SPIN: sex-specific and pathway-based interpretable neural network for sexual dimorphism analysis.

Sexual dimorphism in prevalence, severity and genetic susceptibility exists for most common diseases. However, most genetic and clinical outcome studies are designed in sex-combined framework considering sex as a covariate. Few sex-specific studies have analyzed males and females separately, which failed to identify gene-by-sex interaction. Here, we propose a novel unified biologically interpretable deep learning-based framework (named SPIN) for sexual dimorphism analysis. We demonstrate that SPIN significantly improved the C-index up to 23.6% in TCGA cancer datasets, and it was further validated using asthma datasets. In addition, SPIN identifies sex-specific and -shared risk loci that are often missed in previous sex-combined/-separate analysis. We also show that SPIN is interpretable for explaining how biological pathways contribute to sexual dimorphism and improve risk prediction in an individual level, which can result in the development of precision medicine tailored to a specific individual's characteristics.

Evidential deep learning for trustworthy prediction of enzyme commission number.

The rapid growth of uncharacterized enzymes and their functional diversity urge accurate and trustworthy computational functional annotation tools. However, current state-of-the-art models lack trustworthiness on the prediction of the multilabel classification problem with thousands of classes. Here, we demonstrate that a novel evidential deep learning model (named ECPICK) makes trustworthy predictions of enzyme commission (EC) numbers with data-driven domain-relevant evidence, which results in significantly enhanced predictive power and the capability to discover potential new motif sites. ECPICK learns complex sequential patterns of amino acids and their hierarchical structures from 20 million enzyme data. ECPICK identifies significant amino acids that contribute to the prediction without multiple sequence alignment. Our intensive assessment showed not only outstanding enhancement of predictive performance on the largest databases of Uniprot, Protein Data Bank (PDB) and Kyoto Encyclopedia of Genes and Genomes (KEGG), but also a capability to discover new motif sites in microorganisms. ECPICK is a reliable EC number prediction tool to identify protein functions of an increasing number of uncharacterized enzymes.

A roadmap for multi-omics data integration using deep learning.

High-throughput next-generation sequencing now makes it possible to generate a vast amount of multi-omics data for various applications. These data have revolutionized biomedical research by providing a more comprehensive understanding of the biological systems and molecular mechanisms of disease development. Recently, deep learning (DL) algorithms have become one of the most promising methods in multi-omics data analysis, due to their predictive performance and capability of capturing nonlinear and hierarchical features. While integrating and translating multi-omics data into useful functional insights remain the biggest bottleneck, there is a clear trend towards incorporating multi-omics analysis in biomedical research to help explain the complex relationships between molecular layers. Multi-omics data have a role to improve prevention, early detection and prediction; monitor progression; interpret patterns and endotyping; and design personalized treatments. In this review, we outline a roadmap of multi-omics integration using DL and offer a practical perspective into the advantages, challenges and barriers to the implementation of DL in multi-omics data.

Cryptic mutations of PLC family members in brain disorders: recent discoveries and a deep-learning-based approach.

Phospholipase C (PLC) is an essential isozyme involved in the phosphoinositide signalling pathway, which maintains cellular homeostasis. Gain- and loss-of-function mutations in PLC affect enzymatic activity and are therefore associated with several disorders. Alternative splicing variants of PLC can interfere with complex signalling networks associated with oncogenic transformation and other diseases, including brain disorders. Cells and tissues with various mutations in PLC contribute different phosphoinositide signalling pathways and disease progression, however, identifying cryptic mutations in PLC remains challenging. Herein, we review both the mechanisms underlying PLC regulation of the phosphoinositide signalling pathway and the genetic variation of PLC in several brain disorders. In addition, we discuss the present challenges associated with the potential of deep-learning-based analysis for the identification of PLC mutations in brain disorders.

Prediction of Alzheimer's disease-specific phospholipase c gamma-1 SNV by deep learning-based approach for high-throughput screening.

Exon splicing triggered by unpredicted genetic mutation can cause translational variations in neurodegenerative disorders. In this study, we discover Alzheimer's disease (AD)-specific single-nucleotide variants (SNVs) and abnormal exon splicing of phospholipase c gamma-1 (PLCγ1) gene, using genome-wide association study (GWAS) and a deep learning-based exon splicing prediction tool. GWAS revealed that the identified single-nucleotide variations were mainly distributed in the H3K27ac-enriched region of PLCγ1 gene body during brain development in an AD mouse model. A deep learning analysis, trained with human genome sequences, predicted 14 splicing sites in human PLCγ1 gene, and one of these completely matched with an SNV in exon 27 of PLCγ1 gene in an AD mouse model. In particular, the SNV in exon 27 of PLCγ1 gene is associated with abnormal splicing during messenger RNA maturation. Taken together, our findings suggest that this approach, which combines in silico and deep learning-based analyses, has potential for identifying the clinical utility of critical SNVs in AD prediction.

PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma.

MOTIVATION: Convolutional neural networks (CNNs) have achieved great success in the areas of image processing and computer vision, handling grid-structured inputs and efficiently capturing local dependencies through multiple levels of abstraction. However, a lack of interpretability remains a key barrier to the adoption of deep neural networks, particularly in predictive modeling of disease outcomes. Moreover, because biological array data are generally represented in a non-grid structured format, CNNs cannot be applied directly. RESULTS: To address these issues, we propose a novel method, called PathCNN, that constructs an interpretable CNN model on integrated multi-omics data using a newly defined pathway image. PathCNN showed promising predictive performance in differentiating between long-term survival (LTS) and non-LTS when applied to glioblastoma multiforme (GBM). The adoption of a visualization tool coupled with statistical analysis enabled the identification of plausible pathways associated with survival in GBM. In summary, PathCNN demonstrates that CNNs can be effectively applied to multi-omics data in an interpretable manner, resulting in promising predictive power while identifying key biological correlates of disease. AVAILABILITY AND IMPLEMENTATION: The source code is freely available at: https://github.com/mskspi/PathCNN.

Editorial of Special Issue "Deep Learning and Machine Learning in Bioinformatics".

In recent years, deep learning has emerged as a highly active research field, achieving great success in various machine learning areas, including image processing, speech recognition, and natural language processing, and now rapidly becoming a dominant tool in biomedicine [...].

Deep-Hipo: Multi-scale receptive field deep learning for histopathological image analysis.

Digitizing whole-slide imaging in digital pathology has led to the advancement of computer-aided tissue examination using machine learning techniques, especially convolutional neural networks. A number of convolutional neural network-based methodologies have been proposed to accurately analyze histopathological images for cancer detection, risk prediction, and cancer subtype classification. Most existing methods have conducted patch-based examinations, due to the extremely large size of histopathological images. However, patches of a small window often do not contain sufficient information or patterns for the tasks of interest. It corresponds that pathologists also examine tissues at various magnification levels, while checking complex morphological patterns in a microscope. We propose a novel multi-task based deep learning model for HIstoPatholOgy (named Deep-Hipo) that takes multi-scale patches simultaneously for accurate histopathological image analysis. Deep-Hipo extracts two patches of the same size in both high and low magnification levels, and captures complex morphological patterns in both large and small receptive fields of a whole-slide image. Deep-Hipo has outperformed the current state-of-the-art deep learning methods. We assessed the proposed method in various types of whole-slide images of the stomach: well-differentiated, moderately-differentiated, and poorly-differentiated adenocarcinoma; poorly cohesive carcinoma, including signet-ring cell features; and normal gastric mucosa. The optimally trained model was also applied to histopathological images of The Cancer Genome Atlas (TCGA), Stomach Adenocarcinoma (TCGA-STAD) and TCGA Colon Adenocarcinoma (TCGA-COAD), which show similar pathological patterns with gastric carcinoma, and the experimental results were clinically verified by a pathologist. The source code of Deep-Hipo is publicly available athttp://dataxlab.org/deep-hipo.

Pathway-based deep clustering for molecular subtyping of cancer.

Cancer is a genetic disease comprising multiple subtypes that have distinct molecular characteristics and clinical features. Cancer subtyping helps in improving personalized treatment and making decision, as different cancer subtypes respond differently to the treatment. The increasing availability of cancer related genomic data provides the opportunity to identify molecular subtypes. Several unsupervised machine learning techniques have been applied on molecular data of the tumor samples to identify cancer subtypes that are genetically and clinically distinct. However, most clustering methods often fail to efficiently cluster patients due to the challenges imposed by high-throughput genomic data and its non-linearity. In this paper, we propose a pathway-based deep clustering method (PACL) for molecular subtyping of cancer, which incorporates gene expression and biological pathway database to group patients into cancer subtypes. The main contribution of our model is to discover high-level representations of biological data by learning complex hierarchical and nonlinear effects of pathways. We compared the performance of our model with a number of benchmark clustering methods that recently have been proposed in cancer subtypes. We assessed the hypothesis that clusters (subtypes) may be associated to different survivals by logrank tests. PACL showed the lowest p-value of the logrank test against the benchmark methods. It demonstrates the patient groups clustered by PACL may correspond to subtypes which are significantly associated with distinct survival distributions. Moreover, PACL provides a solution to comprehensively identify subtypes and interpret the model in the biological pathway level. The open-source software of PACL in PyTorch is publicly available at https://github.com/tmallava/PACL.

PASNet: pathway-associated sparse deep neural network for prognosis prediction from high-throughput data.

BACKGROUND: Predicting prognosis in patients from large-scale genomic data is a fundamentally challenging problem in genomic medicine. However, the prognosis still remains poor in many diseases. The poor prognosis may be caused by high complexity of biological systems, where multiple biological components and their hierarchical relationships are involved. Moreover, it is challenging to develop robust computational solutions with high-dimension, low-sample size data. RESULTS: In this study, we propose a Pathway-Associated Sparse Deep Neural Network (PASNet) that not only predicts patients' prognoses but also describes complex biological processes regarding biological pathways for prognosis. PASNet models a multilayered, hierarchical biological system of genes and pathways to predict clinical outcomes by leveraging deep learning. The sparse solution of PASNet provides the capability of model interpretability that most conventional fully-connected neural networks lack. We applied PASNet for long-term survival prediction in Glioblastoma multiforme (GBM), which is a primary brain cancer that shows poor prognostic performance. The predictive performance of PASNet was evaluated with multiple cross-validation experiments. PASNet showed a higher Area Under the Curve (AUC) and F1-score than previous long-term survival prediction classifiers, and the significance of PASNet's performance was assessed by Wilcoxon signed-rank test. Furthermore, the biological pathways, found in PASNet, were referred to as significant pathways in GBM in previous biology and medicine research. CONCLUSIONS: PASNet can describe the different biological systems of clinical outcomes for prognostic prediction as well as predicting prognosis more accurately than the current state-of-the-art methods. PASNet is the first pathway-based deep neural network that represents hierarchical representations of genes and pathways and their nonlinear effects, to the best of our knowledge. Additionally, PASNet would be promising due to its flexible model representation and interpretability, embodying the strengths of deep learning. The open-source code of PASNet is available at https://github.com/DataX-JieHao/PASNet .

A copy number variation in PKD1L2 is associated with colorectal cancer predisposition in korean population.

Recently reported genome-wide association studies have identified more than 20 common low-penetrance colorectal cancer (CRC) susceptibility loci. Recent studies have reported that copy number variations (CNVs) are considered important human genomic variants related to cancer, while the contribution of CNVs remains unclear. We performed array comparative genomic hybridization (aCGH) in 36 CRC patients and 47 controls. Using breakpoint PCR, we confirmed the breakpoint of the PKD1L2 deletion region. High frequency of PKD1L2 CNV was observed in CRC cases. We validated the association between PKD1L2 variation and CRC risk in 1,874 cases and 2,088 controls (OR = 1.44, 95% CI = 1.04-1.98, p = 0.028). Additionally, PKD1L2 CNV is associated with increased CRC risk in patients younger than 50 years (OR = 2.14, 95% CI 1.39-3.30, p = 5.8 × 10-4 ). In subgroup analysis according to body mass index (BMI), we found that the CN loss of PKD1L2 with BMI above or equal to 25 exhibited a significant increase in CRC risk (OR = 2.29, 95% CI 1.29-4.05, p = 0.005). PKD1L2 CNV with BMI above or equal to 25 and age below 50 is associated with a remarkably increased risk of colorectal cancer (OR = 5.24, 95% CI 2.36-11.64, p= 4.8 × 10-5 ). Moreover, we found that PKD1L2 variation in obese patients (BMI ≥ 25) was associated with poor survival rate (p = 0.026). Our results suggest that the common PKD1L2 CNV is associated with CRC, and PKD1L2 CNV with high BMI and/or age below 50 exhibited a significant increased risk of CRC. In obese patients, PKD1L2 variation was associated with poor survival.

Cascade Classification with Adaptive Feature Extraction for Arrhythmia Detection.

Detecting arrhythmia from ECG data is now feasible on mobile devices, but in this environment it is necessary to trade computational efficiency against accuracy. We propose an adaptive strategy for feature extraction that only considers normalized beat morphology features when running in a resource-constrained environment; but in a high-performance environment it takes account of a wider range of ECG features. This process is augmented by a cascaded random forest classifier. Experiments on data from the MIT-BIH Arrhythmia Database showed classification accuracies from 96.59% to 98.51%, which are comparable to state-of-the art methods.

Computational modeling of phagocyte transmigration for foreign body responses to subcutaneous biomaterial implants in mice.

BACKGROUND: Computational modeling and simulation play an important role in analyzing the behavior of complex biological systems in response to the implantation of biomedical devices. Quantitative computational modeling discloses the nature of foreign body responses. Such understanding will shed insight on the cause of foreign body responses, which will lead to improved biomaterial design and will reduce foreign body reactions. One of the major obstacles in computational modeling is to build a mathematical model that represents the biological system and to quantitatively define the model parameters. RESULTS: In this paper, we considered quantitative inter connections and logical relationships among diverse proteins and cells, which have been reported in biological experiments and literature. Based on the established biological discovery, we have built a mathematical model while unveiling the key components that contribute to biomaterial-mediated inflammatory responses. For the parameter estimation of the mathematical model, we proposed a global optimization algorithm, called Discrete Selection Levenberg-Marquardt (DSLM). This is an extension of Levenberg-Marquardt (LM) algorithm which is a gradient-based local optimization algorithm. The proposed DSLM suggests a new approach for the selection of optimal parameters in the discrete space with fast computational convergence. CONCLUSIONS: The computational modeling not only provides critical clues to recognize current knowledge of fibrosis development but also enables the prediction of yet-to-be observed biological phenomena.

eQTL epistasis: detecting epistatic effects and inferring hierarchical relationships of genes in biological pathways.

MOTIVATION: Epistasis is the interactions among multiple genetic variants. It has emerged to explain the 'missing heritability' that a marginal genetic effect does not account for by genome-wide association studies, and also to understand the hierarchical relationships between genes in the genetic pathways. The Fisher's geometric model is common in detecting the epistatic effects. However, despite the substantial successes of many studies with the model, it often fails to discover the functional dependence between genes in an epistasis study, which is an important role in inferring hierarchical relationships of genes in the biological pathway. RESULTS: We justify the imperfectness of Fisher's model in the simulation study and its application to the biological data. Then, we propose a novel generic epistasis model that provides a flexible solution for various biological putative epistatic models in practice. The proposed method enables one to efficiently characterize the functional dependence between genes. Moreover, we suggest a statistical strategy for determining a recessive or dominant link among epistatic expression quantitative trait locus to enable the ability to infer the hierarchical relationships. The proposed method is assessed by simulation experiments of various settings and is applied to human brain data regarding schizophrenia. AVAILABILITY AND IMPLEMENTATION: The MATLAB source codes are publicly available at: http://biomecis.uta.edu/epistasis.

Molecular insights into regulatory RNAs in the cellular machinery.

It is apparent that various functional units within the cellular machinery are derived from RNAs. The evolution of sequencing techniques has resulted in significant insights into approaches for transcriptome studies. Organisms utilize RNA to govern cellular systems, and a heterogeneous class of RNAs is involved in regulatory functions. In particular, regulatory RNAs are increasingly recognized to participate in intricately functioning machinery across almost all levels of biological systems. These systems include those mediating chromatin arrangement, transcription, suborganelle stabilization, and posttranscriptional modifications. Any class of RNA exhibiting regulatory activity can be termed a class of regulatory RNA and is typically represented by noncoding RNAs, which constitute a substantial portion of the genome. These RNAs function based on the principle of structural changes through cis and/or trans regulation to facilitate mutual RNA‒RNA, RNA‒DNA, and RNA‒protein interactions. It has not been clearly elucidated whether regulatory RNAs identified through deep sequencing actually function in the anticipated mechanisms. This review addresses the dominant properties of regulatory RNAs at various layers of the cellular machinery and covers regulatory activities, structural dynamics, modifications, associated molecules, and further challenges related to therapeutics and deep learning.

Trends of emergency department visits for cannabinoid hyperemesis syndrome in Nevada: An interrupted time series analysis.

Cannabis-related emergency department visits have increased after legalization of cannabis for medical and recreational use. Accordingly, the incidence of emergency department visits due to cannabinoid hyperemesis syndrome in patients with chronic cannabis use has also increased. The aim of this study was to examine trends of emergency department visit due to cannabinoid hyperemesis syndrome in Nevada and evaluate factors associated with the increased risk for emergency department visit. The State Emergency Department Databases of Nevada between 2013 and 2021 were used for investigating trends of emergency department visits for cannabinoid hyperemesis syndrome. We compared patients visiting the emergency department due to cannabinoid hyperemesis syndrome with those visiting the emergency department due to other causes except cannabinoid hyperemesis and estimated the impact of cannabis commercialization for recreational use. Emergency department visits due to cannabinoid hyperemesis syndrome have continuously increased during the study period. The number of emergency department visits per 100,000 was 1.07 before commercialization for recreational use. It increased to 2.22 per 100,000 (by approximately 1.1 per 100,000) after commercialization in the third quarter of 2017. Those with cannabinoid hyperemesis syndrome were younger with fewer male patients than those without cannabinoid hyperemesis syndrome. A substantial increase in emergency department visits due to cannabinoid hyperemesis syndrome occurred in Nevada, especially after the commercialization of recreational cannabis. Further study is needed to explore factors associated with emergency department visits.

Harnessing deep learning into hidden mutations of neurological disorders for therapeutic challenges.

The relevant study of transcriptome-wide variations and neurological disorders in the evolved field of genomic data science is on the rise. Deep learning has been highlighted utilizing algorithms on massive amounts of data in a human-like manner, and is expected to predict the dependency or druggability of hidden mutations within the genome. Enormous mutational variants in coding and noncoding transcripts have been discovered along the genome by far, despite of the fine-tuned genetic proofreading machinery. These variants could be capable of inducing various pathological conditions, including neurological disorders, which require lifelong care. Several limitations and questions emerge, including the use of conventional processes via limited patient-driven sequence acquisitions and decoding-based inferences as well as how rare variants can be deduced as a population-specific etiology. These puzzles require harnessing of advanced systems for precise disease prediction, drug development and drug applications. In this review, we summarize the pathophysiological discoveries of pathogenic variants in both coding and noncoding transcripts in neurological disorders, and the current advantage of deep learning applications. In addition, we discuss the challenges encountered and how to outperform them with advancing interpretation.

Opioid Utility and Hospital Outcomes Among Inpatients Admitted With Osteoarthritis and Spine Disorders.

OBJECTIVE: The aim of the study is to evaluate opioid analgesic utilization and predictors for adverse events during hospitalization and discharge disposition among patients admitted with osteoarthritis or spine disorders. DESIGN: This is a retrospective study of 12,747 adult patients admitted to six private community hospitals from 2017 to 2020. Opioid use during hospitalization and risk factors for hospital-acquired adverse events and nonhome discharge were investigated. RESULTS: The total number of patients using opioids decreased; however, the daily morphine milligram equivalent use for patients on opioids increased from 2017 to 2020. Increased odds of nonhome discharge were associated with older age, Medicaid, Medicare insurance, and increased lengths of stay, increased body mass index, daily morphine milligram equivalent, and electrolyte replacement in the osteoarthritis group. In the spine group, older age, Black race, Medicaid, Medicare, no insurance, increased Charlson Comorbidity Index, lengths of stay, polypharmacy, and heparin use were associated with nonhome discharge. Adverse events were associated with increased age, lengths of stay, Medicare, polypharmacy, antiemetic, and benzodiazepine use in the osteoarthritis group and increased Charlson Comorbidity Index, lengths of stay, and electrolyte replacement in the spine group. CONCLUSIONS: Despite the decreasing number of patients using opioids over the years, patients on opioids had an increased daily morphine milligram equivalent over the same period.

Racial and Ethnic Disparity in 4Ms among Older Adults Among Telehealth Users as Primary Care.

Telehealth has been widely accepted as an alternative to in-person primary care. This study examines whether the quality of primary care delivered via telehealth is equitable for older adults across racial and ethnic boundaries in provider-shortage urban settings. The study analyzed documentation of the 4Ms components (What Matters, Mobility, Medication, and Mentation) in relation to self-reported racial and ethnic backgrounds of 254 Medicare Advantage enrollees who used telehealth as their primary care modality in Southern Nevada from July 2021 through June 2022. Results revealed that Asian/Hawaiian/Pacific Islanders had significantly less documentation in What Matters (OR = 0.39, 95%, p = .04) and Blacks had significantly less documentation in Mobility (OR = 0.35, p < .001) compared to their White counterparts. The Hispanic ethnic group had less documentation in What Matters (OR = 0.18, p < .001) compared to non-Hispanic ethnic groups. Our study reveals equipping the geriatrics workforce merely with the 4Ms framework may not be sufficient in mitigating unconscious biases healthcare providers exhibit in the telehealth primary care setting in a provider shortage area, and, by extrapolation, in other care settings across the spectra, whether they be in-person or virtual.