Computational Biology

Mechanism-informed, AI-driven frameworks for discovery and validation of aging-associated chemical space

2026-04-29T22:00:10Z

Mechanism-informed, AI-driven frameworks for discovery and validation of aging-associated chemical space Arora, Sakshi; Ahuja, Gaurav (Advisor) Aging is a progressive, multifactorial biological process that drives the risk of nearly all major chronic diseases, including cancer, neurodegeneration, metabolic disorders, frailty, and cardiovascular dysfunction. Although the past two decades have established a molecular framework through the Hallmarks of Aging, translating this knowledge into actionable, small-molecule interventions that enhance healthspan remains a central challenge in the field of geroscience. Experimental discovery pipelines are slow, resource-intensive, and typically explore only a minute fraction of chemical space. Conversely, computational drug discovery approaches, while high-throughput, often rely on chemistry-centric descriptors, exhibit black-box behavior, lack mechanistic interpretability, and rarely generalize to biologically novel molecules. This thesis addresses these long-standing limitations by developing two complementary artificial intelligence systems, AgeXtend and AgeXtend:: Mimetics, designed to accelerate mechanism-informed discovery of geroprotective molecules and caloric restriction mimetics (CRMs). The first objective introduces AgeXtend, a multimodal, bioactivity-driven, and fully explainable AI framework. AgeXtend integrates curated datasets of experimentally validated geroprotectors and neutral compounds with bioactivity-based descriptors, hallmark-specific classification models, toxicity prediction, and target inference modules. By combining mechanistic knowledge with machine learning, AgeXtend achieves robust predictive accuracy across cross-validation, leave-one-out validation, and independent external datasets. Importantly, the explainability module maps predictions onto nine aging pathways, allowing for a mechanistic interpretation of each compound’s mode of action. Large-scale screening of ~1.1 billion compounds yielded diverse chemical classes with strong geroprotective potential. Experimental validation confirmed these predictions across three biological systems: Saccharomyces cerevisiae chronological lifespan assays, human fibroblast senescence assays, and Celegans lifespan assays. Endogenous metabolites and repurposed drugs predicted by AgeXtend demonstrated lifespan-extending or senomodulatory activity, underscoring the biological fidelity of its predictions. Building upon this foundation, the second objective presents AgeXtend::Mimetics, a novel computational framework designed to identify Caloric Restriction Mimetics, compounds capable of reproducing CR-like physiological responses without structural similarity to known CRMs. Unlike existing approaches that rely on transcriptomic signatures alone or structural matching, AgeXtend::Mimetics explicitly decouples biological convergence from chemical divergence. Using dual similarity modeling, ridge regression residuals, supervised contrastive learning, and composite CRM fingerprinting, the framework identifies molecules whose biological signatures align strongly with known CRMs despite having distinct chemical architectures. Large-scale application across thousands of compounds revealed chemically novel, mechanistically plausible CRM candidates that align with pathways such as nutrient sensing, autophagy, mitochondrial remodeling, and metabolic regulation. This framework substantially broadens the chemical landscape of CRM discovery and provides mechanistic clarity on CRM-like effects. Together, the approaches developed in this thesis demonstrate that explainable, mechanism-oriented AI models can successfully bridge the gap between large-scale chemical exploration and biological relevance. AgeXtend and AgeXtend::Mimetics collectively advance the field of computational geroscience by enabling scalable, interpretable, and experimentally validated discovery of geroprotectors and CRMs. These contributions lay the groundwork for future translational studies, the development of generative design for longevity therapeutics, and the integration of multi-omic datasets to refine mechanism-based discovery pipelines. The thesis highlights both the promise and current limitations of AI in aging biology, providing a roadmap for next-generation computational frameworks that target healthspan extension.

Benchmarking fold recovery: implicit-solvent atomistic & coarse grained simulations of two vs non two state proteins

2026-04-20T22:00:32Z

Benchmarking fold recovery: implicit-solvent atomistic & coarse grained simulations of two vs non two state proteins Das, Mimansha; Murugan, N. Arul (Advisor) Protein folding is a fundamental biological process through which a polypeptide adopts its functional three-dimensional structure. In this study, we systematically investigated the structural response of proteins to thermal denaturation using both atomistic and coarse-grained (CG) molecular dynamics simulations. A curated set of 138 proteins from the PFDB (89 two-state and 49 non-two-state folders) was subjected to a heat–quench protocol (300 K → 1000 K → 300 K) in implicit solvent. Structural recovery was assessed through RMSD and radius of gyration (Rg) calculations after Kabsch superimposition, alongside MM/PBSA energy evaluations. Post-quench alignment revealed distinct behaviors: two-state proteins consistently showed lower RMSD, greater compaction (ΔRg < 0), and higher native contact retention than non-two-state proteins. Furthermore, a significant inverse correlation was observed between log10(kf) and final RMSD in the two-state subset, linking folding rate to structural resilience. Results from CG simulations mirrored these trends, validating their utility for rapid, cost-effective screening. These findings underscore the importance of structural alignment in post-simulation analysis and highlight heat–quench recovery as a powerful proxy for foldability. The combined pipeline offers a scalable framework for evaluating folding kinetics and native-state robustness across protein families.

Challenges in the prediction of half-life of lncRNAs

2026-04-20T22:00:32Z

Challenges in the prediction of half-life of lncRNAs Shuhail, Shaikh; Raghava, Gajendra Pal Singh (Advisor) Long non-coding RNAs (lncRNAs) are key regulators of gene expression, and their stability, commonly quantified as half-life, plays a critical role in cellular function. Recent computational efforts have attempted to predict RNA half-life from sequence, with limited success. For instance, Shi et al. applied deep learning models and initially reported spearman correlations of 0.7–0.8, but performance dropped to 0.06–0.09 after five-fold validation. In this study, we developed machine learning and deep learning models using sequence-derived features to predict lncRNA half-life. Among the approaches tested, Random Forest based on nucleotide composition features performed best, achieving a spearman correlation of 0.9862 on the training dataset but only 0.0592 on the validation dataset. Furthermore, clustering analysis revealed that different transcript groups exhibited nearly identical mean half-life distributions, indicating that sequence-derived features alone do not meaningfully stratify lncRNAs by stability. These results, consistent with prior studies, demonstrate the persistent difficulty of predicting RNA half-life in silico. Further, inclusion of features such as RNA–binding protein motifs, structure–based minimum free energy and sub–cellular localization did not improve the model performances. This suggests that RNA stability is regulated by features beyond those included. Therefore, in this paper, we outline the approaches studied and the challenges to predict the RNA stability, further highlighting the need to integrate multi-omic strategy or design an algorithm to predict RNA half-life.

Role of cofactors/co-enzymes in stabilizing protein-ligand complexes

2026-04-20T22:00:31Z

Role of cofactors/co-enzymes in stabilizing protein-ligand complexes Anand, Harnoor Kaur; Murugan, N. Arul (Advisor) Flavin adenine dinucleotide (FAD) is a ubiquitous redox cofactor that plays a fundamental role in various metabolic and enzymatic reactions. It is involved in electron transfer processes essential for cellular respiration, energy production, and redox homeostasis. Beyond its classical biochemical functions, recent research has suggested that FAD may serve as a promising drug target, particularly in the context of neurological diseases, where alterations in flavoproteins and redox imbalances contribute to disease progression. Despite its well-established role in enzymatic catalysis, the contribution of FAD to the overall stability of protein-ligand complexes remains an open question. Investigating how FAD influences ligand binding and protein conformational dynamics is crucial for understanding its potential as a therapeutic target. In this study, we employed molecular dynamics (MD) simulations in an explicit solvent environment to analyze the interaction energy of protein-ligand complexes containing FAD. A set of diverse protein systems with FAD-dependent interactions was selected, and each complex was subjected to long-timescale MD simulations to capture its structural and energetic properties. By applying energy decomposition analysis, we calculated the interaction energies of all residues within the system, with a particular focus on FAD and the ligand. This allowed us to quantify the contribution of FAD to the stability of the complex and assess its role in modulating ligand interactions. To further understand the structural consequences of FAD removal, volumetric analysis was performed to compare the binding pocket volumes in the presence and absence of FAD. This analysis provided insights into whether the cofactor-induced conformational changes in the binding site, potentially affecting ligand binding and protein function. The comparison of pocket volumes aimed to reveal possible allosteric effects exerted by FAD, shedding light on its stabilizing role within the protein-ligand system. Our findings highlight the importance of FAD in modulating protein-ligand interactions, both from an energetic and structural perspective. The study provides a detailed understanding of how FAD contributes to the stability of protein-ligand complexes and underscores its potential as a target in drug discovery efforts for neurological diseases. By elucidating the molecular mechanisms through which FAD influences binding interactions, this work lays the foundation for future studies exploring FAD-targeted therapeutic strategies. These insights could be particularly valuable in the design of small-molecule inhibitors or modulators that exploit FAD’s structural and energetic role in protein function.