http://repository.iiitd.edu.in/xmlui/handle/123456789/1315 Year-2023 2026-04-11T13:23:18Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1696 Computational design of multi-targeting lead-compounds to disrupt quorum sensing pathway for combating drug-resistant gramnegative bacteria superbugs Yadav, Dilip Kumar; Murugan, N Arul (Advisor); Sharma, D K (Advisor) 2023-12-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1346 Machine learning and deep learning models for solvation energy prediction Tejas; Murugan, N Arul (Advisor) Drug discovery is divided into 4 phases. The first phase is in-silico processes beginning with target identification and validation, followed by the hit discovery process, assay development, high throughput screening, preparing lead, and lead optimization. Screening through all the hits is experimentally unfeasible in terms of both time and resources. Henceforth in-silico models have been developed to predict the properties such as protein-ligand binding affinity, ligand permeability and so on. Here in this thesis, the property in focus is Solvation Energy which provides us with ligand dissolution energy during the protein-ligand binding process in an aqueous medium. The classical mechanics and quantum mechanics-based deterministic approaches can be employed to predict the solvation energies, but these approaches are computationally very demanding. Machine learning and deep learning methods can be used, which can provide reliable results and can be computationally less demanding. Here ten Graph-based deep learning models have been trained using graph representations in combination with two featurizers which help in featurizing the input molecules. Various unsupervised mechanisms like convolution, attention mechanisms, and supervised mechanism interaction networks are implemented for solvation energy prediction. These algorithms work upon graph representations constructed from input molecules by mapping atoms to vertices and bonds to edges. Apart from these three, machine learning models are also trained on different types of descriptors. Weave and CIGIN models perform best in graph-based deep learning algorithms trained on the FreeSolv dataset. Among different machine learning models, the random forest model is found to work best on both datasets of FreeSolv and MNSol. In this thesis, we establish that reliable machine learning and deep learning models can be developed for predicting the solvation energies 2023-08-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1345 ThpPred: an ML based tool for predicting therapeutic proteins/peptides Gupta, Srijanee; Raghava, Gajendra Pal Singh (Advisor) ThpPred is a web-based tool, developed for predicting druggable proteins/peptides. The main dataset used in this study contained 356 therapeutic proteins/peptides and 356 random proteins/peptides, curated from DrugBank, Uniprot and other sources. In order to provide a fair assessment, we did internal validation on 80% of the data and external validation on the remaining 20%. In this study, we have implemented the following methods for predicting druggability of proteins/peptides; i) machine learning models on features chosen using SVC-L1, Variance Threshold, and correlation coefficient; ii) machine learning models on single feature (AAC, DPC & TPC); and iii) MERCI-based motif search. The goal was to construct the best model and install it on a web server by training it on protein sequences of already existing medications. When compared to other models, the XGB-based model performed the best on AAC features and obtained maximum AUCs of 0.91 and 0.91 on the training and validation datasets, respectively for the alternate dataset consisting of 356 positive sequences and 3560 negative sequences. On the other hand, the RF-based model performed admirably on DPC features and obtained maximum AUCs of 0.91 and 0.89 on the training and validation datasets for the main dataset. The AUC score and accuracy for both datasets improved when motif labels were added to ML predicted labels. ThpPred was created to determine if a protein is therapeutic or not by combining motif search with RF and XGB models. The platform helps the scientific community create more effective protein-based medicines by providing a free web server and a standalone package. Overall, the results of the study indicate that ThpPred has the potential to improve the development of pharmaceuticals and protein-based treatments for the treatment of numerous diseases. 2023-07-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1344 Analysis of gene expression and structural variations in common genes across populations: implications for cardiovascular disease and reverse cholesterol pathway Verma, Shivansh; Ray, Arjun (Advisor) Cardiovascular disease (CVD) remains a significant global health challenge, influenced by a complex interplay of genetic and environmental factors. Dysregulated lipid metabolism, a key contributor to CVD, disrupts cholesterol balance and triggers atherosclerotic plaque formation. Understanding how genetics affect lipid balance is crucial for innovative treatments. This study focuses on lipid metabolism, vital for heart health, and its genetic influencers. We combine insights from three independent studies, each uncovering genetic links to lipid metabolism. By merging these findings, we aim for a comprehensive understanding of the genetic landscape. Initially, we identify important genes from each study and then connect them across diverse populations. These genes hold the key to understanding the genetic basis of CVD. Our research delves into how genetic variations impact protein-ligand interactions in terms of binding energy related to lipid metabolism, using virtual screening. We use a method called molecular docking with Autodock Vina, assessing binding energies among 54,162 compounds. To understand the significance of binding energy differences, we use a statistical test (Kolmogorov-Smirnov or K-S test), revealing significant variations in binding energies for specific genes. A significance level (p-value) of 0.05 guides our findings. Our analysis uncovers intriguing insights, highlighting specific genetic variations that cause significant changes in binding energy. These variations can greatly affect crucial protein-ligand interactions, influencing the function of these proteins. For instance, variants like THOC5 V579I, NPC1 R1266Q, NPC1 M642I, NPC1 I858V, NPC1 H215R, ABCA1 V825I, ABCA1 R219K, and ABCA1 K1587R display noticeable differences in binding energies. In contrast, variants like THOC5 V525I, MECR F96L, ENPP2 S493P, and CBR4 L70M show minimal changes, implying less impact on binding energy hence protein-ligand interactions. Our study advances our understanding of how genetic variations impact dynamic protein-ligand interactions in terms of binding affinity. These variations could affect protein function, influencing lipid metabolism and heart health. Notably, we identify genetic variants associated with significant changes in binding energies, potentially altering protein-ligand interactions linked to lipid metabolism. These findings extend to lipid balance and the Reverse Cholesterol Transport pathway, both essential for heart health. The study’s importance lies in its innovative approach to studying how genetic variants impact lipid metabolism at the molecular level. By combining virtual screening and statistical analysis, we identify genetic variations that potentially affect protein binding energies, offering insights into treating lipid-related disorders and CVD. 2023-08-01T00:00:00Z