Biology subjects

Hiroyasu, T.

Publications and source records attributed to Hiroyasu, T..

12 recordsLinked to original sources

bioRxiv2026

Robust Cooperative Learning for Multiview Regression via Soft-IPOD

Multiview data analysis has become increasingly important for integrating heterogeneous information from multiple data sources. Cooperative learning provides a flexible framework for multiview integration by bridging early and late fusion strategies. However, its use of squared loss makes it sensitive to outliers. In this study, we propose robust cooperative learning based on the soft-IPOD framework. The proposed method introduces an observation-specific outlier absorption vector into the cooperative learning objective, thereby reducing the influence of outlying observations while preserving information sharing across views. The resulting optimization problem can be formulated as a weighted Lasso-type problem using an augmented design matrix and can be naturally extended to more than two data views. Numerical simulations and a real-data application to labor onset prediction demonstrate the predictive performance of the proposed method in the presence of outliers.

bioinformatics↗

bioRxiv2026

Comparative Evaluation of Deep Generative Models for Capturing Topological Features in Brain Structural Connectivity

Structural connectivity (SC) data are crucial for brain network analysis, but SC-based machine learning often suffers from limited data availability, hindering model generalization and robustness. Although data augmentation using deep generative models has attracted increasing attention, it remains unclear how different models capture the complex topological features of SC data. To clarify the learning characteristics of deep generative models for SC generation, this study compares three representative models: variational autoencoder (VAE), Wasserstein GAN with gradient penalty (WGAN-GP), and denoising diffusion probabilistic models (DDPM). We systematically evaluated these models using both synthetic datasets with known characteristics and real-world SC data. Generation quality was assessed using graph-theoretic metric comparisons and visual inspection of the generated adjacency matrices. WGAN-GP showed relatively stable performance across datasets and metrics, without severe performance degradation across evaluation settings. In contrast, VAE and DDPM performed well in specific aspects but were more sensitive to data characteristics. These findings suggest that WGAN-GP may serve as the most balanced baseline for future SC data augmentation studies, whereas VAE and DDPM may be useful depending on the target application and structural properties of interest. Furthermore, because all models struggled to fully reproduce strict global constraints such as planarity, our results suggest that standard generative models may be insufficient to capture the complex topological features of SC data. This highlights the importance of incorporating the desired structural properties into the training or generation process.

neuroscience↗

bioRxiv2025

Energy Landscape Analysis with Automated Region-of-Interest Selection via Genetic Algorithms

Understanding brain dynamics is essential for advancing cognitive and clinical neuroscience. Energy landscape analysis (ELA), based on the pairwise maximum entropy model, is a powerful framework to characterize brain activity as transitions among discrete states defined by regional activity patterns. However, traditional ELA relies on the subjective manual selection of a small subset of regions of interest (ROIs) from whole-brain parcellations to satisfy mathematical constraints, which limits the scope and reproducibility of ELA results due to subjective subset selection. To overcome this, we developed ELA/GAopt, a meta-framework that utilizes a genetic algorithm to automate the selection of ROI combinations from the entire atlas search space by optimizing a user-defined objective function. In this study, we implemented a representative objective function balancing model fitting accuracy with the inter-individual variability of model parameters. We applied ELA/GAopt to three independent resting-state functional magnetic resonance imaging datasets. In Scenario 1, using the Creativity dataset (OpenNeuro: ds002330, n = 61), the ROI sets identified by ELA/GAopt achieved significantly higher objective function values and pattern reproducibility than randomly selected ROI sets (p < 0.05). Additional validation with the large-scale Human Connectome Project Young Adult (HCP-YA) dataset (n = 270) confirmed the robustness of our framework in high-dimensional settings. Stability analysis using Jaccard and Hamming metrics demonstrated that ELA/GAopt consistently identified reproducible ROI subsets across independent optimization runs. In Scenarios 2-4, we analyzed data from the Autism Brain Imaging Data Exchange II dataset using a site-disjoint validation design to mitigate findings were robust against multi-site artifacts. ELA/GAopt identified ASD-specific dynamics, where participants tend to visit local minima characterized by global co-activation of selected ROIs within sensory-motor and visual networks. These signatures were replicated in an independent cohort consisting of different scanning sites. Furthermore, ROI sets optimized for one group (ASD or typically developing controls) did not generalize to the other, highlighting distinct neurodynamic architectures. These results demonstrate that ELA/GAopt provides a reproducible, data-driven pathway for characterizing condition-specific brain dynamics, serving as a methodological basis for future, harmonization-aware and externally validated biomarker studies.

neuroscience↗

bioRxiv2024

Task-guided Generative Adversarial Networks for Synthesizing and Augmenting Structural Connectivity Matrices for Connectivity-Based Prediction

Recent machine learning techniques have improved connectome-based predictions by modelling complex dependencies between brain connectivity and cognitive traits. However, they typically require large datasets that are costly and time-consuming to collect. To address this, we propose Task-guided GAN II, a novel data augmentation method that uses generative adversarial networks (GANs) to expand sample sizes in connectome-based prediction tasks. Our method incorporates a task-guided branch within the Wasserstein GAN framework, specifically designed to synthesize structural connectivity matrices and improve prediction accuracy by capturing task-relevant features. We evaluated Task-guided GAN II on the prediction of fluid intelligence using the NIMH Health Research Volunteer Dataset. Results showed that data augmentation improved prediction accuracy. To further assess whether augmentation can substitute for increasing real-world sample sizes, we conducted additional validation using the HCP WU-Minn S1200 dataset. Task-guided GAN II improved prediction performance with limited real data, with gains of up to twofold augmentation observed. However, excessive augmentation did not result in further improvements, suggesting that augmentation complements, but does not fully replace, real data augmentation. These results suggest that Task-guided GAN II is a promising tool for harnessing small datasets in human connectomics research, improving predictive modelling where large-scale data collection is impractical.

neuroscience↗

bioRxiv2023

Comparison of classification accuracy and feature selection between sparse and non-sparse modeling of metabolomics data

Machine learnings such as multivariate analyses and clustering have been frequently used for metabolomics data analyses. In metabolomics data analyses, how much difference there is between the results calculated by supervised and unsupervised learning models is an interesting topic. Since metabolomics data include hundreds to thousands of metabolites greater than the sample numbers, only a small fraction of metabolites is relevant to the phenotype of interest. For this reason, sparse mechanisms have been introduced into many machine learning models. However, its explanatory power decreases when the number of explanatory variables is reduced to an extreme level. In this paper, serum lipidomic data of breast cancer patients (1) pre/post-menopause and (2) before/after neoadjuvant chemotherapy was chosen as one of metabolomics data. Here, this data was analyzed by partial least squares (PLS) for regression and K-means and hierarchical clustering for clustering. Results were also compare with the sparse modeling. Between the non-sparse and sparse modeling accuracy, there is no significant difference. Metabolite subsets selected by sparse modeling were almost identical to the PLS-selected features. At the same time, several metabolites were consistently selected regardless of the algorithm used. These results contribute to exploring biomarkers in high-dimensional metabolomics datasets.

bioinformatics↗

bioRxiv2023

Estimation of a treatment effect based on a modified covariates method with L0 norm

AO_SCPLOWBSTRACTC_SCPLOWIn randomized clinical trials, we assumed the situation that the new treatment is not adequate compared to the control treatment as result. However, it is unknown if the new treatment is ineffective for all patients or if it is effective for only a subgroup of patients with specific characteristics. If such a subgroup exists and can be detected, the patients can receive effective therapy. To detect subgroups, we need to estimate treatment effects. To achieve this, various treatment effect estimation methods have been proposed based on the sparse regression method. However, these methods are affected by noise. Therefore, we propose new treatment effect estimation approaches based on the modified covariate method, one using lasso regression and the other ridge regression, using the L0 norm. The proposed approach was evaluated through numerical simulation and real data examples.

bioinformatics↗

bioRxiv2022

Effects of habitual dart training on hemispheric lateralization in older adults: a cross-sectional study using functional near-infrared spectroscopy

Exercise training integrating physical and cognitive activities is gaining attention because of its potential benefits for brain health. This study focuses on exercise training using a dart game called Wellness Darts. Wellness Darts is a sport involving throwing darts and walking to pull them out of the board, memorizing the score, and subtracting it from the total score, thus allowing the performance of two tasks simultaneously: exercise and calculation. It is expected to maintain and improve cognitive function, and whether the continual dart training affects brain function is of great interest. Before conducting the longitudinal study revealing its effect on brain function, we aimed to cross-sectionally confirm the difference in hemispheric lateralization between expert and non-expert players. Functional near-infrared spectroscopy (fNIRS) was used to measure brain activity for three groups: an expert older group who practiced darts continually, a non-expert older control group, and a non-expert younger control group. Their brain activity patterns were quantified by lateralization index (LI) and compared between groups. The results showed that the younger and the expert older groups had significantly higher LI values than the non-expert older group and did not differ between the expert older and the younger groups. Our results suggest that the Wellness Darts possibly promote hemispheric lateralization.

neuroscience↗

bioRxiv2022

The usefulness of sparse k-means in metabolomics data: Anexample from breast cancer data

In processing metabolomics data, multidimensional quantitative data from thousands of metabolites are often sparse, that is, only a small fraction of metabolites are relevant to the phenotype of interest. Clustering is therefore used to discover subtypes from omics data. Sparse processing, which selects important metabolites from the total omics data, is an effective clustering technique. This study investigated the effectiveness of sparse k-means for metabolomics data. Specifically, sparse k-means was used to cluster blood lipid metabolite data of breast cancer patients in two studies: (1) before and after menopause, and (2) pre- and postoperative chemotherapy. In both cases, sparse k-means showed comparable discrimination accuracy with fewer metabolites than k-means. Furthermore, when the L1 norm values were varied, no significant changes were observed. The mean silhouette coefficients of sparse k-means and k-means were (1) 0.38 {+/-} 0.14 (S.D.) and 0.17 {+/-} 0.01, (2) 0.38 {+/-} 0.07 and 0.17 {+/-} 0.01, indicating that feature selection using sparse k-means can improve clustering results. In addition, metabolite selection using sparse k-means was consistent regardless of the test data or the constrained value of the L1 norm, indicating robustness.

bioinformatics↗

bioRxiv2022

Predicting the Degree of Distracted Driving Based on fNIRS Functional Connectivity: A Pilot Study

Distracted driving is one of the main causes of traffic accidents. By predicting the attentional state of drivers, it is possible to prevent distractions and promote safe driving. In this study, we developed a model that could predict the degree of distracted driving based on brain activity. Changes in oxyhemoglobin concentrations were measured in drivers while driving a real car using functional near-infrared spectroscopy (fNIRS). A regression model was constructed for each participant using functional connectivity as an explanatory variable and break reaction time to random beeps while driving as an objective variable. As a result, we were able to construct a prediction model for 11 of the 12 participants. Furthermore, the regression model with the highest prediction accuracy for each participant was analyzed to gain a better understanding of the neural basis of distracted driving. The 11 models were classified into five clusters by hierarchical clustering based on their functional connectivity edges used in each cluster. The results showed that the combinations of the dorsal attention network (DAN)-sensory motor network (SMN) and DAN-ventral attention network (VAN) connections were common in all clusters and that these networks were essential to predict the degree of distraction in complex multitask driving. They also confirmed the existence of multiple types of prediction models with different within- and between-network connectivity patterns. These results indicate that it is possible to predict the degree of distracted driving based on the brain activity of the driver during actual driving. These results are expected to contribute to the development of safe driving systems and elucidation of the neural basis of distracted driving.

neuroscience↗

bioRxiv2022

Analyzing the relationship between distracted driving and eye movement using multimodal data collected during car driving

Human error is the leading cause of traffic accidents and originates from the distraction caused by various factors, such as the drivers physical condition and mental state. One of the significant factors causing driver distraction is the presence of stress. In a previous study, multiple stressors were used to examine distraction while driving. Multiple stressors were given to the driver and the corresponding driver biometric data were obtained, and a multimodal dataset was published thereafter. In this study, we reiterate the results of existing studies and investigated the relationship between gaze variability while driving and stressor intervention, which has not yet been examined. We also examined whether biometric and vehicle information can estimate the presence or absence of secondary tasks during driving.

bioengineering↗

bioRxiv2021

Interpersonal brain synchronization during face-to-face economic exchange between acquainted dyads

Interpersonal brain synchronization (IBS) has been observed during social interactions and involves various factors, such as familiarity with the partner and type of social activity. A previous study has shown that face-to-face interactions in pairs of strangers increase IBS. However, it is unclear whether this can be observed when the nature of the interacting partners is different. Herein, we aimed to extend these findings to pairs of acquaintances. Neural activity in the frontal and temporal regions was recorded using functional near-infrared spectroscopy hyperscanning. Participants played an ultimatum game that required virtual economic exchange in two experimental settings: the face-to-face and face-blocked conditions. Random pair analysis confirmed whether IBS was induced by social interaction. Contrary to the aforementioned study, our results did not show any cooperative behavior or task-induced IBS increase. Conversely, the random pair analysis results revealed that the pair-specific IBS was significant only in the task condition at the left and right superior frontal, middle frontal, orbital superior frontal, right superior temporal, precentral, and postcentral gyri. Our results revealed that face-to-face interaction in acquainted pairs did not increase IBS and supported the idea that IBS is affected by "with whom we interact and how."

neuroscience↗

bioRxiv2019

Short-term effects on brain functional network caused by focused-attention meditation revealed by Tucker3 clustering on graph theoretical metrics

This study examines the short-term effects of focused-attention meditation on functional brain state in novice meditators. There are a number of feature metrics for functional brain states, such as functional connectivity, graph theoretical metrics, and amplitude of low frequency fluctuation (ALFF). It is necessary to choose appropriate metrics and also to specify the region of interests (ROIs) from a number of brain regions. Here, we use a Tucker3 clustering method, which simultaneously selects the feature vectors (graph theoretical metrics and fractional ALFF) and the ROIs that can discriminate between resting and meditative states based on the characteristics of the given data. In this study, breath-counting meditation, one of the most popular forms of focused-attention meditation, was used and brain activities during resting and meditation states were measured by functional magnetic resonance imaging. The results indicated that the clustering coefficients of eight brain regions tended to increase through the meditation. Our results reveal that short-term effects of breath-counting meditation can be explained by network density changes in these eight brain regions.

neuroscience↗