Abstract

Parkinson’s Disease (PD) neurodegenerative disorder which lacks reliable early diagnostic tests. In this study, we present a method for PD prediction that uses multimodal data from the Parkinson Progression Marker Initiative (PPMI), specifically clinico-demographic, biospecimen, and genetic data, to improve predictive accuracy and facilitate timely interventions via a multimodal machine learning approach. We evaluated data obtained from 598 participants (171 healthy controls and 427 PD patients) in three different modalities: 29 clinical features, five cerebrospinal fluid biomarkers, and 154 SNPs (single nucleotide polymorphisms), which were selected through a biology-driven feature selection method. We utilized three multimodal integration strategies—early, intermediate, and late—and trained various machine learning models, including LightGBM and Multilayer Perceptron (MLP), each of which was optimized by hyperparameter tuning and cross-validation. In early integration, we combined feature sets from all modalities into a single set, leveraging complementary information to increase predictive power. The intermediate integration method made use of autoencoders to encode features into a single 12 dimensional vector as the input into a Neural Network classifier. Late integration combined outputs from the top-performing models for each modality using ensemble techniques such as Voting Classifier and Stacking. We found that early integration achieved the highest performance, with Support Vector Machines with 90% accuracy, 0.98 AUC-ROC, 0.99 precision, and 0.93 F1 score. Intermediate integration with the Neural Network classifier followed with an AUC-ROC of 0.84 and an F1-score of 0.85. Our feature importance analysis identified two clinical scores, namely UPSIT (related to sensory decline) and SCOPA (measuring autonomic dysfunction), along with two SNPs (chr4 90755939 A G and chr4 90646886 G A, both previously linked to PD susceptibility) as crucial predictors, emphasizing their well established relevance in PD diagnosis. Early diagnosis and treatment of PD patients are facilitated by the integration of multiple data modalities, which also greatly increases the predicted accuracy for the disease while also providing us with a thorough understanding of its complexity.

Abstract

Aberrant genome-wide DNA methylation patterns is common in cancers. Understanding how these affect the transcriptome can provide insights into subtype specific development and progression of tumorigenesis. In this study we carried out genome-wide analysis of DNA methylation and gene expression profiles in TCGA-BRCA breast cancer samples to propose a novel set of 35 methylation-based prognostic markers that may provide insights to molecular subtype specific disease stratification. Gene-set enrichment and pathway analysis of the predicted markers using MSigDB and DAVID revealed their role in mammary gland development pathway, various signaling pathways (ERBB2, NOTCH, etc.), and other cancer pathways, and show clear association with genes affected by hormone receptor status. We further show the discriminative power of the proposed DNA methylation signature in classifying breast cancer samples into three molecular subtypes, viz., Luminal, HER2-enriched and Triple Negative. An accuracy of 94.12% and MCC of 0.87 is obtained in stratified 5-fold cross-validation for the three-class classification using SVM-RBF

Abstract

The rising cost of drug discovery, coupled with a stagnation in the approval of novel treatments, highlights the urgent need for innovative strategies such as drug re-purposing. Pharmaceutical companies invest roughly 10-15 years and $2.6 billion to get a single FDA-approved drug to market. The COVID-19 pandemic further underscored the necessity of quickly identifying existing drugs with potential efficacy against a fast-spreading virus to curtail the pandemic. In this study, we perform a comparative analysis of several Graph Neural Networks (GNNs) and recommendation system models to address drug re-purposing. We construct an integrated graph that combines Protein-Protein Interaction networks, Drug-Target Protein graphs, Disease-Protein associations, and Drug-Disease links. We leverage a network learning paradigm implemented over this complex graph via both node-agnostic and heterogeneous graph techniques for link prediction in drug-disease pairs. We implement a Heterogeneous Graph Transformer (HGT) model that processes three node types (drugs, diseases, proteins) and four edge types. The HGT achieved an AUC-ROC of 0.985 and an F1-score of 0.90, demonstrating its efficacy in predicting drug re-purposing candidates. Additionally, we compared several node-agnostic GNN architectures, including Graph Convolutional Networks, Graph Attention Networks, GraphSAGE, and Graph Isomorphism Networks. All architectures performed comparably, with an AUC-ROC of around 0.98. However, when framing the drug re-purposing task as a recommendation problem using Matrix Factorization with side information, we observed a significant drop in performance, with the AUC-ROC falling to 0.82. This performance degradation highlights the importance of incorporating Protein-Protein Interaction networks in the modelling process, as matrix factorization fails to capture these complex network effects critical for drug re-purposing. Our models ranked 6,158 drugs based on their predicted efficacy in treating COVID-19, providing a valuable tool for prioritizing clinical trials and further research. Beyond COVID-19, such an integrated framework can allow us to uncover drug re-purposing prospects for any other novel diseases in a significantly more efficient and cost-effective way.

Abstract

Deep learning assisted diagnosis for assessing the severity of various respiratory infections using chest Computed Tomography (CT) scan images has gained much attention after the COVID-19 pandemic. Major tasks while building such models require an understanding of the characteristic features associated with the disease, patient-to-patient variations and changes associated with disease severity. In this work, an attention-based Convolutional Neural Network (CNN) model with customized bottleneck residual module (Attn-CNN) is proposed for classifying CT images into three classes: COVID-19, Normal, and other Pneumonia. The efficacy of the model is evaluated by carrying out various experiments, such as effect of class imbalance, impact of attention module, generalizability of the model and providing visualization of model’s prediction for the interpretability of results. Comparative performance evaluation with five state-of-the-art deep architectures such as MobileNet, EfficientNet-B7, Inceptionv3, ResNet-50 and VGG-16, and with published models such as COVIDNet-CT, COVNet, COVID-Net CT2, etc. is discussed.

Abstract

The COVID-19 pandemic wrought havoc across India, particularly during its devastating second and third waves. This study undertakes a crucial epidemiological analysis of these waves, leveraging actual variant count data. Given limited sequencing efforts, variant information is sparse, prompting a novel approach to scaling up with actual case data. Employing a multi-strain variant-level SEIRS model tailored to each Indian state, we modeled the disease’s propagation. We report the estimated parameters of the SEIRS models for the two waves separately. Notably, the transmission coefficients ( ) were estimated to be 0.12 for Kappa, 0.35 for Delta, and 0.38 for Omicron. These coefficients signify the contagiousness of each variant, offering critical information for understanding and managing the pandemic’s dynamics. The findings hold significant implications for public health strategies, emphasizing the urgency of comprehensive variant tracking and proactive measures to mitigate the impact of evolving viral strains.

Abstract

Breast cancer remains a significant global health concern, and machine learning algorithms and computer-aided detection systems have shown great promise in enhancing the accuracy and efficiency of mammography image analysis. However, there is a critical need for large, benchmark datasets for training deep learning models for breast cancer detection. In this work we developed Mammo-Bench, a large-scale benchmark dataset of mammography images, by collating data from seven well-curated resources, viz., INbreast, Mini-DDSM, KAU-BCMD, CMMD, CDD-CESM, DMID, and RSNA Screening Dataset. To ensure consistency across images from diverse sources while preserving clinically relevant features, all the images underwent a preprocessing pipeline that includes breast segmentation, pectoral muscle removal, and intelligent cropping. The dataset consists of 71,844 high-quality mammographic images from 26,500 patients across 8 countries and is one of the largest open-source mammography databases to the best of our knowledge. To show the utility of Mammo-Bench, ResNet101 architecture was used for classifying the images into Normal, Benign and Malignant classes. Performance of ResNet101 was evaluated on the proposed dataset and the results compared with a few member datasets and an external dataset, VinDr-Mammo. We show that training on the larger, proposed benchmark dataset is more reliable compared to when trained on other smaller datasets. An accuracy of 78.8% (with data augmentation of the minority classes) and 77.8% (without data augmentation) was achieved on the proposed benchmark dataset, compared to the other datasets for which the accuracy varied from 25 – 69%. Most striking was the improved prediction of the minority classes using the Mammo-Bench. These results establish baseline performance and demonstrate Mammo-Bench's utility as a comprehensive resource for developing and evaluating mammography analysis systems.

Abstract

In shotgun sequencing, the input string (typically, a long DNA sequence composed of nucleotide bases) is sequenced as multiple overlapping fragments of much shorter lengths (called textit{reads}). Modelling the shotgun sequencing pipeline as a communication channel for DNA data storage, the capacity of this channel was identified in a recent work, assuming that the reads themselves are noiseless substrings of the original sequence. Modern shotgun sequencers however also output quality scores for each base read, indicating the confidence in its identification. Bases with low quality scores can be considered to be erased. Motivated by this, we consider the textit{shotgun sequencing channel with erasures}, where each symbol in any read can be independently erased with some probability $delta$. We identify achievable rates for this channel, using a random code construction and a decoder that uses typicality-like arguments to merge the reads.

Abstract

DNA methylation and gene expression are two critical aspects of the epigenetic landscape that contribute significantly to cancer pathogenesis. Analysis of aberrant genome-wide methylation patterns can provide insights into how these affect the cancer transcriptome and possible clinical implications for cancer diagnosis and treatment. The role of tumor suppressors and oncogenes is well known in tumorigenesis. Epigenetic alterations can significantly impact the expression and function of these critical genes, contributing to the initiation and progression of cancer. The present protocol chapter presents a unified workflow to explore the role of DNA methylation in gene expression regulation in breast cancer by identifying differentially expressed genes whose promoter or gene body regions are differentially methylated using various Bioconductor packages in R environment. Functional enrichment analysis of these genes can help in understanding the mechanisms leading to tumorigenesis due to epigenetic alterations.

Abstract

Computer tomography (CT) have been routinely used for the diagnosis of lung diseases and recently, during the pandemic, for detecting the infectivity and severity of COVID-19 disease. One of the major concerns in using machine learning (ML) approaches for automatic processing of CT scan images in clinical setting is that these methods are trained on limited and biased subsets of publicly available COVID-19 data. This has raised concerns regarding the generalizability of these models on external datasets, not seen by the model during training. To address some of these issues, in this work CT scan images from confirmed COVID-19 data obtained from one of the largest public repositories, COVIDx CT 2A were used for training and internal validation of machine learning models. For the external validation we generated Indian-COVID-19 CT dataset, an open-source repository containing 3D CT volumes and 12096 chest CT images from 288 COVID-19 patients from India. Comparative performance evaluation of four state-of-the-art machine learning models, viz., a lightweight convolutional neural network (CNN), and three other CNN based deep learning (DL) models such as VGG-16, ResNet-50 and Inception-v3 in classifying CT images into three classes, viz., normal, non-covid pneumonia, and COVID-19 is carried out on these two datasets. Our analysis showed that the performance of all the models is comparable on the hold-out COVIDx CT 2A test set with 90%–99% accuracies (96% for CNN), while on the external Indian-COVID-19 CT dataset a drop in the performance is observed for all the models (8%–19%). The traditional machine learning model, CNN performed the best on the external dataset (accuracy 88%) in comparison to the deep learning models, indicating that a lightweight CNN is better generalizable on unseen data. The data and code are made available at https://github.com/aleesuss/c19.

Abstract

Deep learning assisted disease diagnosis using chest radiology images to assess severity of various respiratory conditions has garnered a lot of attention after the recent COVID-19 pandemic. Understanding characteristic features associated with the disease in radiology images, along with variations observed from patient-to-patient and with the progression of disease, is important while building such models. In this work, we carried out comparative analysis of various deep architectures with the proposed attention-based Convolutional Neural Network (CNN) model with customized bottleneck residual module (Attn-CNN) in classifying chest CT images into three categories, COVID-19, Normal, and Pneumonia. We show that the attention model with fewer parameters achieved better classification performance compared to state-of-the-art deep architectures such as EfficientNet-B7, Inceptionv3, ResNet-50 and VGG-16, and customized models proposed in similar studies such as COVIDNet-CT, CTnet-10, COVID-19Net, etc.