Evolution-informed modeling improves outcome prediction for cancers

Li Liu, Yung Chang, Tao Yang, David P. Noren, Byron Long, Steven Kornblau, Amina Qutub, Jieping Ye

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Despite wide applications of high-throughput biotechnologies in cancer research, many biomarkers discovered by exploring large-scale omics data do not provide satisfactory performance when used to predict cancer treatment outcomes. This problem is partly due to the overlooking of functional implications of molecular markers. Here, we present a novel computational method that uses evolutionary conservation as prior knowledge to discover bona fide biomarkers. Evolutionary selection at the molecular level is nature's test on functional consequences of genetic elements. By prioritizing genes that show significant statistical association and high functional impact, our new method reduces the chances of including spurious markers in the predictive model. When applied to predicting therapeutic responses for patients with acute myeloid leukemia and to predicting metastasis for patients with prostate cancers, the new method gave rise to evolution-informed models that enjoyed low complexity and high accuracy. The identified genetic markers also have significant implications in tumor progression and embrace potential drug targets. Because evolutionary conservation can be estimated as a gene-specific, position-specific, or allele-specific parameter on the nucleotide level and on the protein level, this new method can be extended to apply to miscellaneous "omics" data to accelerate biomarker discoveries.

Original languageEnglish (US)
JournalEvolutionary Applications
DOIs
StateAccepted/In press - 2016

Fingerprint

cancer
biomarker
biomarkers
neoplasms
prediction
Biomarkers
modeling
Neoplasms
myeloid leukemia
genetic markers
Gene Order
gene
genetic marker
prostatic neoplasms
biotechnology
Biotechnology
methodology
Genetic Markers
Acute Myeloid Leukemia
tumor

Keywords

  • Evolutionary medicine
  • Genomics/proteomics
  • Molecular evolution
  • Transcriptomics

ASJC Scopus subject areas

  • Ecology, Evolution, Behavior and Systematics
  • Genetics
  • Agricultural and Biological Sciences(all)

Cite this

Evolution-informed modeling improves outcome prediction for cancers. / Liu, Li; Chang, Yung; Yang, Tao; Noren, David P.; Long, Byron; Kornblau, Steven; Qutub, Amina; Ye, Jieping.

In: Evolutionary Applications, 2016.

Research output: Contribution to journalArticle

Liu, Li ; Chang, Yung ; Yang, Tao ; Noren, David P. ; Long, Byron ; Kornblau, Steven ; Qutub, Amina ; Ye, Jieping. / Evolution-informed modeling improves outcome prediction for cancers. In: Evolutionary Applications. 2016.
@article{1237df6d26ae46ef85a9db546d1f0126,
title = "Evolution-informed modeling improves outcome prediction for cancers",
abstract = "Despite wide applications of high-throughput biotechnologies in cancer research, many biomarkers discovered by exploring large-scale omics data do not provide satisfactory performance when used to predict cancer treatment outcomes. This problem is partly due to the overlooking of functional implications of molecular markers. Here, we present a novel computational method that uses evolutionary conservation as prior knowledge to discover bona fide biomarkers. Evolutionary selection at the molecular level is nature's test on functional consequences of genetic elements. By prioritizing genes that show significant statistical association and high functional impact, our new method reduces the chances of including spurious markers in the predictive model. When applied to predicting therapeutic responses for patients with acute myeloid leukemia and to predicting metastasis for patients with prostate cancers, the new method gave rise to evolution-informed models that enjoyed low complexity and high accuracy. The identified genetic markers also have significant implications in tumor progression and embrace potential drug targets. Because evolutionary conservation can be estimated as a gene-specific, position-specific, or allele-specific parameter on the nucleotide level and on the protein level, this new method can be extended to apply to miscellaneous {"}omics{"} data to accelerate biomarker discoveries.",
keywords = "Evolutionary medicine, Genomics/proteomics, Molecular evolution, Transcriptomics",
author = "Li Liu and Yung Chang and Tao Yang and Noren, {David P.} and Byron Long and Steven Kornblau and Amina Qutub and Jieping Ye",
year = "2016",
doi = "10.1111/eva.12417",
language = "English (US)",
journal = "Evolutionary Applications",
issn = "1752-4563",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Evolution-informed modeling improves outcome prediction for cancers

AU - Liu, Li

AU - Chang, Yung

AU - Yang, Tao

AU - Noren, David P.

AU - Long, Byron

AU - Kornblau, Steven

AU - Qutub, Amina

AU - Ye, Jieping

PY - 2016

Y1 - 2016

N2 - Despite wide applications of high-throughput biotechnologies in cancer research, many biomarkers discovered by exploring large-scale omics data do not provide satisfactory performance when used to predict cancer treatment outcomes. This problem is partly due to the overlooking of functional implications of molecular markers. Here, we present a novel computational method that uses evolutionary conservation as prior knowledge to discover bona fide biomarkers. Evolutionary selection at the molecular level is nature's test on functional consequences of genetic elements. By prioritizing genes that show significant statistical association and high functional impact, our new method reduces the chances of including spurious markers in the predictive model. When applied to predicting therapeutic responses for patients with acute myeloid leukemia and to predicting metastasis for patients with prostate cancers, the new method gave rise to evolution-informed models that enjoyed low complexity and high accuracy. The identified genetic markers also have significant implications in tumor progression and embrace potential drug targets. Because evolutionary conservation can be estimated as a gene-specific, position-specific, or allele-specific parameter on the nucleotide level and on the protein level, this new method can be extended to apply to miscellaneous "omics" data to accelerate biomarker discoveries.

AB - Despite wide applications of high-throughput biotechnologies in cancer research, many biomarkers discovered by exploring large-scale omics data do not provide satisfactory performance when used to predict cancer treatment outcomes. This problem is partly due to the overlooking of functional implications of molecular markers. Here, we present a novel computational method that uses evolutionary conservation as prior knowledge to discover bona fide biomarkers. Evolutionary selection at the molecular level is nature's test on functional consequences of genetic elements. By prioritizing genes that show significant statistical association and high functional impact, our new method reduces the chances of including spurious markers in the predictive model. When applied to predicting therapeutic responses for patients with acute myeloid leukemia and to predicting metastasis for patients with prostate cancers, the new method gave rise to evolution-informed models that enjoyed low complexity and high accuracy. The identified genetic markers also have significant implications in tumor progression and embrace potential drug targets. Because evolutionary conservation can be estimated as a gene-specific, position-specific, or allele-specific parameter on the nucleotide level and on the protein level, this new method can be extended to apply to miscellaneous "omics" data to accelerate biomarker discoveries.

KW - Evolutionary medicine

KW - Genomics/proteomics

KW - Molecular evolution

KW - Transcriptomics

UR - http://www.scopus.com/inward/record.url?scp=84991830749&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991830749&partnerID=8YFLogxK

U2 - 10.1111/eva.12417

DO - 10.1111/eva.12417

M3 - Article

AN - SCOPUS:84991830749

JO - Evolutionary Applications

JF - Evolutionary Applications

SN - 1752-4563

ER -