A New Information-Theoretic Method for Advertisement Conversion Rate Prediction for Large-Scale Sparse Data Based on Deep Learning.

With the development of online advertising technology, the accurate targeted advertising based on user preferences is obviously more suitable both for the market and users. The amount of conversion can be properly increased by predicting the user's purchasing intention based on the advertising Conversion Rate (CVR). According to the high-dimensional and sparse characteristics of the historical behavior sequences, this paper proposes a LSLM_LSTM model, which is for the advertising CVR prediction based on large-scale sparse data. This model aims at minimizing the loss, utilizing the Adaptive Moment Estimation (Adam) optimization algorithm to mine the nonlinear patterns hidden in the data automatically. Through the experimental comparison with a variety of typical CVR prediction models, it is found that the proposed LSLM_LSTM model can utilize the time series characteristics of user behavior sequences more effectively, as well as mine the potential relationship hidden in the features, which brings higher accuracy and trains faster compared to those with consideration of only low or high order features.

The Role of Gene Expression Changes in ceRNA Network Underlying Ossification of Ligamentum Flavum Development.

We aimed at exploring the role of gene expression changes regulated by non-coding RNAs in ossification of ligamentum flavum (OLF). Three microarray datasets, including long non-coding RNA (lncRNA)/mRNA expression profile (GSE106253), circular RNA (circRNA) expression profile (GSE106255), and microRNA (miRNA) expression profile (GSE106256), were downloaded from the public Gene Expression Omnibus repository. The differentially expressed (DE) mRNAs, lncRNAs, miRNAs, and circRNAs in OLF tissues were analyzed, compared with normal tissues. Two competing endogenous RNA (ceRNA) networks with lncRNA-miRNA-mRNA and circRNA-miRNA-mRNA interactions were constructed, separately. Random walk with the restart model was applied to calculate the correlations of mRNAs with the published OLF-related genes. The top 50 mRNAs were subjected to function enrichment analysis and active small-molecule prediction. Total 2323 DE mRNAs, 1168 lncRNAs, 336 circRNAs, and 29 miRNAs were identified based on the microarray datasets. The LncRNA-related ceRNA network was constructed with 614 lncRNA-miRNA, 494 miRNA-mRNA, and 2099 lncRNA-mRNA interaction pairs; the circRNA-related ceRNA network was constructed with 153 circRNA-miRNA, 190 miRNA-mRNA, and 210 circRNA-mRNA interaction pairs. There were 17 OLF-related genes retrieved from previous literature, such as NPPS, COL6A1, and COL11A2, among which COL6A1 was the overlapped gene with mRNAs in the ceRNA network. Subsequently, top 50 mRNAs that closely correlated with COL6A1 in the ceRNA network were captured and these genes were closely related with the collagen catabolic process, regulation of cell growth, and neuronal action potential. DRD1 and COL6A1 were predicted to be the targets by small active molecule drugs. The collagen catabolic process may be implicated in OLF development. COL6A1 and DRD1 may be the candidate targets for OLF. However, further validations were needed.

Treatment adherence among sputum smear-positive pulmonary tuberculosis patients in Xinjiang, China: a prospective study.

BACKGROUND: Despite great effort to control tuberculosis (TB), low treatment adherence threatens the success of drug therapy, increases the risk of TB transmission, and leads to the development of drug resistance. The present study assessed anti-TB treatment adherence in sputum smear-positive TB patients and examined the risk factors for poor patient adherence to identify targets for intervention. METHODS: We monitored and followed up TB patients who were diagnosed between July 2014 and June 2015 in Xinjiang, China. A total of 8289 sputum smear-positive TB patients were included in this study. All patients registered their information during the first hospital visit or with the Centers for Disease Control, had regular follow-up visits, and accepted the anti-TB treatment. Insufficient re-examination adherence was defined as undergoing fewer than the recommended three sputum smear examinations during the treatment course. RESULTS: Among 8289 patients, 3827 men (84.4% of male patients) and 3220 women (85.7% of female patients) had good adherence during treatment follow-up. 1242 patients (15.0%) did not complete regular follow-up. 332 (4.0%) patients lost contact. An adjusted logistic regression model showed that ethnicity, household address, treatment classification, patient source, and the actual management were significantly associated with non-adherence. CONCLUSION: The Xinjiang TB epidemic situation remains grim. Smear-positive patients had a higher proportion of non-adherence, which increased treatment difficulties and the risk of death from TB. Relevant medical departments should strengthen their supervision and interventions during the TB treatment process to improve patient adherence to anti-TB treatment.

Serum microRNA-376 family as diagnostic and prognostic markers in human gliomas.

BACKGROUND: MicroRNA (miR)-376 family play crucial roles in cancer formation and progression. OBJECTIVE: To investigate expression patterns of circulating miR-376 members in glioma patients, and to explore their diagnostic and prognostic values. METHODS: Expression of miR-376 members in serum samples from 100 glioma patients and 50 healthy controls were detected by quantitative real-time PCR. RESULTS: Serum miR-376a, miR-376b and miR-376c in glioma patients were significantly lower than those in healthy controls (all P< 0.05). Their expression could efficiently distinguish the glioma patients from healthy controls according to the receiver operating characteristic (ROC) analysis [for miR-376a, the area under ROC curve (AUC) = 0.872, the optimal cut-off value = 1.95, the sensitivity = 81.0% and the specificity = 82.0%; for miR-376b, AUC = 0.890, the optimal cut-off value = 2.07, the sensitivity = 82.0% and the specificity = 78.0%; for miR-376c, AUC = 0.837, the optimal cut-off value = 2.12, the sensitivity = 90.0% and the specificity = 70.0%; all P<0. 001]. Decreased expression of miR-376a, miR-376b and miR-376c in patients' sera were significantly associated with advanced WHO grade (all P< 0.01) and low KPS (all P< 0.05). Kaplan-Meier and Cox regression analyses showed that low miR-376a, miR-376b and miR-376c expression, and high grade were all independent factors predicting poor outcome of glioma patients. Notably, subgroup analyses showed that serum miR-376a, miR-376b and miR-376c levels had more significant prognostic values in patients with high grade gliomas than those with low grade gliomas. CONCLUSIONS: Aberrant expression of the miR-376 family may be involved into tumorigenesis and tumor progression of human gliomas. Circulating miR-376a, miR-376b and miR-376c may be promising non-invasive biomarkers for diagnosis and prognosis in glioma patients.