GEOlimma: differential expression analysis and feature selection using pre-existing microarray data.

BACKGROUND: Differential expression and feature selection analyses are essential steps for the development of accurate diagnostic/prognostic classifiers of complicated human diseases using transcriptomics data. These steps are particularly challenging due to the curse of dimensionality and the presence of technical and biological noise. A promising strategy for overcoming these challenges is the incorporation of pre-existing transcriptomics data in the identification of differentially expressed (DE) genes. This approach has the potential to improve the quality of selected genes, increase classification performance, and enhance biological interpretability. While a number of methods have been developed that use pre-existing data for differential expression analysis, existing methods do not leverage the identities of experimental conditions to create a robust metric for identifying DE genes. RESULTS: In this study, we propose a novel differential expression and feature selection method-GEOlimma-which combines pre-existing microarray data from the Gene Expression Omnibus (GEO) with the widely-applied Limma method for differential expression analysis. We first quantify differential gene expression across 2481 pairwise comparisons from 602 curated GEO Datasets, and we convert differential expression frequencies to DE prior probabilities. Genes with high DE prior probabilities show enrichment in cell growth and death, signal transduction, and cancer-related biological pathways, while genes with low prior probabilities were enriched in sensory system pathways. We then applied GEOlimma to four differential expression comparisons within two human disease datasets and performed differential expression, feature selection, and supervised classification analyses. Our results suggest that use of GEOlimma provides greater experimental power to detect DE genes compared to Limma, due to its increased effective sample size. Furthermore, in a supervised classification analysis using GEOlimma as a feature selection method, we observed similar or better classification performance than Limma given small, noisy subsets of an asthma dataset. CONCLUSIONS: Our results demonstrate that GEOlimma is a more effective method for differential gene expression and feature selection analyses compared to the standard Limma method. Due to its focus on gene-level differential expression, GEOlimma also has the potential to be applied to other high-throughput biological datasets.

Prognostic analysis of histopathological images using pre-trained convolutional neural networks: application to hepatocellular carcinoma.

Histopathological images contain rich phenotypic descriptions of the molecular processes underlying disease progression. Convolutional neural networks, state-of-the-art image analysis techniques in computer vision, automatically learn representative features from such images which can be useful for disease diagnosis, prognosis, and subtyping. Hepatocellular carcinoma (HCC) is the sixth most common type of primary liver malignancy. Despite the high mortality rate of HCC, little previous work has made use of CNN models to explore the use of histopathological images for prognosis and clinical survival prediction of HCC. We applied three pre-trained CNN models-VGG 16, Inception V3 and ResNet 50-to extract features from HCC histopathological images. Sample visualization and classification analyses based on these features showed a very clear separation between cancer and normal samples. In a univariate Cox regression analysis, 21.4% and 16% of image features on average were significantly associated with overall survival (OS) and disease-free survival (DFS), respectively. We also observed significant correlations between these features and integrated biological pathways derived from gene expression and copy number variation. Using an elastic net regularized Cox Proportional Hazards model of OS constructed from Inception image features, we obtained a concordance index (C-index) of 0.789 and a significant log-rank test (p = 7.6E-18). We also performed unsupervised classification to identify HCC subgroups from image features. The optimal two subgroups discovered using Inception model image features showed significant differences in both overall (C-index = 0.628 and p = 7.39E-07) and DFS (C-index = 0.558 and p = 0.012). Our work demonstrates the utility of extracting image features using pre-trained models by using them to build accurate prognostic models of HCC as well as highlight significant correlations between these features, clinical survival, and relevant biological pathways. Image features extracted from HCC histopathological images using the pre-trained CNN models VGG 16, Inception V3 and ResNet 50 can accurately distinguish normal and cancer samples. Furthermore, these image features are significantly correlated with survival and relevant biological pathways.

Multi-omic biomarker identification and validation for diagnosing warzone-related post-traumatic stress disorder.

Post-traumatic stress disorder (PTSD) impacts many veterans and active duty soldiers, but diagnosis can be problematic due to biases in self-disclosure of symptoms, stigma within military populations, and limitations identifying those at risk. Prior studies suggest that PTSD may be a systemic illness, affecting not just the brain, but the entire body. Therefore, disease signals likely span multiple biological domains, including genes, proteins, cells, tissues, and organism-level physiological changes. Identification of these signals could aid in diagnostics, treatment decision-making, and risk evaluation. In the search for PTSD diagnostic biomarkers, we ascertained over one million molecular, cellular, physiological, and clinical features from three cohorts of male veterans. In a discovery cohort of 83 warzone-related PTSD cases and 82 warzone-exposed controls, we identified a set of 343 candidate biomarkers. These candidate biomarkers were selected from an integrated approach using (1) data-driven methods, including Support Vector Machine with Recursive Feature Elimination and other standard or published methodologies, and (2) hypothesis-driven approaches, using previous genetic studies for polygenic risk, or other PTSD-related literature. After reassessment of ~30% of these participants, we refined this set of markers from 343 to 28, based on their performance and ability to track changes in phenotype over time. The final diagnostic panel of 28 features was validated in an independent cohort (26 cases, 26 controls) with good performance (AUC = 0.80, 81% accuracy, 85% sensitivity, and 77% specificity). The identification and validation of this diverse diagnostic panel represents a powerful and novel approach to improve accuracy and reduce bias in diagnosing combat-related PTSD.

Multimodal Meta-Analysis of 1,494 Hepatocellular Carcinoma Samples Reveals Significant Impact of Consensus Driver Genes on Phenotypes.

Although driver genes in hepatocellular carcinoma (HCC) have been investigated in various previous genetic studies, prevalence of key driver genes among heterogeneous populations is unknown. Moreover, the phenotypic associations of these driver genes are poorly understood. This report aims to reveal the phenotypic impacts of a group of consensus driver genes in HCC. We used MutSigCV and OncodriveFM modules implemented in the IntOGen pipeline to identify consensus driver genes across six HCC cohorts comprising 1,494 samples in total. To access their global impacts, we used The Cancer Genome Atlas (TCGA) mutations and copy-number variations to predict the transcriptomics data, under generalized linear models. We further investigated the associations of the consensus driver genes to patient survival, age, gender, race, and risk factors. We identify 10 consensus driver genes across six HCC cohorts in total. Integrative analysis of driver mutations, copy-number variations, and transcriptomic data reveals that these consensus driver mutations and their copy-number variations are associated with a majority (62.5%) of the mRNA transcriptome but only a small fraction (8.9%) of miRNAs. Genes associated with TP53, CTNNB1, and ARID1A mutations contribute to the tripod of most densely connected pathway clusters. These driver genes are significantly associated with patients' overall survival. Some driver genes are significantly linked to HCC gender (CTNNB1, ALB, TP53, and AXIN1), race (TP53 and CDKN2A), and age (RB1) disparities. This study prioritizes a group of consensus drivers in HCC, which collectively show vast impacts on the phenotypes. These driver genes may warrant as valuable therapeutic targets of HCC.

Deep Learning-Based Multi-Omics Integration Robustly Predicts Survival in Liver Cancer.

Identifying robust survival subgroups of hepatocellular carcinoma (HCC) will significantly improve patient care. Currently, endeavor of integrating multi-omics data to explicitly predict HCC survival from multiple patient cohorts is lacking. To fill this gap, we present a deep learning (DL)-based model on HCC that robustly differentiates survival subpopulations of patients in six cohorts. We built the DL-based, survival-sensitive model on 360 HCC patients' data using RNA sequencing (RNA-Seq), miRNA sequencing (miRNA-Seq), and methylation data from The Cancer Genome Atlas (TCGA), which predicts prognosis as good as an alternative model where genomics and clinical data are both considered. This DL-based model provides two optimal subgroups of patients with significant survival differences (P = 7.13e-6) and good model fitness [concordance index (C-index) = 0.68]. More aggressive subtype is associated with frequent TP53 inactivation mutations, higher expression of stemness markers (KRT19 and EPCAM) and tumor marker BIRC5, and activated Wnt and Akt signaling pathways. We validated this multi-omics model on five external datasets of various omics types: LIRI-JP cohort (n = 230, C-index = 0.75), NCI cohort (n = 221, C-index = 0.67), Chinese cohort (n = 166, C-index = 0.69), E-TABM-36 cohort (n = 40, C-index = 0.77), and Hawaiian cohort (n = 27, C-index = 0.82). This is the first study to employ DL to identify multi-omics features linked to the differential survival of patients with HCC. Given its robustness over multiple cohorts, we expect this workflow to be useful at predicting HCC prognosis prediction. Clin Cancer Res; 24(6); 1248-59. ©2017 AACR.

Time Series miRNA-mRNA integrated analysis reveals critical miRNAs and targets in macrophage polarization.

Polarization of macrophages is regulated through complex signaling networks. Correlating miRNA and mRNA expression over time after macrophage polarization has not yet been investigated. We used paired RNA-Seq and miRNA-Seq experiments to measure the mRNA and miRNA expression in bone marrow-derived macrophages over a time-series of 8 hours. Bioinformatics analysis identified 31 differentially expressed miRNAs between M1 and M2 polarized macrophages. The top 4 M1 miRNAs (miR-155-3p, miR-155-5p, miR-147-3p and miR-9-5p) and top 4 M2 miRNAs (miR-27a-5p, let-7c-1-3p, miR-23a-5p and miR-23b-5p) were validated by qPCR. Interestingly, M1 specific miRNAs could be categorized to early- and late-response groups, in which three new miRNAs miR-1931, miR-3473e and miR-5128 were validated as early-response miRNAs. M1 polarization led to the enrichment of genes involved in immune responses and signal transduction, whereas M2 polarization enriched genes involved in cell cycle and metabolic processes. C2H2 zinc-finger family members are key targets of DE miRNAs. The integrative analysis between miRNAs and mRNAs demonstrates the regulations of miRNAs on nearly four thousand differentially expressed genes and most of the biological pathways enriched in macrophage polarization. In summary, this study elucidates the expression profiles of miRNAs and their potential targetomes during macrophage polarization.