Multiomics-Based Feature Extraction and Selection for the Prediction of Lung Cancer Survival

Lung cancer is a global health challenge, hindered by delayed diagnosis and the disease's complex molecular landscape. Accurate patient survival prediction is critical, motivating the exploration of various -omics datasets using machine learning methods. Leveraging multi-omics data, this study seeks to enhance the accuracy of survival prediction by proposing new feature extraction techniques combined with unbiased feature selection. Two lung adenocarcinoma multi-omics datasets, originating from the TCGA and CPTAC-3 projects, were employed for this purpose, emphasizing gene expression, methylation, and mutations as the most relevant data sources that provide features for the survival prediction models. Additionally, gene set aggregation was shown to be the most effective feature extraction method for mutation and copy number variation data. Using the TCGA dataset, we identified 32 molecular features that allowed the construction of a 2-year survival prediction model with an AUC of 0.839. The selected features were additionally tested on an independent CPTAC-3 dataset, achieving an AUC of 0.815 in nested cross-validation, which confirmed the robustness of the identified features.

intCC: An efficient weighted integrative consensus clustering of multimodal data

High throughput profiling of multiomics data provides a valuable resource to better understand the complex human disease such as cancer and to potentially uncover new subtypes. Integrative clustering has emerged as a powerful unsupervised learning framework for subtype discovery. In this paper, we propose an efficient weighted integrative clustering called intCC by combining ensemble method, consensus clustering and kernel learning integrative clustering. We illustrate that intCC can accurately uncover the latent cluster structures via extensive simulation studies and a case study on the TCGA pan cancer datasets. An R package intCC implementing our proposed method is available at https://github.com/candsj/intCC.

Prognostic value of neutrophil extracellular trap signature in clear cell renal cell carcinoma

Introduction

Clear cell renal cell carcinoma (ccRCC) is the most prevalent type of urological carcinoma. Although targeted therapy and immunotherapy are usually employed, they often result in primary and acquired resistance. There is currently a lack of dependable biomarkers that can accurately anticipate the prognosis of ccRCC. Recent research has indicated the critical role of neutrophil extracellular traps (NETs) in the development, metastasis, and immune evasion of cancer. The aim of this study was to explore the value of NETs in the development and prognosis of ccRCC.

Methods

Clinical features and genetic expression information of ccRCC patients were acquired from The Cancer Genome Atlas (TCGA), International Cancer Genome Consortium (ICGC) and E-MTAB-1980 database. NETs-related gene set were obtained from previous studies. A NETs-related gene signature was constructed based on TCGA data and validated using ICGC and E-MTAB-1980 databases. Furthermore, the immune microenvironment and responsiveness to anticancer medications in ccRCC patients with varying levels of NETs risks were investigated.

Results

A total of 31 NET-related genes were differently expressed between normal kidney and ccRCC tissues. 17 out of 31 were significantly associated with overall survival. After LASSO Cox regression analysis, nine NETs-related genes were enrolled to construct the NETs prognosis signature, and all the ccRCC patients from TCGA were divided into low and high risk group. This signature demonstrated excellent performance in predicting the overall survival of TCGA patients as well as the validation ICGC and E-MTAB-1980 patients. Additionally, the NETs signature was significantly correlated with immune infiltration and drug sensitivity.

Conclusions

The NETs signature established by the current study has prognostic significance in ccRCC, and may serve as a useful biomarker for patient stratification and treatment decisions. Further validation and clinical studies are required to fully translate these findings into clinical practice.

Integrative multiomics evaluation reveals the importance of pseudouridine synthases in hepatocellular carcinoma

Background: The pseudouridine synthases (PUSs) have been reported to be associated with cancers. However, their involvement in hepatocellular carcinoma (HCC) has not been well documented. Here, we assess the roles of PUSs in HCC. Methods: RNA sequencing data of TCGA-LIHC and LIRI-JP were downloaded from the Cancer Genome Atlas (TCGA) and the International Cancer Genome Consortium (ICGC), respectively. GSE36376 gene expression microarray was downloaded from the Gene Expression Omnibus (GEO). Proteomics data for an HBV-related HCC cohort was obtained from the CPTAC Data Portal. The RT-qPCR assay was performed to measure the relative mRNA expression of genes in clinical tissues and cell lines. Diagnostic efficiency was evaluated by the ROC curve. Prognostic value was assessed using the Kaplan-Meier curve, Cox regression model, and time-dependent ROC curve. Copy number variation (CNV) was analyzed using the GSCA database. Functional analysis was carried out with GSEA, GSVA, and clusterProfiler package. The tumor microenvironment (TME) related analysis was performed using ssGSEA and the ESTIMATE algorithm. Results: We identified 7 PUSs that were significantly upregulated in HCC, and 5 of them (DKC1, PUS1, PUS7, PUSL1, and RPUSD3) were independent risk factors for patients' OS. Meanwhile, the protein expression of DKC1, PUS1, and PUS7 was also upregulated and related to poor survival. Both mRNA and protein of these PUSs were highly diagnostic of HCC. Moreover, the CNV of PUS1, PUS7, PUS7L, and RPUSD2 was also associated with prognosis. Further functional analysis revealed that PUSs were mainly involved in pathways such as genetic information processing, substance metabolism, cell cycle, and immune regulation. Conclusion: PUSs may play crucial roles in HCC and could be used as potential biomarkers for the diagnosis and prognosis of patients.

Managing of Unassigned Mass Spectrometric Data by Neural Network for Cancer Phenotypes Classification

Mass spectrometric profiling provides information on the protein and metabolic composition of biological samples. However, the weak efficiency of computational algorithms in correlating tandem spectra to molecular components (proteins and metabolites) dramatically limits the use of "omics" profiling for the classification of nosologies. The development of machine learning methods for the intelligent analysis of raw mass spectrometric (HPLC-MS/MS) measurements without involving the stages of preprocessing and data identification seems promising. In our study, we tested the application of neural networks of two types, a 1D residual convolutional neural network (CNN) and a 3D CNN, for the classification of three cancers by analyzing metabolomic-proteomic HPLC-MS/MS data. In this work, we showed that both neural networks could classify the phenotypes of gender-mixed oncology, kidney cancer, gender-specific oncology, ovarian cancer, and the phenotype of a healthy person by analyzing 'omics' data in 'mgf' data format. The created models effectively recognized oncopathologies with a model accuracy of 0.95. Information was obtained on the remoteness of the studied phenotypes. The closest in the experiment were ovarian cancer, kidney cancer, and prostate cancer/kidney cancer. In contrast, the healthy phenotype was the most distant from cancer phenotypes and ovarian and prostate cancers. The neural network makes it possible to not only classify the studied phenotypes, but also to determine their similarity (distance matrix), thus overcoming algorithmic barriers in identifying HPLC-MS/MS spectra. Neural networks are versatile and can be applied to standard experimental data formats obtained using different analytical platforms.

Tensor-Decomposition-Based Unsupervised Feature Extraction in Single-Cell Multiomics Data Analysis

Analysis of single-cell multiomics datasets is a novel topic and is considerably challenging because such datasets contain a large number of features with numerous missing values. In this study, we implemented a recently proposed tensor-decomposition (TD)-based unsupervised feature extraction (FE) technique to address this difficult problem. The technique can successfully integrate single-cell multiomics data composed of gene expression, DNA methylation, and accessibility. Although the last two have large dimensions, as many as ten million, containing only a few percentage of nonzero values, TD-based unsupervised FE can integrate three omics datasets without filling in missing values. Together with UMAP, which is used frequently when embedding single-cell measurements into two-dimensional space, TD-based unsupervised FE can produce two-dimensional embedding coincident with classification when integrating single-cell omics datasets. Genes selected based on TD-based unsupervised FE are also significantly related to reasonable biological roles.

TMBIM6, a potential virus target protein identified by integrated multiomics data analysis in SARS-CoV-2-infected host cells

Coronavirus disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In this study, we collected open access data to analyze the mechanisms associated with SARS-CoV-2 infection. Gene set enrichment analysis (GSEA) revealed that apoptosis-related pathways were enriched in the cells after SARS-CoV-2 infection, and the results of differential expression analysis showed that biological functions related to endoplasmic reticulum stress (ERS) and lipid metabolism were disordered. TMBIM6 was identified as a potential target for SARS-CoV-2 in host cells through weighted gene coexpression network analysis (WGCNA) of the time course of expression of host and viral proteins. The expression and related functions of TMBIM6 were subsequently analyzed to illuminate how viral proteins interfere with the physiological function of host cells. The potential function of viral proteins was further analyzed by GEne Network Inference with Ensemble of trees (GENIE3). This study identified TMBIM6 as a target protein associated with the pathogenesis of SARS-CoV-2, which might provide a novel therapeutic approach for COVID-19 in the future.

Extended application of genomic selection to screen multiomics data for prognostic signatures of prostate cancer

Prognostic tests using expression profiles of several dozen genes help provide treatment choices for prostate cancer (PCa). However, these tests require improvement to meet the clinical need for resolving overtreatment, which continues to be a pervasive problem in PCa management. Genomic selection (GS) methodology, which utilizes whole-genome markers to predict agronomic traits, was adopted in this study for PCa prognosis. We leveraged The Cancer Genome Atlas (TCGA) database to evaluate the prediction performance of six GS methods and seven omics data combinations, which showed that the Best Linear Unbiased Prediction (BLUP) model outperformed the other methods regarding predictability and computational efficiency. Leveraging the BLUP-HAT method, an accelerated version of BLUP, we demonstrated that using expression data of a large number of disease-relevant genes and with an integration of other omics data (i.e. miRNAs) significantly increased outcome predictability when compared with panels consisting of a small number of genes. Finally, we developed a novel stepwise forward selection BLUP-HAT method to facilitate searching multiomics data for predictor variables with prognostic potential. The new method was applied to the TCGA data to derive mRNA and miRNA expression signatures for predicting relapse-free survival of PCa, which were validated in six independent cohorts. This is a transdisciplinary adoption of the highly efficient BLUP-HAT method and its derived algorithms to analyze multiomics data for PCa prognosis. The results demonstrated the efficacy and robustness of the new methodology in developing prognostic models in PCa, suggesting a potential utility in managing other types of cancer.

Multiomics data reveals the influences of myasthenia gravis on thymoma and its precision treatment

Thymoma is a rare characterized by a unique association with autoimmune diseases, especially myasthenia gravis (MG). However, little is known about the molecular characteristics of MG-associated thymoma individuals. We aim to examine the influences of MG on thymoma by analyzing multiomics data. A total of 105 samples with thymoma was analyzed from TCGA and these samples were divided into subgroups with MG (MGT) or without MG (MGF) according to clinical information. We then characterized the differential gene expression, pathway activity, somatic mutation frequency, and likelihood of responding to chemotherapies and immunotherapies of the two identified subgroups. MGT subgroup was characterized by elevated inflammatory responses and metabolically related pathways, whereas the MGF subgroup was predicted to be more sensitive to chemotherapy and presented with mesenchymal characteristics. More copy number amplifications and deletions were observed in MGT, whereas GTF2I mutations occur at significantly higher frequencies in MGF. Two molecular subtypes were further identified within MGF samples by unsupervised clustering where one subtype was enriched in TGF-β and WNT pathways with higher sensitivity to relevant targeted drugs but hardly respond to immunotherapy. For another subtype, a higher recurrence rate of thymoma and more likelihood of responding to immunotherapy were observed. Our findings presented a comprehensive molecular characterization of thymoma patients given the status of MG, and provided potential strategies to help individualized management and treatment.