Multimodal CNN-DDI: using multimodal CNN for drug to drug interaction associated events.

Drug-to-drug interaction (DDIs) occurs when a patient consumes multiple drugs. Therefore, it is possible that any medication can influence other drugs' effectiveness. The drug-to-drug interactions are detected based on the interactions of chemical substructures, targets, pathways, and enzymes; therefore, machine learning (ML) and deep learning (DL) techniques are used to find the associated DDI events. The DL model, i.e., Convolutional Neural Network (CNN), is used to analyze the DDI. DDI is based on the 65 different drug-associated events, which is present in the drug bank database. Our model uses the inputs, which are chemical structures (i.e., smiles of drugs), enzymes, pathways, and the target of the drug. Therefore, for the multi-model CNN, we use several layers, activation functions, and features of drugs to achieve better accuracy as compared to traditional prediction algorithms. We perform different experiments on various hyperparameters. We have also carried out experiments on various iterations of drug features in different sets. Our Multi-Modal Convolutional Neural Network - Drug to Drug Interaction (MCNN-DDI) model achieved an accuracy of 90.00% and an AUPR of 94.78%. The results showed that a combination of the drug's features (i.e., chemical substructure, target, and enzyme) performs better in DDIs-associated events prediction than other features.

A comparative proteomic approach using metabolic pathways for the identification of potential drug targets against Helicobacter pylori.

BACKGROUND: Helicobacter pylori is the most highlighted pathogen across the globe especially in developing countries. Severe gastric problems like ulcers, cancers are associated with H. pylori and its prevalence is widespread. Evolution in the genome and cross-resistance with different antibiotics are the major reason of its survival and pandemic resistance against current regimens. OBJECTIVES: To prioritize potential drug target against H. pylori by comparing metabolic pathways of its available strains. METHODS: We used various computational tools to extract metabolic sets of all available (61) strains of H. pylori and performed pan genomics and subtractive genomics analysis to prioritize potential drug target. Additionally, the protein interaction and detailed structure-based studies were performed for further characterization of protein. RESULTS: We found 41 strains showing similar set of metabolic pathways. However, 19 strains were found with unique set of metabolic pathways. The metabolic set of these 19 strains revealed 83 unique proteins and BLAST against human proteome further funneled them to 38 non-homologous proteins. The druggability and essentiality testing further converged our findings to a single unique protein as a potential drug target against H. pylori. CONCLUSION: We prioritized one protein-based drug target which upon subject to applied protocol was found as close homolog of the Saccharopine dehydrogenase. Our study has opened further avenues of research regarding the discovery of new drug targets against H. pylori.