Exon level machine learning analyses elucidate novel candidate miRNA targets in an avian model of fetal alcohol spectrum disorder

Gestational alcohol exposure causes fetal alcohol spectrum disorder (FASD) and is a prominent cause of neurodevelopmental disability. Whole transcriptome sequencing (RNA-Seq) offer insights into mechanisms underlying FASD, but gene-level analysis provides limited information regarding complex transcriptional processes such as alternative splicing and non-coding RNAs. Moreover, traditional analytical approaches that use multiple hypothesis testing with a false discovery rate adjustment prioritize genes based on an adjusted p-value, which is not always biologically relevant. We address these limitations with a novel approach and implemented an unsupervised machine learning model, which we applied to an exon-level analysis to reduce data complexity to the most likely functionally relevant exons, without loss of novel information. This was performed on an RNA-Seq paired-end dataset derived from alcohol-exposed neural fold-stage chick crania, wherein alcohol causes facial deficits recapitulating those of FASD. A principal component analysis along with k-means clustering was utilized to extract exons that deviated from baseline expression. This identified 6857 differentially expressed exons representing 1251 geneIDs; 391 of these genes were identified in a prior gene-level analysis of this dataset. It also identified exons encoding 23 microRNAs (miRNAs) having significantly differential expression profiles in response to alcohol. We developed an RDAVID pipeline to identify KEGG pathways represented by these exons, and separately identified predicted KEGG pathways targeted by these miRNAs. Several of these (ribosome biogenesis, oxidative phosphorylation) were identified in our prior gene-level analysis. Other pathways are crucial to facial morphogenesis and represent both novel (focal adhesion, FoxO signaling, insulin signaling) and known (Wnt signaling) alcohol targets. Importantly, there was substantial overlap between the exomes themselves and the predicted miRNA targets, suggesting these miRNAs contribute to the gene-level expression changes. Our novel application of unsupervised machine learning in conjunction with statistical analyses facilitated the discovery of signaling pathways and miRNAs that inform mechanisms underlying FASD.Author summary: Genomic research often yields an overwhelming amount of information. Accurate models for predicting and validating multivariate big data in genomics distill complex relationships and interactions. A prime example is fetal alcohol spectrum disorders, the largest known cause of neurodevelopmental disability affecting nearly 5% of children in the United States. Alcohol exposure during pregnancy leads to complex epigenetic and transcriptomic modifications, subsequently impairing signaling pathways in neural and morphologic development. Identifying transcriptomic mechanisms regulating alcohol’s teratogenicity during embryonic development is crucial for understanding variable phenotypic outcomes. This allows for the advancement of future therapeutic interventions that may mediate alcohol’s effects. Most genomic studies do not incorporate various levels of transcriptomic analysis, spanning gene, exon, and splicing variants, because it is difficult to meaningfully consolidate all those analyses. Therefore, enhancing machine learning approaches that corroborate traditional statistical methods can yield novel relationships, and is important for robust functional experiments that proceed from such genomic studies.