A Machine Learning-Based Predictive Model of Epidermal Growth Factor Mutations in Lung Adenocarcinomas.

Data from 758 patients with lung adenocarcinoma were retrospectively collected. All patients had undergone computed tomography imaging and EGFR gene testing. Radiomic features were extracted using the medical imaging tool 3D-Slicer and were combined with the clinical features to build a machine learning prediction model. The high-dimensional feature set was screened for optimal feature subsets using principal component analysis (PCA) and the least absolute shrinkage and selection operator (LASSO). Model prediction of EGFR mutation status in the validation group was evaluated using multiple classifiers. We showed that six clinical features and 622 radiomic features were initially collected. Thirty-one radiomic features with non-zero correlation coefficients were obtained by LASSO regression, and 24 features correlated with label values were obtained by PCA. The shared radiomic features determined by these two methods were selected and combined with the clinical features of the respective patient to form a subset of features related to EGFR mutations. The full dataset was partitioned into training and test sets at a ratio of 7:3 using 10-fold cross-validation. The area under the curve (AUC) of the four classifiers with cross-validations was: (1) K-nearest neighbor (AUCmean = 0.83, Acc = 81%); (2) random forest (AUCmean = 0.91, Acc = 83%); (3) LGBM (AUCmean = 0.94, Acc = 88%); and (4) support vector machine (AUCmean = 0.79, Acc = 83%). In summary, the subset of radiographic and clinical features selected by feature engineering effectively predicted the EGFR mutation status of this NSCLC patient cohort.

Spider Toxin Peptide-Induced NIR Gold Nanocluster Fabrication for GSH-Responsive Cancer Cell Imaging and Nuclei Translocation.

Goldnanoclusters (GNCs) have become a promising nanomaterial for bioimaging because of their unique optical properties and biocompatibility. In this study, lycosin-I peptide, which possesses a highly selective anticancer activity by affecting the permeability of cancer cell membrane, was firstly modified for constructing fluorescent GNCs (LGNCs) for bioimaging of tumor cells. The obtained LGNCs exhibited strong near-infrared (NIR) fluorescence, which can be further enhanced by the peptide-induced aggregation and selectively stained three cancerous cell lines over normal cell lines with low intrinsic toxicity. After uptake by tumor cells, LGNC aggregates can be depolymerized into ultrasmall nanoclusters by high-level glutathione (GSH) and realize the nuclear targeting translocation. Collectively, our work suggests the potential of natural active biomolecules in designing NIR fluorescent GNCs for bioimaging.

MicroRNA-100 inhibits breast cancer cell proliferation, invasion and migration by targeting FOXA1.

MicroRNAs (miRNAs/miRs) are highly conserved single-stranded small non-coding RNAs, which are involved in the physiological and pathological processes of breast cancer, and affect the prognosis of patients with breast cancer. The present study used the Gene Expression Omnibus (GEO)2R tool to detect miR-100 expression in breast cancer tissues obtained from GEO breast cancer-related datasets. Bioinformatics analysis revealed that miR-100 expression was downregulated in different stages, grades and lymph node metastasis stages of breast cancer, and patients with high miR-100 expression had a more favorable prognosis. Based on these analyses, Cell Counting Kit-8, wound healing and Transwell assays were performed, and the results demonstrated that overexpression of miR-100 inhibited the proliferation, migration and invasion of breast cancer cells. To verify the tumor-suppressive effect of miR-100 in breast cancer, the LinkedOmics and PITA databases were used to assess the association between miR-100 and forkhead box A1 (FOXA1). The results demonstrated that miR-100 had binding sites within the FOXA1 gene, and FOXA1 expression was negatively associated with miR-100 expression in breast cancer tissues. Similarly, a negative association was observed between miR-100 and FOXA1 expression, using the StarBase V3.0 database. The association between miR-100 and FOXA1 was further verified via reverse transcription-quantitative PCR and western blot analyses, and the dual-luciferase reporter assay. The results demonstrated that miR-100 targeted the 3'-untranslated region of FOXA1 in breast cancer cells. Furthermore, rescue experiments were performed to confirm whether miR-100 exerts its antitumor effects by regulating FOXA1. The results demonstrated that overexpression of FOXA1 promoted the proliferation, migration and invasion of breast cancer cells; thus, the antitumor effects of miR-100 in breast cancer were reversed following overexpression of FOXA1. Taken together, the results of the present study suggest that miR-100 inhibits the proliferation, migration and invasion of breast cancer cells by targeting FOXA1 expression. These results may provide a novel insight and an experimental basis for identifying effective therapeutic targets of high specificity for breast cancer.