Tehran University Medical Journal

Background: Infertility is clinically defined as failure of a couple to conceive after one year of regular sexual intercourse and occurs in both males and females for various reasons. About half of the infertility causes is due to male factors such as azoospermia and the lack of sperm in the ejaculate. Azoosperima is divided into two types: Non-obstructive azoospermia (NOA) and obstructive azoospermia (OA). NOA is a type of male infertility caused by spermatogenesis defects. Therefore, investigating the factors involved in spermatogenesis, including hormones and genes, is one of the important aspects in understanding the mechanism of infertility in men. To this end, we aimed to investigate the expression of the clusterin gene expression and LH, FSH and testosterone hormone levels in the testicular tissue and blood of NOA patients, respectively.
Methods: The study population included 42 NOA infertile men referred to Royan Institute, Tehran, Iran in June 2016 to February 2017. Their blood samples were collected and testosterone, LH and FSH hormones were measured by ELISA. Afterwards, based on the biopsy results the patients were categorized into TESE+ (positive sperm retrieval) and TESE- groups. The genomic RNA was extracted from testicular tissue samples obtained from TESE surgery. After converting to cDNA, the clusterin gene expression was investigated by Real-time PCR technique. The achieved data was analyzed using SPSS software, version 18 (Armonk, NY, USA).
Results: According to Real-time PCR results, the expression level of clusterin gene in TESE+ group was significantly higher than TESE- group (P= 0.035). The mean of FSH and LH hormone levels in the TESE+ group was relatively lower than the TESE- group (P= 0.07 and P= 0.08), but there was no significant difference in the mean of testosterone hormone levels between the two groups (P= 0.66).
Conclusion: Based on the results of this study, the clusterin gene can have a role in spermatogenesis and by evaluating FSH and LH hormones in a larger non-obstructive azoospermic patient’s population significant statistical results can be achieved.

Background: In the current study, a hybrid feature selection approach involving filter and wrapper methods is applied to some bioscience databases with various records, attributes and classes; hence, this strategy enjoys the advantages of both methods such as fast execution, generality, and accuracy. The purpose is diagnosing of the disease status and estimating of the patient survival.
Methods: Feature selection algorithms have been modeled in Matlab R2021a during April and May 2022 in the framework of statistical pattern recognition. First, the features are ranked based on normalized mutual information, as a metric of relevance and redundancy of features, and accordingly, an optimum feature subset with the highest accuracy of classification is selected. Two feature selection algorithms, i.e., inclusion of features enhancing the classification accuracy and exclusion of irrelevant features are applied to the interest datasets, subsequent to the mini-batch k-means clustering of records.

Results: At the end of the execution of both feature selection methods, evaluation metrics including accuracy, precision, recall, and F1 score are measured and compared. Both proposed feature selection approaches for the molecular biology, hepatitis C virus (HCV), and E. coli bacteria datasets result in the precision and recall scores more than 98 percent, meaning that there are few false positives and false negatives in the linear support vector machine (LSVM) classification. Regarding the HCV dataset, selection of nine relevant features among the thirteen present ones using the feature exclusion method yields the classification accuracy and F1 score of 98.92 percent and 99.02 percent, respectively. The feature inclusion approach also results in an accuracy of 98.78 percent with a slight discrepancy. Conclusion: The results reveal superior strength of the feature selection methods used here for life science datasets with higher-order features such as protein/gene expression database. The potentials to generalize to other classifiers and automatically specify the optimal number of features during the feature selection procedure make these approaches flexible in many data mining applications for the life sciences.