http://repository.iiitd.edu.in/xmlui/handle/123456789/1637 2026-04-11T03:17:36Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1694 Integrated large-scale analysis of disease signatures in oral microbiomes Shete, Omprakash; Ghosh, Tarini Shankar (Advisor) Oral health is essential for overall human well-being, with oral diseases impacting 3.5 billion people worldwide every year (WHO Report 2022). Oral microbiome is considered as the 2nd most abundant human body site with respect to microbial composition and diversity. Earlier studies have shown the variation in the oral microbiome in case of different oral and systemic diseases. This variation is associated with variety of endogenous and exogenous factors which include host lifestyle, drug use, host status, environmental factors etc. However, a complete understanding of the alterations of the oral microbiome across diseases (along with shared disease signatures, if any) is still lacking. To investigate this, we have done an extensive meta-analysis of 17,031 Oral Microbiomes encompassing 48 different study cohorts and 29 diseases from 24 different countries across the globe, where we have analysed study-specific effects and the association of diseases with the oral microbiome. We observe that approximately 71% of studies have a significant association of oral alterations with different diseases. However, the age-specific variations in the oral microbial community play a key role as a confounder of these association patterns. We identify variabilities in the number of disease-gained and disease-lost across different diseases, and finally, we identify a shared signature of generic disease signature across oral microbiomes from different studies. 2024-08-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1690 AgAnt : a computational tool to assess the mode of interaction between a protein-ligand complex Choudhary, Bhumika; Ray, Arjun (Advisor) Protein-ligand interactions are fundamental in regulating protein activity within cellular environments, playing a pivotal role in numerous biochemical processes. These interaction studies are important for understanding the mechanisms of biological regulation, and they provide a theoretical basis for the design and discovery of new drug targets. Traditionally, till date, these interactions are uncovered based on simple binding energy calculations. Yet, the lacunae of no functional information arising from these interaction studies remains the biggest challenge. The complexity of these interactions increases when ligands can function as either agonists or antagonists, contingent on specific conditions. Understanding these functional dynamics is crucial for advancing drug discovery and development. This project aims to harness machine learning (ML) techniques to classify agonist and antagonist molecules that relate the biological response of the complexes, based on their mode of action, to their structural features, including hydrophobic, electronic, steric, and topological parameters. The main goal of this study is to make use of limited information to create more general models that cover a wider variety of protein-ligand interactions. This is different from traditional methods that usually focus on specific targets or ligands. In this study, we developed a robust computational tool capable of classifying any proteinligand complex responses as either agonist or antagonist with a test accuracy of 0.87 and precision of 0.91. We also conducted extensive validation of the model on diverse datasets to ensure its accuracy and reliability in predicting protein-ligand interactions. This novel tool demonstrates the ability to interpret and generalize effectively, ensuring precise classification of the mode of action of any specific ligand-protein pair. 2024-08-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1674 A deep learning approach for predicting antimicrobial resistance across various bacterial species using whole genome sequence Muddemmanavar, Prateeksha; Sengupta, Debarka (Advisor) Antimicrobial resistance (AMR) presents an immediate threat to public health as microorganisms evolve to resist antimicrobial drugs, leading to challenging or untreatable infections. AMR-related costs could exceed 1 trillion dollars globally by 2050, surpassing major causes of death. In 2019, AMR directly caused 1.27 million deaths worldwide, surpassing mortality rates of HIV/AIDS and malaria. In particular, tuberculosis (TB) claimed 1.3 million lives in 2022, ranking as the second most prevalent infectious disease globally. This study introduces in silico approach utilizing deep learning to analyze the entire genome sequence of top pathogens such as Escherichia coli, Staphylococcus aureus, Klebsiella pneumonia, Streptococcus pneumonia, Pseudomonas aeruginosa, and Mycobacterium tuberculosis. The goal is to swiftly and accurately predict a pathogen’s resistance to specific drugs, eliminating the necessity for complex laboratory experiments. In addition to employing the standard label encoding technique, this study introduces three novel encoding methods for mutational data: transition- transversion encoding, codon frequency encoding, and gene based codon gain. These novel techniques are the major contribution of this study. Prediction of the AMR profile of the patient’s pathogen against various drugs is crucial before prescribing treatment. This approach helps in identifying the most appropriate drug that will be effective in treating the patient at the early stage, thereby reducing the likelihood of treatment failure caused by prescribing a drug to which the pathogen is resistant. While the model’s performance varies across different drugs and pathogens, it demonstrates the potential for application in antimicrobial resistance prediction. 2024-05-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1673 Deep learning based molecule generation for developing novel therapeutics for neurodegenerative diseases Joshi, Piyush; Murugan, N. Arul (Advisor) Deep learning models and generative AI have revolutionized drug discovery, especially with regard to neurodegenerative diseases like Alzheimer's. The developing of canonical SMILES (Simplified Molecular Input Line Entry System) for certain targets, such as BACE (Beta-secretase),a crucial enzyme linked to the disease progression of neurodegenerative disease, is a noteworthy application of these technologies. These models make use of large datasets to identify complex patterns in chemical structures, which allows them to synthesize new compounds with the necessary properties. The trick with BACE is to design compounds that can block its action only, without causing unwanted side effects.Driven by advanced deep learning architectures like transformers or bidirectional recurrent neural networks (RNNs), generative AI generates and refines SMILES strings iteratively until they meet predetermined standards for drug-like qualities, selectivity, and efficacy. This method drastically shortens the time and cost required for experimental synthesis and assessment, which speeds up the drug discovery process. These AI-driven approaches also make it easier to explore over large chemical landscapes, which may reveal new treatment prospects that traditional approaches might miss.As generative AI is iterative, researchers may gradually refine and enhance the quality of the compounds that are produced. Through the integration of feedback derived from computational assessments and experimental data, the model is capable of improving upon its errors and producing BACE inhibitors that are more potent and the compounds that are produced are docked against the BACE molecule to calculate the biding affinity,how effectively the molecule can bind with the BACE molecule. Iterative processes reduce the need for expensive and time-consuming laboratory studies while accelerating the identification of promising drugs candidates.Apart from producing new compounds, generative AI can also be applied to refine lead compounds that already exist for improved BACE inhibition. Through iterative modifications of the molecules based on feedback from experiments and computer predictions, researchers can optimize the attributes of lead compounds to enhance their safety, selectivity, and efficacy. All things considered, deep learning models and generative AI have great potential to advance drug discovery for neurodegenerative illnesses. These technologies enable researchers to find Alzheimer's and other debilitating disorders' cures more quickly by fusing complex algorithms with computational capacity. There is growing optimism over the development of transformational therapeutics for neurodegenerative disorders as ongoing research continues to hone and enhance the capabilities of generative AI and deep learning models. 2024-05-01T00:00:00Z