Abstract

Long-term transplant success is limited by allograft rejection, a complex process traditionally studied on an organ-specific basis. To establish a unified framework beyond organ-specific studies, we performed a network-based systems biology analysis of transcriptomic data from 672 liver, kidney, and heart transplant biopsies to identify a conserved, pan-organ molecular framework of rejection. By constructing and comparing organ-specific gene co-expression networks, we identified a consensus, six-module immune cascade that captures the hierarchical nature of the alloimmune response. In addition, we also uncovered a highly conserved 24-gene cell cycle signature consistently upregulated in rejecting allografts, implicating cellular proliferation as a core feature of rejection pathology. From this framework, we derived a 172-gene immune signature and applied machine learning models to assess its predictive performance, achieving accuracy comparable to established benchmarks. We further refined this to a minimal, high-performance 20-gene immune signature (AUC > 0.96). Both the immune and cell cycle signatures demonstrated robust, pan-organ utility when independently validated in a lung transplant cohort (n=243). Collectively, these findings define a pan-organ molecular framework for rejection and highlight cell cycle dysregulation as a conserved hallmark, offering a foundation for standardized, cross-organ diagnostic platforms to improve allograft surveillance and patient outcomes.

Abstract

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by challenges in social communication, repetitive behaviors, and restricted interests. Recent research has emphasized the importance of metabolic dysfunctions in the pathophysiology of ASD. This study investigates metabolic alterations associated with ASD by analyzing transcriptomic data obtained from the prefrontal cortex (bulk tissue and single-nucleus) and data from peripheral blood mononuclear cells (PBMC). We assessed the metabolic activity of each patient based on gene expression profiles, revealing significant downregulation of vital metabolic pathways, including glycolysis, the tricarboxylic acid (TCA) cycle, and oxidative phosphorylation, indicative of hypometabolism. Our analysis also highlighted dysregulation in lipid, vitamin, amino acid, and heme metabolism, which may contribute to the neurodevelopmental delays associated with ASD. Cell-specific metabolic activities in the ASD brain showed altered pathways in astrocytes, oligodendrocytes, excitatory neurons, and interneurons. Furthermore, we identified critical metabolic pathways and genes from PBMC gene expression data that distinguish ASD patients from typically developing individuals. Our findings demonstrate a consistent pattern of metabolic dysfunction across brain and blood samples. This research provides a comprehensive understanding of metabolic alterations in ASD, paving the way for exploring potential therapeutic strategies targeting metabolic dysregulation.

Abstract

Oral cancer though preventable, shows high mortality and affect the overall quality of life when detected in late stages. Screening techniques that enable early diagnosis are the need of the hour. The present work aims to evaluate the effectiveness of AI screening tools in the diagnosis of OPMDs and Oral cancers via native or web-application (cloud) using smart phone devices. We trained and tested two deep learning models namely DenseNet201 and FixCaps using 518 images of the oral cavity. While DenseNet201 is a pre-trained model, we modified the FixCaps model from capsule network and trained it ground up. Standardized protocols were used to annotate and classify the lesions (suspicious vs. non-suspicious). In terms of model performance, DenseNet201 achieved an F1 score of 87.50% and AUC of 0.97; while FixCaps exhibited F1 score of 82.8% and AUC of 0.93. DenseNet201 model (20 M) serves as a robust screening model (accuracy 88.6%) that can be hosted on a web-application in the cloud servers; while the adapted FixCaps model with its low parameter size of 0.83 M exhibits comparable accuracy (83.8%) allowing easy transitioning into a native phone-based screening application.

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. In this work, we propose DeepGraphMut (DGM), a novel graph-based deep-learning 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 its lightweight variant and network-based stratification methods in both unsupervised and supervised analyses. In summary, this study 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

Breast cancer, the most common malignancy among women, requires precise detection and classification for effective treatment. Among immunohistochemistry (IHC) biomarkers, HER2 plays a critical role in guiding therapy decisions. In particular, a recent clinical trial has shown that 3-way classification of HER2 (0, low, and high) using IHC is essential for identifying patients with HER2 low expression who may benefit from new targeted therapies. However, traditional IHC classification relies on the expertise of pathologists, making it labor-intensive and prone to significant inter-observer variability. To address these challenges, this study introduces the India Pathology Breast Cancer Dataset, comprising HER2 IHC slides from 500 patients, with a primary focus on automating 3-way HER2 classification. Evaluation of multiple deep learning models revealed that an end-to-end ConvNeXt network using low-resolution IHC images achieved an F1 score of 83.52%, representing an improvement of 5.35% over patch-based methods. Class-wise F1 scores were 75.6% for HER2-0, 82.4% for HER2-low, and 91.5% for HER2-high, indicating the challenge in distinguishing HER2-0 and HER2-low cases. This study highlights the potential of simple yet effective deep learning techniques to significantly improve accuracy and reproducibility in breast cancer classification, supporting their integration into clinical workflows for better patient outcomes.

Abstract

Accurate molecular subtyping of cancer is crucial for advancing personalized medicine. Although multiomics data contain valuable predictive information, effectively integrating them is challenging domics sources, providing a robust framework for molecular characterizations-modal biological interactions. We propose HyperCLSA (Hypergraph Contrastive Learning with Self-Attention), a novel deep learning framework for efficient multi-omics integration in breast cancer subtyping. HyperCLSA combines hypergraph-based sample encoding, supervised contrastive learning for latent space alignment, and multi-head self-attention for adaptive fusion of omics modalities. Evaluated on The Cancer Genome Atlas Breast Cancer dataset (TCGA-BRCA) forPAM50 subtype classification, HyperCLSA achieves a state-of-the-art accuracy of 90.1%, significantly outperforming established baselines. Our results demonstrate HyperCLSA's effectiveness in extracting complementary information across heterogeneous omics sources, providing a robust framework for molecular characterization of breast cancer.

Abstract

Leishmania donovani causes a neglected tropical disease called visceral leishmaniasis. Additionally, leishmaniasis also
manifests opportunistically, under conditions of immune compromise. The continued non-availability of effectively curative
interventions (drugs or vaccines) against this disease necessitates a deeper knowledge of Leishmania biology in order to
evolve novel strategies against the disease. We have used a meta-analysis approach to analyse Leishmania's composite
genetic network rather than investigating individual candidate genes. We performed Weighted Gene Co-expression Network
Analysis (WGCNA) on publicly available Leishmania donovani transcriptome data to identify co-regulatory genetic modules.
This clustering of Leishmania donovani transcriptomes revealed that genes fall in 30 distinct co-regulated modules with 32 to
3012 genes. In order to analyse the distribution of genes in Leishmania gene modules, we queried the enrichment or depletion
of various annotation-qualifiers in the modules. We observed that several modules are specifically and individually enriched
or depleted for annotation qualifiers derived from GO-annotation and KEGG-pathways and are differentially associated with
life-phases and experimental conditions. Additionally, modules are also enriched or depleted for sequence based genetic
features such as chromosomal location, location on co-transcriptional segment, rank of transcript from initiation of transcription, skewed usage of known RNA Binding Protein motifs. Classification of uncharacterized transcripts into co-regulatory
modules provides insights in their probable characteristics, aiding future empirical investigation. Strikingly, two of the modules
have reciprocal features including individual associations with logarithmic or stationary growth phases of Leishmania, two
important life-phases that simulate the vector-dwelling pro-cyclic and the pre-infective meta-cyclic forms. Collectively, our
analyses of Leishmania co-regulated gene modules is suggestive of additional regulatory modes over the mere differential
mRNA stabilization.

Abstract

Cancer metabolism is characterized by significant heterogeneity, presenting challenges for treatment efficacy and patient outcomes. Understanding this heterogeneity and its regulatory mechanisms at single-cell resolution is crucial for developing personalized therapeutic strategies. In this study, we employed a single-cell network approach to characterize malignant heterogeneity in gynecologic and breast cancers, focusing on the transcriptional regulatory mechanisms driving metabolic alterations. By leveraging single-cell RNA sequencing (scRNA-seq) data, we assessed the metabolic pathway activities and inferred cancer-specific protein-protein interactomes (PPI) and gene regulatory networks (GRNs). We explored the crosstalk between these networks to identify key alterations in metabolic regulation. Clustering cells by metabolic pathways revealed tumor heterogeneity across cancers, highlighting variations in oxidative phosphorylation, glycolysis, cholesterol, fatty acid, hormone, amino acid, and redox metabolism. Our analysis identified metabolic modules associated with these pathways, along with their key transcriptional regulators. Notably, transcription factors related to ER stress, immune response, and cell proliferation, along with hypoxia-inducible factor and sterol regulatory element-binding proteins were found to drive metabolic reprogramming. These findings provide new insights into the complex interplay between metabolic rewiring and transcriptional regulation in gynecologic and breast cancers, offering potential avenues for targeted therapeutic strategies in precision oncology. Furthermore, this pipeline for dissecting coregulatory metabolic networks can be broadly applied to decipher metabolic regulation in any disease at single-cell resolution.

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. In this work, we propose
DeepGraphMut (DGM), a novel graph-based deep-learning 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 its lightweight variant and the network-based stratification
method in both unsupervised and supervised analyses. In summary, this study 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

The efective management of brain tumors relies on precise typing, subtyping, and grading. We
present the IPD-Brain Dataset, a crucial resource for the neuropathological community, comprising
547 high-resolution H&E stained slides from 367 patients for the study of glioma subtypes and
immunohistochemical biomarkers. Scanned at 40x magnifcation, this dataset is one of the largest in
Asia, specifcally focusing on the Indian demographics. It encompasses detailed clinical annotations,
including patient age, sex, radiological fndings, diagnosis, CNS WHO grade, and IHC biomarker status
(IDH1R132H, ATRX and TP53 along with proliferation index, Ki67), providing a rich foundation for
research. The dataset is open for public access and is designed for various applications, from machine
learning model training to the exploration of regional and ethnic disease variations. Preliminary
validations utilizing Multiple Instance Learning for tasks such as glioma subtype classifcation and IHC
biomarker identifcation underscore its potential to signifcantly contribute to global collaboration in
brain tumor research, enhancing diagnostic precision and understanding of glioma variability across
diferent populations.