called SALMON (Survival Analysis Learning with Multi-Omics Neural Networks), which aggregates and simplifies gene expression data and cancer biomarkers to enable prognosis prediction. The results revealed improved performance when more omics data were used in model construction. Rather than use raw gene expression values as model inputs, we innovatively use eigengene modules from the result of gene co-expression network analysis. The corresponding high impact co-expression modules and other omics data are identified by feature selection technique, then examined by conducting enrichment analysis and exploiting biological functions, escalated the interpretation of input feature from gene level to co-expression modules level. Our study shows the feasibility of discovering breast cancer related co-expression modules, sketch a blueprint of future endeavors on Deep Learning-based survival analysis. SALMON source code is available at https://github.com/huangzhii/SALMON/.

AB - Improved cancer prognosis is a central goal for precision health medicine. Though many models can predict differential survival from data, there is a strong need for sophisticated algorithms that can aggregate and filter relevant predictors from increasingly complex data inputs. In turn, these models should provide deeper insight into which types of data are most relevant to improve prognosis. Deep Learning-based neural networks offer a potential solution for both problems because they are highly flexible and account for data complexity in a non-linear fashion. In this study, we implement Deep Learning-based networks to determine how gene expression data predicts Cox regression survival in breast cancer. We accomplish this through an algorithm called SALMON (Survival Analysis Learning with Multi-Omics Neural Networks), which aggregates and simplifies gene expression data and cancer biomarkers to enable prognosis prediction. The results revealed improved performance when more omics data were used in model construction. Rather than use raw gene expression values as model inputs, we innovatively use eigengene modules from the result of gene co-expression network analysis. The corresponding high impact co-expression modules and other omics data are identified by feature selection technique, then examined by conducting enrichment analysis and exploiting biological functions, escalated the interpretation of input feature from gene level to co-expression modules level. Our study shows the feasibility of discovering breast cancer related co-expression modules, sketch a blueprint of future endeavors on Deep Learning-based survival analysis. SALMON source code is available at https://github.com/huangzhii/SALMON/.

KW - Breast cancer

KW - Co-expression analysis

KW - Cox regression

KW - Deep Learning

KW - Multi-omics

KW - Neural networks

KW - Survival prognosis

UR - http://www.scopus.com/inward/record.url?scp=85066619337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066619337&partnerID=8YFLogxK

U2 - 10.3389/fgene.2019.00166

DO - 10.3389/fgene.2019.00166

M3 - Article

AN - SCOPUS:85066619337

VL - 10

JO - Frontiers in Genetics

JF - Frontiers in Genetics

SN - 1664-8021

IS - MAR

M1 - 166

ER -