CRUX, a platform for visualising, exploring and analysing cancer genome cohort data.

To better understand how tumours develop, identify prognostic biomarkers and find new treatments, researchers have generated vast catalogues of cancer genome data. However, these datasets are complex, so interpreting their important features requires specialized computational skills and analytical tools, which presents a significant technical challenge. To address this, we developed CRUX, a platform for exploring genomic data from cancer cohorts. CRUX enables researchers to perform common analyses including cohort comparisons, biomarker discovery, survival analysis, and to create visualisations including oncoplots and lollipop charts. CRUX simplifies cancer genome analysis in several ways: (i) it has an easy-to-use graphical interface; (ii) it enables users to create custom cohorts, as well as analyse precompiled public and private user-created datasets; (iii) it allows analyses to be run locally to address data privacy concerns (though an online version is also available) and (iv) it makes it easy to use additional specialized tools by exporting data in the correct formats. We showcase CRUX's capabilities with case studies employing different types of cancer genome analysis, demonstrating how it can be used flexibly to generate valuable insights into cancer biology. CRUX is freely available at https://github.com/CCICB/CRUX and https://ccicb.shinyapps.io/crux (DOI: 10.5281/zenodo.8015714).

HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN.

Deep learning-based models have achieved significant success in detecting cardiac arrhythmia by analyzing ECG signals to categorize patient heartbeats. To improve the performance of such models, we have developed a novel hybrid hierarchical attention-based bidirectional recurrent neural network with dilated CNN (HARDC) method for arrhythmia classification. This solves problems that arise when traditional dilated convolutional neural network (CNN) models disregard the correlation between contexts and gradient dispersion. The proposed HARDC fully exploits the dilated CNN and bidirectional recurrent neural network unit (BiGRU-BiLSTM) architecture to generate fusion features. As a result of incorporating both local and global feature information and an attention mechanism, the model's performance for prediction is improved. By combining the fusion features with a dilated CNN and a hierarchical attention mechanism, the trained HARDC model showed significantly improved classification results and interpretability of feature extraction on the PhysioNet 2017 challenge dataset. Sequential Z-Score normalization, filtering, denoising, and segmentation are used to prepare the raw data for analysis. CGAN (Conditional Generative Adversarial Network) is then used to generate synthetic signals from the processed data. The experimental results demonstrate that the proposed HARDC model significantly outperforms other existing models, achieving an accuracy of 99.60%, F1 score of 98.21%, a precision of 97.66%, and recall of 99.60% using MIT-BIH generated ECG. In addition, this approach significantly reduces run time when using dilated CNN compared to normal convolution. Overall, this hybrid model demonstrates an innovative and cost-effective strategy for ECG signal compression and high-performance ECG recognition. Our results indicate that an automated and highly computed method to classify multiple types of arrhythmia signals holds considerable promise.

AMYPred-FRL is a novel approach for accurate prediction of amyloid proteins by using feature representation learning.

Amyloid proteins have the ability to form insoluble fibril aggregates that have important pathogenic effects in many tissues. Such amyloidoses are prominently associated with common diseases such as type 2 diabetes, Alzheimer's disease, and Parkinson's disease. There are many types of amyloid proteins, and some proteins that form amyloid aggregates when in a misfolded state. It is difficult to identify such amyloid proteins and their pathogenic properties, but a new and effective approach is by developing effective bioinformatics tools. While several machine learning (ML)-based models for in silico identification of amyloid proteins have been proposed, their predictive performance is limited. In this study, we present AMYPred-FRL, a novel meta-predictor that uses a feature representation learning approach to achieve more accurate amyloid protein identification. AMYPred-FRL combined six well-known ML algorithms (extremely randomized tree, extreme gradient boosting, k-nearest neighbor, logistic regression, random forest, and support vector machine) with ten different sequence-based feature descriptors to generate 60 probabilistic features (PFs), as opposed to state-of-the-art methods developed by a single feature-based approach. A logistic regression recursive feature elimination (LR-RFE) method was used to find the optimal m number of 60 PFs in order to improve the predictive performance. Finally, using the meta-predictor approach, the 20 selected PFs were fed into a logistic regression method to create the final hybrid model (AMYPred-FRL). Both cross-validation and independent tests showed that AMYPred-FRL achieved superior predictive performance than its constituent baseline models. In an extensive independent test, AMYPred-FRL outperformed the existing methods by 5.5% and 16.1%, respectively, with accuracy and MCC of 0.873 and 0.710. To expedite high-throughput prediction, a user-friendly web server of AMYPred-FRL is freely available at http://pmlabstack.pythonanywhere.com/AMYPred-FRL . It is anticipated that AMYPred-FRL will be a useful tool in helping researchers to identify new amyloid proteins.

SCORPION is a stacking-based ensemble learning framework for accurate prediction of phage virion proteins.

Fast and accurate identification of phage virion proteins (PVPs) would greatly aid facilitation of antibacterial drug discovery and development. Although, several research efforts based on machine learning (ML) methods have been made for in silico identification of PVPs, these methods have certain limitations. Therefore, in this study, we propose a new computational approach, termed SCORPION, (StaCking-based Predictior fOR Phage VIrion PrOteiNs), to accurately identify PVPs using only protein primary sequences. Specifically, we explored comprehensive 13 different feature descriptors from different aspects (i.e., compositional information, composition-transition-distribution information, position-specific information and physicochemical properties) with 10 popular ML algorithms to construct a pool of optimal baseline models. These optimal baseline models were then used to generate probabilistic features (PFs) and considered as a new feature vector. Finally, we utilized a two-step feature selection strategy to determine the optimal PF feature vector and used this feature vector to develop a stacked model (SCORPION). Both tenfold cross-validation and independent test results indicate that SCORPION achieves superior predictive performance than its constitute baseline models and existing methods. We anticipate SCORPION will serve as a useful tool for the cost-effective and large-scale screening of new PVPs. The source codes and datasets for this work are available for downloading in the GitHub repository ( https://github.com/saeed344/SCORPION ).

Machine learning models for classification and identification of significant attributes to detect type 2 diabetes.

Type 2 Diabetes (T2D) is a chronic disease characterized by abnormally high blood glucose levels due to insulin resistance and reduced pancreatic insulin production. The challenge of this work is to identify T2D-associated features that can distinguish T2D sub-types for prognosis and treatment purposes. We thus employed machine learning (ML) techniques to categorize T2D patients using data from the Pima Indian Diabetes Dataset from the Kaggle ML repository. After data preprocessing, several feature selection techniques were used to extract feature subsets, and a range of classification techniques were used to analyze these. We then compared the derived classification results to identify the best classifiers by considering accuracy, kappa statistics, area under the receiver operating characteristic (AUROC), sensitivity, specificity, and logarithmic loss (logloss). To evaluate the performance of different classifiers, we investigated their outcomes using the summary statistics with a resampling distribution. Therefore, Generalized Boosted Regression modeling showed the highest accuracy (90.91%), followed by kappa statistics (78.77%) and specificity (85.19%). In addition, Sparse Distance Weighted Discrimination, Generalized Additive Model using LOESS and Boosted Generalized Additive Models also gave the maximum sensitivity (100%), highest AUROC (95.26%) and lowest logarithmic loss (30.98%) respectively. Notably, the Generalized Additive Model using LOESS was the top-ranked algorithm according to non-parametric Friedman testing. Of the features identified by these machine learning models, glucose levels, body mass index, diabetes pedigree function, and age were consistently identified as the best and most frequently accurate outcome predictors. These results indicate the utility of ML methods in constructing improved prediction models for T2D and successfully identified outcome predictors for this Pima Indian population. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s13755-021-00168-2.

Adverse Effects of COVID-19 Vaccination: Machine Learning and Statistical Approach to Identify and Classify Incidences of Morbidity and Postvaccination Reactogenicity.

Good vaccine safety and reliability are essential for successfully countering infectious disease spread. A small but significant number of adverse reactions to COVID-19 vaccines have been reported. Here, we aim to identify possible common factors in such adverse reactions to enable strategies that reduce the incidence of such reactions by using patient data to classify and characterise those at risk. We examined patient medical histories and data documenting postvaccination effects and outcomes. The data analyses were conducted using a range of statistical approaches followed by a series of machine learning classification algorithms. In most cases, a group of similar features was significantly associated with poor patient reactions. These included patient prior illnesses, admission to hospitals and SARS-CoV-2 reinfection. The analyses indicated that patient age, gender, taking other medications, type-2 diabetes, hypertension, allergic history and heart disease are the most significant pre-existing factors associated with the risk of poor outcome. In addition, long duration of hospital treatments, dyspnoea, various kinds of pain, headache, cough, asthenia, and physical disability were the most significant clinical predictors. The machine learning classifiers that are trained with medical history were also able to predict patients with complication-free vaccination and have an accuracy score above 90%. Our study identifies profiles of individuals that may need extra monitoring and care (e.g., vaccination at a location with access to comprehensive clinical support) to reduce negative outcomes through classification approaches.

Machine learning-based statistical analysis for early stage detection of cervical cancer.

Cervical cancer (CC) is the most common type of cancer in women and remains a significant cause of mortality, particularly in less developed countries, although it can be effectively treated if detected at an early stage. This study aimed to find efficient machine-learning-based classifying models to detect early stage CC using clinical data. We obtained a Kaggle data repository CC dataset which contained four classes of attributes including biopsy, cytology, Hinselmann, and Schiller. This dataset was split into four categories based on these class attributes. Three feature transformation methods, including log, sine function, and Z-score were applied to these datasets. Several supervised machine learning algorithms were assessed for their performance in classification. A Random Tree (RT) algorithm provided the best classification accuracy for the biopsy (98.33%) and cytology (98.65%) data, whereas Random Forest (RF) and Instance-Based K-nearest neighbor (IBk) provided the best performance for Hinselmann (99.16%), and Schiller (98.58%) respectively. Among the feature transformation methods, logarithmic gave the best performance for biopsy datasets whereas sine function was superior for cytology. Both logarithmic and sine functions performed the best for the Hinselmann dataset, while Z-score was best for the Schiller dataset. Various Feature Selection Techniques (FST) methods were applied to the transformed datasets to identify and prioritize important risk factors. The outcomes of this study indicate that appropriate system design and tuning, machine learning methods and classification are able to detect CC accurately and efficiently in its early stages using clinical data.

A deep learning approach using effective preprocessing techniques to detect COVID-19 from chest CT-scan and X-ray images.

Coronavirus disease-19 (COVID-19) is a severe respiratory viral disease first reported in late 2019 that has spread worldwide. Although some wealthy countries have made significant progress in detecting and containing this disease, most underdeveloped countries are still struggling to identify COVID-19 cases in large populations. With the rising number of COVID-19 cases, there are often insufficient COVID-19 diagnostic kits and related resources in such countries. However, other basic diagnostic resources often do exist, which motivated us to develop Deep Learning models to assist clinicians and radiologists to provide prompt diagnostic support to the patients. In this study, we have developed a deep learning-based COVID-19 case detection model trained with a dataset consisting of chest CT scans and X-ray images. A modified ResNet50V2 architecture was employed as deep learning architecture in the proposed model. The dataset utilized to train the model was collected from various publicly available sources and included four class labels: confirmed COVID-19, normal controls and confirmed viral and bacterial pneumonia cases. The aggregated dataset was preprocessed through a sharpening filter before feeding the dataset into the proposed model. This model attained an accuracy of 96.452% for four-class cases (COVID-19/Normal/Bacterial pneumonia/Viral pneumonia), 97.242% for three-class cases (COVID-19/Normal/Bacterial pneumonia) and 98.954% for two-class cases (COVID-19/Viral pneumonia) using chest X-ray images. The model acquired a comprehensive accuracy of 99.012% for three-class cases (COVID-19/Normal/Community-acquired pneumonia) and 99.99% for two-class cases (Normal/COVID-19) using CT-scan images of the chest. This high accuracy presents a new and potentially important resource to enable radiologists to identify and rapidly diagnose COVID-19 cases with only basic but widely available equipment.

Machine Learning Approaches to Identify Patient Comorbidities and Symptoms That Increased Risk of Mortality in COVID-19.

Providing appropriate care for people suffering from COVID-19, the disease caused by the pandemic SARS-CoV-2 virus, is a significant global challenge. Many individuals who become infected may have pre-existing conditions that may interact with COVID-19 to increase symptom severity and mortality risk. COVID-19 patient comorbidities are likely to be informative regarding the individual risk of severe illness and mortality. Determining the degree to which comorbidities are associated with severe symptoms and mortality would thus greatly assist in COVID-19 care planning and provision. To assess this we performed a meta-analysis of published global literature, and machine learning predictive analysis using an aggregated COVID-19 global dataset. Our meta-analysis suggested that chronic obstructive pulmonary disease (COPD), cerebrovascular disease (CEVD), cardiovascular disease (CVD), type 2 diabetes, malignancy, and hypertension as most significantly associated with COVID-19 severity in the current published literature. Machine learning classification using novel aggregated cohort data similarly found COPD, CVD, CKD, type 2 diabetes, malignancy, and hypertension, as well as asthma, as the most significant features for classifying those deceased versus those who survived COVID-19. While age and gender were the most significant predictors of mortality, in terms of symptom-comorbidity combinations, it was observed that Pneumonia-Hypertension, Pneumonia-Diabetes, and Acute Respiratory Distress Syndrome (ARDS)-Hypertension showed the most significant associations with COVID-19 mortality. These results highlight the patient cohorts most likely to be at risk of COVID-19-related severe morbidity and mortality, which have implications for prioritization of hospital resources.

Recognition of human emotions using EEG signals: A review.

Assessment of the cognitive functions and state of clinical subjects is an important aspect of e-health care delivery, and in the development of novel human-machine interfaces. A subject can display a range of emotions that significantly influence cognition, and emotion classification through the analysis of physiological signals is a key means of detecting emotion. Electroencephalography (EEG) signals have become a common focus of such development compared to other physiological signals because EEG employs simple and subject-acceptable methods for obtaining data that can be used for emotion analysis. We have therefore reviewed published studies that have used EEG signal data to identify possible interconnections between emotion and brain activity. We then describe theoretical conceptualization of basic emotions, and interpret the prevailing techniques that have been adopted for feature extraction, selection, and classification. Finally, we have compared the outcomes of these recent studies and discussed the likely future directions and main challenges for researchers developing EEG-based emotion analysis methods.

Heart disease prediction using supervised machine learning algorithms: Performance analysis and comparison.

Machine learning and data mining-based approaches to prediction and detection of heart disease would be of great clinical utility, but are highly challenging to develop. In most countries there is a lack of cardiovascular expertise and a significant rate of incorrectly diagnosed cases which could be addressed by developing accurate and efficient early-stage heart disease prediction by analytical support of clinical decision-making with digital patient records. This study aimed to identify machine learning classifiers with the highest accuracy for such diagnostic purposes. Several supervised machine-learning algorithms were applied and compared for performance and accuracy in heart disease prediction. Feature importance scores for each feature were estimated for all applied algorithms except MLP and KNN. All the features were ranked based on the importance score to find those giving high heart disease predictions. This study found that using a heart disease dataset collected from Kaggle three-classification based on k-nearest neighbor (KNN), decision tree (DT) and random forests (RF) algorithms the RF method achieved 100% accuracy along with 100% sensitivity and specificity. Thus, we found that a relatively simple supervised machine learning algorithm can be used to make heart disease predictions with very high accuracy and excellent potential utility.

Deep convolutional neural networks based ECG beats classification to diagnose cardiovascular conditions.

Medical practitioners need to understand the critical features of ECG beats to diagnose and identify cardiovascular conditions accurately. This would be greatly facilitated by identifying the significant features of frequency components in temporal ECG wave-forms using computational methods. In this study, we have proposed a novel ECG beat classifier based on a customized VGG16-based Convolution Neural Network (CNN) that uses the time-frequency representation of temporal ECG, and a method to identify the contribution of interpretable ECG frequencies when classifying based on the SHapley Additive exPlanations (SHAP) values. We applied our model to the MIT-BIH arrhythmia dataset to classify the ECG beats and to characterise of the beats frequencies. This model was evaluated with two advanced time-frequency analysis methods. Our results indicated that for 2-4 classes our proposed model achieves a classification accuracy of 100% and for 5 classes it achieves a classification accuracy of 99.90%. We have also tested the proposed model using premature ventricular contraction beats from the American Heart Association (AHA) database and normal beats from Lobachevsky University Electrocardiography database (LUDB) and obtained a classification accuracy of 99.91% for the 5-classes case. In addition, SHAP value increased the interpretability of the ECG frequency features. Thus, this model could be applicable to the automation of the cardiovascular diagnosis system and could be used by clinicians.

Machine learning and network-based models to identify genetic risk factors to the progression and survival of colorectal cancer.

Colorectal cancer (CRC) is one of the most common and lethal malignant lesions. Determining how the identified risk factors drive the formation and development of CRC could be an essential means for effective therapeutic development. Aiming this, we investigated how the altered gene expression resulting from exposure to putative CRC risk factors contribute to prognostic biomarker identification. Differentially expressed genes (DEGs) were first identified for CRC and other eight risk factors. Gene set enrichment analysis (GSEA) through the molecular pathway and gene ontology (GO), as well as protein-protein interaction (PPI) network, were then conducted to predict the functions of these DEGs. Our identified genes were explored through the dbGaP and OMIM databases to compare with the already identified and known prognostic CRC biomarkers. The survival time of CRC patients was also examined using a Cox Proportional Hazard regression-based prognostic model by integrating transcriptome data from The Cancer Genome Atlas (TCGA). In this study, PPI analysis identified 4 sub-networks and 8 hub genes that may be potential therapeutic targets, including CXCL8, ICAM1, SOD2, CXCL2, CCL20, OIP5, BUB1, ASPM and IL1RN. We also identified seven signature genes (PRR5.ARHGAP8, CA7, NEDD4L, GFR2, ARHGAP8, SMTN, OIP5) in independent analysis and among which PRR5. ARHGAP8 was found in both multivariate analyses and in analyses that combined gene expression and clinical information. This approach provides both mechanistic information and, when combined with predictive clinical information, good evidence that the identified genes are significant biomarkers of processes involved in CRC progression and survival.

Transcriptomic studies revealed pathophysiological impact of COVID-19 to predominant health conditions.

Despite the association of prevalent health conditions with coronavirus disease 2019 (COVID-19) severity, the disease-modifying biomolecules and their pathogenetic mechanisms remain unclear. This study aimed to understand the influences of COVID-19 on different comorbidities and vice versa through network-based gene expression analyses. Using the shared dysregulated genes, we identified key genetic determinants and signaling pathways that may involve in their shared pathogenesis. The COVID-19 showed significant upregulation of 93 genes and downregulation of 15 genes. Interestingly, it shares 28, 17, 6 and 7 genes with diabetes mellitus (DM), lung cancer (LC), myocardial infarction and hypertension, respectively. Importantly, COVID-19 shared three upregulated genes (i.e. MX2, IRF7 and ADAM8) with DM and LC. Conversely, downregulation of two genes (i.e. PPARGC1A and METTL7A) was found in COVID-19 and LC. Besides, most of the shared pathways were related to inflammatory responses. Furthermore, we identified six potential biomarkers and several important regulatory factors, e.g. transcription factors and microRNAs, while notable drug candidates included captopril, rilonacept and canakinumab. Moreover, prognostic analysis suggests concomitant COVID-19 may result in poor outcome of LC patients. This study provides the molecular basis and routes of the COVID-19 progression due to comorbidities. We believe these findings might be useful to further understand the intricate association of these diseases as well as for the therapeutic development.

TClustVID: A novel machine learning classification model to investigate topics and sentiment in COVID-19 tweets.

COVID-19, caused by SARS-CoV2 infection, varies greatly in its severity but presents with serious respiratory symptoms with vascular and other complications, particularly in older adults. The disease can be spread by both symptomatic and asymptomatic infected individuals. Uncertainty remains over key aspects of the virus infectiousness (particularly the newly emerging variants) and the disease has had severe economic impacts globally. For these reasons, COVID-19 is the subject of intense and widespread discussion on social media platforms including Facebook and Twitter. These public forums substantially influence public opinions and in some cases can exacerbate the widespread panic and misinformation spread during the crisis. Thus, this work aimed to design an intelligent clustering-based classification and topic extracting model named TClustVID that analyzes COVID-19-related public tweets to extract significant sentiments with high accuracy. We gathered COVID-19 Twitter datasets from the IEEE Dataport repository and employed a range of data preprocessing methods to clean the raw data, then applied tokenization and produced a word-to-index dictionary. Thereafter, different classifications were employed on these datasets which enabled the exploration of the performance of traditional classification and TClustVID. Our analysis found that TClustVID showed higher performance compared to traditional methodologies that are determined by clustering criteria. Finally, we extracted significant topics from the clusters, split them into positive, neutral and negative sentiments, and identified the most frequent topics using the proposed model. This approach is able to rapidly identify commonly prevailing aspects of public opinions and attitudes related to COVID-19 and infection prevention strategies spreading among different populations.

System biology and bioinformatics pipeline to identify comorbidities risk association: Neurodegenerative disorder case study.

Alzheimer's disease (AD) is the commonest progressive neurodegenerative condition in humans, and is currently incurable. A wide spectrum of comorbidities, including other neurodegenerative diseases, are frequently associated with AD. How AD interacts with those comorbidities can be examined by analysing gene expression patterns in affected tissues using bioinformatics tools. We surveyed public data repositories for available gene expression data on tissue from AD subjects and from people affected by neurodegenerative diseases that are often found as comorbidities with AD. We then utilized large set of gene expression data, cell-related data and other public resources through an analytical process to identify functional disease links. This process incorporated gene set enrichment analysis and utilized semantic similarity to give proximity measures. We identified genes with abnormal expressions that were common to AD and its comorbidities, as well as shared gene ontology terms and molecular pathways. Our methodological pipeline was implemented in the R platform as an open-source package and available at the following link: https://github.com/unchowdhury/AD_comorbidity. The pipeline was thus able to identify factors and pathways that may constitute functional links between AD and these common comorbidities by which they affect each others development and progression. This pipeline can also be useful to identify key pathological factors and therapeutic targets for other diseases and disease interactions.

Osteocyte transcriptome mapping identifies a molecular landscape controlling skeletal homeostasis and susceptibility to skeletal disease.

Osteocytes are master regulators of the skeleton. We mapped the transcriptome of osteocytes from different skeletal sites, across age and sexes in mice to reveal genes and molecular programs that control this complex cellular-network. We define an osteocyte transcriptome signature of 1239 genes that distinguishes osteocytes from other cells. 77% have no previously known role in the skeleton and are enriched for genes regulating neuronal network formation, suggesting this programme is important in osteocyte communication. We evaluated 19 skeletal parameters in 733 knockout mouse lines and reveal 26 osteocyte transcriptome signature genes that control bone structure and function. We showed osteocyte transcriptome signature genes are enriched for human orthologs that cause monogenic skeletal disorders (P = 2.4 × 10-22) and are associated with the polygenic diseases osteoporosis (P = 1.8 × 10-13) and osteoarthritis (P = 1.6 × 10-7). Thus, we reveal the molecular landscape that regulates osteocyte network formation and function and establish the importance of osteocytes in human skeletal disease.

Clinically Applicable Machine Learning Approaches to Identify Attributes of Chronic Kidney Disease (CKD) for Use in Low-Cost Diagnostic Screening.

OBJECTIVE: Chronic kidney disease (CKD) is a major public health concern worldwide. High costs of late-stage diagnosis and insufficient testing facilities can contribute to high morbidity and mortality rates in CKD patients, particularly in less developed countries. Thus, early diagnosis aided by vital parameter analytics using affordable computer-aided diagnosis could not only reduce diagnosis costs but improve patient management and outcomes. METHODS: In this study, we developed machine learning models using selective key pathological categories to identify clinical test attributes that will aid in accurate early diagnosis of CKD. Such an approach will save time and costs for diagnostic screening. We have also evaluated the performance of several classifiers with k-fold cross-validation on optimized datasets derived using these selected clinical test attributes. RESULTS: Our results suggest that the optimized datasets with important attributes perform well in diagnosis of CKD using our proposed machine learning models. Furthermore, we evaluated clinical test attributes based on urine and blood tests along with clinical parameters that have low costs of acquisition. The predictive models with the optimized and pathologically categorized attributes set yielded high levels of CKD diagnosis accuracy with random forest (RF) classifier being the best performing. CONCLUSIONS: Our machine learning approach has yielded effective predictive analytics for CKD screening which can be developed as a resource to facilitate improved CKD screening for enhanced and timely treatment plans.

COVID-19 patient transcriptomic and genomic profiling reveals comorbidity interactions with psychiatric disorders.

Psychiatric symptoms are seen in some COVID-19 patients, as direct or indirect sequelae, but it is unclear whether SARS-CoV-2 infection interacts with underlying neuronal or psychiatric susceptibilities. Such interactions might arise from COVID-19 immune responses, from infection of neurons themselves or may reflect social-psychological causes. To clarify this we sought the key gene expression pathways altered in COVID-19 also affected in bipolar disorder, post-traumatic stress disorder (PTSD) and schizophrenia, since this may identify pathways of interaction that could be treatment targets. We performed large scale comparisons of whole transcriptome data and immune factor transcript data in peripheral blood mononuclear cells (PBMC) from COVID-19 patients and patients with psychiatric disorders. We also analysed genome-wide association study (GWAS) data for symptomatic COVID-19 patients, comparing GWAS and whole-genome sequence data from patients with bipolar disorder, PTSD and schizophrenia patients. These studies revealed altered signalling and ontology pathways shared by COVID-19 patients and the three psychiatric disorders. Finally, co-expression and network analyses identified gene clusters common to the conditions. COVID-19 patients had peripheral blood immune system profiles that overlapped with those of patients with psychiatric conditions. From the pathways identified, PTSD profiles were the most highly correlated with COVID-19, perhaps consistent with stress-immune system interactions seen in PTSD. We also revealed common inflammatory pathways that may exacerbate psychiatric disorders, which may support the usage of anti-inflammatory medications in these patients. It also highlights the potential clinical application of multi-level dataset studies in difficult-to-treat psychiatric disorders in this COVID-19 pandemic.