Logistic ridge regression to predict bipolar disorder using mRNA expression levels in the N-methyl-D-aspartate receptor genes

Digital phenotyping from wearables using AI characterizes psychiatric disorders and identifies genetic associations

Psychiatric disorders are complex and influenced by both genetic and environmental factors. However, studying the full spectrum of these disorders is hindered by practical limitations on measuring human behavior. This highlights the need for novel technologies that can measure behavioral changes at an intermediate level between diagnosis and genotype. Wearable devices are a promising tool in precision medicine, since they can record physiological measurements over time in response to environmental stimuli and do so at low cost and minimal invasiveness. Here we analyzed wearable and genetic data from a cohort of the Adolescent Brain Cognitive Development study. We generated >250 wearable-derived features and used them as intermediate phenotypes in an interpretable AI modeling framework to assign risk scores and classify adolescents with psychiatric disorders. Our model identifies key physiological processes and leverages their temporal patterns to achieve a higher performance than has been previously possible. To investigate how these physiological processes relate to the underlying genetic architecture of psychiatric disorders, we also utilized these intermediate phenotypes in univariate and multivariate GWAS. We identified a total of 29 significant genetic loci and 52 psychiatric-associated genes, including ELFN1 and ADORA3. These results show that wearable-derived continuous features enable a more precise representation of psychiatric disorders and exhibit greater detection power compared to categorical diagnostic labels. In summary, we demonstrate how consumer wearable technology can facilitate dimensional approaches in precision psychiatry and uncover etiological linkages between behavior and genetics.

Inference of social cognition in schizophrenia patients with neurocognitive domains and neurocognitive tests using automated machine learning

AIM

It has been suggested that single neurocognitive domain or neurocognitive test can be used to determine the overall cognitive function in schizophrenia using machine learning algorithms. It is unknown whether social cognition in schizophrenia patients can be estimated with machine learning based on neurocognitive domains or neurocognitive tests.

METHODS

To predict social cognition in schizophrenia, we applied an automated machine learning (AutoML) framework resulting from the analysis of predictive factors such as six neurocognitive domain scores and nine neurocognitive test scores of 380 schizophrenia patients in the Taiwanese population. Four clinical parameters (i.e., age, gender, subgroup, and education) were also used as predictive factors. We utilized an AutoML framework called Tree-based Pipeline Optimization Tool (TPOT) to generate predictive pipelines automatically.

RESULTS

The analysis revealed that all neurocognitive domains and tests except the reasoning and problem solving domain/test showed significant associations with social cognition. In addition, a TPOT-generated pipeline can best predict social cognition in schizophrenia using seven predictive factors, including five neurocognitive domains (i.e., speed of processing, sustained attention, working memory, verbal learning and memory, and visual learning and memory) and two clinical parameters (i.e., age and gender). This predictive pipeline consists of machine learning algorithms such as function transformers, an approximate feature map, independent component analysis, and linear regression.

CONCLUSION

The study indicates that an AutoML framework such as TPOT may provide a promising way to produce truly effective machine learning pipelines for predicting social cognition in schizophrenia using neurocognitive domains and/or neurocognitive tests.

RNA Biomarkers in Bipolar Disorder and Response to Mood Stabilizers

Bipolar disorder (BD) is a severe chronic disorder that represents one of the main causes of disability among young people. To date, no reliable biomarkers are available to inform the diagnosis of BD or clinical response to pharmacological treatment. Studies focused on coding and noncoding transcripts may provide information complementary to genome-wide association studies, allowing to correlate the dynamic evolution of different types of RNAs based on specific cell types and developmental stage with disease development or clinical course. In this narrative review, we summarize findings from human studies that evaluated the potential utility of messenger RNAs and noncoding transcripts, such as microRNAs, circular RNAs and long noncoding RNAs, as peripheral markers of BD and/or response to lithium and other mood stabilizers. The majority of available studies investigated specific targets or pathways, with large heterogeneity in the included type of cells or biofluids. However, a growing number of studies are using hypothesis-free designs, with some studies also integrating data on coding and noncoding RNAs measured in the same participants. Finally, studies conducted in neurons derived from induced-pluripotent stem cells or in brain organoids provide promising preliminary findings supporting the power and utility of these cellular models to investigate the molecular determinants of BD and clinical response.

A Novel Algorithm for Feature Selection Using Penalized Regression with Applications to Single-Cell RNA Sequencing Data

With the emergence of single-cell RNA sequencing (scRNA-seq) technology, scientists are able to examine gene expression at single-cell resolution. Analysis of scRNA-seq data has its own challenges, which stem from its high dimensionality. The method of machine learning comes with the potential of gene (feature) selection from the high-dimensional scRNA-seq data. Even though there exist multiple machine learning methods that appear to be suitable for feature selection, such as penalized regression, there is no rigorous comparison of their performances across data sets, where each poses its own challenges. Therefore, in this paper, we analyzed and compared multiple penalized regression methods for scRNA-seq data. Given the scRNA-seq data sets we analyzed, the results show that sparse group lasso (SGL) outperforms the other six methods (ridge, lasso, elastic net, drop lasso, group lasso, and big lasso) using the metrics area under the receiver operating curve (AUC) and computation time. Building on these findings, we proposed a new algorithm for feature selection using penalized regression methods. The proposed algorithm works by selecting a small subset of genes and applying SGL to select the differentially expressed genes in scRNA-seq data. By using hierarchical clustering to group genes, the proposed method bypasses the need for domain-specific knowledge for gene grouping information. In addition, the proposed algorithm provided consistently better AUC for the data sets used.