Biology subjects

Taguchi, Y.-h.

Publications and source records attributed to Taguchi, Y.-h..

At least 19 recordsLinked to original sources

bioRxiv2026

Novel two-stage deep learning-based approach applied to gene expression data pertaining to esophageal adenocarcinoma boosting biological knowledge discovery

Esophageal cancer (EC) is characterized by complex transcriptional alterations and therapeutic resistance, posing challenges for traditional computational methods. In this study, we propose a deep learning (DL)-based computational framework to identify important genes and biologically relevant pathways in bulk cell RNA-seq data (GSE234304 and GSE273848), which comprise tumor and non-tumor esophageal tissue samples. A fully connected feedforward neural network was trained for binary classification, and two feature selection strategies were implemented: Neural Network followed by Support Vector Regression (NN+SVR) and Integrated Gradients combined with SVR (IG+SVR). The genes were then ranked according to their weights in SVR deriving the importance scores, and the top 100 genes were subjected to enrichment analysis using Enrichr and Metascape. The proposed DL-based approaches identified a greater number of expressed genes across established esophageal cancer cell lines than LIMMA, SAM, and the t-test did. Specifically, in the GSE234304 dataset, IG + SVR, our best method, identified a total of 9 expressed genes while the best baseline method, LIMMA, identified a total of 3 expressed genes. In terms of GSE273848 dataset, IG + SVR was also the best identifying a total of 11 expressed genes while the best baseline method, t-test, had a total of 7 expressed genes. The key genes identified included CEBPB, SUMO1, RORA, STAT1, GATA, OCT1, RUNX1, and NR3C1, as well as pathways related to nucleoprotein maturation, collagen fibril organization, the immunoglobulin-mediated immune response, immune regulation, and insulin signaling. These results show that combining neural networks and attribution-based regression creates an effective and interpretable framework for selecting genes in esophageal cancer research.

bioinformatics↗

bioRxiv2026

Implicit Hierarchical Tensor Decomposition of Single-Cell Four-Omics Data Reveals Cell-Type-Associated Enhancer--Promoter Regulatory Programs

Single-cell multi-omics provides complementary views of gene regulation, but integrating modalities with natural features comprising enhancers, genes, and three-dimensional (3D) genomic loci remains challenging. This study developed an implicit hierarchical tensor decomposition framework and applied it to the CHARM single-cell four-omics mouse brain data (GSE303006) by jointly analyzing ATAC, H3K27ac, RNA, and reconstructed 3D enhancer--promoter (E--P) distances. After quality control, 730,969 E--P pairs, 42,669 enhancers, 16,239 genes, 391,435 20-kb bin pairs, and 4,258 cells were retained. Each modality was independently reduced to 20 components and mapped to an implicit 730,969x4, 258x20x4 tensor, which was decomposed without materializing the full array. All 12 distinct cell components represented among the 100 largest Tucker core elements showed greater cell-type effects than replicate effects (P=2.44 x 10-4, sign test). A representative core linked the Inh_Ndnf/Lamp5--Ex_L3/4_IT cell axis to contrasting presynaptic-transmission and developmental/morphogenetic E--P programs. Backprojection showed reproducible ATAC, H3K27ac, and 3D effects across three biological replicates, whereas module-level RNA effects were weaker. The framework reveals the regulatory structure that is shared across molecular modalities while remaining distinct from any single molecular modality.

bioinformatics↗

bioRxiv2026

Automatic Bevacizumab Response Prediction in Ovarian Cancer from Digital Pathology Images via Novel AI-based Computational Pipeline

Ovarian cancer is a gynecological cancer, which, if metastasized and not detected early, can cause death among women. Therefore, accurate prediction of drug responses to ovarian cancer is needed. A gynecological pathologist inspects abnormality in tissues and provides a report for patients; however, this diagnostic process (1) is difficult to undertake; (2) requires experience; and (3) is time-consuming. Moreover, existing tools are imperfect. Hence, we present a computational pipeline to improve predictions of drug response pertaining to ovarian cancer. First, we downloaded digital pathology images pertaining to ovarian responses to bevacizumab from the Cancer Imaging Archive Repository. We employed a histogram of oriented gradients for images, constructed feature vectors, and used Fishers linear discriminant analysis to alter data representations through dimensionality reduction. This reduced-dimensionality data was used for regression analysis, employing support vector regression coupled with various kernels and calculating the area under the ROC curve (AUC). Experimental results were validated using transformerbased models (ViT and Swin) and other deep learning (DL) models (VGG16, ResNet50, InceptionV3, MobileNetV2, and EfficientNetB6). Our approach using a radial kernel (named SVRD+R) improved AUC performance by 17% compared to the best-performing transformer-based model (ViT). Likewise, AUC performance improved by 14.9% when compared against the best DL-based model (MobileNetV2). These results demonstrate feasibility, showing that induced models via the presented AI-based pipeline can lead to superior performance when investigating prediction problems pertaining to gynecologic cancer studies. MSC92B05; 68T09

bioinformatics↗

bioRxiv2026

Novel Parameter-Free and Interpretable Integration of CITE-seq RNA and ADT Profiles via Tensor Decomposition-Based Unsupervised Feature Extraction

CITE-seq jointly profiles cellular transcripts and surface proteins, but RNA and ADT modalities differ markedly in dimensionality, sparsity, and noise characteristics. We applied tensor-decomposition-based unsupervised feature extraction to paired CITE-seq data by constructing a gene x cell x protein tensor and performing HOSVD. The proposed workflow does not require explicit RNA/ADT modality-weight tuning or prior HVG-based gene filtering, and it provides cell-mode singular vectors together with post hoc unsupervised gene selection. Across ImmGen T-cell CITE-seq datasets, TD-derived cell representations preserved cell-type-related local structure and showed competitive kNN-based consistency compared with scMoMaT, a related factorization-based reference. However, ADT-only embeddings and Seurat WNN graphs often showed higher cell-type neighborhood consistency, indicating that TD-based UFE should not be interpreted as a replacement for marker-based or graph-based cell-type analysis. Enrichment analysis of TD-selected genes supported their biological plausibility but was interpreted as an exploratory check rather than proof of complete marker recovery. These results position TD-based UFE as a lightweight tensor-based unsupervised feature extraction framework for paired RNA/ADT data, rather than as a universally superior CITE-seq integration method.

bioinformatics↗

bioRxiv2026

Novel 4D tensor decomposition-based approach integrating tri-omics profiling data can identify functionally relevant gene clusters

Understanding gene expression requires integrating multiple regulatory layers, because transcript abundance does not necessarily correspond to translational activity or protein abundance. Ribosome profiling and proteomics help distinguish increased translation from ribosome stacking or translational buffering, but no de facto standard framework exists for unsupervised integration of transcriptome, translatome, and proteome profiles. Here, we propose a four-dimensional tensor decomposition-based unsupervised feature extraction approach for tri-omics integration. We applied higher-order singular value decomposition to transcriptome, Ribo-seq, and proteome profiles measured under branched-chain amino acid starvation. The resulting singular value vectors captured relationships among the three omics layers, including a component consistent with ribosome stacking, where transcrip-tome and translatome signals increased while proteome signals decreased, and another consistent with translational buffering, where proteome variation was suppressed despite transcriptome and translatome changes. Gene selection identified 1,781 genes associated with ribosome stacking and 227 genes associated with translational buffering. Enrichment analyses linked the former to translation, post-translational protein modification, RNA polymerase II transcription, cell cycle regulation, endoplasmic reticulum protein processing, ubiquitin-mediated proteolysis, and stress-related pathways, and the latter to ribosome, translation elongation and termination, spliceosome, immune- and stress-related pathways, and ribosomopathy-associated diseases. Robustness analyses indicated that the results were not substantially affected by the duplicated proteome replicate or missing-value handling. Under the tested settings, comparison with MOFA+ and mixOmics suggested that our approach more directly extracted components interpretable as ribosome stacking and translational buffering. These results demonstrate that tensor decomposition-based unsupervised feature extraction is useful for identifying functionally relevant gene clusters from tri-omics data.

bioinformatics↗

bioRxiv2025

Somatostatin-expressing neurons regulate sleep deprivation and recovery

Background/ObjectivesWe re-analyzed publicly available gene expression profiles from the male mouse cortex under conditions of sleep deprivation (SD) using tensor decomposition-based unsupervised feature extraction, originally proposed by one of the authors in 2017. MethodsWe focused on two distinct expression patterns: genes whose levels were altered in SD and failed to normalize during recovery sleep (RS), and genes that overshot normal levels during RS. This selection excluded the expected "altered in SD and recovered in RS" pattern, which was not significantly observed. These two gene sets showed substantial overlap, but were still distinct from each other. ResultsThe analysis revealed that the selected gene sets were enriched in various brain regions, as evidenced through clustering in the Allen Brain Atlas. This suggests that the successful selection identified biologically meaningful genes. Furthermore, somatostatin (Sst)-expressing neuronal clusters were among the most highly enriched. ConclusionsGiven that sst is already implicated in SD and RS, our fully data driven transcriptomic analysis successfully identified the activity of sst during SD and RS. These findings reveal that Sst-expressing neurons may play a key role in SD. These results were further validated using AlphaGenome by uploading the selected genes to it.

bioinformatics↗

bioRxiv2025

De novo single-cell biological analysis of drug resistance in human melanoma through a novel deep learning-powered approach

Elucidating drug response mechanisms in human melanoma is crucial for improving treatment outcomes. Although scRNA-seq captures gene expression at the individual cell level, existing tools to gain deeper insights into a studied population pertaining to melanoma drug resistance are far from perfect. Therefore, we propose a deep learning (DL)-based approach to unveil molecular mechanisms underlying melanoma drug resistance as follows. First, we processed two single-cell datasets related to human melanoma from GEO (GSE108383_A375 and GSE108383_451Lu) database and trained a fully connected neural network with five adapted methods (L1-Regularization, DeepLIFT, SHAP, IG, LRP) to discriminate between BRAFi-resistant and parental cell lines, followed by identifying top 100 genes. Compared to existing bioinformatics tools from a biological perspective, the presented DL-based methods identified more expressed genes in four well-established melanoma cell lines, including MALME-3M, MDA-MB435, SK-MEL-28, and SK-MEL-5. Moreover, we identified FDA-approved melanoma drugs (e.g., Vemurafenib and Dabrafenib), critical genes such as ARAF, SOX10, DCT, AXL, and key TFs including MITF and TFAP2A. From a classification perspective, we provided gene sets by all methods to three machine learning algorithms, including support vector machine, random forests, and neural networks. Results demonstrate that Integrated gradients (IG) method adapted in our DL approach contributed to 2.2% and 0.5% overall performance improvements over the best-performing baselines when using A375 and 451Lu cell line datasets.

bioinformatics↗

bioRxiv2025

L1 GABAergic neurones in the frontal cortex and L6 glutamatergic neurones in the prefrontal cortex use RHO GTPase to differentiate between unconsciousness states

Unconsciousness can be induced by sleep and general anaesthesia alike; however, the extent to which these states differ is not well understood. In this study, we aimed to determine the similarities and differences between the unconscious states caused by sleep and those caused by anaesthesia, as well as investigate gene expression profiles by applying tensor decomposition-based unsupervised feature extraction to the two gene expression profiles. One of the two expression profiles was obtained from mice treated with sevoflurane, a type of inhaled anaesthesia, whereas the other two expression profiles were obtained from sleeping and awake mice. We selected two sets of genes (507 and 1048 genes) that were distinctly expressed between sleep- or anaesthesia-induced unconsciousness and the awake state. Both sets of genes include various distinct genes which are common to the state of unconsciousness during sleep and anaesthesia. The former was enriched in GABAergic synapses and the first layer of the frontal cortex, whereas the latter was enriched in glutamatergic synapses and the sixth layer of the prefrontal cortex. Additionally, both sets of genes were enriched in the RHO GTPase pathway. Based on these results, we hypothesised that L1 GABAergic neurons in the frontal cortex and L6 glutamatergic neurons in the prefrontal cortex use RHO GTPase to differentiate between the states of unconsciousness induced by general anaesthesia and sleep.

bioinformatics↗

bioRxiv2025

Gene and cell line efficiency of CRISPR computed by tensor decomposition in genome-wide CRISPR-Cas9 knockout screens

Genome-wide CRISPR-Cas9 knockout screens are often used to experimentally evaluate gene function. However, the efficacy of individual sgRNAs targeting unique genes varies and is difficult to integrate. In this study, tensor decomposition (TD) was used to integrate multiple sgRNAs and sgRNA profiles simultaneously. Thus, TD can discriminate between essential and non-essential genes with the performance comparative to that of Joint analysis of CRISPR/-Cas9 knockout screens (JACKS), a type of SOTA that previously outperformed various other SOTA. In addition, although TD uses simple linear algebra, it can achieve good performance even without control samples, without which JACKS cannot be performed. Moreover, because raw and logarithmic values can achieve similar performances through TD for the largest dataset among the tested datasets, taking logarithmic values as has been done frequently, which is questioned. In conclusion, TD is the first method that can integrate multiple sgRNAs attributed to single a target and sgRNA profiles at the beginning simultaneously and can achieve a performance comparable to that of JACKS.

bioinformatics↗

bioRxiv2025

Novel AI-based approach for cell type deconvolution in Visium datasets when reference scRNA-seqs include multiple minor cell types

We have applied tensor decomposition (TD)-based unsupervised feature extraction (FE) to integrate multiple Visium datasets, as a platform for spatial gene expression profiling (spatial transcriptomics). As a result, TD-based unsupervised FE successfully obtains singular value vectors consistent with the spatial distribution, that is, singular value vectors with similar values are assigned to neighboring spots. Furthermore, TD-based unsupervised FE successfully infers the cell-type fractions within individual Visium spots (i.e., successful deconvolution) by referencing single-cell RNA-seq experiments that include multiple minor cell types, for which other conventional methods--RCTD, SPOTlight, SpaCET, and cell2location--fail. Therefore, TD-based unsupervised FE can be used to perform deconvolution even when other conventional methods fail because it includes multiple minor cell types in the reference profiles, although it cannot be used in typical cases. TD-based unsupervised FE is thus expected to be applied to a wide range of deconvolution applications.

bioinformatics↗

bioRxiv2024

Novel AI-powered computational method using tensor decomposition can discover the common optimal bin sizes when integrating multiple Hi-C datasets

Identifying the optimal bin sizes (or resolutions) for the integration of multiple Hi-C datasets is a challenge due to the fact that bin sizes must be common over multiple datasets. By contrast, the dependence of quality upon bin sizes can vary from dataset to dataset. Moreover, common structures should not be sought in bin sizes smaller than the optimal bin sizes, below which common structure cannot be the primary structure any more even after increasing the number of mapped short reads per bin. In this case, there are no common structures at finer resolutions, suggesting that individual Hi-C datasets may have to be analyzed separately in the bin sizes smaller than the optimal one. Thus, quality assessments of individual datasets have a limited ability to determine the best bin size for all datasets. In this study, we propose a novel application of tensor decomposition (TD) based unsupervised feature extraction (FE) to choose the optimal bin sizes for the integration of multiple Hi-C datasets. TD-based unsupervised FE exhibit phase transition-like phenomena through which the smallest possible bin size (or the highest resolution) can be automatically estimated empirically, without the need to manually set a threshold value for the integration of multiple Hi-C datasets, retrieved from GEO with GEO ID, GSE260760 and GSE255264. To our knowledge, ours is the first one that can optimize bin sizes over multiple Hi-C profiles without any tunable parameters.

bioinformatics↗

bioRxiv2024

Novel artificial intelligence-based identification of drug-gene-disease interaction through using protein-protein interaction

The evaluation of drug-gene-disease interactions is key for the identification of drugs effective against disease. However, at present, drugs that are effective against genes that are critical for disease are difficult to identify. Following a disease-centric approach, there is a need to identify genes critical to disease function and find drugs that are effective against them. By contrast, following a drug-centric approach comprises identifying the genes targeted by drugs, and then the diseases in which the identified genes are critical. Both of these processes are complex. Using a gene-centric approach, whereby we identify genes that are effective against the disease and can be targeted by drugs, is much easier. However, how such sets of genes can be identified without specifying either the target diseases or drugs is not known. In this study, a novel artificial intelligencebased approach that employs unsupervised methods and identifies genes without specifying neither diseases nor drugs is presented. To evaluate its feasibility, we applied tensor decomposition (TD)-based unsupervised feature extraction (FE) to perform drug repositioning from protein-protein interactions (PPI) without any other information. Proteins selected by TD-based unsupervised FE include many genes related to cancers, as well as drugs that target the selected proteins. Thus, we were able to identify cancer drugs using only PPI. Because the selected proteins had more interactions, we replaced the selected proteins with hub proteins and found that hub proteins themselves could be used for drug repositioning. In contrast to hub proteins, which can only identify cancer drugs, TD-based unsupervised FE enables the identification of drugs for other diseases. In addition, TD-based unsupervised FE can be used to identify drugs that are effective in in vivo experiments, which is difficult when hub proteins are used. In conclusion, TD-based unsupervised FE is a useful tool for drug repositioning using only PPI without other information.

bioinformatics↗

bioRxiv2024

Novel Automatic Classification of Human Adult Lung Alveolar Type II Cells Infected with SARS-CoV-2 through Deep Transfer Learning Approach

SARS-CoV-2 can infect alveoli, inducing a lung injury and thereby impairing the lung function. Healthy alveolar type II (AT2) cells play a major role in lung injury repair as well as keeping alveoli space free from fluids, which is not the case for infected AT2 cells. Unlike previous studies, this novel study aims to automatically differentiate between healthy and infected AT2 cells with SARS-CoV-2 through using efficient AI-based models, which can aid in disease control and treatment. Therefore, we introduce a highly accurate deep transfer learning (DTL) approach that works as follows. First, we downloaded and processed 286 images pertaining to healthy and infected human AT2 (hAT2) cells, obtained from the electron microscopy public image archive. Second, we provided processed images to two DTL computations to induce ten DTL models. The first DTL computation employs five pre-trained models (including DenseNet201 and ResNet152V2) trained on more than million images from ImageNet database to extract features from hAT2 images. Then, flattening and providing the output feature vectors to a trained densely connected classifier with Adam optimizer. The second DTL computation works in a similar manner with a minor difference in which we freeze the first layers for feature extraction in pre-trained models while unfreezing and training the next layers. Compared to TFtDenseNet201, experimental results using five-fold cross-validation demonstrate that TFeDenseNet201 is 12.37 x faster and superior, yielding the highest average ACC of 0.993 (F1 of 0.992 and MCC of 0.986) with statistical significance (p < 2.2 x 10-16 from a t-test).

bioinformatics↗

bioRxiv2024

Analysis of Methicillin Resistance in Staphylococcus Aureus Sepsis Using TDbasedUFE

scATAC-seq explains chromatin accessibility at cell-type resolution. Accordingly, this process is crucial for advancing our understanding of pathology and disease states. However, annotated data from scATAC-seq are both extensive and sparse; thus, conducting multidimensional analyses under multiple conditions is a challenging task. TDbasedUFE is a valuable tool for analyzing scATAC-seq data as it can extract genes in an unsupervised manner under multiple conditions based on tensor decomposition. We analyzed scATAC-seq data from the peripheral blood mononuclear cells of patients with sepsis infected with S. aureus using TDbasedUFE. We extracted genes that exhibited different responses in methicillin-resistant (MSSA) and methicillin-sensitive S. aureus (MSSA) strains in sepsis for each cell type. Subsequently, we searched for studies containing gene sets similar to the extracted genes and predicted their functions. We also constructed protein-protein interactions (PPIs) for the extracted genes, defined hub proteins as central to the interactions based on degrees and clustering coefficients, and investigated the functions of these hub proteins. The genes of interest were abundant across all cell types, ranging from 710 to 1,372 genes. The functions of the extracted genes were predicted to be associated with several diseases or physiological substances. The hub proteins identified from the PPI analysis were mainly related to the ribosome, and their functions were associated with protein synthesis. These results highlight the suitability of TDbasedUFE for the analysis of scATAC-seq data. The functions of the genes identified in this study may provide insights into new promising therapeutic approaches, considering the distinction between methicillin resistance and S. aureus sepsis.

bioinformatics↗

bioRxiv2023

maGENEgerZ: An Efficient AI-Based Framework Can Extract More Expressed Genes and Biological Insights Underlying Breast Cancer Drug Response Mechanism

Understanding breast cancer drug response mechanism can play a crucial role in improving the treatment outcomes and survival rates. Existing bioinformatics-based approaches are far from perfect and do not adopt computational methods based on advanced artificial intelligence concepts. Therefore, we introduce a novel computational framework based on an efficient support vector machines (esvm) working as follows. First, we downloaded and processed three gene expression datasets related to breast cancer responding and non-responding to the treatments from the gene expression omnibus (GEO) according to the following GEO accession numbers: GSE130787, GSE140494, and GSE196093. Our method esvm is formulated as a constrained optimization problem in the dual form as a function of {lambda}. We recover the importance of each gene as a function of {lambda}, y, and x. Then, we select p genes out of n, provided as input to enrichment analysis tools, Enrichr and Metascape. Compared to existing baseline methods including deep learning, results demonstrate superiority and efficiency of esvm achieving high performance results and having more expressed genes in well-established breast cancer cell lines including MD-MB231, MCF7, and HS578T. Moreover, esvm is able to identify (1) various drugs including clinically approved ones (e.g., tamoxifen and erlotinib); (2) seventy-four unique genes (including tumor suppression genes such as TP53 and BRCA1); and (3) thirty-six unique TFs (including SP1 and RELA). These results have been reported to be linked to breast cancer drug response mechanism, progression, and metastasizing. Our method is available publicly in the maGENEgerZ web server at https://aibio.shinyapps.io/maGENEgerZ/.

bioinformatics↗

bioRxiv2023

TDbasedUFE and TDbasedUFEadv: bioconductor packages to perform tensor decomposition based unsupervised feature extraction

MotivationTensor decomposition (TD) based unsupervised feature extraction (FE) was proposed almost five years ago and has been successfully applied to a wide range of bioinformatics problems ranging from biomarker identification to the identification of disease-causing genes and drug repositioning. Despite its successful applications, the use of TD-based unsupervised FE was not widely accepted because of the unpopularity of TD in this field. ResultsTo overcome this difficulty, we developed two bioconductor packages, TDbasedUFE and TDbasedUFEadv. Using these two packages, all researchers who are not familiar with the concept of TD can make use of TD-based unsupervised FE for their purposes. When the performances of two specific functions, identification of differentially expressed genes and multiomics analysis, are implemented in TDbasedUFE and compared with those of two state-of-the-art (SOTA) methods (i.e., DESeq2 and DIABLO), TDbasedUFE can outperform these two SOTAs. Availability and implementationTDbasedUFE and TDbasedUFEadv are freely available as R/Bioconductor packages hosted at https://bioconductor.org/packages/TDbasedUFE and https://bioconductor.org/packages/TDbasedUFEadv, respectively.

bioinformatics↗

bioRxiv2023

Advanced tensor decomposition-based integrated analysis of protein-protein interaction with cancer gene expression can improve coincidence with clinical labels

MotivationIntegration of gene expression (GE) and protein-protein interaction (PPI) is not straightforward because the former is provided as a matrix, whereas the latter is provided as a network. In many cases, genes processed with GE analysis are refined further based on a PPI network or vice versa. This is hardly regarded as a true integration of GE and PPI. To address this problem, we proposed a tensor decomposition (TD) based method that can integrate GE and PPI prior to any analyses where PPI is also formatted as a matrix to which singular value decomposition (SVD) is applied. ResultsIntegrated analyses with TD improved the coincidence between vectors attributed to samples and class labels over 27 cancer types retrieved from The Cancer Genome Atlas Program (TCGA) toward five class labels. Enrichment using genes selected with this strategy were also improved with the integration using TD. The PPI network associated with the information on the strength of the PPI can improve the performance than PPI that stores only if the interaction exists in individual pairs. In addition, even restricting genes to the intersection of GE and PPI can improve coincidence and enrichment. Availability and implementationThe R source code used to perform this analyses is in the supplementary file.

bioinformatics↗

bioRxiv2023

GENEvaRX: A Novel AI-Driven Method and Web Tool Can Identify Critical Genes and Effective Drugs for Lichen Planus

Lichen planus (LP) is an autoimmune disorder diagnosed based on physical symptoms and lab tests. Examples of symptoms include flat bumps, and itchy and purplish skin, while lab tests include a shave biopsy of the lesion. When the pathology report shows consistency with LP and is negative for potential triggers for an allergy test and hepatitis C, a dermatologist typically prescribes corticosteroid in the form of pills or injection into the lesion to treat the symptoms. To understand the molecular mechanism of the disease and thereby overcome issues associated with disease treatment, there is a need to identify potential effective drugs, drug targets, and therapeutic targets associated the LP. Hence, we propose a novel computational framework based on new constrained optimization to support vector machines coupled with enrichment analysis. First, we downloaded three gene expression datasets (GSE63741, GSE193351, GSE52130) pertaining to healthy and LP patients from the gene expression omnibus (GEO) database. We then processed each dataset and entered it into our computational framework to select important genes. Finally, we performed enrichment analysis of selected genes, reporting the following results. Our methods outperformed baseline methods in terms of identifying disease and skin tissue. Moreover, we report 5 drugs (including, dexamethasone, retinoic acid, and quercetin), 45 unique genes (including PSMB8, KRT31, KRT16, KRT19, KRT17, COL3A1, LCE2D, LCE2A), and 23 unique TFs (including NFKB1, STAT1, STAT3) reportedly related to LP pathogenesis, treatments, and therapeutic targets. Our methods are publicly available in the GENEvaRX web server at https://aibio.shinyapps.io/GENEvaRX/.

bioinformatics↗