Cross-Platform Toxicogenomics for the Prediction of Non-Genotoxic Hepatocarcinogenesis in Rat

In the area of omics profiling in toxicology, i.e. toxicogenomics, characteristic molecular profiles have previously been incorporated into prediction models for early assessment of a carcinogenic potential and mechanism-based classification of compounds. Traditionally, the biomarker signatures used for model construction were derived from individual high-throughput techniques, such as microarrays designed for monitoring global mRNA expression. In this study, we built predictive models by integrating omics data across complementary microarray platforms and introduced new concepts for modeling of pathway alterations and molecular interactions between multiple biological layers. We trained and evaluated diverse machine learning-based models, differing in the incorporated features and learning algorithms on a cross-omics dataset encompassing mRNA, miRNA, and protein expression profiles obtained from rat liver samples treated with a heterogeneous set of substances. Most of these compounds could be unambiguously classified as genotoxic carcinogens, non-genotoxic carcinogens, or non-hepatocarcinogens based on evidence from published studies. Since mixed characteristics were reported for the compounds Cyproterone acetate, Thioacetamide, and Wy-14643, we reclassified these compounds as either genotoxic or non-genotoxic carcinogens based on their molecular profiles. Evaluating our toxicogenomics models in a repeated external cross-validation procedure, we demonstrated that the prediction accuracy of our models could be increased by joining the biomarker signatures across multiple biological layers and by adding complex features derived from cross-platform integration of the omics data. Furthermore, we found that adding these features resulted in a better separation of the compound classes and a more confident reclassification of the three undefined compounds as non-genotoxic carcinogens.     

Genomic Models of Short-Term Exposure Accurately Predict Long-Term Chemical Carcinogenicity and Identify Putative Mechanisms of Action

Background

Despite an overall decrease in incidence of and mortality from cancer, about 40% of Americans will be diagnosed with the disease in their lifetime, and around 20% will die of it. Current approaches to test carcinogenic chemicals adopt the 2-year rodent bioassay, which is costly and time-consuming. As a result, fewer than 2% of the chemicals on the market have actually been tested. However, evidence accumulated to date suggests that gene expression profiles from model organisms exposed to chemical compounds reflect underlying mechanisms of action, and that these toxicogenomic models could be used in the prediction of chemical carcinogenicity.

Results

In this study, we used a rat-based microarray dataset from the NTP DrugMatrix Database to test the ability of toxicogenomics to model carcinogenicity. We analyzed 1,221 gene-expression profiles obtained from rats treated with 127 well-characterized compounds, including genotoxic and non-genotoxic carcinogens. We built a classifier that predicts a chemical''s carcinogenic potential with an AUC of 0.78, and validated it on an independent dataset from the Japanese Toxicogenomics Project consisting of 2,065 profiles from 72 compounds. Finally, we identified differentially expressed genes associated with chemical carcinogenesis, and developed novel data-driven approaches for the molecular characterization of the response to chemical stressors.

Conclusion

Here, we validate a toxicogenomic approach to predict carcinogenicity and provide strong evidence that, with a larger set of compounds, we should be able to improve the sensitivity and specificity of the predictions. We found that the prediction of carcinogenicity is tissue-dependent and that the results also confirm and expand upon previous studies implicating DNA damage, the peroxisome proliferator-activated receptor, the aryl hydrocarbon receptor, and regenerative pathology in the response to carcinogen exposure.     

Clinical drug response can be predicted using baseline gene expression levels and in vitro drug sensitivity in cell lines

We demonstrate a method for the prediction of chemotherapeutic response in patients using only before-treatment baseline tumor gene expression data. First, we fitted models for whole-genome gene expression against drug sensitivity in a large panel of cell lines, using a method that allows every gene to influence the prediction. Following data homogenization and filtering, these models were applied to baseline expression levels from primary tumor biopsies, yielding an in vivo drug sensitivity prediction. We validated this approach in three independent clinical trial datasets, and obtained predictions equally good, or better than, gene signatures derived directly from clinical data.     

Identification of Common Prognostic Gene Expression Signatures with Biological Meanings from Microarray Gene Expression Datasets

Numerous prognostic gene expression signatures for breast cancer were generated previously with few overlap and limited insight into the biology of the disease. Here we introduce a novel algorithm named SCoR (Survival analysis using Cox proportional hazard regression and Random resampling) to apply random resampling and clustering methods in identifying gene features correlated with time to event data. This is shown to reduce overfitting noises involved in microarray data analysis and discover functional gene sets linked to patient survival. SCoR independently identified a common poor prognostic signature composed of cell proliferation genes from six out of eight breast cancer datasets. Furthermore, a sequential SCoR analysis on highly proliferative breast cancers repeatedly identified T/B cell markers as favorable prognosis factors. In glioblastoma, SCoR identified a common good prognostic signature of chromosome 10 genes from two gene expression datasets (TCGA and REMBRANDT), recapitulating the fact that loss of one copy of chromosome 10 (which harbors the tumor suppressor PTEN) is linked to poor survival in glioblastoma patients. SCoR also identified prognostic genes on sex chromosomes in lung adenocarcinomas, suggesting patient gender might be used to predict outcome in this disease. These results demonstrate the power of SCoR to identify common and biologically meaningful prognostic gene expression signatures.     

Accurate molecular classification of cancer using simple rules

Background

One intractable problem with using microarray data analysis for cancer classification is how to reduce the extremely high-dimensionality gene feature data to remove the effects of noise. Feature selection is often used to address this problem by selecting informative genes from among thousands or tens of thousands of genes. However, most of the existing methods of microarray-based cancer classification utilize too many genes to achieve accurate classification, which often hampers the interpretability of the models. For a better understanding of the classification results, it is desirable to develop simpler rule-based models with as few marker genes as possible.

Methods

We screened a small number of informative single genes and gene pairs on the basis of their depended degrees proposed in rough sets. Applying the decision rules induced by the selected genes or gene pairs, we constructed cancer classifiers. We tested the efficacy of the classifiers by leave-one-out cross-validation (LOOCV) of training sets and classification of independent test sets.

Results

We applied our methods to five cancerous gene expression datasets: leukemia (acute lymphoblastic leukemia [ALL] vs. acute myeloid leukemia [AML]), lung cancer, prostate cancer, breast cancer, and leukemia (ALL vs. mixed-lineage leukemia [MLL] vs. AML). Accurate classification outcomes were obtained by utilizing just one or two genes. Some genes that correlated closely with the pathogenesis of relevant cancers were identified. In terms of both classification performance and algorithm simplicity, our approach outperformed or at least matched existing methods.

Conclusion

In cancerous gene expression datasets, a small number of genes, even one or two if selected correctly, is capable of achieving an ideal cancer classification effect. This finding also means that very simple rules may perform well for cancerous class prediction.     

EMERGE: a flexible modelling framework to predict genomic regulatory elements from genomic signatures

Regulatory DNA elements, short genomic segments that regulate gene expression, have been implicated in developmental disorders and human disease. Despite this clinical urgency, only a small fraction of the regulatory DNA repertoire has been confirmed through reporter gene assays. The overall success rate of functional validation of candidate regulatory elements is low. Moreover, the number and diversity of datasets from which putative regulatory elements can be identified is large and rapidly increasing. We generated a flexible and user-friendly tool to integrate the information from different types of genomic datasets, e.g. ATAC-seq, ChIP-seq, conservation, aiming to increase the ease and success rate of functional prediction. To this end, we developed the EMERGE program that merges all datasets that the user considers informative and uses a logistic regression framework, based on validated functional elements, to set optimal weights to these datasets. ROC curve analysis shows that a combination of datasets leads to improved prediction of tissue-specific enhancers in human, mouse and Drosophila genomes. Functional assays based on this prediction can be expected to have substantially higher success rates. The resulting integrated signal for prediction of functional elements can be plotted in a build-in genome browser or exported for further analysis.     

GO-PCA: An Unsupervised Method to Explore Gene Expression Data Using Prior Knowledge

Method

Genome-wide expression profiling is a widely used approach for characterizing heterogeneous populations of cells, tissues, biopsies, or other biological specimen. The exploratory analysis of such data typically relies on generic unsupervised methods, e.g. principal component analysis (PCA) or hierarchical clustering. However, generic methods fail to exploit prior knowledge about the molecular functions of genes. Here, I introduce GO-PCA, an unsupervised method that combines PCA with nonparametric GO enrichment analysis, in order to systematically search for sets of genes that are both strongly correlated and closely functionally related. These gene sets are then used to automatically generate expression signatures with functional labels, which collectively aim to provide a readily interpretable representation of biologically relevant similarities and differences. The robustness of the results obtained can be assessed by bootstrapping.

Results

I first applied GO-PCA to datasets containing diverse hematopoietic cell types from human and mouse, respectively. In both cases, GO-PCA generated a small number of signatures that represented the majority of lineages present, and whose labels reflected their respective biological characteristics. I then applied GO-PCA to human glioblastoma (GBM) data, and recovered signatures associated with four out of five previously defined GBM subtypes. My results demonstrate that GO-PCA is a powerful and versatile exploratory method that reduces an expression matrix containing thousands of genes to a much smaller set of interpretable signatures. In this way, GO-PCA aims to facilitate hypothesis generation, design of further analyses, and functional comparisons across datasets.     

Accurate Prediction of Transposon-Derived piRNAs by Integrating Various Sequential and Physicochemical Features

BackgroundPiwi-interacting RNA (piRNA) is the largest class of small non-coding RNA molecules. The transposon-derived piRNA prediction can enrich the research contents of small ncRNAs as well as help to further understand generation mechanism of gamete.MethodsIn this paper, we attempt to differentiate transposon-derived piRNAs from non-piRNAs based on their sequential and physicochemical features by using machine learning methods. We explore six sequence-derived features, i.e. spectrum profile, mismatch profile, subsequence profile, position-specific scoring matrix, pseudo dinucleotide composition and local structure-sequence triplet elements, and systematically evaluate their performances for transposon-derived piRNA prediction. Finally, we consider two approaches: direct combination and ensemble learning to integrate useful features and achieve high-accuracy prediction models.ResultsWe construct three datasets, covering three species: Human, Mouse and Drosophila, and evaluate the performances of prediction models by 10-fold cross validation. In the computational experiments, direct combination models achieve AUC of 0.917, 0.922 and 0.992 on Human, Mouse and Drosophila, respectively; ensemble learning models achieve AUC of 0.922, 0.926 and 0.994 on the three datasets.ConclusionsCompared with other state-of-the-art methods, our methods can lead to better performances. In conclusion, the proposed methods are promising for the transposon-derived piRNA prediction. The source codes and datasets are available in S1 File.     

A signature inferred from Drosophila mitotic genes predicts survival of breast cancer patients

Introduction

The classification of breast cancer patients into risk groups provides a powerful tool for the identification of patients who will benefit from aggressive systemic therapy. The analysis of microarray data has generated several gene expression signatures that improve diagnosis and allow risk assessment. There is also evidence that cell proliferation-related genes have a high predictive power within these signatures.

Methods

We thus constructed a gene expression signature (the DM signature) using the human orthologues of 108 Drosophila melanogaster genes required for either the maintenance of chromosome integrity (36 genes) or mitotic division (72 genes).

Results

The DM signature has minimal overlap with the extant signatures and is highly predictive of survival in 5 large breast cancer datasets. In addition, we show that the DM signature outperforms many widely used breast cancer signatures in predictive power, and performs comparably to other proliferation-based signatures. For most genes of the DM signature, an increased expression is negatively correlated with patient survival. The genes that provide the highest contribution to the predictive power of the DM signature are those involved in cytokinesis.

Conclusion

This finding highlights cytokinesis as an important marker in breast cancer prognosis and as a possible target for antimitotic therapies.     

Knowledge-based gene expression classification via matrix factorization

MOTIVATION: Modern machine learning methods based on matrix decomposition techniques, like independent component analysis (ICA) or non-negative matrix factorization (NMF), provide new and efficient analysis tools which are currently explored to analyze gene expression profiles. These exploratory feature extraction techniques yield expression modes (ICA) or metagenes (NMF). These extracted features are considered indicative of underlying regulatory processes. They can as well be applied to the classification of gene expression datasets by grouping samples into different categories for diagnostic purposes or group genes into functional categories for further investigation of related metabolic pathways and regulatory networks. RESULTS: In this study we focus on unsupervised matrix factorization techniques and apply ICA and sparse NMF to microarray datasets. The latter monitor the gene expression levels of human peripheral blood cells during differentiation from monocytes to macrophages. We show that these tools are able to identify relevant signatures in the deduced component matrices and extract informative sets of marker genes from these gene expression profiles. The methods rely on the joint discriminative power of a set of marker genes rather than on single marker genes. With these sets of marker genes, corroborated by leave-one-out or random forest cross-validation, the datasets could easily be classified into related diagnostic categories. The latter correspond to either monocytes versus macrophages or healthy vs Niemann Pick C disease patients.     

Single sample expression-anchored mechanisms predict survival in head and neck cancer

Gene expression signatures that are predictive of therapeutic response or prognosis are increasingly useful in clinical care; however, mechanistic (and intuitive) interpretation of expression arrays remains an unmet challenge. Additionally, there is surprisingly little gene overlap among distinct clinically validated expression signatures. These “causality challenges” hinder the adoption of signatures as compared to functionally well-characterized single gene biomarkers. To increase the utility of multi-gene signatures in survival studies, we developed a novel approach to generate “personal mechanism signatures” of molecular pathways and functions from gene expression arrays. FAIME, the Functional Analysis of Individual Microarray Expression, computes mechanism scores using rank-weighted gene expression of an individual sample. By comparing head and neck squamous cell carcinoma (HNSCC) samples with non-tumor control tissues, the precision and recall of deregulated FAIME-derived mechanisms of pathways and molecular functions are comparable to those produced by conventional cohort-wide methods (e.g. GSEA). The overlap of “Oncogenic FAIME Features of HNSCC” (statistically significant and differentially regulated FAIME-derived genesets representing GO functions or KEGG pathways derived from HNSCC tissue) among three distinct HNSCC datasets (pathways:46%, p<0.001) is more significant than the gene overlap (genes:4%). These Oncogenic FAIME Features of HNSCC can accurately discriminate tumors from control tissues in two additional HNSCC datasets (n = 35 and 91, F-accuracy = 100% and 97%, empirical p<0.001, area under the receiver operating characteristic curves = 99% and 92%), and stratify recurrence-free survival in patients from two independent studies (p = 0.0018 and p = 0.032, log-rank). Previous approaches depending on group assignment of individual samples before selecting features or learning a classifier are limited by design to discrete-class prediction. In contrast, FAIME calculates mechanism profiles for individual patients without requiring group assignment in validation sets. FAIME is more amenable for clinical deployment since it translates the gene-level measurements of each given sample into pathways and molecular function profiles that can be applied to analyze continuous phenotypes in clinical outcome studies (e.g. survival time, tumor volume).     

A network-based gene expression signature informs prognosis and treatment for colorectal cancer patients

Background

Several studies have reported gene expression signatures that predict recurrence risk in stage II and III colorectal cancer (CRC) patients with minimal gene membership overlap and undefined biological relevance. The goal of this study was to investigate biological themes underlying these signatures, to infer genes of potential mechanistic importance to the CRC recurrence phenotype and to test whether accurate prognostic models can be developed using mechanistically important genes.

Methods and Findings

We investigated eight published CRC gene expression signatures and found no functional convergence in Gene Ontology enrichment analysis. Using a random walk-based approach, we integrated these signatures and publicly available somatic mutation data on a protein-protein interaction network and inferred 487 genes that were plausible candidate molecular underpinnings for the CRC recurrence phenotype. We named the list of 487 genes a NEM signature because it integrated information from Network, Expression, and Mutation. The signature showed significant enrichment in four biological processes closely related to cancer pathophysiology and provided good coverage of known oncogenes, tumor suppressors, and CRC-related signaling pathways. A NEM signature-based Survival Support Vector Machine prognostic model was trained using a microarray gene expression dataset and tested on an independent dataset. The model-based scores showed a 75.7% concordance with the real survival data and separated patients into two groups with significantly different relapse-free survival (p = 0.002). Similar results were obtained with reversed training and testing datasets (p = 0.007). Furthermore, adjuvant chemotherapy was significantly associated with prolonged survival of the high-risk patients (p = 0.006), but not beneficial to the low-risk patients (p = 0.491).

Conclusions

The NEM signature not only reflects CRC biology but also informs patient prognosis and treatment response. Thus, the network-based data integration method provides a convergence between biological relevance and clinical usefulness in gene signature development.     

Clinical Value of Prognosis Gene Expression Signatures in Colorectal Cancer: A Systematic Review

Introduction

The traditional staging system is inadequate to identify those patients with stage II colorectal cancer (CRC) at high risk of recurrence or with stage III CRC at low risk. A number of gene expression signatures to predict CRC prognosis have been proposed, but none is routinely used in the clinic. The aim of this work was to assess the prediction ability and potential clinical usefulness of these signatures in a series of independent datasets.

Methods

A literature review identified 31 gene expression signatures that used gene expression data to predict prognosis in CRC tissue. The search was based on the PubMed database and was restricted to papers published from January 2004 to December 2011. Eleven CRC gene expression datasets with outcome information were identified and downloaded from public repositories. Random Forest classifier was used to build predictors from the gene lists. Matthews correlation coefficient was chosen as a measure of classification accuracy and its associated p-value was used to assess association with prognosis. For clinical usefulness evaluation, positive and negative post-tests probabilities were computed in stage II and III samples.

Results

Five gene signatures showed significant association with prognosis and provided reasonable prediction accuracy in their own training datasets. Nevertheless, all signatures showed low reproducibility in independent data. Stratified analyses by stage or microsatellite instability status showed significant association but limited discrimination ability, especially in stage II tumors. From a clinical perspective, the most predictive signatures showed a minor but significant improvement over the classical staging system.

Conclusions

The published signatures show low prediction accuracy but moderate clinical usefulness. Although gene expression data may inform prognosis, better strategies for signature validation are needed to encourage their widespread use in the clinic.     

Genomic analyses based on pulmonary adenocarcinoma in situ reveal early lung cancer signature

Background

Non-small cell lung cancer (NSCLC) represents more than about 80% of the lung cancer. The early stages of NSCLC can be treated with complete resection with a good prognosis. However, most cases are detected at late stage of the disease. The average survival rate of the patients with invasive lung cancer is only about 4%. Adenocarcinoma in situ (AIS) is an intermediate subtype of lung adenocarcinoma that exhibits early stage growth patterns but can develop into invasion.

Methods

In this study, we used RNA-seq data from normal, AIS, and invasive lung cancer tissues to identify a gene module that represents the distinguishing characteristics of AIS as AIS-specific genes. Two differential expression analysis algorithms were employed to identify the AIS-specific genes. Then, the subset of the best performed AIS-specific genes for the early lung cancer prediction were selected by random forest. Finally, the performances of the early lung cancer prediction were assessed using random forest, support vector machine (SVM) and artificial neural networks (ANNs) on four independent early lung cancer datasets including one tumor-educated blood platelets (TEPs) dataset.

Results

Based on the differential expression analysis, 107 AIS-specific genes that consisted of 93 protein-coding genes and 14 long non-coding RNAs (lncRNAs) were identified. The significant functions associated with these genes include angiogenesis and ECM-receptor interaction, which are highly related to cancer development and contribute to the smoking-free lung cancers. Moreover, 12 of the AIS-specific lncRNAs are involved in lung cancer progression by potentially regulating the ECM-receptor interaction pathway. The feature selection by random forest identified 20 of the AIS-specific genes as early stage lung cancer signatures using the dataset obtained from The Cancer Genome Atlas (TCGA) lung adenocarcinoma samples. Of the 20 signatures, two were lncRNAs, BLACAT1 and CTD-2527I21.15 which have been reported to be associated with bladder cancer, colorectal cancer and breast cancer. In blind classification for three independent tissue sample datasets, these signature genes consistently yielded about 98% accuracy for distinguishing early stage lung cancer from normal cases. However, the prediction accuracy for the blood platelets samples was only 64.35% (sensitivity 78.1%, specificity 50.59%, and AUROC 0.747).

Conclusions

The comparison of AIS with normal and invasive tumor revealed diseases-specific genes and offered new insights into the mechanism underlying AIS progression into an invasive tumor. These genes can also serve as the signatures for early diagnosis of lung cancer with high accuracy. The expression profile of gene signatures identified from tissue cancer samples yielded remarkable early cancer prediction for tissues samples, however, relatively lower accuracy for boold platelets samples.

     

Cross-platform comparison of microarray-based multiple-class prediction

High-throughput microarray technology has been widely applied in biological and medical decision-making research during the past decade. However, the diversity of platforms has made it a challenge to re-use and/or integrate datasets generated in different experiments or labs for constructing array-based diagnostic models. Using large toxicogenomics datasets generated using both Affymetrix and Agilent microarray platforms, we carried out a benchmark evaluation of cross-platform consistency in multiple-class prediction using three widely-used machine learning algorithms. After an initial assessment of model performance on different platforms, we evaluated whether predictive signature features selected in one platform could be directly used to train a model in the other platform and whether predictive models trained using data from one platform could predict datasets profiled using the other platform with comparable performance. Our results established that it is possible to successfully apply multiple-class prediction models across different commercial microarray platforms, offering a number of important benefits such as accelerating the possible translation of biomarkers identified with microarrays to clinically-validated assays. However, this investigation focuses on a technical platform comparison and is actually only the beginning of exploring cross-platform consistency. Further studies are needed to confirm the feasibility of microarray-based cross-platform prediction, especially using independent datasets.     

Biological and Clinical Significance of MAD2L1 and BUB1, Genes Frequently Appearing in Expression Signatures for Breast Cancer Prognosis

To investigate the biologic relevance and clinical implication of genes involved in multiple gene expression signatures for breast cancer prognosis, we identified 16 published gene expression signatures, and selected two genes, MAD2L1 and BUB1. These genes appeared in 5 signatures and were involved in cell-cycle regulation. We analyzed the expression of these genes in relation to tumor features and disease outcomes. In vitro experiments were also performed in two breast cancer cell lines, MDA-MB-231 and MDA-MB-468, to assess cell proliferation, migration and invasion after knocking down the expression of these genes. High expression of these genes was found to be associated with aggressive tumors and poor disease-free survival of 203 breast cancer patients in our study, and the association with survival was confirmed in an online database consisting of 914 patients. In vitro experiments demonstrated that lowering the expression of these genes by siRNAs reduced tumor cell growth and inhibited cell migration and invasion. Our investigation suggests that MAD2L1 and BUB1 may play important roles in breast cancer progression, and measuring the expression of these genes may assist the prediction of breast cancer prognosis.     

A collection of glycosyltransferases from rice (Oryza sativa) exposed to atrazine

The rice (Oryza sativa) GTs belong to a super family possibly with hundreds of members. However, which GTs are involved in plant response to toxic chemicals is unknown. Here, we demonstrated 59 novel GT genes screened from our recent genome-wide sequencing datasets of rice crops exposed to atrazine (a herbicide persistent in ecosystems). Analysis of GT genes showed that most of the GTs contain functional domains typically found in proteins transferring glycosyl moieties to their target compounds. A phylogenetic analysis revealed that many GT genes from different families have diverse cis-elements necessary for response to biotic and environmental stresses. Experimental validation for the GTs was undertaken through a microarray, and 36 GT genes were significantly detected with an expression pattern similar to that from deep-sequencing datasets. Furthermore, 12 GT genes were randomly selected and confirmed by quantitative real-time RT-PCR. Finally, the special activity of total GTs was determined in rice roots and shoots, with an increased activity under the atrazine exposure. This response was closely associated with atrazine absorption in the rice tissues. These results indicate that exposure to atrazine can trigger specific GT genes and enzyme activities in rice.