Abstract

Cancer remains a leading cause of morbidity and mortality worldwide. Despite advances in genomics, identifying clinically relevant subtypes of cancer remains challenging due to its complex and heterogeneous nature. This thesis explores the application of network-based stratification (NBS) approaches to stratify cancer types into clinically relevant subtypes, which can aid in precision medicine and targeted therapy efforts. First, we investigate the effectiveness of a standard NBS pipeline using somatic mutation data to stratify Renal Cell Carcinoma (RCC). We explore the impact of network composition on RCC stratification performance and extend the NBS approach to copy number variation (CNV) data for RCC subtyping. Next, we introduce DeepGraphMut (DGM), a novel graph-based deeplearning pipeline that integrates somatic mutation data with protein-protein interaction (PPI) networks. By employing a graph autoencoder with a graph attention layer and a node-level attention decoder, DGM generates patient-specific clinically relevant encodings for unsupervised and supervised tasks. We demonstrate the effectiveness of DGM across 16 cancer types comprising of 7352 samples from The Cancer Genome Atlas (TCGA). Unsupervised clustering reveals distinct subtypes with significant survival differences in 11 cancer types. In supervised analysis using a Cox regression model, DGM demonstrates excellent performance in predicting survival outcomes, achieving a high concordance index (c-index) value in the range of 0.7 across most cancers, underscoring its robust predictive performance using only somatic mutation data. Furthermore, DGM outperforms traditional methods and its lightweight variant in both unsupervised and supervised analyses. In summary, this thesis presents a promising approach for cancer subtype identification and prognosis, especially in resource-limited settings where multi-omics data may not be readily available. By leveraging the strengths of graph learning and network biology, DGM offers a valuable tool for advancing personalized medicine.

Abstract

Application of machine learning methods to two important problems, namely, detection of COVID- 19 using chest radiographs (X-rays and CT scans), and molecular subtyping of breast cancer using multi-omics data is carried out. The recent pandemic made clear the need for fast and reliable tech- niques in distinguishing pneumonia caused by the novel virus SARS-CoV-2 from pneumonia caused by other viral/bacterial/fungal infections. In this work, a basic CNN model was built from scratch and spatial attention-based mechanism (Attn-CNN) incorporated to detect the manifestations of COVID-19 in CXR and CT scan images with improved generalizability and explainability has been developed. The proposed spatial attention-based solution overcomes the need for lung segmentation and region-based annotations for training the CNN models while keeping the model complexity minimized, thus making it deployable in clinical settings. To verify the generalizability of the models, testing has also been carried out on external datasets and explainability has been provided using Grad-CAM visualization of the pixels, selected by the model for classification. Performance evaluation of the proposed approach against five state-of-the-art deep learning models showed 95% accuracy for CXRs and 96% for CT images and outperformed all other models and comparatively generalized well on external datasets. Advancements in the high-throughput techniques have generated large volumes of data, enabling genome-wide profiling of various omics data, such as protein-coding and non-coding (e.g., miRNA, lncRNA, etc.) genes, DNA methylation, and analysis of genetic variations (SNVs, CNVs, etc.). How- ever, identification of diagnostic and prognostic biomarkers is challenging due to heterogeneity at mul- tiple levels and the huge number of features associated with each. This heterogeneity is seen to affect the generalizability and explainability of ML models. To address the high dimensionality and explain- ability issues, a knowledge-based feature selection framework along with a filtering approach using pre- dominant correlations is proposed for multi-omics-based biomarker identification. Breast cancer being hormone-dependent cancer, we considered the molecular subtype classification based on the three hor- mone receptors, viz., estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2): Luminal (ER+, PR±, HER2±), HER2-enriched (ER–, PR–, HER2+), and Triple Negative (ER–, PR–, HER2–). DNA methylation data from protein-coding genes and long non- coding RNAs (lncRNAs) were integrated with gene expression data of the associated genes and copy variant genes for feature selection and classification. Using 172 features obtained from the proposed framework, stratified 5-fold cross-validation was carried out using five ML models. The best perfor- mance is obtained for Random Forest model with an accuracy value of 98.19% and AUC values ≥ 0.98 for all the three classes showing the effectiveness of the proposed approach.

Abstract

Traditional drug discovery and development processes are time-consuming and costly, with only a fraction of compounds progressing to clinical testing and an even smaller percentage making it to mar- ket. To address these challenges, computer-aided drug discovery (CADD) methodologies have emerged as efficient tools for designing and evaluating potential drug candidates. By utilizing computational al- gorithms to model drug-receptor interactions, CADD significantly reduces costs and timeframes associ- ated with lead identification and optimization while maintaining high quality. Integrating deep learning algorithms further enhances drug discovery pipelines by enabling the analysis of molecular structures, genetic data, and biochemical interactions to predict drug efficacy and toxicity, and optimize dosage regimens. Deep learning helps to design new small molecule drugs and peptide drugs. Nowadays, target-based drug design is giving promising results. We propose a novel computational pipeline that leverages single-cell transcriptomic data to identify crucial proteins as drug targets for malaria, a dis- ease with increasing resistance to conventional treatments. Through mutual-information-based feature reduction and protein-protein interaction network analysis, key proteins vital for the survival of Plas- modium falciparum are identified, and potential drug molecules are computationally predicted using deep learning techniques. We can use this pipeline to select targets for any disease for developing drugs. Additionally, we explored peptides as promising therapeutic agents due to their targeted interactions with biological targets and reduced side effects compared to small-molecule drugs. We introduce HY- DRA, a hybrid diffusion model for designing therapeutic peptides tailored to specific target receptors, exemplified by the design of peptides targeting Plasmodium falciparum Erythrocyte Membrane Protein 1 (PfEMP1) genes. HYDRA generates highly stable and diverse peptides based on a protein target. Gene expression is a multifaceted process crucial to understanding molecular biology and pharmacol- ogy. We worked on elucidating the intricate relationship between gene length and kinetic parameters, such as transcription rate (S i ), association rate of transcription factor to bind with DNA (K on ), dissoci- ation rate of transcription faction detached from DNA (K of f ), Burst size (SK of f ), which significantly influence the mean expression levels of genes.Using a two-state stochastic gene expression model im- plemented in Python, we analyzed single-cell transcriptomics data to predict kinetic parameters for each gene. We classified genes into short and long categories, revealing distinct patterns in the relationship between gene length and these parameters. Our results indicate that burst size plays a critical role in mean expression, highlighting its importance for identifying gene targets that require lower drug doses for therapeutic effects. This integrated computational framework holds promise for accelerating drug discovery efforts and combating drug-resistant diseases such as malaria.

Abstract

The convergence of computer vision and advertising analysis has seen progress, but existing adver- tisement datasets remain limited. Many are small subsets of larger datasets, and while larger datasets may offer multiple annotations, they often lack consistent organization across all images, making it challenging to structure ads hierarchically. This lack of clear categorization and overlap in labeling hinders in-depth analysis. To address this, we introduce MAdVerse 1 , a comprehensive, multilingual dataset of over 50,000 advertisements sourced from websites, social media, and e-newspapers. MAd- Verse organizes ads into a hierarchy with 11 primary categories, 51 sub-categories, and 524 specific brands, facilitating fine-grained analysis across a diverse range of brands. We establish baseline perfor- mance metrics for key ad-related tasks, including hierarchical classification, source classification, and hierarchy induction in other ad datasets and, in a multilingual context, thereby providing a structured foundation for advertisement analysis. In our second work, we investigate foundational aspects of out-of-distribution (OOD) detection. Existing OOD benchmarks typically focus on broad, class-level shifts but lack controlled environments for assessing how individual attribute changes such as color or shape affect OOD detection. To bridge this gap, we created two synthetic datasets, SHAPES and CHARS 2 , each designed to allow controlled experimentation with isolated shifts in attributes. Through variations in color, size, rotation, and other factors, these datasets facilitate a targeted examination of OOD detection performance under specific conditions, providing insights into how OOD detection is affected under different attribute shifts. Later, we apply OOD detection methods to advertisements, where models face real-world distribution shifts characteristic of diverse advertising styles. Our contributions, MAdVerse for structured ad analysis and SHAPES and CHARS for controlled OOD studies emphasize the importance of robust, adaptable models for both foundational research and practical applications in advertisement analysis.

Abstract

Geography markup language (GML) is an XML specification for expressing geographical features. Defined by Open Geospatial Consortium (OGC), it is widely used for storage and transmission of maps over the Internet. XML schemas provide the convenience to define custom features profiles in GML for specific needs as seen in widely popular cityGML, simple features profile, coverage, etc. Simple features profile is a simpler subset of GML profile with support for point, line and polygon geometries. SFP has been constructed to make sure it covers most commonly used GML geometries. Web Feature Service (WFS) serves query results in SFP by default. But it falls short of being an ideal choice due to its high verbosity and size-heavy nature, which provides immense scope for compression. Generic text-based compression models are simple and fast but there are two issues that needs to be addressed. They cannot leverage the structure that exists in data to achieve better compression and there is an unnecessary decompression step before the user can actually use the data. To address these issues, we came up with GMZ, a lossless compression model aimed at achieving high compression ratios. The decision to design GMZ exclusively for GML’s Simple Features Profile (SFP) seems fair because of the high use of SFP in WFS and that it facilitates high optimization of the compression model. Our experiments indicate GMZ achieves reasonably good compression ratios and can be useful in WebGIS based applications. In a typical server-client model such as Web Feature Service, the server is the primary creator and provider of GML, and therefore, requires compression and query capabilities. On the other hand, the client is the primary consumer of GML, and therefore, requires decompression and visualization capa- bilities. In the first part of our work, we demonstrated compression using a python script that can be plugged in a server architecture, and decompression and visualization in a web browser using a Firefox add-on. The focus of this work is to develop the already existing tools to provide query capability to server. Our model provides the ability to decompress individual features in isolation, which is an es- sential requirement for realizing query in compressed state. We construct an R-Tree index for spatial data and a custom index for non-spatial data and store these in a separate index file to prevent altering the compression model. This facilitates independent use of compressed GMZ file where index can be constructed when required. The focus of this work is the bounding-box or range query commonly used in WebGIS with provision for other spatial and non-spatial queries. The decrement in compression ra- tios due to the new index file is in the range of 1-3 percent which is trivial considering the benefits of querying in compressed state. With around 75% average compression of the original data, query support in compressed state and decompression support in the browser, GMZ can be a good alternative to GML for WFS-like services.

Abstract

The analysis of digital histopathology slides or Whole Slide Images (WSIs) is critical for several diagnoses. Recent advancements in computational techniques, particularly in the field of digital pathol- ogy, have shown promise in automating the classification process. Whole Slide Imaging (WSI), com- bined with deep learning and modern computer vision techniques, has emerged as a powerful tool in this domain. This thesis addresses two major medical challenges using deep learning and computer vi- sion techniques: the classification of Lupus Nephritis (LN) and low-grade gliomas into their respective subtypes. Systemic lupus erythematosus (SLE) is an autoimmune disease wherein the patient’s immune sys- tem attacks healthy tissues, leading to Lupus Nephritis (LN), a severe condition causing renal failure. Traditional methods for diagnosing LN require meticulous pathological assessment of renal biopsies, which is time-consuming. In the first architecture(chapter 3), We propose a novel pipeline that au- tomates this process by: 1) detecting various glomerular patterns in WSIs using Periodic Acid-Schiff (PAS) stained images, and 2) classifying each image based on these extracted glomerular features. This approach leverages deep learning to improve the accuracy and efficiency of LN classification. Low-grade glioma, a type of brain tumor originating from glial cells, also presents significant diag- nostic challenges due to the large size and complexity of WSIs. In the second architecture(chapter 4), our work involves the classification of low-grade gliomas into Astrocytoma and Oligodendroglioma. Given the computational infeasibility of training deep learning models on gigapixel images, we adopt a weakly supervised method to extract discriminative patches from WSIs, which represent the tumor regions. A Convolutional Neural Network (CNN) is then trained on these discriminative patches, and the results are aggregated to determine the WSI label. Evaluated on a dataset of 581,616 patches from 286 WSIs obtained from The Cancer Genome Atlas (TCGA) portal, our method achieved a slide-wise accuracy of 79.31%, which increased to 89.65% when trained only on discriminative patches. The methodologies presented in this thesis not only demonstrate significant improvements in classi- fication accuracy but also offer scalable and efficient solutions for enhancing the diagnostic processes in pathology, ultimately contributing to better patient outcomes and more efficient healthcare delivery.

Abstract

The rapid growth of deep neural network models in the face domain has led to their adoption in safety-critical applications. However, a crucial limitation hindering their widespread deployment is the lack of comprehensive understanding of how these models work and the inability to explain their de- cisions. Explainability is essential for ensuring the correctness, reliability, and fairness of AI systems, and there is a growing recognition of its importance across AI applications. Despite the significance of explainability, most current methods are designed for general object recognition tasks and cannot be directly applied to the face domain. Faces are highly structured objects, and face tasks often in- volve fine-grained details, making them unique and distinct from general object recognition. This thesis aims to bridge the gap in explainability literature for the face domain by providing novel methods for interpreting and analyzing deep face representations. In this thesis, we embark on a comprehensive journey of interpreting and analyzing deep face repre- sentations to uncover the underlying mechanisms behind DNN-based face-processing models. We first visualize face representations and introduce methods to identify functional concepts in face representa- tions using ’cross-task aware filters’ (CRAFT). Our approach includes an efficient task-aware pruning method using CRAFTs. We also present state-of-the-art Canonical Saliency Maps (CMS) to pinpoint critical input features. We thoroughly analyze deep face representations to understand the learned fea- tures and their functional relevance in different face tasks. To further enhance our understanding of human attention in the context of driving behavior, we investigate driver gaze patterns and develop DashGaze, a large-scale naturalistic driver gaze dataset . Using this dataset, we propose an innovative calibration-free driver gaze estimation algorithm that provides valuable information for studying and predicting driver behavior. The comprehensive overview, experimental studies, and analyses presented in this thesis contribute to the wider adoption of explainability methods in face-processing tasks, enabling safer and more trust- worthy deployment of deep-face algorithms in real-world applications. By shedding light on the inner workings of these models and their biases, this work paves the way for the responsible and ethical development of AI technologies in the face domain.

Abstract

The field of therapeutic peptide design is ripe for transformation, fueled by the convergence of biotechnology and artificial intelligence. Peptides, short chains of amino acids, offer a promising avenue for targeted drug therapies due to their inherent advantages over small molecules, including specificity and reduced side effects. However, the development of peptide therapeutics has been hindered by their limited oral bioavailability and susceptibility to enzymatic degradation. Recent advancements in deep learning techniques have opened new possibilities for addressing these challenges through innovative peptide design strategies. This thesis explores the development of a novel hybrid deep learning framework for de novo peptide design. By harnessing the power of diffusion models, known for their ability to learn complex data distributions, and integrating them with binding affinity maximization algorithms, we have created a system capable of generating peptide sequences optimized for specific target receptors. To demonstrate the applicability of this framework, we focus on designing therapeutic peptides targeting proteins ex- pressed by Plasmodium falciparum Erythrocyte Membrane Protein 1 (PfEMP1) genes, key contributors to malaria pathogenesis. Our results highlight the potential of this hybrid deep learning approach to revolutionize peptide drug discovery. By generating peptide candidates conditioned on the binding sites of target receptors, we offer a promising avenue for developing effective therapies for malaria and other diseases. This research underscores the transformative power of AI in peptide therapeutics, paving the way for a new era of precision medicine with enhanced efficacy and reduced toxicity.

Abstract

Geospatial data capture and handling of indoor spaces is increasing over the years and has had a varied history of data sources ranging from architectural and building drawings to indoor data acquisition approaches. While these have been more data format and information driven primarily for the physical representation of spaces, it is important to note that many application require for the semantic information to be made available for enriching their usecases. This work proposes a space classification model leading to an ontology for indoor spaces that accounts for both the semantic and geometric characteristics of the spaces. Furthermore, a Space semantic model is defined, based on this ontology, which can form the basis for extended data models which can be used appropriately in multiple applications. To demonstrate the utility of the model, an extension to the IndoorGML data standard is presented with a set of proposed classes that can help capture both the syntactic and semantic components of the model. It is expected that these proposed classes can be appropriately harnessed for use in diverse applications ranging from indoor data visualization to more user customised building evacuation path planning with a semantic overtone. The aim of the work presented here is to showcase the benefits of semantically rich indoor data and propose a model to do so. This work hopes to lay a foundation and pave way for more sophisticated and application/domain targeted data models which incorporates both semantic and syntactic properties of indoor space.

Abstract

Non-coding RNAs, including non-coding regions of pre-mRNAs, though they do not code for protein, play key functional and regulatory roles in gene expression at the transcriptional and post-transcriptional stages, influencing a wide range of biological processes. Their huge impact on several molecular mechanisms underpins their contribution to the development and progression of a broad spectrum of diseases, including cancer. With the availability of RNA structurome data and that of advanced RNA folding algorithms, it is possible to study the structural and conformational space spanned by these regulatory RNAs. These studies, in conjunction with detailed investigation of the associated regulatory processes and of genetic diseaserelated variations thereof, could help us in exploring new approaches towards understanding, diagnosing, and managing genetic diseases. We have explored disease-causing RNA structural disruptions called riboSNitches, in the splice junctions of pre-mRNAs, and shortlisted potential riboSNitches associated with somatic cancer mutations, aberrant splice mutations, and genetic diseases. We have developed an approach that is more reliable than other available methods for riboSNitch detection. Circular RNAs (circRNAs), one of the largest classes of non-coding RNAs, have exhibited a regulatory role in gene expression by acting as miRNA sponges. A significant number of studies have explored their capability as therapeutic agents and as biomarkers in several pathological conditions associated with their unique characteristics, such as diversity, stability, and abundance of tissue-specific expression. It was proposed that non-coding RNA transcripts, especially circRNAs and long noncoding RNAs (lncRNAs), form an extensive network by competitively binding to miRNA binding sites. This network, termed ceRNA/competitive endogenous network (circRNA/lncRNA-miRNA-mRNA), was demonstrated to regulate the translation of miRNA target genes. In this study, we proposed ceRNA network construction based on atrial fibrillation, one of the widely studied diseases for ceRNA networks, by exploring the existing approaches. Our review process led to the compilation of results highlighting promising candidate biomarkers for atrial fibrillation. We leveraged our comprehensive ceRNA network construction approach to investigate ceRNA networks in obesity, a disease with limited exploration in the context of ceRNA networks. To elucidate the role of non-coding RNAs in obesity, we constructed a visceral adipose tissue-specific integrated circRNA-miRNA-mRNA network, identified potential miRNA targets that regulate the mechanisms of obesity, and cataloged the circRNAs and miRNAs involved in the molecular pathways contributing to the disease. We also identified the candidate genes that potentially link to obesity-driven type 2 diabetes. To unravel the connections between obesity, diabetes, and cancer, we extended our analysis to pan-cancer data by exploring genes with similar expression patterns in obesity and diabetes. Our findings report associations between these genes and various cancer types that require further exploration to understand their underlying mechanisms. Taken together, our studies on non-coding circular RNAs and structure-disrupting mutations in the splice junctions of pre-mRNAs that regulate gene expression a) provide insights into the gene-specific and disease-specific mechanisms and b) identify potential biomarkers and regulatory RNA structures that can be explored for RNA-based therapies