Identifying disease genes from a vast amount of genetic data is one of the most challenging tasks in the post-genomic era. Also, complex diseases present highly heterogeneous genotype, which difficult biological marker identification. Machine learning methods are widely used to identify these markers, but their performance is highly dependent upon the size and quality of available data. In this study, we demonstrated that machine learning classifiers trained on gene functional similarities, using Gene Ontology (GO), can improve the identification of genes involved in complex diseases. For this purpose, we developed a supervised machine learning methodology to predict complex disease genes. The proposed pipeline was assessed using Autism Spectrum Disorder (ASD) candidate genes. A quantitative measure of gene functional similarities was obtained by employing different semantic similarity measures. To infer the hidden functional similarities between ASD genes, various types of machine learning classifiers were built on quantitative semantic similarity matrices of ASD and non-ASD genes. The classifiers trained and tested on ASD and non-ASD gene functional similarities outperformed previously reported ASD classifiers. For example, a Random Forest (RF) classifier achieved an AUC of 0. 80 for predicting new ASD genes, which was higher than the reported classifier (0.73). Additionally, this classifier was able to predict 73 novel ASD candidate genes that were enriched for core ASD phenotypes, such as autism and obsessive-compulsive behavior. In addition, predicted genes were also enriched for ASD co-occurring conditions, including Attention Deficit Hyperactivity Disorder (ADHD). We also developed a KNIME workflow with the proposed methodology which allows users to configure and execute it without requiring machine learning and programming skills. Machine learning is an effective and reliable technique to decipher ASD mechanism by identifying novel disease genes, but this study further demonstrated that their performance can be improved by incorporating a quantitative measure of gene functional similarities. Source code and the workflow of the proposed methodology are available at https://github.com/Muh-Asif/ASD-genes-prediction.

Heritability estimates support the contribution of genetics and the environment to the etiology of Autism Spectrum Disorder (ASD), but a role for gene-environment interactions is insufficiently explored. Genes involved in detoxification pathways and physiological permeability barriers (e.g., blood-brain barrier, placenta and respiratory airways), which regulate the effects of exposure to xenobiotics during early stages of neurodevelopment when the immature brain is extremely vulnerable, may be particularly relevant in this context. Our objective was to identify genes involved in the regulation of xenobiotic detoxification or the function of physiological barriers (the XenoReg genes) presenting predicted damaging variants in subjects with ASD, and to understand their interaction patterns with ubiquitous xenobiotics previously implicated in this disorder. We defined a panel of 519 XenoReg genes through literature review and database queries. Large ASD datasets were inspected for in silico predicted damaging Single Nucleotide Variants (SNVs) (N = 2,674 subjects) or Copy Number Variants (CNVs) (N = 3,570 subjects) in XenoReg genes. We queried the Comparative Toxicogenomics Database (CTD) to identify interaction pairs between XenoReg genes and xenobiotics. The interrogation of ASD datasets for variants in the XenoReg gene panel identified 77 genes with high evidence for a role in ASD, according to pre-specified prioritization criteria. These include 47 genes encoding detoxification enzymes and 30 genes encoding proteins involved in physiological barrier function, among which 15 are previous reported candidates for ASD. The CTD query revealed 397 gene-environment interaction pairs between these XenoReg genes and 80% (48/60) of the analyzed xenobiotics. The top interacting genes and xenobiotics were, respectively, CYP1A2, ABCB1, ABCG2, GSTM1, and CYP2D6 and benzo-(a)-pyrene, valproic acid, bisphenol A, particulate matter, methylmercury, and perfluorinated compounds. Individuals carrying predicted damaging variants in high evidence XenoReg genes are likely to have less efficient detoxification systems or impaired physiological barriers. They can therefore be particularly susceptible to early life exposure to ubiquitous xenobiotics, which elicit neuropathological mechanisms in the immature brain, such as epigenetic changes, oxidative stress, neuroinflammation, hypoxic damage, and endocrine disruption. As exposure to environmental factors may be mitigated for individuals with risk variants, this work provides new perspectives to personalized prevention and health management policies for ASD.

Personalized medicine is a concept that has been subject of increasing interest in medical research and practice in the last few years. However, significant challenges stand in the way of practical implementations, namely in regard to extracting clinically valuable insights from the vast amount of biomedical knowledge generated in the last few years. Here, we describe an approach that uses Knowledge Graph Embedding (KGE) methods on a biomedical Knowledge Graph (KG) as a path to reasoning over the wealth of information stored in publicly accessible databases. We built a Knowledge Graph using data from DisGeNET and GO, containing relationships between genes, diseases and other biological entities. The KG contains 93,657 nodes of 5 types and 1,705,585 relationships of 59 types. We applied KGE methods to this KG, obtaining an excellent performance in predicting gene‐disease associations (MR 0.13, MRR 0.96, HITS@1 0.93, HITS@3 0.99, and HITS@10 0.99). The optimal hyperparameter set was used to predict all possible novel gene‐disease associations. An in‐depth analysis of novel gene‐disease predictions for disease terms related to Autism Spectrum Disorder (ASD) shows that this approach produces predictions consistent with known candidate genes and biological pathways and yields relevant insights into the biology of this paradigmatic complex disorder.

The complex genetic architecture of Autism Spectrum Disorder (ASD) and its heterogeneous phenotype makes molecular diagnosis and patient prognosis challenging tasks. To establish more precise genotype–phenotype correlations in ASD, we developed a novel machine-learning integrative approach, which seeks to delineate associations between patients’ clinical profiles and disrupted biological processes, inferred from their copy number variants (CNVs) that span brain genes. Clustering analysis of the relevant clinical measures from 2446 ASD cases in the Autism Genome Project identified two distinct phenotypic subgroups. Patients in these clusters differed significantly in ADOS-defined severity, adaptive behavior profiles, intellectual ability, and verbal status, the latter contributing the most for cluster stability and cohesion. Functional enrichment analysis of brain genes disrupted by CNVs in these ASD cases identified 15 statistically significant biological processes, including cell adhesion, neural development, cognition, and polyubiquitination, in line with previous ASD findings. A Naive Bayes classifier, generated to predict the ASD phenotypic clusters from disrupted biological processes, achieved predictions with a high precision (0.82) but low recall (0.39), for a subset of patients with higher biological Information Content scores. This study shows that milder and more severe clinical presentations can have distinct underlying biological mechanisms. It further highlights how machine-learning approaches can reduce clinical heterogeneity by using multidimensional clinical measures, and establishes genotype–phenotype correlations in ASD. However, predictions are strongly dependent on patient’s information content. Findings are therefore a first step toward the translation of genetic information into clinically useful applications, and emphasize the need for larger datasets with very complete clinical and biological information.