M.Phil / MS
Permanent URI for this collectionhttps://repository.cuilahore.edu.pk/handle/123456789/52
This collection archives the complete set of theses produced by students of the COMSATS University Islamabad, Lahore Campus.
Browse
4 results
Search Results
Item Graph Topological Indices and Machine Learning for Protein Networks and Drug Property Prediction(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Ahmad Mehmood; CIIT/SP24-RMT-025/LHR; Dr. Sana Javed; LHR TP 10085Molecular property prediction for drugs is an integral part of computational chemistry in the early stages of drug discovery for efficient screening and optimization before experi- mental verification. In the present work, an exhaustive and interpretable machine learning (ML) strategy is proposed that combines SMILES-based molecular feature extraction with topological indices using molecular graph theoretical approaches for the prediction of key physicochemical properties of drugs. The dataset consisting of forty-seven pharmacolog- ically active molecules from DrugBank, with their structures characterized using sixteen topological descriptors such as the Wiener, Balaban, Harary, Randi´c, Zagreb, Schultz, and Shannon Entropy indexes, were identified using the RDKit grouping library coupled with mathematical formulations from molecular graph theory. Preprocessing steps were per- formed rigorously for missing values using imputation; removal with cutoffs using the inter-quartile range method; variance for stabilization using the Box-Cox transformation; and normalization with MinMax scaling. Four different regression models, namely Ordi- nary Least Squares (OLS), Ridge Regression, LASSO, and Elastic Net algorithms, were employed for the prediction of the MW, LogP, and HBD properties for the dataset with evaluations made in terms of R2, MAE, and Root MSE metrics; with feature interpreta- tion from SHapley Additive exPlanations (SHAP) analyses for feature interpretation. The results achieved for MW with high predictive precision with R2 ≈ 0.96 using linear mod- els effectively; moderate accuracy with R2 ≈ 0.4 for Lipophilicity; with poorer accuracy for HBD values likely due to their dependence on chemical principles underlying chem- ical groupings in chemistry. The interpretation using SHAP explained the contributions made by the Shannon entropy, Wiener, Zagreb, Schultz indices being the principal predic- ix tors in each case. The present work clearly illustrates the utility of integrating molecular chem-graph principles with interpretable ML algorithms for efficient, scalable, and insight- ful property-based predictions in early stage computational screens for drug identification strategies. Protein-protein interactions (PPIs) networks are very important to decode cellular signal- ing and mechanisms of disease. PPI also play a key to spot possible drug targets. A strong computational strategy is presented in this paper. It unites the graph theoretic approach with unsupervised machine learning. This study is used to detect biologically significant hub genes in a large scale lung cancer associated PPI network. The network retrieved from the STRING database (461 proteins, 18,704 weighted interactions). Using NetworkX, we constructed an undirected graph by extracting source and target node from the dataset. We computed 17 comprehensive topological centrality measures, confirming the networks scale free and small world properties (average clustering coefficient = 0.67, average short- est path length ≈ 1.96). The Isolation Forest algorithm identified 61 topological outliers. These outliers were related to nodes which had a very high influence. The K-means cluster- ing (that was optimized by the elbow curve) sorted the rest of the nodes into three groups. The hub genes were given ranks according to degree centrality and a composite centrality score. Among the genes, CALM3, CREB1, AKT1, MAPK1, EGFR and KRAS came out as the strongest candidates. The pathway enrichment analysis performed with KEGG and Reactome showed that the oncogenic pathways were remarkably over represented. These pathways were PI3KAkt, Ras, MAPK, and proteoglycans in cancer and EGFR signaling. Our methodology, which combines together the multiple centrality metrics, anomaly de- tection, and clustering, has indeed solved the drawbacks of traditional single metric ap- proaches. It has also provided greater sensitivity in hub detection. The hubs that were identified not only correspond to the well established lung cancer drivers but also point to potential novel biomarkers. The detected targets are thus a scalable and reproducible pipeline for systems level analysis of disease specific interactomesItem Emerging Patterns in Machine Learning for Disease Detection(Library Information Services COMSATS University Lahore Campus, 2024-03-18) Shagufta Mufeez; SP23-RMT-038; Dr. Sana Javed; LHR TP 9582The growing number of diseases and disorders worldwide further supports the need for prompt and precise diagnosis and classification. Understanding how disease diagnosis can be enhanced through the use of reliable computational techniques including pre process ing approaches, feature selection methods, and hyper parameter tuning with Grid Search Cross-Validation (Grid Search CV), primarily boosts and optimizes feature selection from the machine learning field is the goal of this thesis.” These procedures are essential for ad dressing problems with the developed models’ performance, interpretability, and depend ability. The dataset in the context of disease classification is a comprehensive collection of mea sures. Missing values and encoding have been addressed at the pre processing stage of the data handling process to guarantee a stable and clean baseline for the subsequent steps. Feature selection techniques are employed in order to eliminate insignificant instances and prevent the issue of their dominance. Decision Tree, Random Forest, Support Vector Classifier (SVC), XG Boost, Light GBM and CAT Boost are the six machine learning models that were applied to the dataset. The Grid Search Cross Validation process, which enables the proper configuration of hyper pa rameters, is used to tune the parameters of each model. The evaluation metrics such as confusion matrix, accuracy, precision, recall and F1 score are used to assess models’ per formance. These findings demonstrate how feature selection and hyperparameter modification may be used to enhance the model. This is an interesting finding that raises the possibility of using machine learning to increase early diagnosis rates and decrease diagnostic errors. This study advances the field of machine learning in healthcare and offers a method for effectively and efficiently detecting illnesses.Item Machine Learning Methodologies for Forecasting Drug Properties and Identifying Disease Indicators(Library Information Services COMSATS University Lahore Campus, 2024-03) Muhammad Owais; FA22-RMT-015; Dr. Sana Javed; LHR TP 9385This thesis investigates the use of machine learning approaches to predict and analyze drug properties in terms of topological indices, which are important for understanding their chemical and biological characteristics. Topological indices, generated from graphical rep resentation of chemical formation of a drug, give a measurable assessment of the molecule’s structure and are widely utilized in drug design and discovery. This study uses advanced machine learning methods to improve the accuracy and efficiency of predicting the drug property namely molecular weight, allowing for faster screening and optimization of med ication candidates. The number of patients registered to the hospitals diagnosed with liver disorder is very high. ML approaches might be utilized to overcome the burden on the doctors by developing accurate classifiers for disease prediction. It is also advantageous to detect the key factors involved in the development of the disease so that precautionary measures might be taken for prevention. This thesis is also focused to develop a machine learning classifier to predict liver disease.Item Exploring Various Diseases Based on Regularized Machine Learning Approaches(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Iqra Iqbal Khan; FA23-RMT-015; Dr. Sana Javed; LHR TP 9762The early diagnosis of physical and mental health issues is critically important in avoiding complications and enhancing patient outcomes. This thesis investigates the predictive po tential of regularized machine learning methods that predict and quantify the risk of disease; especially in eating disorders and stroke, on three different datasets. The thesis focuses on trade-offs between the performance and interpretability of regularized models (Lasso, Ridge, ElasticNet) as well as comparing them to non-regularized methods (ensemble trees, Support Vector Regression, etc). In the prediction of eating disorders, four preprocessing techniques: standard scaling, PCA, power transformation, and combination of these meth ods were compared through different models. Ensemble methods and SVR in every case produced a higher predictive accuracy, but regularized models were more interpretable and performed consistently across preprocessing conditions. The use of the same set of models on synthetic mental health data revealed lower accuracy across all models but especially the tree-based and SVR models. The regularized models showed, however, more consis tent performance, revealing the limitations of synthetic data in storing complex correlations between variables. Partial Least Squares (PLS) regression achieved the best accuracy when predicting stroke. Regularized models were used on PLS component and showed similar performance supporting their usefulness in terms of capturing important signal patterns and model simplicity. In sum, this thesis emphasizes the comparative advantage of regular ized machine learning in disease prediction extending to balanced accuracy, stability, and interpretability.