Construction of an index system of core competence assessment for otolaryngology nurse specialists in China: A Delphi study.

BACKGROUND: Clinical nurse specialists play a vital role in the work quality, patient safety and team development of nurses. However, there is currently no prior study constructing the index of core competence assessment for otolaryngology Nurse Specialists. OBJECTIVES: To establish an index system for the evaluation of Chinese otolaryngology Nurse Specialists' core competence. DESIGN: A Delphi study. SETTINGS: The study was mainly conducted in a university-affiliated hospital in China. PARTICIPANTS: Twenty-two experts with otolaryngology knowledge and practical experience from different regions and organizations in China. METHODS: We used literature reviews and expert meetings to establish a draft index system . Subsequently, a two-round Delphi survey was utilized to consult opinions from 22 experts about the index for the evaluation of otolaryngology nurse specialists' core competence and provide qualitative comments on their ratings. Consensus was predefined as a mean important score of 4.0 or above and a coefficient of variation is not above 0.25 among the participants. RESULTS: The final evaluation indexes of the core competencies for otolaryngology Nurse Specialists included 5 first-level indexes (clinical competence, critical thinking competence, leadership, professional development competence, professionalism), 19 second-level indexes, and 85 third-level indexes. The effective response rates of the two expert consultation rounds were 100 %. The expert authority coefficients were 0.864 and 0.859 in the first and second rounds of consultation, respectively. In the second round of consultation, the first, second and third indexes of Kendall's coefficient of concordance were 0.357, 0.330, and 0.232, respectively (P < 0.001). CONCLUSIONS: The constructed evaluation indexes of the core competencies of otolaryngology Nurse Specialists are scientific, reasonable, comprehensive, and specific and may provide references for the training and evaluation of otolaryngology Nurse Specialists.

Deciphering ligand-receptor-mediated intercellular communication based on ensemble deep learning and the joint scoring strategy from single-cell transcriptomic data.

BACKGROUND: Cell-cell communication in a tumor microenvironment is vital to tumorigenesis, tumor progression and therapy. Intercellular communication inference helps understand molecular mechanisms of tumor growth, progression and metastasis. METHODS: Focusing on ligand-receptor co-expressions, in this study, we developed an ensemble deep learning framework, CellComNet, to decipher ligand-receptor-mediated cell-cell communication from single-cell transcriptomic data. First, credible LRIs are captured by integrating data arrangement, feature extraction, dimension reduction, and LRI classification based on an ensemble of heterogeneous Newton boosting machine and deep neural network. Next, known and identified LRIs are screened based on single-cell RNA sequencing (scRNA-seq) data in certain tissues. Finally, cell-cell communication is inferred by incorporating scRNA-seq data, the screened LRIs, a joint scoring strategy that combines expression thresholding and expression product of ligands and receptors. RESULTS: The proposed CellComNet framework was compared with four competing protein-protein interaction prediction models (PIPR, XGBoost, DNNXGB, and OR-RCNN) and obtained the best AUCs and AUPRs on four LRI datasets, elucidating the optimal LRI classification ability. CellComNet was further applied to analyze intercellular communication in human melanoma and head and neck squamous cell carcinoma (HNSCC) tissues. The results demonstrate that cancer-associated fibroblasts highly communicate with melanoma cells and endothelial cells strong communicate with HNSCC cells. CONCLUSIONS: The proposed CellComNet framework efficiently identified credible LRIs and significantly improved cell-cell communication inference performance. We anticipate that CellComNet can contribute to anticancer drug design and tumor-targeted therapy.

CellEnBoost: A Boosting-Based Ligand-Receptor Interaction Identification Model for Cell-to-Cell Communication Inference.

Cell-to-cell communication (CCC) plays important roles in multicellular organisms. The identification of communication between cancer cells themselves and one between cancer cells and normal cells in tumor microenvironment helps understand cancer genesis, development and metastasis. CCC is usually mediated by Ligand-Receptor Interactions (LRIs). In this manuscript, we developed a Boosting-based LRI identification model (CellEnBoost) for CCC inference. First, potential LRIs are predicted by data collection, feature extraction, dimensional reduction, and classification based on an ensemble of Light gradient boosting machine and AdaBoost combining convolutional neural network. Next, the predicted LRIs and known LRIs are filtered. Third, the filtered LRIs are applied to CCC elucidation by combining CCC strength measurement and single-cell RNA sequencing data. Finally, CCC inference results are visualized using heatmap view, Circos plot view, and network view. The experimental results show that CellEnBoost obtained the best AUCs and AUPRs on the collected four LRI datasets. Case study in human head and neck squamous cell carcinoma (HNSCC) tissues demonstrates that fibroblasts were more likely to communicate with HNSCC cells, which is in accord with the results from iTALK. We anticipate that this work can contribute to the diagnosis and treatment of cancers.

LPI-EnEDT: an ensemble framework with extra tree and decision tree classifiers for imbalanced lncRNA-protein interaction data classification.

BACKGROUND: Long noncoding RNAs (lncRNAs) have dense linkages with various biological processes. Identifying interacting lncRNA-protein pairs contributes to understand the functions and mechanisms of lncRNAs. Wet experiments are costly and time-consuming. Most computational methods failed to observe the imbalanced characterize of lncRNA-protein interaction (LPI) data. More importantly, they were measured based on a unique dataset, which produced the prediction bias. RESULTS: In this study, we develop an Ensemble framework (LPI-EnEDT) with Extra tree and Decision Tree classifiers to implement imbalanced LPI data classification. First, five LPI datasets are arranged. Second, lncRNAs and proteins are separately characterized based on Pyfeat and BioTriangle and concatenated as a vector to represent each lncRNA-protein pair. Finally, an ensemble framework with Extra tree and decision tree classifiers is developed to classify unlabeled lncRNA-protein pairs. The comparative experiments demonstrate that LPI-EnEDT outperforms four classical LPI prediction methods (LPI-BLS, LPI-CatBoost, LPI-SKF, and PLIPCOM) under cross validations on lncRNAs, proteins, and LPIs. The average AUC values on the five datasets are 0.8480, 0,7078, and 0.9066 under the three cross validations, respectively. The average AUPRs are 0.8175, 0.7265, and 0.8882, respectively. Case analyses suggest that there are underlying associations between HOTTIP and Q9Y6M1, NRON and Q15717. CONCLUSIONS: Fusing diverse biological features of lncRNAs and proteins and exploiting an ensemble learning model with Extra tree and decision tree classifiers, this work focus on imbalanced LPI data classification as well as interaction information inference for a new lncRNA (or protein).