Malik Yousef

Gene Expression Profiles in Peripheral Blood Mononuclear Cells Can Distinguish Patients with Non–Small Cell Lung Cancer from Patients with Nonmalignant Lung Disease

Early diagnosis of lung cancer followed by surgery presently is the most effective treatment for non-small cell lung cancer (NSCLC). An accurate, minimally invasive test that could detect early disease would permit timely intervention and potentially reduce mortality. Recent studies have shown that the peripheral blood can carry information related to the presence of disease, including prognostic information and information on therapeutic response. We have analyzed gene expression in peripheral blood mononuclear cell samples including 137 patients with NSCLC tumors and 91 patient controls with nonmalignant lung conditions, including histologically diagnosed benign nodules. Subjects were primarily smokers and former smokers. We have identified a 29-gene signature that separates these two patient classes with 86% accuracy (91% sensitivity, 80% specificity). Accuracy in an independent validation set, including samples from a new location, was 78% (sensitivity of 76% and specificity of 82%). An analysis of this NSCLC gene signature in 18 NSCLCs taken presurgery, with matched samples from 2 to 5 months postsurgery, showed that in 78% of cases, the signature was reduced postsurgery and disappeared entirely in 33%. Our results show the feasibility of using peripheral blood gene expression signatures to identify early-stage NSCLC in at-risk populations.

Circulating Monocytes in HIV-1-Infected Viremic Subjects Exhibit an Antiapoptosis Gene Signature and Virus- and Host-Mediated Apoptosis Resistance

Mechanisms that may allow circulating monocytes to persist as CD4 T cells diminish in HIV-1 infection have not been investigated. We have characterized steady-state gene expression signatures in circulating monocytes from HIV-infected subjects and have identified a stable antiapoptosis gene signature comprised of 38 genes associated with p53, CD40L, TNF, and MAPK signaling networks. The significance of this gene signature is indicated by our demonstration of cadmium chloride- or Fas ligand-induced apoptosis resistance in circulating monocytes in contrast to increasing apoptosis in CD4 T cells from the same infected subjects. As potential mechanisms in vivo, we show that monocyte CCR5 binding by HIV-1 virus or agonist chemokines serves as independent viral and host modulators resulting in increased monocyte apoptosis resistance in vitro. We also show evidence for concordance between circulating monocyte apoptosis-related gene expression in HIV-1 infection in vivo and available datasets following viral infection or envelope exposure in monocyte-derived macrophages in vitro. The identification of in vivo gene expression associated with monocyte resistance to apoptosis is of relevance to AIDS pathogenesis since it would contribute to: 1) maintaining viability of infection targets and long-term reservoirs of HIV-1 infection in the monocyte/macrophage populations, and 2) protecting a cell subset critical to host survival despite sustained high viral replication.

Recursive Cluster Elimination (RCE) for classification and feature selection from gene expression data

BackgroundClassification studies using gene expression datasets are usually based on small numbers of samples and tens of thousands of genes. The selection of those genes that are important for distinguishing the different sample classes being compared, poses a challenging problem in high dimensional data analysis. We describe a new procedure for selecting significant genes as recursive cluster elimination (RCE) rather than recursive feature elimination (RFE). We have tested this algorithm on six datasets and compared its performance with that of two related classification procedures with RFE.ResultsWe have developed a novel method for selecting significant genes in comparative gene expression studies. This method, which we refer to as SVM-RCE, combines K-means, a clustering method, to identify correlated gene clusters, and Support Vector Machines (SVMs), a supervised machine learning classification method, to identify and score (rank) those gene clusters for the purpose of classification. K-means is used initially to group genes into clusters. Recursive cluster elimination (RCE) is then applied to iteratively remove those clusters of genes that contribute the least to the classification performance. SVM-RCE identifies the clusters of correlated genes that are most significantly differentially expressed between the sample classes. Utilization of gene clusters, rather than individual genes, enhances the supervised classification accuracy of the same data as compared to the accuracy when either SVM or Penalized Discriminant Analysis (PDA) with recursive feature elimination (SVM-RFE and PDA-RFE) are used to remove genes based on their individual discriminant weights.ConclusionSVM-RCE provides improved classification accuracy with complex microarray data sets when it is compared to the classification accuracy of the same datasets using either SVM-RFE or PDA-RFE. SVM-RCE identifies clusters of correlated genes that when considered together provide greater insight into the structure of the microarray data. Clustering genes for classification appears to result in some concomitant clustering of samples into subgroups.Our present implementation of SVM-RCE groups genes using the correlation metric. The success of the SVM-RCE method in classification suggests that gene interaction networks or other biologically relevant metrics that group genes based on functional parameters might also be useful.

Learning from positive examples when the negative class is undetermined- microRNA gene identification

BackgroundThe application of machine learning to classification problems that depend only on positive examples is gaining attention in the computational biology community. We and others have described the use of two-class machine learning to identify novel miRNAs. These methods require the generation of an artificial negative class. However, designation of the negative class can be problematic and if it is not properly done can affect the performance of the classifier dramatically and/or yield a biased estimate of performance. We present a study using one-class machine learning for microRNA (miRNA) discovery and compare one-class to two-class approaches using naïve Bayes and Support Vector Machines. These results are compared to published two-class miRNA prediction approaches. We also examine the ability of the one-class and two-class techniques to identify miRNAs in newly sequenced species.ResultsOf all methods tested, we found that 2-class naive Bayes and Support Vector Machines gave the best accuracy using our selected features and optimally chosen negative examples. One class methods showed average accuracies of 70–80% versus 90% for the two 2-class methods on the same feature sets. However, some one-class methods outperform some recently published two-class approaches with different selected features. Using the EBV genome as and external validation of the method we found one-class machine learning to work as well as or better than a two-class approach in identifying true miRNAs as well as predicting new miRNAs.ConclusionOne and two class methods can both give useful classification accuracies when the negative class is well characterized. The advantage of one class methods is that it eliminates guessing at the optimal features for the negative class when they are not well defined. In these cases one-class methods can be superior to two-class methods when the features which are chosen as representative of that positive class are well defined.AvailabilityThe OneClassmiRNA program is available at: [1]

A study of microRNAs in silico and in vivo: bioinformatics approaches to microRNA discovery and target identification

The discovery that microRNAs (miRNAs) are synthesized as hairpin‐containing precursors and share many features has stimulated the development of several computational approaches for identifying new miRNA genes in various animal species. Many of these approaches rely heavily on conservation of sequence within and between species, whereas others emphasize machine‐learning methods to screen hairpin candidates for structural features shared with known miRNA precursors. The identification of animal miRNA targets is a particularly difficult problem because an exact match to the target sequence is not required. We discuss the most recently devised algorithms for miRNA and target discovery. We do not discuss plant miRNAs because their varying sizes and structural characteristics pose different problems of identification and target selection.

Increased metallothionein gene expression, zinc, and zinc-dependent resistance to apoptosis in circulating monocytes during HIV viremia

Circulating monocytes exhibit an apoptotic resistance phenotype during HIV viremia in association with increased MT expression. MTs are known to play an important role in zinc metabolism and immune function. We now show, in a cross‐sectional study using peripheral monocytes, that expression of MT1 isoforms E, G, H, and X is increased significantly in circulating monocyte cells from HIV+ subjects during chronic viremic episodes as compared with uninfected subjects. This increase in expression is also observed during acute viremia following interruption of suppressive ART. Circulating monocytes from HIV+ donors were also found to have elevated zinc importer gene Zip8 expression in conjunction with elevated intracellular zinc levels in contrast to CD4+T‐lymphocytes. In vitro HIV‐1 infection studies with elutriated MDM confirm a direct relation between HIV‐1 infection and increased MDM MT1 (isoform G) gene expression and increased intracellular zinc levels. A direct link between elevated zinc levels and apoptosis resistance was established using a cell‐permeable zinc chelator TPEN, which reversed apoptosis resistance effectively in monocytes from HIV‐infected to levels comparable with uninfected controls. Taken together, increases in MT gene expression and intracellular zinc levels may contribute directly to maintenance of an immune‐activated monocyte by mediating an increased resistance to apoptosis during active HIV‐1 viremia.

Classification and biomarker identification using gene network modules and support vector machines

BackgroundClassification using microarray datasets is usually based on a small number of samples for which tens of thousands of gene expression measurements have been obtained. The selection of the genes most significant to the classification problem is a challenging issue in high dimension data analysis and interpretation. A previous study with SVM-RCE (Recursive Cluster Elimination), suggested that classification based on groups of correlated genes sometimes exhibits better performance than classification using single genes. Large databases of gene interaction networks provide an important resource for the analysis of genetic phenomena and for classification studies using interacting genes.We now demonstrate that an algorithm which integrates network information with recursive feature elimination based on SVM exhibits good performance and improves the biological interpretability of the results. We refer to the method as SVM with Recursive Network Elimination (SVM-RNE)ResultsInitially, one thousand genes selected by t-test from a training set are filtered so that only genes that map to a gene network database remain. The Gene Expression Network Analysis Tool (GXNA) is applied to the remaining genes to form n clusters of genes that are highly connected in the network. Linear SVM is used to classify the samples using these clusters, and a weight is assigned to each cluster based on its importance to the classification. The least informative clusters are removed while retaining the remainder for the next classification step. This process is repeated until an optimal classification is obtained.ConclusionMore than 90% accuracy can be obtained in classification of selected microarray datasets by integrating the interaction network information with the gene expression information from the microarrays.The Matlab version of SVM-RNE can be downloaded from http://web.macam.ac.il/~myousef

Computational Methods for MicroRNA Target Prediction

MicroRNAs (miRNAs) are important players in gene regulation. The final and maybe the most important step in their regulatory pathway is the targeting. Targeting is the binding of the miRNA to the mature RNA via the RNA-induced silencing complex. Expression patterns of miRNAs are highly specific in respect to external stimuli, developmental stage, or tissue. This is used to diagnose diseases such as cancer in which the expression levels of miRNAs are known to change considerably. Newly identified miRNAs are increasing in number with every new release of miRBase which is the main online database providing miRNA sequences and annotation. Many of these newly identified miRNAs do not yet have identified targets. This is especially the case in animals where the miRNA does not bind to its target as perfectly as it does in plants. Valid targets need to be identified for miRNAs in order to properly understand their role in cellular pathways. Experimental methods for target validations are difficult, expensive, and time consuming. Having considered all these facts it is of crucial importance to have accurate computational miRNA target predictions. There are many proposed methods and algorithms available for predicting targets for miRNAs, but only a few have been developed to become available as independent tools and software. There are also databases which collect and store information regarding predicted miRNA targets. Current approaches to miRNA target prediction produce a huge amount of false positive and an unknown amount of false negative results, and thus the need for better approaches is evermore evident. This chapter aims to give some detail about the current tools and approaches used for miRNA target prediction, provides some grounds for their comparison, and outlines a possible future.

Computational methods for ab initio detection of microRNAs

MicroRNAs are small RNA sequences of 18–24 nucleotides in length, which serve as templates to drive post-transcriptional gene silencing. The canonical microRNA pathway starts with transcription from DNA and is followed by processing via the microprocessor complex, yielding a hairpin structure. Which is then exported into the cytosol where it is processed by Dicer and then incorporated into the RNA-induced silencing complex. All of these biogenesis steps add to the overall specificity of miRNA production and effect. Unfortunately, their modes of action are just beginning to be elucidated and therefore computational prediction algorithms cannot model the process but are usually forced to employ machine learning approaches. This work focuses on ab initio prediction methods throughout; and therefore homology-based miRNA detection methods are not discussed. Current ab initio prediction algorithms, their ties to data mining, and their prediction accuracy are detailed.

Constitutive gene expression in monocytes from chronic HIV-1 infection overlaps with acute Toll-like receptor induced monocyte activation profiles.

Elevated TLR expression/signalling in monocyte/macrophages has been shown to mediate systemic immune activation, a hallmark of progressive HIV-1 infection. Here we show, via differential gene expression comparisons, the presence of a constitutive in vivo TLR-like gene activation signature in steady-state circulating monocytes from chronically HIV-1 infected subjects. The TLR2-like gene signature was defined as an 82 gene subset of the 376 genes constitutively modulated in in vivo HIV-1 monocytes, based on their overlap with de novo TLR2-induced genes in uninfected subjects’ monocytes following acute ex vivo stimulation with Staphylococcus Aureus Cowan (SAC). Additional comparison of in vivo gene networks with available datasets from acute TLR activations in M/M expanded the overlap to 151-gene concordance among the 376 differential genes with emphasis on ERK/MAPK, TNF/IL6 (NFκB) and p53 gene networks. TLR2 stimulation of monocytes from HIV-1 infected subjects resulted in further upregulation of inflammatory genes indicative of a sustained transcriptional potential upon stimulation. In summary, our data support the presence of a sustained TLR-like gene activation profile in circulating monocyte from steady-state viremia in HIV-1 infected subjects.