Software defect prediction using hybrid model (CBIL) of convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM).

In recent years, the software industry has invested substantial effort to improve software quality in organizations. Applying proactive software defect prediction will help developers and white box testers to find the defects earlier, and this will reduce the time and effort. Traditional software defect prediction models concentrate on traditional features of source code including code complexity, lines of code, etc. However, these features fail to extract the semantics of source code. In this research, we propose a hybrid model that is called CBIL. CBIL can predict the defective areas of source code. It extracts Abstract Syntax Tree (AST) tokens as vectors from source code. Mapping and word embedding turn integer vectors into dense vectors. Then, Convolutional Neural Network (CNN) extracts the semantics of AST tokens. After that, Bidirectional Long Short-Term Memory (Bi-LSTM) keeps key features and ignores other features in order to enhance the accuracy of software defect prediction. The proposed model CBIL is evaluated on a sample of seven open-source Java projects of the PROMISE dataset. CBIL is evaluated by applying the following evaluation metrics: F-measure and area under the curve (AUC). The results display that CBIL model improves the average of F-measure by 25% compared to CNN, as CNN accomplishes the top performance among the selected baseline models. In average of AUC, CBIL model improves AUC by 18% compared to Recurrent Neural Network (RNN), as RNN accomplishes the top performance among the selected baseline models used in the experiments.

Validation of analytical breast cancer microarray analysis in medical laboratory.

A previously reported microarray data analysis by RISS algorithm on breast cancer showed over-expression of the growth factor receptor (Grb7) and it also highlighted Tweety (TTYH1) gene to be under expressed in breast cancer for the first time. Our aim was to validate the results obtained from the microarray analysis with respect to these genes. Also, the relationship between their expression and the different prognostic indicators was addressed. RNA was extracted from the breast tissue of 30 patients with primary malignant breast cancer. Control samples from the same patients were harvested at a distance of ≥5 cm from the tumour. Semi-quantitative RT-PCR analysis was done on all samples. There was a significant difference between the malignant and control tissues as regards Grb7 expression. It was significantly related to the presence of lymph node metastasis, stage and histological grade of the malignant tumours. There was a significant inverse relation between expression of Grb7 and expression of both oestrogen and progesterone receptors. Grb7 was found to be significantly related to the biological classification of breast cancer. TTYH1 was not expressed in either the malignant or the control samples. The RISS by our group algorithm developed was laboratory validated for Grb7, but not for TTYH1. The newly developed software tool needs to be improved.