Search

This paper identifies prognosis factors for survival in patients with acute myeloid leukemia (AML) using machine learning techniques. We have integrated machine learning with feature selection methods and have compared their performances to identify the most suitable factors in assessing the survival of AML patients. Here, six data mining algorithms including Decision Tree, Random Forrest, Logistic Regression, Naive Bayes, W-Bayes Net, and Gradient Boosted Tree (GBT) are employed for the detection model and implemented using the common data mining tool RapidMiner and open-source R package. To improve the predictive ability of our model, a set of features were selected by employing multiple feature selection methods. The accuracy of classification was obtained using 10-fold cross-validation for the various combinations of the feature selection methods and machine learning algorithms. The performance of the models was assessed by various measurement indexes including accuracy, kappa, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC curve (AUC). Our results showed that GBT with an accuracy of 85.17%, AUC of 0.930, and the feature selection via the Relief algorithm has the best performance in predicting the survival rate of AML patients., Competing Interests: The authors have declared that no competing interests exist.

Genomic imprinting results in monoallelic expression of genes in mammals and flowering plants. Understanding the function of imprinted genes improves our knowledge of the regulatory processes in the genome. In this study, we have employed classification and clustering algorithms with attribute weighting to specify the unique attributes of both imprinted (monoallelic) and biallelic expressed genes. We have obtained characteristics of 22 known monoallelically expressed (imprinted) and 8 biallelic expressed genes that have been experimentally validated alongside 208 randomly selected genes in bovine (Bos taurus). Attribute weighting methods and various supervised and unsupervised algorithms in machine learning were applied. Unique characteristics were discovered and used to distinguish mono and biallelic expressed genes from each other in bovine. To obtain the accuracy of classification, 10-fold cross-validation with concerning each combination of attribute weighting (feature selection) and machine learning algorithms, was used. Our approach was able to accurately predict mono and biallelic genes using the genomics and proteomics attributes. [ABSTRACT FROM AUTHOR]

Imprinted genes display biased expression of paternal and maternal alleles in mammals. They are marked through epigenetic process during gametogenesis. Characterization of imprinted genes has expanded our understanding of the regulation and function of genes. In the current study, 22 experimentally validated imprinted genes in bovine (Bos Taurus) were analysed. Several supervised machine learning algorithms and attribute weighting methods were used to find characteristics of different types of imprinted genes and suggest a classification method for finding maternally and paternally expressed genes in bovine. For assessing the best model and comparing attributes in other organisms, we have also conducted a comparative analysis for human and sheep imprinted genes. According to the results of the present study, GC contents 10 and 100 kb upstream, Gly and Gln amino acids, Ile/ATC codon usage, LINE and SINE in 100kbup and length of first intron were significantly different between the maternal and paternal genes in cattle. Considering all species together, we found that GC content 100 kb up, LINE 100 kb up and the frequency of amino acids like Gly, Gln and Met were the most important attributes for identifying the paternal and maternal imprinted genes. These findings could imply conservation pattern in the attributes among these species. [ABSTRACT FROM AUTHOR]