Search

Triple-negative breast cancer (TNBC) is the breast cancer subtype with the highest fatality rate, and it seriously threatens women's health. Recent studies found that the level of immune cell infiltration in TNBC was associated with tumor progression and prognosis. However, due to practical constraints, most of these TNBC immune infiltration studies only used a small number of patient samples and a few immune cell types. Therefore, it is necessary to integrate more TNBC patient samples and immune cell types to comprehensively study immune infiltration in TNBC to contribute to the prognosis and treatment of patients. In this study, 12 TNBC datasets were integrated and an extensive collection of 182 gene sets with immune-related signatures were included to comprehensively investigate tumor immune microenvironment of TNBC. A single sample gene set enrichment analysis was performed to calculate the infiltration score of each immune-related signature in each patient, and an immune-related risk scoring model for TNBC was constructed to accurately assess patient prognosis. Significant differences were found in immunogenomic landscape between different immune risk subtypes. In addition, the immunotherapy response and chemotherapy drug sensitivity of patients with different immune risk subtypes were also analyzed. The results showed that there were significant differences in these characteristics. Finally, a prediction model for immune risk subtypes of TNBC patients was constructed to accurately predict patients with unknown subtypes. Based on the aforementioned findings, we believed that the immune-related risk score constructed in this study can assist in providing personalized medicine to TNBC patients. [ABSTRACT FROM AUTHOR]

Breast cancer is a kind of malignant tumor that occurs in breast tissue, which is the most common cancer in women. Cellular metabolism is a critical determinant of the viability and function of cancer cells in tumor microenvironment. In this study, based on the gene expression profile of metabolism-related genes, the prognostic value of 20 metabolic pathways in patients with breast cancer was identified. A universal risk stratification signature that relies on 20 metabolic pathways was established and validated in training cohort, two testing cohorts and The Cancer Genome Atlas pan cancer cohort. Then, the relationship between metabolic risk score subtype, prognosis, immune infiltration level, cancer genotypes and their impact on therapeutic benefit were characterized. Results demonstrated that the patients with the low metabolic risk score subtype displayed good prognosis, high level of immune infiltration and exhibited a favorable response to neoadjuvant chemotherapy and immunotherapy. Taken together, the work presented in this study may deepen the understanding of metabolic hallmarks of breast cancer, and may provide some valuable information for personalized therapies in patients with breast cancer. [ABSTRACT FROM AUTHOR]

The success of software projects for organizations heavily relies on accurate workforce and cost estimates. Initially, effort estimation was based on non-algorithmic methods, but with technological advancements, algorithmic approaches such as regression emerged. In recent years, there has been a growing interest in using Machine Learning and Artificial Intelligence for software cost estimation. In this study, Linear Regression, Multilayer Perceptron, Bagging, SMOreg, IBk, KStar, RandomTree, and RandomForest algorithms were trained with four open-source datasets. Firstly, models were trained with original feature sets, then six different hybrid feature selection methods were proposed to eliminate low-impact features and prevent overfitting. These hybrid feature selection methods, developed using evaluation methods like Relief, Classifier, and Correlation, along with search methods like RandomSearch, PSO, GA, and Ranker. And trained models tested by the 10-fold cross-validation technique. The results showed the ability to quickly obtain adaptable models and the effectiveness of feature selection. KStar, SMOreg, Multilayer Perceptron, and Linear Regression algorithms, along with PSO and GA search methods, yielded satisfactory results even with different feature subsets. [ABSTRACT FROM AUTHOR]