Robust identification of common genomic biomarkers from multiple gene expression profiles for the prognosis, diagnosis, and therapies of pancreatic cancer

miRNA signatures underlie chemoresistance in the gemcitabine-resistant pancreatic ductal adenocarcinoma cell line MIA PaCa-2 GR

Introduction: Chemotherapy resistance remains a significant challenge in the treatment of pancreatic adenocarcinoma (PDAC), particularly in relation to gemcitabine (Gem), a commonly used chemotherapeutic agent. MicroRNAs (miRNAs) are known to influence cancer progression and chemoresistance. This study investigates the association between miRNA expression profiles and gemcitabine resistance in PDAC. Methods: The miRNA expression profiles of a gemcitabine-sensitive (GS) PDAC cell line, MIA PaCa-2, and its gemcitabine-resistant (GR) progeny, MIA PaCa-2 GR, were analyzed. miRNA sequencing (miRNA-seq) was employed to identify miRNAs expressed in these cell lines. Differential expression analysis was performed, and Ingenuity Pathway Analysis (IPA) was utilized to elucidate the biological functions of the differentially expressed miRNAs. Results: A total of 1867 miRNAs were detected across both cell lines. Among these, 97 (5.2%) miRNAs showed significant differential expression between the GR and GS cell lines, with 65 (3.5%) miRNAs upregulated and 32 (1.7%) miRNAs downregulated in the GR line. The most notably altered miRNAs were implicated in key biological processes such as cell proliferation, migration, invasion, chemosensitization, alternative splicing, apoptosis, and angiogenesis. A subset of these miRNAs was further analyzed in patient samples to identify potential markers for recurrent tumors. Discussion: The differential miRNA expression profiles identified in this study highlight the complex regulatory roles of miRNAs in gemcitabine resistance in PDAC. These findings suggest potential targets for improving prognosis and tailoring treatment strategies in PDAC patients, particularly those showing resistance to gemcitabine. Future research should focus on validating these miRNAs as biomarkers for resistance and exploring their therapeutic potential in overcoming chemoresistance.

A Deep Auto-Optimized Collaborative Learning (DACL) model for disease prognosis using AI-IoMT systems

In modern healthcare, integrating Artificial Intelligence (AI) and Internet of Medical Things (IoMT) is highly beneficial and has made it possible to effectively control disease using networks of interconnected sensors worn by individuals. The purpose of this work is to develop an AI-IoMT framework for identifying several of chronic diseases form the patients' medical record. For that, the Deep Auto-Optimized Collaborative Learning (DACL) Model, a brand-new AI-IoMT framework, has been developed for rapid diagnosis of chronic diseases like heart disease, diabetes, and stroke. Then, a Deep Auto-Encoder Model (DAEM) is used in the proposed framework to formulate the imputed and preprocessed data by determining the fields of characteristics or information that are lacking. To speed up classification training and testing, the Golden Flower Search (GFS) approach is then utilized to choose the best features from the imputed data. In addition, the cutting-edge Collaborative Bias Integrated GAN (ColBGaN) model has been created for precisely recognizing and classifying the types of chronic diseases from the medical records of patients. The loss function is optimally estimated during classification using the Water Drop Optimization (WDO) technique, reducing the classifier's error rate. Using some of the well-known benchmarking datasets and performance measures, the proposed DACL's effectiveness and efficiency in identifying diseases is evaluated and compared.

Pancreatic cancer pathology image segmentation with channel and spatial long-range dependencies

Based on deep learning, pancreatic cancer pathology image segmentation technology effectively assists pathologists in achieving improved treatment outcomes. However, compared to traditional image segmentation tasks, the large size of tissues in pathology images requires a larger receptive field. While methods based on dilated convolutions or attention mechanisms can enhance the receptive field, they cannot capture long-range feature dependencies. Directly applying self-attention mechanisms to capture long-range dependencies results in intolerable computational complexity. To address these challenges, we introduce a channel and spatial self-attention (CS) Module designed for efficiently capturing both channel and spatial long-range feature dependencies in pancreatic cancer pathological images. Specifically, the channel and spatial self-attention module consists of an adaptive channel self-attention module and a window-shift spatial self-attention module. The adaptive channel self-attention module adaptively pools features to a fixed size to capture long-range feature dependencies. While the window-shift spatial self-attention module captures spatial long-range dependencies in a window-based manner. Additionally, we propose a re-weighted cross-entropy loss to mitigate the impact of long-tail distribution on performance. Our proposed method surpasses state-of-the-art on both our Pancreatic Cancer Pathology Image (PCPI) dataset and the GlaS challenge dataset. The mDice and mIoU have achieved 73.93% and 59.42% in our PCPI dataset.

An integrated study to decipher immunosuppressive cellular communication in the PDAC environment

Pancreatic ductal adenocarcinoma (PDAC) is one the most aggressive cancers and characterized by a highly rigid and immunosuppressive tumor microenvironment (TME). The extensive cellular interactions are known to play key roles in the immune evasion, chemoresistance, and poor prognosis. Here, we used the spatial transcriptomics, scRNA-seq, and bulk RNA-seq datasets to enhance the insights obtained from each to decipher the cellular communication in the TME. The complex crosstalk in PDAC samples was revealed by the single-cell and spatial transcriptomics profiles of the samples. We show that tumor-associated macrophages (TAMs) are the central cell types in the regulation of microenvironment in PDAC. They colocalize with the cancer cells and tumor-suppressor immune cells and take roles to provide an immunosuppressive environment. LGALS9 gene which is upregulated in PDAC tumor samples in comparison to healthy samples was also found to be upregulated in TAMs compared to tumor-suppressor immune cells in cancer samples. Additionally, LGALS9 was found to be the primary component in the crosstalk between TAMs and the other cells. The widespread expression of P4HB gene and its interaction with LGALS9 was also notable. Our findings point to a profound role of TAMs via LGALS9 and its interaction with P4HB that should be considered for further elucidation as target in the combinatory immunotherapies for PDAC.

Identifying Effective Biomarkers for Accurate Pancreatic Cancer Prognosis Using Statistical Machine Learning

Pancreatic cancer (PC) has one of the lowest survival rates among all major types of cancer. Consequently, it is one of the leading causes of mortality worldwide. Serum biomarkers historically correlate well with the early prognosis of post-surgical complications of PC. However, attempts to identify an effective biomarker panel for the successful prognosis of PC were almost non-existent in the current literature. The current study investigated the roles of various serum biomarkers including carbohydrate antigen 19-9 (CA19-9), chemokine (C-X-C motif) ligand 8 (CXCL-8), procalcitonin (PCT), and other relevant clinical data for identifying PC progression, classified into sepsis, recurrence, and other post-surgical complications, among PC patients. The most relevant biochemical and clinical markers for PC prognosis were identified using a random-forest-powered feature elimination method. Using this informative biomarker panel, the selected machine-learning (ML) classification models demonstrated highly accurate results for classifying PC patients into three complication groups on independent test data. The superiority of the combined biomarker panel (Max AUC-ROC = 100%) was further established over using CA19-9 features exclusively (Max AUC-ROC = 75%) for the task of classifying PC progression. This novel study demonstrates the effectiveness of the combined biomarker panel in successfully diagnosing PC progression and other relevant complications among Egyptian PC survivors.

Robust Identification of Differential Gene Expression Patterns from Multiple Transcriptomics Datasets for Early Diagnosis, Prognosis, and Therapies for Breast Cancer

Background and Objectives: Breast cancer (BC) is one of the major causes of cancer-related death in women globally. Proper identification of BC-causing hub genes (HubGs) for prognosis, diagnosis, and therapies at an earlier stage may reduce such death rates. However, most of the previous studies detected HubGs through non-robust statistical approaches that are sensitive to outlying observations. Therefore, the main objectives of this study were to explore BC-causing potential HubGs from robustness viewpoints, highlighting their early prognostic, diagnostic, and therapeutic performance. Materials and Methods: Integrated robust statistics and bioinformatics methods and databases were used to obtain the required results. Results: We robustly identified 46 common differentially expressed genes (cDEGs) between BC and control samples from three microarrays (GSE26910, GSE42568, and GSE65194) and one scRNA-seq (GSE235168) dataset. Then, we identified eight cDEGs (COL11A1, COL10A1, CD36, ACACB, CD24, PLK1, UBE2C, and PDK4) as the BC-causing HubGs by the protein-protein interaction (PPI) network analysis of cDEGs. The performance of BC and survival probability prediction models with the expressions of HubGs from two independent datasets (GSE45827 and GSE54002) and the TCGA (The Cancer Genome Atlas) database showed that our proposed HubGs might be considered as diagnostic and prognostic biomarkers, where two genes, COL11A1 and CD24, exhibit better performance. The expression analysis of HubGs by Box plots with the TCGA database in different stages of BC progression indicated their early diagnosis and prognosis ability. The HubGs set enrichment analysis with GO (Gene ontology) terms and KEGG (Kyoto Encyclopedia of Genes and Genomes) pathways disclosed some BC-causing biological processes, molecular functions, and pathways. Finally, we suggested the top-ranked six drug molecules (Suramin, Rifaximin, Telmisartan, Tukysa Tucatinib, Lynparza Olaparib, and TG.02) for the treatment of BC by molecular docking analysis with the proposed HubGs-mediated receptors. Molecular docking analysis results also showed that these drug molecules may inhibit cancer-related post-translational modification (PTM) sites (Succinylation, phosphorylation, and ubiquitination) of hub proteins. Conclusions: This study's findings might be valuable resources for diagnosis, prognosis, and therapies at an earlier stage of BC.

Exploring Core Genes by Comparative Transcriptomics Analysis for Early Diagnosis, Prognosis, and Therapies of Colorectal Cancer

Colorectal cancer (CRC) is one of the most common cancers with a high mortality rate. Early diagnosis and therapies for CRC may reduce the mortality rate. However, so far, no researchers have yet investigated core genes (CGs) rigorously for early diagnosis, prognosis, and therapies of CRC. Therefore, an attempt was made in this study to explore CRC-related CGs for early diagnosis, prognosis, and therapies. At first, we identified 252 common differentially expressed genes (cDEGs) between CRC and control samples based on three gene-expression datasets. Then, we identified ten cDEGs (AURKA, TOP2A, CDK1, PTTG1, CDKN3, CDC20, MAD2L1, CKS2, MELK, and TPX2) as the CGs, highlighting their mechanisms in CRC progression. The enrichment analysis of CGs with GO terms and KEGG pathways revealed some crucial biological processes, molecular functions, and signaling pathways that are associated with CRC progression. The survival probability curves and box-plot analyses with the expressions of CGs in different stages of CRC indicated their strong prognostic performance from the earlier stage of the disease. Then, we detected CGs-guided seven candidate drugs (Manzamine A, Cardidigin, Staurosporine, Sitosterol, Benzo[a]pyrene, Nocardiopsis sp., and Riccardin D) by molecular docking. Finally, the binding stability of four top-ranked complexes (TPX2 vs. Manzamine A, CDC20 vs. Cardidigin, MELK vs. Staurosporine, and CDK1 vs. Riccardin D) was investigated by using 100 ns molecular dynamics simulation studies, and their stable performance was observed. Therefore, the output of this study may play a vital role in developing a proper treatment plan at the earlier stages of CRC.