YWHAZ has been suggested to as an oncogene in various human malignancies, including non‐small–cell lung cancer (NSCLC). Our study presents more evidence to confirm the clinical significance and biological function of YWHAZ in NSCLC. In our results, YWHAZ was upregulated in lung squamous cell carcinoma tissues and lung adenocarcinoma tissues through analyzing The Cancer Genome Atlas (TCGA) database, and confirmed high levels of YWHAZ messenger RNA and protein in lung squamous cell carcinoma tissues and lung adenocarcinoma tissues through quantitative real‐time polymerase chain reaction and immunohistochemistry. Moreover, YWHAZ overexpression was correlated with advanced clinical stage, more lymph node metastasis and present distant metastasis in NSCLC patients. Survival analysis indicated that high level of YWHAZ protein expression was associated with short overall survival time in NSCLC patients, and YWHAZ expression was independent prognostic factors for overall survival in NSCLC patients. Moreover, Silencing of YWHAZ expression represses NSCLC cell migration and invasion. In conclusion, YWHAZ is a credible prognostic biomarker, and may be a therapeutic target in NSCLC.

Ability to quantify and predict progression of a disease is fundamental for selecting an appropriate treatment. Many clinical metrics cannot be acquired frequently either because of their cost (e.g. MRI, gait analysis) or because they are inconvenient or harmful to a patient (e.g. biopsy, x-ray). In such scenarios, in order to estimate individual trajectories of disease progression, it is advantageous to leverage similarities between patients, i.e. the covariance of trajectories, and find a latent representation of progression. Most of existing methods for estimating trajectories do not account for events in-between observations, what dramatically decreases their adequacy for clinical practice. In this study, we develop a machine learning framework named Coordinatewise-Soft-Impute (CSI) for analyzing disease progression from sparse observations in the presence of confounding events. CSI is guaranteed to converge to the global minimum of the corresponding optimization problem. Experimental results also demonstrates the effectiveness of CSI using both simulated and real dataset.Preprint. Under review.