Search

Software defect prediction (SDP) is a crucial phase preceding the launch of software products. Cross-project defect prediction (CPDP) is introduced for the anticipation of defects in novel projects lacking defect labels. CPDP can use defect information of mature projects to speed up defect prediction for new projects. So that developers can quickly get the defect information of the new project, so that they can test the software project pertinently. At present, the predominant approaches in CPDP rely on deep learning, and the performance of the ultimate model is notably affected by the quality of the training dataset. However, the dataset of CPDP not only has few samples but also has almost no label information in new projects, which makes the general deep-learning-based CPDP model not ideal. In addition, most of the current CPDP models do not fully consider the enrichment of classification boundary samples after cross-domain, leading to suboptimal predictive capabilities of the model. To overcome these obstacles, we present contrastive learning pretraining for CPDP (ConCPDP), a CPDP method integrating contrastive pretraining and category boundary adjustment. We first perform data augmentation on the source and target domain code files and then extract the enhanced data as an abstract syntax tree (AST). The AST is then transformed into an integer sequence using specific mapping rules, serving as input for the subsequent neural network. A neural network based on bidirectional long short-term memory (Bi-LSTM) will receive an integer sequence and output a feature vector. Then, the feature vectors are input into the contrastive module to optimise the feature extraction network. The pretrained feature extractor can be fine-tuned by the maximum mean discrepancy (MMD) between the feature distribution of the source domain and the target domain and the binary classification loss on the source domain. This paper conducts a large number of experiments on the PROMISE dataset, which is commonly used for CPDP, to validate ConCPDP’s efficacy, achieving superior results in terms of F1 measure, area under curve (AUC), and Matthew’s correlation coefficient (MCC).

Abstract Cross‐project defect prediction (CPDP) is an important research direction in software defect prediction. Traditional CPDP methods based on hand‐crafted features ignore the semantic information in the source code. Existing CPDP methods based on the deep learning model may not fully consider the differences among projects. Additionally, these methods may not accurately classify the samples near the classification boundary. To solve these problems, the authors propose a model based on multi‐adaptation and nuclear norm (MANN) to deal with samples in projects. The feature of samples were embedded into the multi‐core Hilbert space for distribution and the multi‐kernel maximum mean discrepancy method was utilised to reduce differences among projects. More importantly, the nuclear norm module was constructed, which improved the discriminability and diversity of the target sample by calculating and maximizing the nuclear norm of the target sample in the process of domain adaptation, thus improving the performance of MANN. Finally, extensive experiments were conducted on 11 sizeable open‐source projects. The results indicate that the proposed method exceeds the state of the art under the widely used metrics.

Abstract The exostosin (EXT) protein family is involved in diverse human diseases. However, the expression and prognostic value of EXT genes in human lung squamous cell carcinoma (LUSC) is not well understood. In this study, we analyzed the association between expression of EXT1 and EXT2 genes and survival in patients with LUSC using bioinformatics resources such as Oncomine and The Cancer Genome Atlas (TCGA) databases, the Gene Expression Profiling Interactive Analysis (GEPIA) server and Kaplan–Meier plotter. Furthermore, regulatory microRNAs (miRNAs) were predicted for EXT1 and used to establish a potential miRNA‐messenger RNA (mRNA) regulation network for LUSC using the ENCORI platform. We observed that EXT1 and EXT2 expression levels were higher in LUSC than those in normal tissues. However, only EXT1 expression was significantly associated with poor overall survival (OS) in LUSC patients. Functional annotation enrichment analysis showed that genes co‐expressed with the EXT1 gene were enriched in biological processes such as cell adhesion and migration, and KEGG pathways such as extracellular matrix receptor interactions, complement and coagulation cascades, and cell death. Furthermore, three miRNAs, hsa‐mir‐190a‐5p, hsa‐mir‐195‐5p, and hsa‐mir‐490‐3p, were identified to be potentially involved in the regulation of EXT1. In summary, we identified EXT1 expression as a novel potential prognostic marker for human LUSC and the regulatory miRNAs that could possibly contribute to the prognosis of the disease.

Background. Transjugular intrahepatic portosystemic shunt (TIPS) is suggested as the salvage therapy for gastroesophageal variceal bleeding in cirrhosis. However, rebleeding might occur in some patients after TIPS. Currently, there is a lack of evidence in the endoscopic management of recurrent bleeding in these patients. Aims. To evaluate the efficacy of endoscopic treatment in cirrhotic patients with recurrent bleeding after TIPS. Methods. Cirrhotic patients with gastroesophageal varices who received endoscopic treatment for recurrent bleeding after TIPS were included. Results. 6 patients were enrolled in this study. The median age of the patients was 47 years (range 27 to 65 years), and the duration of follow-up time was 346 (17-773) days. Stent stenosis or occlusion was found in 5 out of 6 patients after TIPS. Salvage endoscopic treatment, including esophageal variceal ligation (EVL), gastric variceal cyanoacrylate injection, esophageal variceal sclerotherapy, and balloon-occluded retrograde transvenous obliteration- (BRTO-) assisted endoscopic cyanoacrylate injection. Among included patients, 2 died shortly after EVL (14 and 19 days) due to variceal bleeding. Among other 4 patients, 2 had rebleeding episodes at 422 and 789 days, respectively. Conclusion. Endoscopic treatment may be an option for recurrent bleeding after TIPS in selected patients. Further studies are needed to carefully define the indication and efficacy of this option.