Biology subjects

Tsunoda, T.

Publications and source records attributed to Tsunoda, T..

At least 19 recordsLinked to original sources

bioRxiv2026

QBayMic: Quantum-coupled variational Bayes for clustering and feature selection in low-signal microbiome data

Clustering microbiome samples into community types is central to cohort stratification and biomarker discovery, yet the resulting inference becomes unstable when the between group signal is small compared with sampling noise: variational Bayes yields different partitions across initialisations, and common fixes do not solve the problem. Simple restarts are ineffective because the variational free energy is anti-correlated with clustering accuracy; deterministic annealing collapses to the same solution as greedy ascent, with the operator staying diagonal at every temperature; and parallel tempering replicas remain too similar to permit configuration exchanges. We propose QBayMic, which replaces the assignment step of a Dirichlet-multinomial mixture with sparse variable selection via a quantum Gibbs state under an annealed Hamiltonian, coupling competing assignments through a transverse-field term that cannot be reproduced by temperature scaling alone. We present two gate-based circuit designs for this step, evaluating on noiseless qubit-register simulations, and we derive a signal fraction, computable prior to clustering, that predicts the expected strength of quantum coupling. With matched compute in the predicted regime, the three classical methods recovered the reference partition (ARI > 0.4) in 0/100 seeds, while QBayMic recovered it in 47-64/100; when the number of clusters exceeded three, only QBayMic recovered the correct cluster count. For a soil pH dataset, the diagnostic indicates a narrow separation margin; for a human-derived dataset tuned into the predicted band via controlled dilution, classical methods recovered the cluster count in 0/100 seeds, compared with 61-76% for QBayMic. The implementation is publicly available at https://github.com/tungtokyo1108/QBayMic.

bioinformatics↗

bioRxiv2026

A hyperspherical deep Bayesian model for interpretable clustering and relationship prediction in microbiome multi-omics integration

The microbiome plays a significant role in the development and progression of many diseases, yet extracting interpretable insights from multi-omics data remains challenging. Existing approaches face a recurring practical trade-off: deep learning methods achieve high predictive performance but lack uncertainty quantification, whereas probabilistic methods provide interpretable results but require data-type-specific likelihood functions that limit generalization across diverse omics modalities. Here, we introduce DBayesCM (Deep Bayesian Clustering for Multi-omics), which combines deep learning modeling with Bayesian nonparametric methods. DBayesCM employs separate encoders to project microbiome and host omics data into a shared latent space, where an infinite mixture model with a Dirichlet process prior determines the number of clusters automatically while quantifying the uncertainty of each samples assignment. Spike-and-slab priors identify discriminative features, and a Bayesian neural network estimates probabilistic co-occurrence between microbial species and host omics features. To isolate the effect of latent geometry, we evaluate two variants that are identical except for their latent space: DBayesCM-vMF constrains the latent to the unit hypersphere and applies a von Mises-Fisher mixture, while DBayesCM-GMM uses a Euclidean latent space and a Gaussian mixture. On simulated data, the hyperspherical variant recovered the correct number of clusters, whereas the Euclidean variant over-segmented, demonstrating that the latent geometry affects cluster recovery. Applied to colon, breast, and kidney cancer cohorts spanning metagenomics, host metabolomics, RNA-seq, and miRNA data, and to an obstructive sleep apnea model, DBayesCM ranked consistently among the existing methods while uniquely combining data-driven cluster-number determination, sample-level uncertainty, and interpretable feature selection within a single framework. DBayesCM reveals conditional probabilistic co-occurrence between core microbial species and host omics features, enabling uncertainty-aware exploration of microbiome-host relationships across diverse diseases.

bioinformatics↗

bioRxiv2026

vDeepInsight: an injective three-dimensional voxel carrier for tabular-feature neighborhood learning

DeepInsight-style methods make tabular feature relationships accessible to convolutional networks by placing each feature at a fixed position on an image carrier. An open design question is how the carrier geometry should be constructed when feature neighborhoods themselves carry part of the signal. We introduce vDeepInsight, an injective three-dimensional (3D) voxel carrier that preserves feature neighborhoods more faithfully than matched two-dimensional (2D) carriers while keeping a one-to-one mapping from each feature to a single voxel. Genes are embedded with t-SNE or UMAP, assigned one-to-one to a sparse voxel grid by linear-sum assignment, and processed by a submanifold sparse 3D convolutional network. We evaluate the carrier on gene expression through four linked analyses. First, representation-quality metrics show that 3D layouts reduce gene-neighborhood distortion relative to matched 2D layouts before any model is trained. Second, controlled synthetic tasks show that a sparse 3D convolution can exploit this preserved locality, but only when the supervised signal is constructed to depend on co-located genes and the receptive field spans adjacent voxels. Third, on real omics tasks the 3D carrier matches or exceeds tuned tabular baselines and consistently exceeds matched 2D carriers; the margin is small on marker-type classification, where individual genes already carry much of the label (tissue, lineage and cancer-type classification), and larger on program-type tasks, where the target depends on coordinated, pathway-level multi-gene activity (drug-response regression, TCGA immunogenomic-context regression and mechanism-of-action classification). Fourth, because the assignment is injective, voxel attribution maps directly back to genes, enabling gene-level attribution and pathway-level functional interpretation without voxel-to-gene deconvolution. Overall, the added carrier dimension improves the fidelity of feature-neighborhood representation and translates this improvement into prediction gains that are largest when the signal is distributed across local gene programs rather than dominated by individual marker genes.

bioinformatics↗

bioRxiv2026

Training Strategy Optimization to Mitigate Shortcut Learning in Pan-Cancer Drug Response Prediction

BackgroundPrediction of in vivo drug response is a central challenge in precision medicine, but the scarcity of labeled clinical data still necessitates the use of large-scale cancer cell line resources for model training. Domain adaptation methods, which aim to transfer knowledge learned from a source domain (cell lines) to a target domain (patients) by aligning feature distributions across domains, are a promising approach to bridge the gap between in vitro models and in vivo patients. However, we observed that these methods can exhibit a significant discrepancy between pan-cancer evaluation metrics and cancer type-specific prediction accuracy. This performance gap warrants a detailed investigation into their underlying predictive characteristics. ResultsWe discovered that cancer-type-specific class imbalances in training data can lead domain adaptation models to engage in shortcut learning, where they primarily discriminate between cancer types rather than capturing the actual biological determinants of drug sensitivity. To address this, we propose a strategy of combining two approaches: (1) excluding cancer types causing imbalance from the training data, and (2) adjusting class balance through oversampling and class weighting while retaining cancer types causing the imbalance. Among all configurations tested in conjunction with the CODE-AE (Context-aware Deconfounding AutoEncoder) framework, the combination of moderate oversampling (30% non-responder ratio) with class weighting achieved the best performance, significantly improving prediction accuracy in 5 out of 11 external patient cohorts from TCGA and GEO. ConclusionsOur findings demonstrate that appropriate class imbalance correction--rather than wholesale exclusion of imbalanced cancer subtypes--enables effective utilization of biologically relevant information shared across cancer types for drug response prediction. This study highlights the critical importance of jointly optimizing training data composition and class balance adjustment strategies in developing robust pan-cancer drug response prediction models for precision medicine applications. HighlightsO_LIIdentified a critical discrepancy in current domain adaptation models for drug response prediction: high pan-cancer accuracy often masks poor performance within specific cancer types. C_LIO_LIRevealed the root cause as "shortcut learning," where models tend to distinguish between cancer tissue types (hematological vs. solid) rather than learning individual drug sensitivity. C_LIO_LIDiscovered severe class imbalance in training data, with hematological cell lines being disproportionately drug-responsive across multiple chemotherapeutics. C_LIO_LIProposed an architecture-agnostic fix using the CODE-AE framework: moderate oversampling (30% minority ratio) combined with class weighting. C_LIO_LIDemonstrated significant improvements in 5 of 11 external patient cohorts, showing that correcting class bias is more effective than simply excluding problematic data. C_LI

bioinformatics↗

bioRxiv2026

Dynamic multimodal survival prediction in multiple myeloma integrating gene expression, longitudinal laboratories, and treatment history

Prognostic stratification in multiple myeloma (MM) relies on staging systems that assign patients to fixed categories at diagnosis and discard the temporal information that accumulates during treatment. We developed a dynamic multimodal framework that predicts residual overall survival using observation windows ranging from 1 to 18 months post-diagnosis. The model integrates DeepInsight-transformed gene expression representation, longitudinal laboratory measurement trajectories across 10 analytes, and treatment history for three drug classes through an adaptive fusion mechanism that accounts for missing clinical observations. On the MMRF CoMMpass cohort (n = 752), five-fold cross-validation yielded a concordance index (C-index) of 0.773 {+/-} 0.024 and a time-dependent AUC at a 1-year prediction horizon (tdAUC1yr) of 0.789 {+/-} 0.021, outperforming all evaluated baseline methods including DeepSurv (0.633 {+/-} 0.095) and random survival forests (0.636 {+/-} 0.024) on matched cross-validation splits. Modality ablation identified longitudinal laboratory measurements as the strongest individual contributor (C-index 0.693); the DeepInsight spatial encoding of gene expression yielded higher discrimination than a multilayer perceptron (MLP) baseline operating on the same features (0.624 vs. 0.596). Kaplan-Meier analysis showed significant prognostic group separation at all primary landmarks (log-rank p < 0.001; hazard ratios 3.46-3.93). A distilled student model retaining only the DeepInsight representation and five baseline clinical features achieved C-index 0.672 and tdAUC1yr 0.740 on an independent microarray cohort (GSE24080, n = 507) without retraining. Interpretability analysis identified prognostic associations consistent with established myeloma biology, including ubiquitin-proteasome pathway genes, endoplasmic reticulum stress markers, and Interferon Alpha Response pathway enrichment.

bioinformatics↗

bioRxiv2025

scHDeepInsight: A Hierarchical Deep Learning Framework for Precise Immune Cell Annotation in Single-Cell RNA-seq Data

Immune cell classification from single-cell RNA sequencing (scRNA-seq) presents significant challenges due to complex hierarchical relationships among cell types. We introduce scHDeepInsight, a deep learning framework that extends our previous scDeepInsight model by integrating a biologically-informed classification architecture with an adaptive hierarchical focal loss. The framework leverages our established method of transforming gene expression data into two-dimensional structured images for use with convolutional neural networks by effectively capturing both global and fine-grained transcriptomic features, overcoming the limitations of flat classification approaches that ignore hierarchical relationships between cell types. scHDeepInsight dynamically adjusts loss contributions to balance performance across the hierarchy levels. It also employs STACAS batch correction, robust random masking, and SHAP-based interpretability to enhance prediction accuracy and biological insight. Comprehensive benchmarking across seven diverse tissue datasets shows scHDeepInsight achieves an average accuracy of 93.2%, representing a 5.1 percentage point improvement over current state-of-the-art methods. The model successfully distinguishes 50 distinct immune cell subtypes with high accuracy, demonstrating proficiency for identifying rare and closely related cell subtypes. These advantages make scHDeepInsight a robust tool for high-resolution immune cell subtype characterization, well suited for detailed immune profiling in immunological studies.

bioinformatics↗

bioRxiv2024

VBayesMM: Variational Bayesian neural network to prioritize important relationships of high-dimensional microbiome multiomics data

The analysis of high-dimensional microbiome multiomics datasets is crucial for understanding the complex interactions between microbial communities and host physiological states across health and disease conditions. Despite their importance, current methods such as the microbe-metabolite vectors (MMvec) approach, often fail to efficiently identify keystone species. This arises from the vast dimensionality of metagenomics data which complicates the inference of significant relationships, particularly the estimation of co-occurrence probabilities between microbes and metabolites. Here we propose the variational Bayesian microbiome multiomics (VBayesMM) approach, which enhances MMvec by incorporating a spike-and-slab prior within a Bayesian neural network. This allows VBayesMM to rapidly and precisely identify crucial microbial species, improving the accuracy of estimated co-occurrence probabilities between microbes and metabolites, while also robustly managing the uncertainty inherent in high-dimensional data. Moreover, we have implemented variational inference to address computational bottlenecks, enabling scalable analysis across extensive multiomics datasets. Our comparative evaluation of large-scale human and mouse multiomics datasets demonstrates that VBayesMM not only outperforms existing methods in accuracy but also provides a scalable solution for analyzing massive datasets. VBayesMM enhances the interpretability of the Bayesian neural network by identifying a core set of influential microbial species, thus facilitating a deeper understanding of their probabilistic relationships with the host.

bioinformatics↗

bioRxiv2023

Clinal variation in drought response is consistent across life stages but not between native and non-native ranges

Clinal variation, i.e., intraspecific variation that corresponds to environmental gradients, is common in widely distributed species. Studies on clinal variation across multiple ranges and life stages are lacking, but can enhance our understanding of specie[s] adaptive potential to abiotic environments and may aid in predicting future species distributions. This study examined clinal variation in drought responses of 59 Conyza canadensis populations across large aridity gradients from the native and non-native ranges in three greenhouse studies. Experimental drought was applied to recruitment, juveniles, and adult stages. Drought reduced growth at all three life stages. However, contrasting patterns of clinal variation emerged between the two ranges. Native populations from xeric habitats were less inhibited by drought than mesic populations, but such clinal variation was not apparent for non-native populations. These range-specific patterns of clinal variation were consistent across the life stages. The experiments suggest that invaders may succeed without complete local adaptation to their new abiotic environments, and that long-established invaders may still be evolving to the abiotic environment. These findings may explain lag times in some invasions and raise concern about future expansions.

evolutionary biology↗

bioRxiv2023

Deep Learning for Protein Peptide bindingPrediction: Incorporating Sequence, Structural andLanguage Model Features

Protein-peptide interactions play a crucial role in various cellular processes and are implicated in abnormal cellular behaviors leading to diseases such as cancer. Therefore, understanding these interactions is vital for both functional genomics and drug discovery efforts. Despite a significant increase in the availability of protein-peptide complexes, experimental methods for studying these interactions remain laborious, time-consuming, and expensive. Computational methods offer a complementary approach but often fall short in terms of prediction accuracy. To address these challenges, we introduce PepCNN, a deep learning-based prediction model that incorporates structural and sequence-based information from primary protein sequences. By utilizing a combination of half-sphere exposure, position specific scoring matrices, and pre-trained transformer language model, PepCNN outperforms state-of-the-art methods in terms of specificity, precision, and AUC. The PepCNN software and datasets are publicly available at https://github.com/abelavit/PepCNN.git.

bioinformatics↗

bioRxiv2023

Multi-representation DeepInsight: an improvement on tabular data analysis

Tabular data analysis is a critical task in various domains, enabling us to uncover valuable insights from structured datasets. While traditional machine learning methods have been employed for feature engineering and dimensionality reduction, they often struggle to capture the intricate relationships and dependencies within real-world datasets. In this paper, we present Multi-representation DeepInsight (abbreviated as MRep-DeepInsight), an innovative extension of the DeepInsight method, specifically designed to enhance the analysis of tabular data. By generating multiple representations of samples using diverse feature extraction techniques, our approach aims to capture a broader range of features and reveal deeper insights. We demonstrate the effectiveness of MRep-DeepInsight on single-cell datasets, Alzheimers data, and artificial data, showcasing an improved accuracy over the original DeepInsight approach and machine learning methods like random forest and L2-regularized logistic regression. Our results highlight the value of incorporating multiple representations for robust and accurate tabular data analysis. By embracing the power of diverse representations, MRep-DeepInsight offers a promising avenue for advancing decision-making and scientific discovery across a wide range of fields.

bioinformatics↗

bioRxiv2023

DRPBind: prediction of DNA, RNA and protein binding residues in intrinsically disordered protein sequences

DRPbind predicts three components: deoxyribonucleic acid (DNA) binding, ribonucleic acid (RNA) binding and protein-binding residues of query protein sequences. DRPbind utilizes independent sources of information encoded for each component predictor and relies on the information-rich profiles of protein evolutionary-based features, protein physicochemical-based features, and protein structural-based features. DRPbind employs protein profile-based features extracted from the bigrams of PSSM and HMM profiles. It also extracts features from physicochemical and structural attributes. DRPbind takes primary protein sequences as input, and through the Support Vector Machine (SVM) classifier, it provides the binding prediction. DRPbind is optimized based on a specific binding type and shown superior performance in terms of simultaneously predicting the DNA-binding, RNA-binding and protein-binding residues. The source code is available at https://github.com/roneshsharma/DNA-RNA-Protein-Binding/wiki

bioinformatics↗

bioRxiv2023

scDeepInsight: a supervised cell-type identification method for scRNA-seq data with deep learning

Annotation of cell-types is a critical step in the analysis of single-cell RNA sequencing (scRNA-seq) data that allows the study of heterogeneity across multiple cell populations. Currently this is most commonly done using unsupervised clustering algorithms, which project single-cell expression data into a lower dimensional space and then cluster cells based on their distances from each other. However, as these methods do not use reference datasets, they can only achieve a rough classification of cell-types, and it is difficult to improve the recognition accuracy further. To effectively solve this issue we propose a novel supervised annotation method, scDeepInsight. The scDeepInsight method is capable of performing manifold assignments. It is competent in executing data integration through batch normalization, performing supervised training on the reference dataset, doing outlier detection and annotating cell-types on query datasets. Moreover, it can help identify active genes or marker genes related to cell-types. The training of the scDeepInsight model is performed in a unique way. Tabular scRNA-seq data are first converted to corresponding images through the DeepInsight methodology. DeepInsight can create a trainable image transformer to convert non-image RNA data to images by comprehensively comparing interrelationships among multiple genes. Subsequently, the converted images are fed into convolutional neural networks (CNNs) such as EfficientNet-b3. This enables automatic feature extraction to identify the cell-types of scRNA-seq samples. We benchmarked scDeepInsight with six other mainstream cell annotation methods. The average accuracy rate of scDeepInsight reached 87.5%, which is more than 7% higher compared with the state-of-the-art methods.

bioinformatics↗

bioRxiv2022

DeepInsight-3D for precision oncology: an improved anti-cancer drug response prediction from high-dimensional multi-omics data with convolutional neural networks

Modern oncology offers a wide range of treatments and therefore choosing the best option for particular patient is very important for optimal outcomes. Multi-omics profiling in combination with AI-based predictive models have great potential for streamlining these treatment decisions. However, these encouraging developments continue to be hampered by very high dimensionality of the datasets in combination with insufficiently large numbers of annotated samples. In this study, we propose a novel deep learning-based method to predict patient-specific anticancer drug response from three types of multiomics data. The proposed DeepInsight-3D approach relies on structured data-to-image conversion that then allows use of convolutional neural networks, which are particularly robust to high dimensionality of the inputs while retaining capabilities to model highly complex relationships between variables. Of particular note, we demonstrate that in this formalism additional channels of an image can be effectively used to accommodate data from different omics layers while explicitly encoding the connection between them. DeepInsight-3D was able to outperform two other state-of-the-art methods proposed for this task. These advances can facilitate the development of better personalized treatment strategies for different cancers in the future.

bioinformatics↗

bioRxiv2022

Splicing QTL analysis focusing on coding sequences reveals pathogenicity of disease susceptibility loci.

Splicing QTL (sQTL) are one of the major causal mechanisms in GWAS loci, but their role in disease pathogenesis is poorly understood. One reason is the huge complexity of alternative splicing events producing many unknown isoforms. Here, we proposed two novel approaches, namely integration and selection, for this complexity by focusing on protein-structure of isoforms. First, we integrated isoforms with the same coding sequence (CDS) and identified 369-601 integrated-isoform ratio QTLs (i2-rQTLs), which altered protein-structure, in six immune subsets. Second, we selected CDS incomplete isoforms annotated in GENCODE and identified 175-337 isoform-ratio QTL (i-rQTL). By comprehensive long-read capture RNA-seq among these incomplete isoforms, we revealed 29 full-length isoforms with novel CDSs associated with GWAS traits. Furthermore, we have shown that disease-causal sQTL genes can be identified by evaluating their trans-eQTL effects. Our approaches highlight the understudied role of protein-altering sQTLs and are broadly applicable to other tissues and diseases.

genetics↗

bioRxiv2021

A triple-negative matrix-producing breast carcinoma is arrested by tumor-targeting Salmonella typhimurium A1-R in a PDOX model

Background/AimMatrix-producing breast carcinoma (MPBC), is a rare, recalcitrant and highly aggressive. The present study aimed to determine the efficacy of tumor-targeting Salmonella typhimurium (S. typhimurium) A1-R on a triple-negative MPBC in a patient-derived orthotopic xenograft (PDOX) model. MethodsThe PDOX model was established in the left second mammary gland of a nude mouse by surgical orthotopic implantation (SOI) of the patient triple-negative MPBC PDOX models were randomized into two groups: G1, control group (n=6); G2, tumor-targeting S. typhimurium A1-R group (n=7, intravenous (i.v.) injection via tail vein, weekly, for two weeks). All mice were sacrificed on day 15. Tumor volume and body weight were measured one time per week. ResultsS. typhimurium A1-R arrested tumor growth compared to the control group (P = 0.016). ConclusionThe results of the present study suggest that S. typhimurium A1-R has future clinical potential in triple-negative MPBC patients.

cancer biology↗

bioRxiv2020

DeepInsight-FS: Selecting features for non-image data using convolutional neural network

Identifying smaller element or gene subsets from biological or other data types is an essential step in discovering underlying mechanisms. Statistical machine learning methods have played a key role in revealing gene subsets. However, growing data complexity is pushing the limits of these techniques. A review of the recent literature shows that arranging elements by similarity in image-form for a convolutional neural network (CNN) improves classification performance over treating them individually. Expanding on this, here we show a pipeline, DeepInsight-FS, to uncover gene subsets of clinical relevance. DeepInsight-FS converts non-image samples into image-form and performs element selection via CNN. To our knowledge, this is the first approach to employ CNN for element or gene selection on non-image data. A real world application of DeepInsight-FS to publicly available cancer data identified gene sets with significant overlap to several cancer-associated pathways suggesting the potential of this method to discover biomedically meaningful connections.

bioinformatics↗

bioRxiv2019

Systematic detection of Mendelian and non-Mendelian variants associated with retinitis pigmentosa by genome-wide association study

To uncover genetic basis of autosomal recessive retinitis pigmentosa (ARRP), we applied 2-step genome-wide association study (GWAS) in 640 Japanese patients prescreened with targeted re-sequencing. Meta-GWAS identified three independent peaks at P < 5.0x10-8, all within the major ARRP gene EYS. Two were each tagged by a low frequency variant (allele frequency < 0.05); a known founder Mendelian mutation (c.4957dupA, p.S1653Kfs*2) and a presumably hypomorphic non-synonymous variant (c.2528G>A, p.G843E). c.2528G>A newly solved 7.0% of Japanese ARRP cases, improving genetic diagnosis by 26.8% and simultaneously serving as a new attractive target for genome editing gene therapy. The third peak was tagged by an intronic common variant, representing a novel disease-susceptibility signal. GWAS successfully unraveled genetic causes of a rare "monogenic" disorder for the first time, which provided unexpected insights into significant contribution of non-Mendelian genetic factors and identified a novel high frequency variant directly linked to development of local genome therapeutics.

genetics↗

bioRxiv2019

Quantification of multicellular colonization in tumor metastasis using exome sequencing data

Metastasis is a major cause of cancer-related mortality, and it is essential to understand how metastasis occurs in order to overcome it. One relevant question is the origin of a metastatic tumor cell population. Although the hypothesis of a single-cell origin for metastasis from a primary tumor has long been prevalent, several recent studies using mouse models have supported a multi-cellular origin of metastasis. Human bulk whole-exome sequencing (WES) studies also have demonstrated a multiple clonal origin of metastasis, with different mutational compositions. Specifically, there has not yet been strong research to determine how many founder cells colonize a metastatic tumor. To address this question, we developed a method to quantify the founder cell population size in a metastasis using paired WES data from primary and metachronous metastatic tumors. Simulation studies demonstrated the proposed method gives unbiased results with sufficient accuracy in the range of realistic settings. Applying the proposed method to real WES data from four colorectal cancer patients, all samples supported a multi-cellular origin of metastasis and the founder size was quantified, ranging from 3 to 15 cells. Such a wide-ranging founder sizes estimated by the proposed method suggests that there are large variations in genetic similarity between primary and metastatic tumors in the same subjects, which might be involved in (dis)similarity of drug responses between tumors.

cancer biology↗