mitoPADdb: A database of mitochondrial proteins associated with diseases.

Mitochondrial protein/gene mutations and expression variations contribute to the pathogenesis of various diseases, such as neurodegenerative and metabolic diseases. Detailed studies on mitochondrial protein-encoding (MPE) genes across diseases can provide clues for novel therapeutic strategies. Here, we collected, compiled, and manually curated the MPE gene mutation and expression variations data and their association with diseases in a single platform named mitoPADdb. The database contains 810 genes with 18,356 mutations and 1284 qualitative expression variations associated with 1793 diseases, grouped into 15 categories. It allows users to perform a comparative quantitative gene expression analysis for 317 transcriptomic studies across disease categories. Further, it provides information on MPE genes-associated molecular pathways. The mitoPADdb is a valuable resource for investigating mitochondrial dysfunction-related diseases. It can be accessed via http://bicresources.jcbose.ac.in/ssaha4/mitopaddb/index.html.

Symptom-based drug prediction of lifestyle-related chronic diseases using unsupervised machine learning techniques.

BACKGROUND AND OBJECTIVES: Lifestyle-related diseases (LSDs) impose a substantial economic burden on patients and health care services. LSDs are chronic in nature and can directly affect the heart and lungs. Therapeutic interventions only based on symptoms can be crucial for prompt treatment initiation in LSDs, as symptoms are the first information available to clinicians. So, this work aims to apply unsupervised machine learning (ML) techniques for developing models to predict drugs from symptoms for LSDs, with a specific focus on pulmonary and heart diseases. METHODS: The drug-disease and disease-symptom associations of 143 LSDs, 1271 drugs, and 305 symptoms were used to compute direct associations between drugs and symptoms. ML models with four different algorithms - K-Means, Bisecting K-Means, Mean Shift, and Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) - were developed to cluster the drugs using symptoms as features. The optimal model was saved in a server for the development of a web application. A web application was developed to perform the prediction based on the optimal model. RESULTS: The Bisecting K-means model showed the best performance with a silhouette coefficient of 0.647 and generated 138 drug clusters. The drugs within the optimal clusters showed good similarity based on i) gene ontology annotations of the gene targets, ii) chemical ontology annotations, and iii) maximum common substructure of the drugs. In the web application, the model also provides a confidence score for each predicted drug while predicting from a new set of input symptoms. CONCLUSION: In summary, direct associations between drugs and symptoms were computed, and those were used to develop a symptom-based drug prediction tool for LSDs with unsupervised ML models. The ML-based prediction can provide a second opinion to clinicians to aid their decision-making for early treatment of LSD patients. The web application (URL - http://bicresources.jcbose.ac.in/ssaha4/sdldpred) can provide a simple interface for all end-users to perform the ML-based prediction.

LHSPred: A web based application for predicting lung health severity.

Background and objectives: The computed tomography (CT) scan facilities are crucial for diagnosis of pulmonary diseases and are overburdened during the current pandemic of novel coronavirus disease 2019 (COVID-19). LHSPred (Lung Health Severity Prediction) is a web based tool that enables users to determine a score that evaluates CT scans, without radiologist intervention, and predict risk of pneumonia with features of blood examination and age of patient. It can help in early assessment of lung health severity of patients without CT-scan results and also enable monitoring of post-COVID lung health for recovered patients. Methods: This tool uses Support Vector Regression (SVR) and Multi-Layer Perceptron Regression (MLPR), trained on COVID-19 patient data reported in the literature. It allows to compute a score (CT severity score) that evaluates the involvement of lesions in lung lobes and to predict risk of pneumonia. A web application was implemented that uses the trained regression models. Results: The application has proven to be effective and user friendly in a clinical setting for pulmonary disease treatment. The SVR model achieved Pearson correlation coefficient (PCC) of 0.77 and mean absolute error (MAE) of 2.239 while determining the computed tomography (CT) severity score. The MLPR model achieved PCC of 0.77 and MAE of 2.309. Thus, it can be applied as a useful tool in predicting pneumonia in the post COVID-19 era. Conclusion: LHSPred can be used as a decision support system by the clinicians and as a tool for self-assessment by the patients with only six blood test input features.