Machine learning in schizophrenia genomics, a case‐control study using 5,090 exomes

Abstract

Our hypothesis is that machine learning (ML) analysis of whole exome sequencing (WES) data can be used to identify individuals at high risk for schizophrenia (SCZ). This study applies ML to WES data from 2,545 individuals with SCZ and 2,545 unaffected individuals, accessed via the database of genotypes and phenotypes (dbGaP). Single nucleotide variants and small insertions and deletions were annotated by ANNOVAR using the reference genome hg19/GRCh37. Rare (predicted functional) variants with a minor allele frequency ≤1% and genotype quality ≥90 including missense, frameshift, stop gain, stop loss, intronic, and exonic splicing variants were selected. A file containing all cases and controls, the names of genes with variants meeting our criteria, and the number of variants per gene for each individual, was used for ML analysis. The supervised machine-learning algorithm used the patterns of variants observed in the different genes to determine which subset of genes can best predict that an individual is affected. Seventy percent of the data was used to train the algorithm and the remaining 30% of data (n = 1,526) was used to evaluate its efficiency. The supervised ML algorithm, gradient boosted trees with regularization (eXtreme Gradient Boosting implementation) was the best performing algorithm yielding promising results (accuracy: 85.7%, specificity: 86.6%, sensitivity: 84.9%, area under the receiver-operator characteristic curve: 0.95). The top 50 features (genes) of the algorithm were analyzed using bioinformatics resources for new insights about the pathophysiology of SCZ. This manuscript presents a novel predictor which could potentially enable studies exploring disease-modifying intervention in the early stages of the disease.

Genetic stratification of depression in UK Biobank suggests a subgroup linked to age of natural menopause

“…Furthermore, stratifying depression using genetic data remains a key goal within the psychiatric genetics community [47] and should lead to improved classification of mental health conditions and more efficacious treatment for patients. Machine learning [48, 49] and polygenic risk score [6, 50] approaches offer possible methods for stratification in mental health. In the current study, we used BUHMBOX [14] to identify whether traits that were genetically correlated with depression were correlated due to a subgroup, i.e.…”

Machine learning analysis of exome trios to contrast the genomic architecture of autism and schizophrenia

“…Many powerful ML algorithms render themselves uninterpretable, making it difficult to understand their decision-making process. Trying to balance interpretability with model performance, we used a more interpretable state of the art ML algorithm: regularized gradient boosted machine (GBM) (XGBoost implementation) [32], which we also demonstrated as an effective algorithm in our previous study [23].…”

“…Our group recently applied supervised ML to rare, predicted functional variants from whole-exome sequencing (WES) data of a SCZ case-control dataset (n = 5090). 70% of the data was used to train the ML algorithm and 30% (n = 1526) to evaluate its performance, showing encouraging results (86% accuracy, AUC: 0.95) [23]. Studies based on supervised learning, like the one just mentioned, are focused on learning from input-to-output labeled data where a model is trained to learn the best function or map from input variables of data instances to their labels.…”

Genomics and Machine Learning

“…Machine learning is one of the moist important application of artificial intelligence which have ability to detect, analysis and produce results related to disease [14][15][16][17]. The beauty of machine learning process is deep learning.…”