Classifying chemical mode of action using gene networks and machine learning: A case study with the herbicide linuron

Anna Ornostay, Andrew M. Cowie, Matthew Hindle, Christopher J.O. Baker, Christopher J. Martyniuk*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The herbicide linuron (LIN) is an endocrine disruptor with an anti-androgenic mode of action. The objectives of this study were to (1) improve knowledge of androgen and anti-androgen signaling in the teleostean ovary and to (2) assess the ability of gene networks and machine learning to classify LIN as an anti-androgen using transcriptomic data. Ovarian explants from vitellogenic fathead minnows (FHMs) were exposed to three concentrations of either 5α-dihydrotestosterone (DHT), flutamide (FLUT), or LIN for 12 h. Ovaries exposed to DHT showed a significant increase in 17β-estradiol (E2) production while FLUT and LIN had no effect on E2. To improve understanding of androgen receptor signaling in the ovary, a reciprocal gene expression network was constructed for DHT and FLUT using pathway analysis and these data suggested that steroid metabolism, translation, and DNA replication are processes regulated through AR signaling in the ovary. Sub-network enrichment analysis revealed that FLUT and LIN shared more regulated gene networks in common compared to DHT. Using transcriptomic datasets from different fish species, machine learning algorithms classified LIN successfully with other anti-androgens. This study advances knowledge regarding molecular signaling cascades in the ovary that are responsive to androgens and anti-androgens and provides proof of concept that gene network analysis and machine learning can classify priority chemicals using experimental transcriptomic data collected from different fish species.

Original languageEnglish
Pages (from-to)263-274
Number of pages12
JournalComparative Biochemistry and Physiology - Part D: Genomics and Proteomics
Volume8
Issue number4
DOIs
Publication statusPublished - 12 Sep 2013

Keywords

  • Machine learning Sub-network enrichment analysis Wnt-frizzled pathway Herbicides Notch signaling

Fingerprint

Dive into the research topics of 'Classifying chemical mode of action using gene networks and machine learning: A case study with the herbicide linuron'. Together they form a unique fingerprint.

Cite this