Novel methods to identify biologically relevant genes for leukemia and prostate cancer from gene expression profiles

An ensemble machine learning model based on multiple filtering and supervised attribute clustering algorithm for classifying cancer samples

BACKGROUND

Machine learning is one kind of machine intelligence technique that learns from data and detects inherent patterns from large, complex datasets. Due to this capability, machine learning techniques are widely used in medical applications, especially where large-scale genomic and proteomic data are used. Cancer classification based on bio-molecular profiling data is a very important topic for medical applications since it improves the diagnostic accuracy of cancer and enables a successful culmination of cancer treatments. Hence, machine learning techniques are widely used in cancer detection and prognosis.

METHODS

In this article, a new ensemble machine learning classification model named Multiple Filtering and Supervised Attribute Clustering algorithm based Ensemble Classification model (MFSAC-EC) is proposed which can handle class imbalance problem and high dimensionality of microarray datasets. This model first generates a number of bootstrapped datasets from the original training data where the oversampling procedure is applied to handle the class imbalance problem. The proposed MFSAC method is then applied to each of these bootstrapped datasets to generate sub-datasets, each of which contains a subset of the most relevant/informative attributes of the original dataset. The MFSAC method is a feature selection technique combining multiple filters with a new supervised attribute clustering algorithm. Then for every sub-dataset, a base classifier is constructed separately, and finally, the predictive accuracy of these base classifiers is combined using the majority voting technique forming the MFSAC-based ensemble classifier. Also, a number of most informative attributes are selected as important features based on their frequency of occurrence in these sub-datasets.

RESULTS

To assess the performance of the proposed MFSAC-EC model, it is applied on different high-dimensional microarray gene expression datasets for cancer sample classification. The proposed model is compared with well-known existing models to establish its effectiveness with respect to other models. From the experimental results, it has been found that the generalization performance/testing accuracy of the proposed classifier is significantly better compared to other well-known existing models. Apart from that, it has been also found that the proposed model can identify many important attributes/biomarker genes.

Reversal of multidrug resistance in leukemia cells using a transferrin-modified nanomicelle encapsulating both doxorubicin and psoralen

To ameliorate multidrug resistance (MDR) observed in leukemia cells, nanomicelles modified by transferrin (Tf-M-DOX/PSO), coencapsulating doxorubicin (DOX) and psoralen (PSO), were designed, synthesized and tested in K562 and doxorubicin-resistant K562 (K562/DOX) cells. In vitro drug release kinetics for constructed nanomicelles were measured using high-performance liquid chromatography. Characterization of the produced nanomicelles was completed using transmission electron microscopy and dynamic light scattering. Uptake of the nanomicelles in K562 cells was investigated using both confocal microscopy and flow cytometry. Apoptosis levels as well as the expression of glycoprotein (P-gp) were analyzing by western blotting and flow cytometry. Cellular cytotoxicity resulting from the exposure of nanomicelles was evaluated using MTT assays. The nanomicelles all showed mild release of DOX in PBS solution. In K562/DOX cells, Tf-M-Dox/PSO exhibited higher uptake compared to the other nanomicelles observed. Furthermore, cellular cytotoxicity when exposed to Tf-M-Dox/PSO was 2.8 and 1.6-fold greater than observed in the unmodified DOX and Tf-nanomicelles loaded with DOX alone, respectively. Tf-M-Dox/PSO strongly increased apoptosis of K562/DOX cells. Finally, the reversal of the drug resistance when cells are exposed to Tf-M-DOX/PSO was associated with P-gp expression inhibition. The Tf-M-Dox/PSO nanomicelle showed a reversal of MDR, with enhanced cellular uptake and delivery release.

Fast approximate inference for variable selection in Dirichlet process mixtures, with an application to pan-cancer proteomics

The Dirichlet Process (DP) mixture model has become a popular choice for model-based clustering, largely because it allows the number of clusters to be inferred. The sequential updating and greedy search (SUGS) algorithm (Wang & Dunson, 2011) was proposed as a fast method for performing approximate Bayesian inference in DP mixture models, by posing clustering as a Bayesian model selection (BMS) problem and avoiding the use of computationally costly Markov chain Monte Carlo methods. Here we consider how this approach may be extended to permit variable selection for clustering, and also demonstrate the benefits of Bayesian model averaging (BMA) in place of BMS. Through an array of simulation examples and well-studied examples from cancer transcriptomics, we show that our method performs competitively with the current state-of-the-art, while also offering computational benefits. We apply our approach to reverse-phase protein array (RPPA) data from The Cancer Genome Atlas (TCGA) in order to perform a pan-cancer proteomic characterisation of 5157 tumour samples. We have implemented our approach, together with the original SUGS algorithm, in an open-source R package named sugsvarsel, which accelerates analysis by performing intensive computations in C++ and provides automated parallel processing. The R package is freely available from: https://github.com/ococrook/sugsvarsel.

Identification of DNA methylation prognostic signature of acute myelocytic leukemia

BACKGROUND

The aim of this study is to find the potential survival related DNA methylation signature capable of predicting survival time for acute myelocytic leukemia (AML) patients.

METHODS

DNA methylation data were downloaded. DNA methylation signature was identified in the training group, and subsequently validated in an independent validation group. The overall survival of DNA methylation signature was performed. Functional analysis was used to explore the function of corresponding genes of DNA methylation signature. Differentially methylated sites and CpG islands were also identified in poor-risk group.

RESULTS

A DNA methylation signature involving 8 DNA methylation sites and 6 genes were identified. Functional analysis showed that protein binding and cytoplasm were the only two enriched Gene Ontology terms. A total of 70 differentially methylated sites and 6 differentially methylated CpG islands were identified in poor-risk group.

CONCLUSIONS

The identified survival related DNA methylation signature adds to the prognostic value of AML.

Biomarker Identification for Cancer Disease Using Biclustering Approach: An Empirical Study

This paper presents an exhaustive empirical study to identify biomarkers using two approaches: frequency-based and network-based, over seventeen different biclustering algorithms and six different cancer expression datasets. To systematically analyze the biclustering algorithms, we perform enrichment analysis, subtype identification and biomarker identification. Biclustering algorithms such as C&C, SAMBA and Plaid are useful to detect biomarkers by both approaches for all datasets except prostate cancer. We detect a total of 102 gene biomarkers using frequency-based method out of which 19 are for blood cancer, 36 for lung cancer, 25 for colon cancer, 13 for multi-tissue cancer and 9 for prostate cancer. Using the network-based approach we detect a total of 41 gene biomarkers of which 15 are from blood cancer, 12 from lung cancer, 6 from colon cancer, 7 from multi-tissue cancer and 1 from prostate cancer dataset. We further extend our network analysis over some biclusters and detect some gene biomarkers not detected earlier by both frequency-based or network-based approach. We expand our work on breast cancer miRNA expression data to evaluate the performance of the biclustering algorithms. We detect 19 breast cancer biomarkers by frequency-based method and 5 by network-based method for the miRNA dataset.

Detection approaches for multidrug resistance genes of leukemia

Leukemia is a clonal malignant hematopoietic stem cell disease. It is the sixth most lethal cancer and accounts for 4% of all cancers. The main form of treatment for leukemia is chemotherapy. While some cancer types with a higher incidence than leukemia, such as lung and gastric cancer, have shown a sharp decline in mortality rates in recent years, leukemia has not followed this trend. Drug resistance is often regarded as the main clinical obstacle to effective chemotherapy in patients diagnosed with leukemia. Many resistance mechanisms have now been identified, and multidrug resistance (MDR) is considered the most important and prevalent mechanism involved in the failure of chemotherapy in leukemia. In order to reverse MDR and improve leukemia prognosis, effective detection methods are needed to identify drug resistance genes at initial diagnosis. This article provides a comprehensive overview of published approaches for the detection of MDR in leukemia. Identification of relevant MDR genes and methods for early detection of these genes will be needed in order to treat leukemia more effectively.

Decreased expression of EFS is correlated with the advanced prostate cancer

Prostate cancer is the most frequently diagnosed malignant neoplasm in men in the developed countries. Although the progression of prostate cancer and the processes of invasion and metastasis by tumor cells are comparatively well understood, the genes involved in these processes are not fully determined. Therefore, a common area of research interest is the identification of novel molecules that are involved in these processes. In the present study, we have used in silico and experimental approaches to compare the expression of embryonal Fyn-associated substrate (EFS) between normal prostate and prostate cancer. We showed that EFS expression is remarkably downregulated in prostate cancer cells, compared to normal prostate cells. We also found that decreased expression of EFS in prostate cancer cells is due to DNA methylation. In addition, we showed that high EFS expression is important to suppress a malignant behavior of prostate cancer cells. Therefore, we suggest that EFS should be considered as a novel tumor suppressor gene in prostate cancer.

Identification of cichlid fishes from Lake Malawi using computer vision

BACKGROUND

The explosively radiating evolution of cichlid fishes of Lake Malawi has yielded an amazing number of haplochromine species estimated as many as 500 to 800 with a surprising degree of diversity not only in color and stripe pattern but also in the shape of jaw and body among them. As these morphological diversities have been a central subject of adaptive speciation and taxonomic classification, such high diversity could serve as a foundation for automation of species identification of cichlids.

METHODOLOGY/PRINCIPAL FINDING

Here we demonstrate a method for automatic classification of the Lake Malawi cichlids based on computer vision and geometric morphometrics. For this end we developed a pipeline that integrates multiple image processing tools to automatically extract informative features of color and stripe patterns from a large set of photographic images of wild cichlids. The extracted information was evaluated by statistical classifiers Support Vector Machine and Random Forests. Both classifiers performed better when body shape information was added to the feature of color and stripe. Besides the coloration and stripe pattern, body shape variables boosted the accuracy of classification by about 10%. The programs were able to classify 594 live cichlid individuals belonging to 12 different classes (species and sexes) with an average accuracy of 78%, contrasting to a mere 42% success rate by human eyes. The variables that contributed most to the accuracy were body height and the hue of the most frequent color.

CONCLUSIONS

Computer vision showed a notable performance in extracting information from the color and stripe patterns of Lake Malawi cichlids although the information was not enough for errorless species identification. Our results indicate that there appears an unavoidable difficulty in automatic species identification of cichlid fishes, which may arise from short divergence times and gene flow between closely related species.

Identification of new genes downregulated in prostate cancer and investigation of their effects on prognosis

Prostate cancer is the most common noncutaneous malignant neoplasm in men in the Western countries. It is well established that genetic and epigenetic alterations are common events in prostate cancer, which may lead to aberrant expression of critical genes. Most of the studies are focused on the overexpressed or duplicated genes in prostate cancer. However, it is known that some of the differentially expressed genes in prostate cancer are downregulated. Since the inventory of downregulated genes is incomplete, we performed in silico approaches to reveal the novel prostate cancer downregulated genes. Moreover, we also investigated for a possible link between the expression of the downregulated genes and tumor grade, recurrence, metastasis, or survival status in prostate cancer. Our results showed that the expression of GSTP1 and AOX1 are downregulated in prostate cancer, in concordance with previous reports. Moreover, we showed that TPM2, CLU, and COL4A6 mRNA levels are downregulated in prostate cancer. Further, we found a significant negative correlation between the expression of the above-mentioned genes and the prognosis of prostate cancer.

A network flow approach to predict drug targets from microarray data, disease genes and interactome network - case study on prostate cancer

BACKGROUND

Systematic approach for drug discovery is an emerging discipline in systems biology research area. It aims at integrating interaction data and experimental data to elucidate diseases and also raises new issues in drug discovery for cancer treatment. However, drug target discovery is still at a trial-and-error experimental stage and it is a challenging task to develop a prediction model that can systematically detect possible drug targets to deal with complex diseases.

METHODS

We integrate gene expression, disease genes and interaction networks to identify the effective drug targets which have a strong influence on disease genes using network flow approach. In the experiments, we adopt the microarray dataset containing 62 prostate cancer samples and 41 normal samples, 108 known prostate cancer genes and 322 approved drug targets treated in human extracted from DrugBank database to be candidate proteins as our test data. Using our method, we prioritize the candidate proteins and validate them to the known prostate cancer drug targets.

RESULTS

We successfully identify potential drug targets which are strongly related to the well known drugs for prostate cancer treatment and also discover more potential drug targets which raise the attention to biologists at present. We denote that it is hard to discover drug targets based only on differential expression changes due to the fact that those genes used to be drug targets may not always have significant expression changes. Comparing to previous methods that depend on the network topology attributes, they turn out that the genes having potential as drug targets are weakly correlated to critical points in a network. In comparison with previous methods, our results have highest mean average precision and also rank the position of the truly drug targets higher. It thereby verifies the effectiveness of our method.

CONCLUSIONS

Our method does not know the real ideal routes in the disease network but it tries to find the feasible flow to give a strong influence to the disease genes through possible paths. We successfully formulate the identification of drug target prediction as a maximum flow problem on biological networks and discover potential drug targets in an accurate manner.

Learning biomarkers of pluripotent stem cells in mouse

Pluripotent stem cells are able to self-renew, and to differentiate into all adult cell types. Many studies report data describing these cells, and characterize them in molecular terms. Machine learning yields classifiers that can accurately identify pluripotent stem cells, but there is a lack of studies yielding minimal sets of best biomarkers (genes/features). We assembled gene expression data of pluripotent stem cells and non-pluripotent cells from the mouse. After normalization and filtering, we applied machine learning, classifying samples into pluripotent and non-pluripotent with high cross-validated accuracy. Furthermore, to identify minimal sets of best biomarkers, we used three methods: information gain, random forests and a wrapper of genetic algorithm and support vector machine (GA/SVM). We demonstrate that the GA/SVM biomarkers work best in combination with each other; pathway and enrichment analyses show that they cover the widest variety of processes implicated in pluripotency. The GA/SVM wrapper yields best biomarkers, no matter which classification method is used. The consensus best biomarker based on the three methods is Tet1, implicated in pluripotency just recently. The best biomarker based on the GA/SVM wrapper approach alone is Fam134b, possibly a missing link between pluripotency and some standard surface markers of unknown function processed by the Golgi apparatus.