Classification of early and late stage liver hepatocellular carcinoma patients from their genomics and epigenomics profiles

DeepHistoNet: A robust deep-learning model for the classification of hepatocellular, lung, and colon carcinoma

In recent days, non-communicable diseases (NCDs) require more attention since they require specialized infrastructure for treatment. As per the cancer population registry estimate, nearly 800,000 new cancer cases will be detected yearly. The statistics alarm the need for early cancer detection and diagnosis. Cancer identification can be made either through manual efforts or by computer-aided algorithms. Manual efforts-based cancer detection is labor intensive and also offers more time complexity. In contrast, computer-aided algorithms offer feasibility in reducing time and manual efforts. With the motivation to develop a computer-aided diagnosis system for NCD, we developed a cancer detection methodology. In the present article, a deep learning (DL)-based cancer identification model is developed. In DL-based architectures, the features are generally extracted using convolutional neural networks. The proposed attention-guided, densely connected residual, and dilated convolution deep neural network called DeepHistoNet acquire precise patterns for classification. Experimentation has been carried out on Kasturba Medical College (KMC), TCGA-LIHC, and LC25000 datasets to prove the robustness of the model. Performance evaluation metrics like F1-score, sensitivity, specificity, recall, and accuracy validate the experimentation. Experimental results demonstrate that the proposed DeepHistoNet model outperforms the other state-of-the-art methods. The proposed model has been able to classify the KMC liver dataset with 97.1% accuracy and 0.9867 value of area under the curve-receiver operating characteristic curve (AUC-ROC), which is the best result obtained compared to the state-of-the-art techniques. The performance of the DeepHistoNet has been even better on the LC25000 dataset. On the LC25000 dataset, the proposed model achieved 99.8% classification accuracy. To our knowledge, DeepHistoNet is a novel approach for multiple histopathological image classification. RESEARCH HIGHLIGHTS: A novel robust DL model is proposed for histopathological image carcinoma classification. The precise patterns for accurate classification are extracted using dense cross-connected residual blocks. Spatial attention is provided to the network so that the spatial information is not lost during the feature extraction. DeepHistoNet is trained and evaluated on the liver, lung, and colon histopathology datasets to demonstrate its resilience. The results are promising and outperform state-of-the-art techniques. The proposed methodology has obtained the AUC-ROC value of 0.9867 with a classification accuracy of 97.1% on the KMC dataset. The proposed DeepHistoNet has classified the LC25000 dataset with 99.8% accuracy. The results are the best obtained till date.

Uncovering myocardial infarction genetic signatures using GWAS exploration in Saudi and European cohorts

Genome-wide association studies (GWAS) have yielded significant insights into the genetic architecture of myocardial infarction (MI), although studies in non-European populations are still lacking. Saudi Arabian cohorts offer an opportunity to discover novel genetic variants impacting disease risk due to a high rate of consanguinity. Genome-wide genotyping (GWG), imputation and GWAS followed by meta-analysis were performed based on two independent Saudi Arabian studies comprising 3950 MI patients and 2324 non-MI controls. Meta-analyses were then performed with these two Saudi MI studies and the CardioGRAMplusC4D and UK BioBank GWAS as controls. Meta-analyses of the two Saudi MI studies resulted in 17 SNPs with genome-wide significance. Meta-analyses of all 4 studies revealed 66 loci with genome-wide significance levels of p < 5 × 10-8. All of these variants, except rs2764203, have previously been reported as MI-associated loci or to have high linkage disequilibrium with known loci. One SNP association in Shisa family member 5 (SHISA5) (rs11707229) was evident at a much higher frequency in the Saudi MI populations (> 12% MAF). In conclusion, our results replicated many MI associations, whereas in Saudi-only GWAS (meta-analyses), several new loci were implicated that require future validation and functional analyses.

The Role of Artificial Intelligence in the Detection and Implementation of Biomarkers for Hepatocellular Carcinoma: Outlook and Opportunities

Liver cancer is a leading cause of cancer-related death worldwide, and its early detection and treatment are crucial for improving morbidity and mortality. Biomarkers have the potential to facilitate the early diagnosis and management of liver cancer, but identifying and implementing effective biomarkers remains a major challenge. In recent years, artificial intelligence has emerged as a promising tool in the cancer sphere, and recent literature suggests that it is very promising in facilitating biomarker use in liver cancer. This review provides an overview of the status of AI-based biomarker research in liver cancer, with a focus on the detection and implementation of biomarkers for risk prediction, diagnosis, staging, prognostication, prediction of treatment response, and recurrence of liver cancers.

Key therapeutic targets implicated at the early stage of hepatocellular carcinoma identified through machine-learning approaches

Hepatocellular carcinoma (HCC) is the most frequent type of primary liver cancer. Early-stage detection plays an essential role in making treatment decisions and identifying dominant molecular mechanisms. We utilized machine learning algorithms to find significant mRNAs and microRNAs (miRNAs) at the early and late stages of HCC. First, pre-processing approaches, including organization, nested cross-validation, cleaning, and normalization were applied. Next, the t-test/ANOVA methods and binary particle swarm optimization were used as a filter and wrapper method in the feature selection step, respectively. Then, classifiers, based on machine learning and deep learning algorithms were utilized to evaluate the discrimination power of selected features (mRNAs and miRNAs) in the classification step. Finally, the association rule mining algorithm was applied to selected features for identifying key mRNAs and miRNAs that can help decode dominant molecular mechanisms in HCC stages. The applied methods could identify key genes associated with the early (e.g., Vitronectin, thrombin-activatable fibrinolysis inhibitor, lactate dehydrogenase D (LDHD), miR-590) and late-stage (e.g., SPRY domain containing 4, regucalcin, miR-3199-1, miR-194-2, miR-4999) of HCC. This research could establish a clear picture of putative candidate genes, which could be the main actors at the early and late stages of HCC.

In silico transcriptional analysis of asymptomatic and severe COVID-19 patients reveals the susceptibility of severe patients to other comorbidities and non-viral pathological conditions

COVID-19 is a severe respiratory disease caused by SARS-CoV-2, a novel human coronavirus. Patients infected with SARS-CoV-2 exhibit heterogeneous symptoms that pose pragmatic hurdles for implementing appropriate therapy and management of the COVID-19 patients and their post-COVID complications. Thus, understanding the impact of infection severity at the molecular level in the host is vital to understand the host response and accordingly it's precise management. In the current study, we performed a comparative transcriptomics analysis of publicly available seven asymptomatic and eight severe COVID-19 patients. Exploratory data analysis employing Principal Component Analysis (PCA) showed the distinct clusters of asymptomatic and severe patients. Subsequently, the differential gene expression analysis using DESeq2 identified 1224 significantly upregulated genes (logFC≥ 1.5, p-adjusted value <0.05) and 268 significantly downregulated genes (logFC≤ −1.5, p-adjusted value <0.05) in severe samples in comparison to asymptomatic samples. Eventually, Gene Set Enrichment Analysis (GSEA) revealed the upregulation of anti-viral and anti-inflammatory pathways, secondary infections, Iron homeostasis, anemia, cardiac-related, etc.; while, downregulation of lipid metabolism, adaptive immune response, translation, recurrent respiratory infections, heme-biosynthetic pathways, etc. Conclusively, these findings provide insight into the enhanced susceptibility of severe COVID-19 patients to other health comorbidities including non-viral pathogenic infections, atherosclerosis, autoinflammatory diseases, anemia, male infertility, etc. owing to the activation of biological processes, pathways and molecular functions associated with them. We anticipate this study will facilitate the researchers in finding efficient therapeutic targets and eventually the clinicians in management of COVID-19 patients and post-COVID-19 effects in them.

A machine learning method for improving liver cancer staging

Liver cancer is a common malignant tumor, and its clinical stage is closely related to the clinical treatment and prognosis of patients. Currently, the BCLC staging system revised by the BCLC group of University of Barcelona is the globally recognized staging system for liver cancer. However, with the deepening of related research, the current staging system can no longer fully meet the clinical needs. In this work, we propose a novel machine learning method for constructing an automatic hepatocellular carcinoma staging model that incorporates far more clinical variables than any existing staging system. Our model is based on random survival forests, which generates a unique hazard function for each patient. B-splines are used to embed hazard functions into vectors in low-dimensional space and hierarchical clustering method groups similar patients to form staging cohorts. The resulting staging system significantly outperforms the BCLC system in terms of distinctiveness between patients in different stages.

A novel four-gene signature for predicting the prognosis of hepatocellular carcinoma

OBJECTIVE

To identify and utilize gene signatures for the prognostic evaluation of postoperative patients with hepatocellular carcinoma (HCC).

METHODS

The gene mRNA expression profiles and corresponding clinicopathological data of postoperative patients with HCC were downloaded from The Cancer Genome Atlas (TCGA) database. Highly differentially expressed genes (DEGs) in tumor tissues compared to adjacent tissues were identified, and their associations with the overall survival (OS) of HCC patients were analyzed. The strongly associated genes were used to develop a prognostic score for the survival stratification of HCC, and the underlying mechanisms were analyzed using bioinformatics.

RESULTS

A total of 376 DEGs were identified and four DEGs (ADH4, COL15A1, RET and KCNJ16) were independently associated with OS. A prognostic score derived from the four genes could effectively stratify HCC patients with different OS outcomes, independent of clinical parameters. Patients with high scores exhibited poorer OS than patients with low scores (HR 5.526, 95% CI: 2.451-12.461, p < .001). The four genes were involved in cancer-related biological processes and were independent of each other in bioinformatics analyses.

CONCLUSION

Four genes strongly associated with the prognosis of postoperative patients with HCC were identified, and the derived prognostic score was simple and valuable for overall survival prediction.

Comprehensive Analysis on the Specific Role and Function of Mitochondrial Inner Membrane Protein MPV17 in Liver Hepatocellular Carcinoma

Background

Liver hepatocellular carcinoma (LIHC) is the predominant type of liver cancer, and its treatment still faces great challenges presently. Mitochondrial inner membrane protein MPV17 is reported to be involved in multiple biological activities of cancers. Here, we seek to investigate the specific role and functions of MPV17 in LIHC progression.

Methods

Firstly, MPV17 expressions in various tumors and corresponding normal samples and LIHC groups with various clinical features were analyzed, respectively. Next, the relationship between MPV17 expression and LIHC survival was analyzed and verified by AUC curves. Besides, differentially expressed genes (DEGs) for LIHC were screened from TCGA and then analyzed by GO and KEGG. Then, MPV17 was analyzed by prognostic model, Cox analysis, predictive nomogram, pathway correlation, and immunoassay. Finally, the functions of MPV17 were determined by CCK-8 and Tranwell assays.

Results

In most tumors, MPV17 expression was higher than that in the normal group, and it was related to LIHC clinical features. In the LIHC survival analysis, highly expressed MPV17 was associated with a poor prognosis. Besides, 314 upregulated and 193 downregulated DEGs are mainly involved in the TNF signaling pathway and tyrosine metabolism. Through prognostic model, Cox analysis, and predictive nomogram, MPV17 had the prognostic value for LIHC. Gene-pathway correlation analysis showed that MPV17 had the strongest correlation with the G2M_checkpoint pathway. In an immunoassay, MPV17 had a strong correlation with many immune cells. Functional assays showed that MPV17 reduction in LIHC cells could inhibit cell invasion, migration, and proliferation.

Conclusion

MPV17, as a tumor promoter, could be a new biomarker for LIHC diagnosis and prognosis and probably shed new light on the exploration of LIHC therapies.

Utilizing Gut Microbiota to Improve Hepatobiliary Tumor Treatments: Recent Advances

Hepatobiliary tumors, which include cholangiocarcinoma, hepatocellular carcinoma (HCC), and gallbladder cancer, are common cancers that have high morbidity and mortality rates and poor survival outcomes. In humans, the microbiota is comprised of symbiotic microbial cells (10-100 trillion) that belong to the bacterial ecosystem mainly residing in the gut. The gut microbiota is a complicated group that can largely be found in the intestine and has a dual role in cancer occurrence and progression. Previous research has focused on the crucial functions of the intestinal microflora as the main pathophysiological mechanism in HCC development. Intestinal bacteria produce a broad range of metabolites that exhibit a variety of pro- and anticarcinogenic effects on HCC. Therefore, probiotic alteration of the gut microflora could promote gut flora balance and help prevent the occurrence of HCC. Recent evidence from clinical and translational studies suggests that fecal microbiota transplant is one of the most successful therapies to correct intestinal bacterial imbalance. We review the literature describing the effects and mechanisms of the microbiome in the gut in the context of HCC, including gut bacterial metabolites, probiotics, antibiotics, and the transplantation of fecal microbiota, and discuss the potential influence of the microbiome environment on cholangiocarcinoma and gallbladder cancer. Our findings are expected to reveal therapeutic targets for the prevention of hepatobiliary tumors, and the development of clinical treatment strategies, by emphasizing the function of the gut microbiota.

Machine-learning algorithms based on personalized pathways for a novel predictive model for the diagnosis of hepatocellular carcinoma

BACKGROUND

At present, the diagnostic ability of hepatocellular carcinoma (HCC) based on serum alpha-fetoprotein level is limited. Finding markers that can effectively distinguish cancer and non-cancerous tissues is important for improving the diagnostic efficiency of HCC.

RESULTS

In this study, we developed a predictive model for HCC diagnosis using personalized biological pathways combined with a machine learning algorithm based on regularized regression and carry out relevant examinations. In two training sets, the overall cross-study-validated area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve and the Brier score of the diagnostic model were 0.987 [95%confidence interval (CI): 0.979-0.996], 0.981 and 0.091, respectively. Besides, the model showed good transferability in external validation set. In TCGA-LIHC cohort, the AUROC, AURPC and Brier score were 0.992 (95%CI: 0.985-0.998), 0.967 and 0.112, respectively. The diagnostic model has accomplished very impressive performance in distinguishing HCC from non-cancerous liver tissues. Moreover, we further analyzed the extracted biological pathways to explore molecular features and prognostic factors. The risk score generated from a 12-gene signature extracted from the characteristic pathways was correlated with some immune related pathways and served as an independent prognostic factor for HCC.

CONCLUSION

We used personalized biological pathways analysis and machine learning algorithm to construct a highly accurate HCC diagnostic model. The excellent interpretable performance and good transferability of this model enables it with great potential for personalized medicine, which can assist clinicians in diagnosis for HCC patients.

The application of artificial intelligence in hepatology: A systematic review

The integration of human and artificial intelligence (AI) in medicine has only recently begun but it has already become obvious that intelligent systems can dramatically improve the management of liver diseases. Big data made it possible to envisage transformative developments of the use of AI for diagnosing, predicting prognosis and treating liver diseases, but there is still a lot of work to do. If we want to achieve the 21^st century digital revolution, there is an urgent need for specific national and international rules, and to adhere to bioethical parameters when collecting data. Avoiding misleading results is essential for the effective use of AI. A crucial question is whether it is possible to sustain, technically and morally, the process of integration between man and machine. We present a systematic review on the applications of AI to hepatology, highlighting the current challenges and crucial issues related to the use of such technologies.

USP8 regulates liver cancer progression via the inhibition of TRAF6-mediated signal for NF-κB activation and autophagy induction by TLR4

Herein, we aimed to elucidate the molecular and cellular mechanism in which ubiquitin-specific protease 8 (USP8) is implicated in liver cancer progression via TRAF6-mediated signal. USP8 induces the deubiquitination of TRAF6, TAB2, TAK1, p62, and BECN1, which are pivotal roles for NF-κB activation and autophagy induction. Notably, the LIHC patient with low USP8 mRNA expression showed markedly shorter survival time, whereas there was no significant difference in the other 18-human cancers. Importantly, the TCGA data analysis on LIHC and transcriptome analysis on the USP8 knockout (USP8KO) SK-HEP-1 cells revealed a significant correlation between USP8 and TRAF6, TAB2, TAK1, p62, and BECN1, and enhanced NF-κB-dependent and autophagy-related cancer progression/metastasis-related genes in response to LPS stimulation. Furthermore, USP8KO SK-HEP-1 cells showed an increase in cancer migration and invasion by TLR4 stimulation, and a marked increase of tumorigenicity and metastasis in xenografted NSG mice. The results demonstrate that USP8 is negatively implicated in the LIHC progression through the regulation of TRAF6-mediated signal for the activation of NF-κB activation and autophagy induction. Our findings provide useful insight into the LIHC pathogenesis of cancer progression.

In silico tools and databases for designing cancer immunotherapy

Immunotherapy is a rapidly growing therapy for cancer which have numerous benefits over conventional treatments like surgery, chemotherapy, and radiation. Overall survival of cancer patients has improved significantly due to the use of immunotherapy. It acts as a novel pillar for treating different malignancies from their primary to the metastatic stage. Recent preferments in high-throughput sequencing and computational immunology leads to the development of targeted immunotherapy for precision oncology. In the last few decades, several computational methods and resources have been developed for designing immunotherapy against cancer. In this review, we have summarized cancer-associated genomic, transcriptomic, and mutation profile repositories. We have also enlisted in silico methods for the prediction of vaccine candidates, HLA binders, cytokines inducing peptides, and potential neoepitopes. Of note, we have incorporated the most important bioinformatics pipelines and resources for the designing of cancer immunotherapy. Moreover, to facilitate the scientific community, we have developed a web portal entitled ImmCancer (https://webs.iiitd.edu.in/raghava/immcancer/), comprises cancer immunotherapy tools and repositories.

Machine Learning in Epigenomics: Insights into Cancer Biology and Medicine

The recent deluge of genome-wide technologies for the mapping of the epigenome and resulting data in cancer samples has provided the opportunity for gaining insights into and understanding the roles of epigenetic processes in cancer. However, the complexity, high-dimensionality, sparsity, and noise associated with these data pose challenges for extensive integrative analyses. Machine Learning (ML) algorithms are particularly suited for epigenomic data analyses due to their flexibility and ability to learn underlying hidden structures. We will discuss four overlapping but distinct major categories under ML: dimensionality reduction, unsupervised methods, supervised methods, and deep learning (DL). We review the preferred use cases of these algorithms in analyses of cancer epigenomics data with the hope to provide an overview of how ML approaches can be used to explore fundamental questions on the roles of epigenome in cancer biology and medicine.

Identification of NAA40 as a Potential Prognostic Marker for Aggressive Liver Cancer Subtypes

Liver hepatocellular carcinoma (LIHC) is a leading cause of cancer-related mortality. In this study we initially interrogated the Cancer Genome Atlas (TCGA) dataset to determine the implication of N-terminal acetyltransferases (NATs), a family of enzymes that modify the N-terminus of the majority of eukaryotic proteins, in LIHC. This examination unveiled NAA40 as the NAT family member with the most prominent upregulation and significant disease prognosis for this cancer. Focusing on this enzyme, which selectively targets histone proteins, we show that its upregulation occurs from early stages of LIHC and is not specifically correlated with any established risk factors such as viral infection, obesity or alcoholic disease. Notably, in silico analysis of TCGA and other LIHC datasets found that expression of this epigenetic enzyme is associated with high proliferating, poorly differentiating and more aggressive LIHC subtypes. In particular, NAA40 upregulation was preferentially linked to mutational or non-mutational P53 functional inactivation. Accordingly, we observed that high NAA40 expression was associated with worse survival specifically in liver cancer patients with inactivated P53. These findings define NAA40 as a NAT with potentially oncogenic functions in LIHC and uncover its prognostic value for aggressive LIHC subtypes.

Increasing prediction accuracy of pathogenic staging by sample augmentation with a GAN

Accurate prediction of cancer stage is important in that it enables more appropriate treatment for patients with cancer. Many measures or methods have been proposed for more accurate prediction of cancer stage, but recently, machine learning, especially deep learning-based methods have been receiving increasing attention, mostly owing to their good prediction accuracy in many applications. Machine learning methods can be applied to high throughput DNA mutation or RNA expression data to predict cancer stage. However, because the number of genes or markers generally exceeds 10,000, a considerable number of data samples is required to guarantee high prediction accuracy. To solve this problem of a small number of clinical samples, we used a Generative Adversarial Networks (GANs) to augment the samples. Because GANs are not effective with whole genes, we first selected significant genes using DNA mutation data and random forest feature ranking. Next, RNA expression data for selected genes were expanded using GANs. We compared the classification accuracies using original dataset and expanded datasets generated by proposed and existing methods, using random forest, Deep Neural Networks (DNNs), and 1-Dimensional Convolutional Neural Networks (1DCNN). When using the 1DCNN, the F1 score of GAN5 (a 5-fold increase in data) was improved by 39% in relation to the original data. Moreover, the results using only 30% of the data were better than those using all of the data. Our attempt is the first to use GAN for augmentation using numeric data for both DNA and RNA. The augmented datasets obtained using the proposed method demonstrated significantly increased classification accuracy for most cases. By using GAN and 1DCNN in the prediction of cancer stage, we confirmed that good results can be obtained even with small amounts of samples, and it is expected that a great deal of the cost and time required to obtain clinical samples will be reduced. The proposed sample augmentation method could also be applied for other purposes, such as prognostic prediction or cancer classification.

Computational resources for identification of cancer biomarkers from omics data

Cancer is one of the most prevailing, deadly and challenging diseases worldwide. The advancement in technology led to the generation of different types of omics data at each genome level that may potentially improve the current status of cancer patients. These data have tremendous applications in managing cancer effectively with improved outcome in patients. This review summarizes the various computational resources and tools housing several types of omics data related to cancer. Major categorization of resources includes-cancer-associated multiomics data repositories, visualization/analysis tools for omics data, machine learning-based diagnostic, prognostic, and predictive biomarker tools, and data analysis algorithms employing the multiomics data. The review primarily focuses on providing comprehensive information on the open-source multiomics tools and data repositories, owing to their broader applicability, economic-benefit and usability. Sections including the comparative analysis, tools applicability and possible future directions have also been discussed in detail. We hope that this information will significantly benefit the researchers and clinicians, especially those with no sound background in bioinformatics and who lack sufficient data analysis skills to interpret something from the plethora of cancer-specific data generated nowadays.

CancerLivER: a database of liver cancer gene expression resources and biomarkers

Liver cancer is the fourth major lethal malignancy worldwide. To understand the development and progression of liver cancer, biomedical research generated a tremendous amount of transcriptomics and disease-specific biomarker data. However, dispersed information poses pragmatic hurdles to delineate the significant markers for the disease. Hence, a dedicated resource for liver cancer is required that integrates scattered multiple formatted datasets and information regarding disease-specific biomarkers. Liver Cancer Expression Resource (CancerLivER) is a database that maintains gene expression datasets of liver cancer along with the putative biomarkers defined for the same in the literature. It manages 115 datasets that include gene-expression profiles of 9611 samples. Each of incorporated datasets was manually curated to remove any artefact; subsequently, a standard and uniform pipeline according to the specific technique is employed for their processing. Additionally, it contains comprehensive information on 594 liver cancer biomarkers which include mainly 315 gene biomarkers or signatures and 178 protein- and 46 miRNA-based biomarkers. To explore the full potential of data on liver cancer, a web-based interactive platform was developed to perform search, browsing and analyses. Analysis tools were also integrated to explore and visualize the expression patterns of desired genes among different types of samples based on individual gene, GO ontology and pathways. Furthermore, a dataset matrix download facility was provided to facilitate the users for their extensive analysis to elucidate more robust disease-specific signatures. Eventually, CancerLivER is a comprehensive resource which is highly useful for the scientific community working in the field of liver cancer.Availability: CancerLivER can be accessed on the web at https://webs.iiitd.edu.in/raghava/cancerliver.

An Eight-CpG-based Methylation Classifier for Preoperative Discriminating Early and Advanced-Late Stage of Colorectal Cancer

Aim

To develop and validate a CpG-based classifier for preoperative discrimination of early and advanced-late stage colorectal cancer (CRC).

Methods

We identified an epigenetic signature based on methylation status of multiple CpG sites (CpGs) from 372 subjects in The Cancer Genome Atlas (TCGA) CRC cohort, and an external cohort (GSE48684) with 64 subjects by LASSO regression algorithm. A classifier derived from the methylation signature was used to establish a multivariable logistic regression model to predict the advanced-late stage of CRC. A nomogram was further developed by incorporating the classifier and some independent clinical risk factors, and its performance was evaluated by discrimination and calibration analysis. The prognostic value of the classifier was determined by survival analysis. Furthermore, the diagnostic performance of several CpGs in the methylation signature was evaluated.

Results

The eight-CpG-based methylation signature discriminated early stage from advanced-late stage CRC, with a satisfactory AUC of more than 0.700 in both the training and validation sets. This methylation classifier was identified as an independent predictor for CRC staging. The nomogram showed favorable predictive power for preoperative staging, and the C-index reached 0.817 (95% CI: 0.753–0.881) and 0.817 (95% CI: 0.721–0.913) in another training set and validation set respectively, with good calibration. The patients stratified in the high-risk group by the methylation classifier had significantly worse survival outcome than those in the low-risk group. Combination diagnosis utilizing only four of the eight specific CpGs performed well, even in CRC patients with low CEA level or at early stage.

Conclusions

Our classifier is a valuable predictive indicator that can supplement established methods for more accurate preoperative staging and also provides prognostic information for CRC patients. Besides, the combination of multiple CpGs has a high value in the diagnosis of CRC.

A deep learning and similarity-based hierarchical clustering approach for pathological stage prediction of papillary renal cell carcinoma

Papillary renal cell carcinoma (pRCC), which accounts for 10–15% of renal cell carcinomas, is the second most frequent renal cell carcinoma. pRCC patient classification is difficult because of disease heterogeneity, histologic subtypes, and variations in both disease progression and patient outcomes. Nevertheless, symptom-based patient classification is indispensable in deciding treatment options. Here we introduce a prediction method for distinguishing pRCC pathological tumour stages using deep learning and similarity-based hierarchical clustering approaches. Differentially expressed genes (DEGs) were identified from gene expression data of pRCC patients retrieved from TCGA. Thirty-three of these genes were distinguished based on expression in early or late stage pRCC using the Wilcoxon rank sum test, confidence interval, and LASSO regression. Then, a deep learning model was constructed to predict tumour progression with an accuracy of 0.942 and area under curve of 0.933. Furthermore, pathological sub-stage information with an accuracy of 0.857 was obtained via similarity-based hierarchical clustering using 18 DEGs between stages I and II, and 11 DEGs between stages III and IV, identified through Wilcoxon rank sum test and quantile approach. Additionally, we offer this classification process as an R function. This is the first report of a model distinguishing the pathological tumour stages of pRCC using deep learning and similarity-based hierarchical clustering methods. Our findings are potentially applicable for improving early detection and treatment of pRCC and establishing a clearer classification of the pathological stages in other tumours.

Expression based biomarkers and models to classify early and late-stage samples of Papillary Thyroid Carcinoma

INTRODUCTION

Recently, the rise in the incidences of thyroid cancer worldwide renders it to be the sixth most common cancer among women. Commonly, Fine Needle Aspiration biopsy predominantly facilitates the diagnosis of the nature of thyroid nodules. However, it is inconsiderable in determining the tumor's state, i.e., benign or malignant. This study aims to identify the key RNA transcripts that can segregate the early and late-stage samples of Thyroid Carcinoma (THCA) using RNA expression profiles.

MATERIALS AND METHODS

In this study, we used the THCA RNA-Seq dataset of The Cancer Genome Atlas, consisting of 500 cancer and 58 normal (adjacent non-tumorous) samples obtained from the Genomics Data Commons (GDC) data portal. This dataset was dissected to identify key RNA expression features using various feature selection techniques. Subsequently, samples were classified based on selected features employing different machine learning algorithms.

RESULTS

Single gene ranking based on the Area Under the Receiver Operating Characteristics (AUROC) curve identified the DCN transcript that can classify the early-stage samples from late-stage samples with 0.66 AUROC. To further improve the performance, we identified a panel of 36 RNA transcripts that achieved F1 score of 0.75 with 0.73 AUROC (95% CI: 0.62-0.84) on the validation dataset. Moreover, prediction models based on 18-features from this panel correctly predicted 75% of the samples of the external validation dataset. In addition, the multiclass model classified normal, early, and late-stage samples with AUROC of 0.95 (95% CI: 0.84-1), 0.76 (95% CI: 0.66-0.85) and 0.72 (95% CI: 0.61-0.83) on the validation dataset. Besides, a five protein-coding transcripts panel was also recognized, which segregated cancer and normal samples in the validation dataset with F1 score of 0.97 and 0.99 AUROC (95% CI: 0.91-1).

CONCLUSION

We identified 36 important RNA transcripts whose expression segregated early and late-stage samples with reasonable accuracy. The models and dataset used in this study are available from the webserver CancerTSP (http://webs.iiitd.edu.in/raghava/cancertsp/).

Computing Skin Cutaneous Melanoma Outcome From the HLA-Alleles and Clinical Characteristics

Human leukocyte antigen (HLA) are essential components of the immune system that stimulate immune cells to provide protection and defense against cancer. Thousands of HLA alleles have been reported in the literature, but only a specific set of HLA alleles are present in an individual. The capability of the immune system to recognize cancer-associated mutations depends on the presence of a particular set of alleles, which elicit an immune response to fight against cancer. Therefore, the occurrence of specific HLA alleles affects the survival outcome of cancer patients. In the current study, prediction models were developed, using 401 cutaneous melanoma patients, to predict the overall survival (OS) of patients using their clinical data and HLA alleles. We observed that the presence of certain favorable superalleles like HLA-B∗55 (HR = 0.15, 95% CI 0.034-0.67), HLA-A∗01 (HR = 0.5, 95% CI 0.3-0.8), is responsible for the improved OS. In contrast, the presence of certain unfavorable superalleles such as HLA-B∗50 (HR = 2.76, 95% CI 1.284-5.941), HLA-DRB1∗12 (HR = 3.44, 95% CI 1.64-7.2) is responsible for the poor survival. We developed prediction models using key 14 HLA superalleles, demographic, and clinical characteristics for predicting high-risk cutaneous melanoma patients and achieved HR = 4.52 (95% CI 3.088-6.609, p-value = 8.01E-15). Eventually, we also provide a web-based service to the community for predicting the risk status in cutaneous melanoma patients (https://webs.iiitd.edu.in/raghava/skcmhrp/).

Identification of Platform-Independent Diagnostic Biomarker Panel for Hepatocellular Carcinoma Using Large-Scale Transcriptomics Data

The high mortality rate of hepatocellular carcinoma (HCC) is primarily due to its late diagnosis. In the past, numerous attempts have been made to design genetic biomarkers for the identification of HCC; unfortunately, most of the studies are based on small datasets obtained from a specific platform or lack reasonable validation performance on the external datasets. In order to identify a universal expression-based diagnostic biomarker panel for HCC that can be applicable across multiple platforms, we have employed large-scale transcriptomic profiling datasets containing a total of 2,316 HCC and 1,665 non-tumorous tissue samples. These samples were obtained from 30 studies generated by mainly four types of profiling techniques (Affymetrix, Illumina, Agilent, and High-throughput sequencing), which are implemented in a wide range of platforms. Firstly, we scrutinized overlapping 26 genes that are differentially expressed in numerous datasets. Subsequently, we identified a panel of three genes (FCN3, CLEC1B, and PRC1) as HCC biomarker using different feature selection techniques. Three-genes-based HCC biomarker identified HCC samples in training/validation datasets with an accuracy between 93 and 98%, Area Under Receiver Operating Characteristic curve (AUROC) in a range of 0.97 to 1.0. A reasonable performance, i.e., AUROC 0.91–0.96 achieved on validation dataset containing peripheral blood mononuclear cells, concurred their non-invasive utility. Furthermore, the prognostic potential of these genes was evaluated on TCGA-LIHC and GSE14520 cohorts using univariate survival analysis. This analysis revealed that these genes are prognostic indicators for various types of the survivals of HCC patients (e.g., Overall Survival, Progression-Free Survival, Disease-Free Survival). These genes significantly stratified high-risk and low-risk HCC patients (p-value <0.05). In conclusion, we identified a universal platform-independent three-genes-based biomarker that can predict HCC patients with high precision and also possess significant prognostic potential. Eventually, we developed a web server HCCpred based on the above study to facilitate scientific community (http://webs.iiitd.edu.in/raghava/hccpred/).