Integrating spatial transcriptomics and bulk RNA-seq: predicting gene expression with enhanced resolution through graph attention networks.

Spatial transcriptomics data play a crucial role in cancer research, providing a nuanced understanding of the spatial organization of gene expression within tumor tissues. Unraveling the spatial dynamics of gene expression can unveil key insights into tumor heterogeneity and aid in identifying potential therapeutic targets. However, in many large-scale cancer studies, spatial transcriptomics data are limited, with bulk RNA-seq and corresponding Whole Slide Image (WSI) data being more common (e.g. TCGA project). To address this gap, there is a critical need to develop methodologies that can estimate gene expression at near-cell (spot) level resolution from existing WSI and bulk RNA-seq data. This approach is essential for reanalyzing expansive cohort studies and uncovering novel biomarkers that have been overlooked in the initial assessments. In this study, we present STGAT (Spatial Transcriptomics Graph Attention Network), a novel approach leveraging Graph Attention Networks (GAT) to discern spatial dependencies among spots. Trained on spatial transcriptomics data, STGAT is designed to estimate gene expression profiles at spot-level resolution and predict whether each spot represents tumor or non-tumor tissue, especially in patient samples where only WSI and bulk RNA-seq data are available. Comprehensive tests on two breast cancer spatial transcriptomics datasets demonstrated that STGAT outperformed existing methods in accurately predicting gene expression. Further analyses using the TCGA breast cancer dataset revealed that gene expression estimated from tumor-only spots (predicted by STGAT) provides more accurate molecular signatures for breast cancer sub-type and tumor stage prediction, and also leading to improved patient survival and disease-free analysis. Availability: Code is available at https://github.com/compbiolabucf/STGAT.

Incomplete time-series gene expression in integrative study for islet autoimmunity prediction.

Type 1 diabetes (T1D) outcome prediction plays a vital role in identifying novel risk factors, ensuring early patient care and designing cohort studies. TEDDY is a longitudinal cohort study that collects a vast amount of multi-omics and clinical data from its participants to explore the progression and markers of T1D. However, missing data in the omics profiles make the outcome prediction a difficult task. TEDDY collected time series gene expression for less than 6% of enrolled participants. Additionally, for the participants whose gene expressions are collected, 79% time steps are missing. This study introduces an advanced bioinformatics framework for gene expression imputation and islet autoimmunity (IA) prediction. The imputation model generates synthetic data for participants with partially or entirely missing gene expression. The prediction model integrates the synthetic gene expression with other risk factors to achieve better predictive performance. Comprehensive experiments on TEDDY datasets show that: (1) Our pipeline can effectively integrate synthetic gene expression with family history, HLA genotype and SNPs to better predict IA status at 2 years (sensitivity 0.622, AUC 0.715) compared with the individual datasets and state-of-the-art results in the literature (AUC 0.682). (2) The synthetic gene expression contains predictive signals as strong as the true gene expression, reducing reliance on expensive and long-term longitudinal data collection. (3) Time series gene expression is crucial to the proposed improvement and shows significantly better predictive ability than cross-sectional gene expression. (4) Our pipeline is robust to limited data availability. Availability: Code is available at https://github.com/compbiolabucf/TEDDY.

Fractal feature selection model for enhancing high-dimensional biological problems.

The integration of biology, computer science, and statistics has given rise to the interdisciplinary field of bioinformatics, which aims to decode biological intricacies. It produces extensive and diverse features, presenting an enormous challenge in classifying bioinformatic problems. Therefore, an intelligent bioinformatics classification system must select the most relevant features to enhance machine learning performance. This paper proposes a feature selection model based on the fractal concept to improve the performance of intelligent systems in classifying high-dimensional biological problems. The proposed fractal feature selection (FFS) model divides features into blocks, measures the similarity between blocks using root mean square error (RMSE), and determines the importance of features based on low RMSE. The proposed FFS is tested and evaluated over ten high-dimensional bioinformatics datasets. The experiment results showed that the model significantly improved machine learning accuracy. The average accuracy rate was 79% with full features in machine learning algorithms, while FFS delivered promising results with an accuracy rate of 94%.

In silico model for miRNA-mediated regulatory network in cancer.

Deregulation of gene expression is associated with the pathogenesis of numerous human diseases including cancer. Current data analyses on gene expression are mostly focused on differential gene/transcript expression in big data-driven studies. However, a poor connection to the proteome changes is a widespread problem in current data analyses. This is partly due to the complexity of gene regulatory pathways at the post-transcriptional level. In this study, we overcome these limitations and introduce a graph-based learning model, PTNet, which simulates the microRNAs (miRNAs) that regulate gene expression post-transcriptionally in silico. Our model does not require large-scale proteomics studies to measure the protein expression and can successfully predict the protein levels by considering the miRNA-mRNA interaction network, the mRNA expression, and the miRNA expression. Large-scale experiments on simulations and real cancer high-throughput datasets using PTNet validated that (i) the miRNA-mediated interaction network affects the abundance of corresponding proteins and (ii) the predicted protein expression has a higher correlation with the proteomics data (ground-truth) than the mRNA expression data. The classification performance also shows that the predicted protein expression has an improved prediction power on cancer outcomes compared to the prediction done by the mRNA expression data only or considering both mRNA and miRNA. Availability: PTNet toolbox is available at http://github.com/CompbioLabUCF/PTNet.

CancerCellTracker: a brightfield time-lapse microscopy framework for cancer drug sensitivity estimation.

MOTIVATION: Time-lapse microscopy is a powerful technique that relies on images of live cells cultured ex vivo that are captured at regular intervals of time to describe and quantify their behavior under certain experimental conditions. This imaging method has great potential in advancing the field of precision oncology by quantifying the response of cancer cells to various therapies and identifying the most efficacious treatment for a given patient. Digital image processing algorithms developed so far require high-resolution images involving very few cells originating from homogeneous cell line populations. We propose a novel framework that tracks cancer cells to capture their behavior and quantify cell viability to inform clinical decisions in a high-throughput manner. RESULTS: The brightfield microscopy images a large number of patient-derived cells in an ex vivo reconstruction of the tumor microenvironment treated with 31 drugs for up to 6 days. We developed a robust and user-friendly pipeline CancerCellTracker that detects cells in co-culture, tracks these cells across time and identifies cell death events using changes in cell attributes. We validated our computational pipeline by comparing the timing of cell death estimates by CancerCellTracker from brightfield images and a fluorescent channel featuring ethidium homodimer. We benchmarked our results using a state-of-the-art algorithm implemented in ImageJ and previously published in the literature. We highlighted CancerCellTracker's efficiency in estimating the percentage of live cells in the presence of bone marrow stromal cells. AVAILABILITY AND IMPLEMENTATION: https://github.com/compbiolabucf/CancerCellTracker. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

APA-Scan: detection and visualization of 3'-UTR alternative polyadenylation with RNA-seq and 3'-end-seq data.

BACKGROUND: The eukaryotic genome is capable of producing multiple isoforms from a gene by alternative polyadenylation (APA) during pre-mRNA processing. APA in the 3'-untranslated region (3'-UTR) of mRNA produces transcripts with shorter or longer 3'-UTR. Often, 3'-UTR serves as a binding platform for microRNAs and RNA-binding proteins, which affect the fate of the mRNA transcript. Thus, 3'-UTR APA is known to modulate translation and provides a mean to regulate gene expression at the post-transcriptional level. Current bioinformatics pipelines have limited capability in profiling 3'-UTR APA events due to incomplete annotations and a low-resolution analyzing power: widely available bioinformatics pipelines do not reference actionable polyadenylation (cleavage) sites but simulate 3'-UTR APA only using RNA-seq read coverage, causing false positive identifications. To overcome these limitations, we developed APA-Scan, a robust program that identifies 3'-UTR APA events and visualizes the RNA-seq short-read coverage with gene annotations. METHODS: APA-Scan utilizes either predicted or experimentally validated actionable polyadenylation signals as a reference for polyadenylation sites and calculates the quantity of long and short 3'-UTR transcripts in the RNA-seq data. APA-Scan works in three major steps: (i) calculate the read coverage of the 3'-UTR regions of genes; (ii) identify the potential APA sites and evaluate the significance of the events among two biological conditions; (iii) graphical representation of user specific event with 3'-UTR annotation and read coverage on the 3'-UTR regions. APA-Scan is implemented in Python3. Source code and a comprehensive user's manual are freely available at https://github.com/compbiolabucf/APA-Scan . RESULT: APA-Scan was applied to both simulated and real RNA-seq datasets and compared with two widely used baselines DaPars and APAtrap. In simulation APA-Scan significantly improved the accuracy of 3'-UTR APA identification compared to the other baselines. The performance of APA-Scan was also validated by 3'-end-seq data and qPCR on mouse embryonic fibroblast cells. The experiments confirm that APA-Scan can detect unannotated 3'-UTR APA events and improve genome annotation. CONCLUSION: APA-Scan is a comprehensive computational pipeline to detect transcriptome-wide 3'-UTR APA events. The pipeline integrates both RNA-seq and 3'-end-seq data information and can efficiently identify the significant events with a high-resolution short reads coverage plots.

Multi-omics data integration by generative adversarial network.

MOTIVATION: Accurate disease phenotype prediction plays an important role in the treatment of heterogeneous diseases like cancer in the era of precision medicine. With the advent of high throughput technologies, more comprehensive multi-omics data is now available that can effectively link the genotype to phenotype. However, the interactive relation of multi-omics datasets makes it particularly challenging to incorporate different biological layers to discover the coherent biological signatures and predict phenotypic outcomes. In this study, we introduce omicsGAN, a generative adversarial network model to integrate two omics data and their interaction network. The model captures information from the interaction network as well as the two omics datasets and fuse them to generate synthetic data with better predictive signals. RESULTS: Large-scale experiments on The Cancer Genome Atlas breast cancer, lung cancer and ovarian cancer datasets validate that (i) the model can effectively integrate two omics data (e.g. mRNA and microRNA expression data) and their interaction network (e.g. microRNA-mRNA interaction network). The synthetic omics data generated by the proposed model has a better performance on cancer outcome classification and patients survival prediction compared to original omics datasets. (ii) The integrity of the interaction network plays a vital role in the generation of synthetic data with higher predictive quality. Using a random interaction network does not allow the framework to learn meaningful information from the omics datasets; therefore, results in synthetic data with weaker predictive signals. AVAILABILITY AND IMPLEMENTATION: Source code is available at: https://github.com/CompbioLabUCF/omicsGAN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

omicsGAT: Graph Attention Network for Cancer Subtype Analyses.

The use of high-throughput omics technologies is becoming increasingly popular in all facets of biomedical science. The mRNA sequencing (RNA-seq) method reports quantitative measures of more than tens of thousands of biological features. It provides a more comprehensive molecular perspective of studied cancer mechanisms compared to traditional approaches. Graph-based learning models have been proposed to learn important hidden representations from gene expression data and network structure to improve cancer outcome prediction, patient stratification, and cell clustering. However, these graph-based methods cannot rank the importance of the different neighbors for a particular sample in the downstream cancer subtype analyses. In this study, we introduce omicsGAT, a graph attention network (GAT) model to integrate graph-based learning with an attention mechanism for RNA-seq data analysis. The multi-head attention mechanism in omicsGAT can more effectively secure information of a particular sample by assigning different attention coefficients to its neighbors. Comprehensive experiments on The Cancer Genome Atlas (TCGA) breast cancer and bladder cancer bulk RNA-seq data and two single-cell RNA-seq datasets validate that (1) the proposed model can effectively integrate neighborhood information of a sample and learn an embedding vector to improve disease phenotype prediction, cancer patient stratification, and cell clustering of the sample and (2) the attention matrix generated from the multi-head attention coefficients provides more useful information compared to the sample correlation-based adjacency matrix. From the results, we can conclude that some neighbors play a more important role than others in cancer subtype analyses of a particular sample based on the attention coefficient.

Control Plane Optimisation for an SDN-Based WBAN Framework to Support Healthcare Applications.

Software-Defined Networking (SDN) offers an abstract view of the network and assists network operators to control the network traffic and the associated network resources more effectively. For the past few years, SDN has shown a lot of merits in diverse fields of applications, an important one being the Wireless Body Area Network (WBAN) for healthcare services. With the amalgamation of SDN with WBAN (SDWBAN), the patient monitoring and management system has gained much more flexibility and scalability compared to the conventional WBAN. However, the performance of the SDWBAN framework largely depends on the controller which is a core element of the control plane. The reason is that an optimal number of controllers assures the satisfactory level of performance and control of the network traffic originating from the underlying data plane devices. This paper proposes a mathematical model to determine the optimal number of controllers for the SDWBAN framework in healthcare applications. To achieve this goal, the proposed mathematical model adopts the convex optimization method and incorporates three critical SDWBAN factors in the design process: number of controllers, latency and number of SDN-enabled switches (SDESW). The proposed analytical model is validated by means of simulations in Castalia 3.2 and the outcomes indicate that the network achieves high level of Packet Delivery Ratio (PDR) and low latency for optimal number of controllers as derived in the mathematical model.

Distributed efficient similarity search mechanism in wireless sensor networks.

The Wireless Sensor Network similarity search problem has received considerable research attention due to sensor hardware imprecision and environmental parameter variations. Most of the state-of-the-art distributed data centric storage (DCS) schemes lack optimization for similarity queries of events. In this paper, a DCS scheme with metric based similarity searching (DCSMSS) is proposed. DCSMSS takes motivation from vector distance index, called iDistance, in order to transform the issue of similarity searching into the problem of an interval search in one dimension. In addition, a sector based distance routing algorithm is used to efficiently route messages. Extensive simulation results reveal that DCSMSS is highly efficient and significantly outperforms previous approaches in processing similarity search queries.

An effective ensemble learning approach for classification of glioma grades based on novel MRI features.

The preoperative diagnosis of brain tumors is important for therapeutic planning as it contributes to the tumors' prognosis. In the last few years, the development in the field of artificial intelligence and machine learning has contributed greatly to the medical area, especially the diagnosis of the grades of brain tumors through radiological images and magnetic resonance images. Due to the complexity of tumor descriptors in medical images, assessing the accurate grade of glioma is a major challenge for physicians. We have proposed a new classification system for glioma grading by integrating novel MRI features with an ensemble learning method, called Ensemble Learning based on Adaptive Power Mean Combiner (EL-APMC). We evaluate and compare the performance of the EL-APMC algorithm with twenty-one classifier models that represent state-of-the-art machine learning algorithms. Results show that the EL-APMC algorithm achieved the best performance in terms of classification accuracy (88.73%) and F1-score (93.12%) over the MRI Brain Tumor dataset called BRATS2015. In addition, we showed that the differences in classification results among twenty-two classifier models have statistical significance. We believe that the EL-APMC algorithm is an effective method for the classification in case of small-size datasets, which are common cases in medical fields. The proposed method provides an effective system for the classification of glioma with high reliability and accurate clinical findings.

Early detection of depression using a conversational AI bot: A non-clinical trial.

BACKGROUND: Artificial intelligence (AI) has gained momentum in behavioural health interventions in recent years. However, a limited number of studies use or apply such methodologies in the early detection of depression. A large population needing psychological-intervention is left unidentified due to barriers such as cost, location, stigma and a global shortage of health workers. Therefore, it is essential to develop a mass screening integrative approach that can identify people with depression at its early stage to avoid a potential crisis. OBJECTIVES: This study aims to understand the feasibility and efficacy of using AI-enabled chatbots in the early detection of depression. METHODS: We use Dialogflow as a conversation interface to build a Depression Analysisn (DEPRA) chatbot. A structured and authoritative early detection depression interview guide, which contains 27 questions combining the structured interview guide for the Hamilton Depression Scale (SIGH-D) and the inventory of depressive symptomatology (IDS-C), underpins the design of the conversation flow. To attain better accuracy and a wide variety of responses, we train Dialogflow with the utterances collected from a focus group of 10 people. The occupation of the focus group members included academics and HDR candidates who are conscious, vigilant and have a clear understanding of the questions. In addition, DEPRA is integrated with a social media platform to provide practical access to all the participants. For the non-clinical trial, we recruited 50 participants aged between 18 and 80 from across Australia. To evaluate the practicability and performance of DEPRA, we also asked participants to submit a user satisfaction survey at the end of the conversation. RESULTS: A sample of 50 participants, with an average age of 34.7 years, completed this non-clinical trial. More than half of the participants (54%) are male and the major ethnicities are Asian (63%), Middle Eastern (25%), and others 12%. The first group comprises professional academic staff and HDR candidates, the second and third groups comprise relatives, friends, and volunteers who were recruited via social media promotions. DEPRA uses two scientific scoring systems, QIDS-SR and IDS-SR to verify the results of early depression detection. As the results indicate, both scoring systems return a similar outcome with slight variations for different depression levels. According to IDS-SR, 30% of participants were healthy, 14% mild, 22% moderate, 14% severe, and 20% very severe. QIDS-SR suggests 32% were healthy, 18% mild, 10% moderate, 18% severe, and 22% very severe. Furthermore, the overall satisfaction rate of using DEPRA was 79% indicating that the participants had a high rate of user satisfaction and engagement. CONCLUSION: DEPRA shows promises as a feasible option for developing a mass screening integrated approach for early detection of depression. Although the chatbot is not intended to replace the functionality of mental health professionals, it does show promise as a means of assisting with automation and concealed communication with verified scoring systems.

Automated detection of COVID-19 through convolutional neural network using chest x-ray images.

The COVID-19 epidemic has a catastrophic impact on global well-being and public health. More than 27 million confirmed cases have been reported worldwide until now. Due to the growing number of confirmed cases, and challenges to the variations of the COVID-19, timely and accurate classification of healthy and infected patients is essential to control and treat COVID-19. We aim to develop a deep learning-based system for the persuasive classification and reliable detection of COVID-19 using chest radiography. Firstly, we evaluate the performance of various state-of-the-art convolutional neural networks (CNNs) proposed over recent years for medical image classification. Secondly, we develop and train CNN from scratch. In both cases, we use a public X-Ray dataset for training and validation purposes. For transfer learning, we obtain 100% accuracy for binary classification (i.e., Normal/COVID-19) and 87.50% accuracy for tertiary classification (Normal/COVID-19/Pneumonia). With the CNN trained from scratch, we achieve 93.75% accuracy for tertiary classification. In the case of transfer learning, the classification accuracy drops with the increased number of classes. The results are demonstrated by comprehensive receiver operating characteristics (ROC) and confusion metric analysis with 10-fold cross-validation.

Image Preprocessing in Classification and Identification of Diabetic Eye Diseases.

Diabetic eye disease (DED) is a cluster of eye problem that affects diabetic patients. Identifying DED is a crucial activity in retinal fundus images because early diagnosis and treatment can eventually minimize the risk of visual impairment. The retinal fundus image plays a significant role in early DED classification and identification. An accurate diagnostic model's development using a retinal fundus image depends highly on image quality and quantity. This paper presents a methodical study on the significance of image processing for DED classification. The proposed automated classification framework for DED was achieved in several steps: image quality enhancement, image segmentation (region of interest), image augmentation (geometric transformation), and classification. The optimal results were obtained using traditional image processing methods with a new build convolution neural network (CNN) architecture. The new built CNN combined with the traditional image processing approach presented the best performance with accuracy for DED classification problems. The results of the experiments conducted showed adequate accuracy, specificity, and sensitivity.

Automated detection of mild and multi-class diabetic eye diseases using deep learning.

Diabetic eye disease is a collection of ocular problems that affect patients with diabetes. Thus, timely screening enhances the chances of timely treatment and prevents permanent vision impairment. Retinal fundus images are a useful resource to diagnose retinal complications for ophthalmologists. However, manual detection can be laborious and time-consuming. Therefore, developing an automated diagnose system reduces the time and workload for ophthalmologists. Recently, the image classification using Deep Learning (DL) in between healthy or diseased retinal fundus image classification already achieved a state of the art performance. While the classification of mild and multi-class diseases remains an open challenge, therefore, this research aimed to build an automated classification system considering two scenarios: (i) mild multi-class diabetic eye disease (DED), and (ii) multi-class DED. Our model tested on various datasets, annotated by an opthalmologist. The experiment conducted employing the top two pretrained convolutional neural network (CNN) models on ImageNet. Furthermore, various performance improvement techniques were employed, i.e., fine-tune, optimization, and contrast enhancement. Maximum accuracy of 88.3% obtained on the VGG16 model for multi-class classification and 85.95% for mild multi-class classification.

Healthchain: A novel framework on privacy preservation of electronic health records using blockchain technology.

The privacy of Electronic Health Records (EHRs) is facing a major hurdle with outsourcing private health data in the cloud as there exists danger of leaking health information to unauthorized parties. In fact, EHRs are stored on centralized databases that increases the security risk footprint and requires trust in a single authority which cannot effectively protect data from internal attacks. This research focuses on ensuring the patient privacy and data security while sharing the sensitive data across same or different organisations as well as healthcare providers in a distributed environment. This research develops a privacy-preserving framework viz Healthchain based on Blockchain technology that maintains security, privacy, scalability and integrity of the e-health data. The Blockchain is built on Hyperledger fabric, a permissioned distributed ledger solutions by using Hyperledger composer and stores EHRs by utilizing InterPlanetary File System (IPFS) to build this healthchain framework. Moreover, the data stored in the IPFS is encrypted by using a unique cryptographic public key encryption algorithm to create a robust blockchain solution for electronic health data. The objective of the research is to provide a foundation for developing security solutions against cyber-attacks by exploiting the inherent features of the blockchain, and thus contribute to the robustness of healthcare information sharing environments. Through the results, the proposed model shows that the healthcare records are not traceable to unauthorized access as the model stores only the encrypted hash of the records that proves effectiveness in terms of data security, enhanced data privacy, improved data scalability, interoperability and data integrity while sharing and accessing medical records among stakeholders across the healthchain network.

Network-based drug sensitivity prediction.

BACKGROUND: Drug sensitivity prediction and drug responsive biomarker selection on high-throughput genomic data is a critical step in drug discovery. Many computational methods have been developed to serve this purpose including several deep neural network models. However, the modular relations among genomic features have been largely ignored in these methods. To overcome this limitation, the role of the gene co-expression network on drug sensitivity prediction is investigated in this study. METHODS: In this paper, we first introduce a network-based method to identify representative features for drug response prediction by using the gene co-expression network. Then, two graph-based neural network models are proposed and both models integrate gene network information directly into neural network for outcome prediction. Next, we present a large-scale comparative study among the proposed network-based methods, canonical prediction algorithms (i.e., Elastic Net, Random Forest, Partial Least Squares Regression, and Support Vector Regression), and deep neural network models for drug sensitivity prediction. All the source code and processed datasets in this study are available at https://github.com/compbiolabucf/drug-sensitivity-prediction . RESULTS: In the comparison of different feature selection methods and prediction methods on a non-small cell lung cancer (NSCLC) cell line RNA-seq gene expression dataset with 50 different drug treatments, we found that (1) the network-based feature selection method improves the prediction performance compared to Pearson correlation coefficients; (2) Random Forest outperforms all the other canonical prediction algorithms and deep neural network models; (3) the proposed graph-based neural network models show better prediction performance compared to deep neural network model; (4) the prediction performance is drug dependent and it may relate to the drug's mechanism of action. CONCLUSIONS: Network-based feature selection method and prediction models improve the performance of the drug response prediction. The relations between the genomic features are more robust and stable compared to the correlation between each individual genomic feature and the drug response in high dimension and low sample size genomic datasets.