mFusion: a multiscale fusion method bridging neuroimages to genes through neurotransmissions in mental health disorders.

Mental health disorders emerge from complex interactions among neurobiological processes across multiple scales, which poses challenges in uncovering pathological pathways from molecular dysfunction to neuroimaging changes. Here, we proposed a multiscale fusion (mFusion) method to evaluate the relevance of each gene to the neuroimaging traits of mental health disorders. We combined gene-neuroimaging associations with gene-positron emission tomography (PET) and PET-neuroimaging associations using protein-protein interaction networks, where various genes traced by PET maps are involved in neurotransmission.

Working memory processing deficit associated with a nonlinear response pattern of the anterior cingulate cortex in first-episode and drug-naïve schizophrenia.

Impaired working memory (WM) is a core neuropsychological dysfunction of schizophrenia, however complex interactions among the information storage, information processing and attentional aspects of WM tasks make it difficult to uncover the psychophysiological mechanisms of this deficit. Thirty-six first-episode and drug-naïve schizophrenia and 29 healthy controls (HCs) were enrolled in this study. Here, we modified a WM task to isolate components of WM storage and WM processing, while also varying the difficulty level (load) of the task to study regional differences in load-specific activation using mixed effects models, and its relationship to distributed gene expression.

Research on Pathogenic Hippocampal Voxel Detection in Alzheimer's Disease Using Clustering Genetic Random Forest.

Alzheimer's disease (AD) is an age-related neurological disease, which is closely associated with hippocampus, and subdividing the hippocampus into voxels can capture subtle signals that are easily missed by region of interest (ROI) methods. Therefore, studying interpretable associations between voxels can better understand the effect of voxel set on the hippocampus and AD. In this study, by analyzing the hippocampal voxel data, we propose a novel method based on clustering genetic random forest to identify the important voxels.

Research on Frequent Itemset Mining of Imaging Genetics GWAS in Alzheimer's Disease.

As an efficient method, genome-wide association study (GWAS) is used to identify the association between genetic variation and pathological phenotypes, and many significant genetic variations founded by GWAS are closely associated with human diseases. However, it is not enough to mine only a single marker effect variation on complex biological phenotypes. Mining highly correlated single nucleotide polymorphisms (SNP) is more meaningful for the study of Alzheimer's disease (AD).

Hippocampal Subregion and Gene Detection in Alzheimer's Disease Based on Genetic Clustering Random Forest.

The distinguishable subregions that compose the hippocampus are differently involved in functions associated with Alzheimer's disease (AD). Thus, the identification of hippocampal subregions and genes that classify AD and healthy control (HC) groups with high accuracy is meaningful. In this study, by jointly analyzing the multimodal data, we propose a novel method to construct fusion features and a classification method based on the random forest for identifying the important features.

Multi-dimensional persistent feature analysis identifies connectivity patterns of resting-state brain networks in Alzheimer's disease.

The characterization of functional brain network is crucial to understanding the neural mechanisms associated with Alzheimer's disease (AD) and mild cognitive impairment (MCI). Some studies have shown that graph theoretical analysis could reveal changes of the disease-related brain networks by thresholding edge weights. But the choice of threshold depends on ambiguous cognitive conditions, which leads to the lack of interpretability.