Background Epidemiological studies have confirmed that abnormal circadian rhythms are associated with tumorigenesis in breast cancer. However, few studies have investigated the pathological roles of rhythm genes in breast cancer progression. In this study, we aimed to evaluate the aberrant expression of 32 rhythm genes in breast cancer and detect the pathological roles and molecular mechanisms of the altered rhythm gene in regulating the progression of triple negative breast cancer (TNBC). Methods The aberrant expression of rhythm genes in breast cancer was screened by searching the GEPIA database and validated by using qRT-PCR and immunohistochemistry staining. Bioinformatics analysis combined with luciferase reporter experiment and chromatinimmunopercitation (ChIP) were used to investigate the molecular mechanism about aberrant expression of identified rhythm gene in breast cancer. The pathological roles of identified rhythm gene in TNBC progression was evaluated by colony formation assay, wound healing experiment, transwell assay, subcutaneous tumor formation and the mouse tail vein injection model through gain-of-function and loss-of-function strategies respectively. mRNA array, bioinformatics analysis, luciferase reporter experiment, ChIP and immunoflurescence assay were employed to investigate the key molecules and signaling pathways by which the identified rhythm gene regulating TNBC progression. Results We identified that nuclear factor interleukin 3 regulated (NFIL3) expression is significantly altered in TNBC compared with both normal breast tissues and other subtypes of breast cancer. We found that NFIL3 inhibits its own transcription, and thus, downregulated NFIL3 mRNA indicates high expression of NFIL3 protein in breast cancer. We demonstrated that NFIL3 promotes the proliferation and metastasis of TNBC cells in vitro and in vivo, and higher expression of NFIL3 is associated with poor prognosis of patients with TNBC. We further demonstrated that NFIL3 enhances the activity of NF-κB signaling. Mechanistically, we revealed that NFIL3 directly suppresses the transcription of NFKBIA, which blocks the activation of NF-κB and inhibits the progression of TNBC cells in vitro and in vivo. Moreover, we showed that enhancing NF-κB activity by repressing NFKBIA largely mimics the oncogenic effect of NFIL3 in TNBC, and anti-inflammatory strategies targeting NF-κB activity block the oncogenic roles of NFIL3 in TNBC. Conclusion NFIL3 promotes the progression of TNBC by suppressing NFKBIA transcription and then enhancing NF-κB signaling-mediated cancer-associated inflammation. This study may provide a new target for TNBC prevention and therapy. Graphical Abstract

PurposeThis study aimed to develop a machine learning model to retrospectively study and predict the recurrence risk of breast cancer patients after surgery by extracting the clinicopathological features of tumors from unstructured clinical electronic health record (EHR) data.MethodsThis retrospective cohort included 1,841 breast cancer patients who underwent surgical treatment. To extract the principal features associated with recurrence risk, the clinical notes and histopathology reports of patients were collected and feature engineering was used. Predictive models were next conducted based on this important information. All algorithms were implemented using Python software. The accuracy of prediction models was further verified in the test cohort. The area under the curve (AUC), precision, recall, and F1 score were adopted to evaluate the performance of each model.ResultsA training cohort with 1,289 patients and a test cohort with 552 patients were recruited. From 2011 to 2019, a total of 1,841 textual reports were included. For the prediction of recurrence risk, both LSTM, XGBoost, and SVM had favorable accuracies of 0.89, 0.86, and 0.78. The AUC values of the micro-average ROC curve corresponding to LSTM, XGBoost, and SVM were 0.98 ± 0.01, 0.97 ± 0.03, and 0.92 ± 0.06. Especially the LSTM model achieved superior execution than other models. The accuracy, F1 score, macro-avg F1 score (0.87), and weighted-avg F1 score (0.89) of the LSTM model produced higher values. All P values were statistically significant. Patients in the high-risk group predicted by our model performed more resistant to DNA damage and microtubule targeting drugs than those in the intermediate-risk group. The predicted low-risk patients were not statistically significant compared with intermediate- or high-risk patients due to the small sample size (188 low-risk patients were predicted via our model, and only two of them were administered chemotherapy alone after surgery). The prognosis of patients predicted by our model was consistent with the actual follow-up records.ConclusionsThe constructed model accurately predicted the recurrence risk of breast cancer patients from EHR data and certainly evaluated the chemoresistance and prognosis of patients. Therefore, our model can help clinicians to formulate the individualized management of breast cancer patients.

No abstract