DCDA: CircRNA-Disease Association Prediction with Feed-Forward Neural Network and Deep Autoencoder

Circular RNA is a single-stranded RNA with a closed-loop structure. In recent years, academic research has revealed that circular RNAs play critical roles in biological processes and are related to human diseases. The discovery of potential circRNAs as disease biomarkers and drug targets is crucial since it can help diagnose diseases in the early stages and be used to treat people. However, in conventional experimental methods, conducting experiments to detect associations between circular RNAs and diseases is time-consuming and costly. To overcome this problem, various computational methodologies are proposed to extract essential features for both circular RNAs and diseases and predict the associations. Studies showed that computational methods successfully predicted performance and made it possible to detect possible highly related circular RNAs for diseases. This study proposes a deep learning-based circRNA-disease association predictor methodology called DCDA, which uses multiple data sources to create circRNA and disease features and reveal hidden feature codings of a circular RNA-disease pair with a deep autoencoder, then predict the relation score of the pair by a deep neural network. Fivefold cross-validation results on the benchmark dataset showed that our model outperforms state-of-the-art prediction methods in the literature with the AUC score of 0.9794.

A study of depression and anxiety among doctors working in emergency units in Denizli, Turkey

BACKGROUND

Major work has been carried out on the psychological well-being of emergency room doctors in the US, Canada and in other developed countries, but little has been published regarding the same in the countries in economic transition.

OBJECTIVE

To determine the level of, and the factors related to, depression and anxiety among doctors working in emergency units in Denizli, Turkey.

METHODS

This cross-sectional study was conducted in May 2004, using a sample of 192 doctors employed in emergency units in Pamukkale University Hospital, the City Hospital, the Social Security Hospital, private hospitals, citywide primary healthcare centres and 112 emergency services in Denizli, Turkey. Data were obtained using a self-administered questionnaire, including questions on sociodemographic characteristics and two instruments determining the level of depressive symptoms and anxiety. Logistic regression was the method chosen for multivariate statistical analysis.

RESULTS

The mean (standard deviation (SD)) depression score was 10.6 (6.5) and the frequency (%) of depression was 29 (15.1). Not having any hobby and having high anxiety scores were salient factors among doctors experiencing depressive symptomatology in bivariate comparisons. Logistic regression analysis showed that not having any hobby (p = 0.07) and having increased anxiety scores (p<0.001) were positive contributors to depression scores. The mean (SD) anxiety score was 8.7 (8.2) and the frequency (%) of anxiety was 28 (14.6). Being a woman, having a low monthly income and having high depression scores contributed considerably to the anxiety of doctors in bivariate comparisons. Low monthly income (<1000 v 1000-2000 YTL) (p = 0.03), the number of years spent in emergency units (p = 0.03) and having high depression scores (p<0.001) were the factors that contributed significantly to the anxiety of doctors in the multivariate regression analysis.

CONCLUSION

The considerable amount of depression and anxiety found among doctors in this study should trigger further work. Studies using more powerful designs would help to illuminate the factors leading to depression and anxiety, which result in attrition among doctors from emergency units.

Effect of taphonomic processes on dental microwear

Taphonomic processes have the potential to affect microscopic wear on teeth and to modify the wear patterns so as to confound dietary reconstructions based on dental microwear which was formed during the lifetime of an animal. This study describes a series of experiments which were conducted to simulate various taphonomic agents and to record their effect on dental microwear. Three types of experiment were carried out in order to explain anomalous microscopic wear that had been found on the dentition of several hominoid specimens from the 15 M.a. site of Pasalar in Turkey. The effect of two different acids-citric and hydrochloric acid-on dental microwear was investigated. Modification to microscopic wear caused by alkali (carbonatite ash) was examined in the second set of experiments. Lastly, the effect of abrasion by three different size classes of sediment from the site of Pasalar-quartz pebbles (grain size varied from 2,000-11,000 microm), coarse sand (grain size ranged from 500-1,000 microm), and medium-sized sand (grain diameters were between 250 and 500 microm)-was investigated. Results confirm previous findings that the taphonomic modification of dental microwear is readily identifiable and causes the obliteration rather than secondary alteration of microwear features. The experiments show that both citric and hydrochloric acid affect dental microwear but to varying degrees, whereas alkali did not cause any modification of microscopic features. The different size classes of sediment also had different effects on the dental microwear. The largest size sediment (quartz pebbles) polished the enamel and removed finer microwear features. The coarse sand, however, did not have any effect on the microwear. The greatest amount of abrasion was caused by the smallest sediment particles -the medium-sized sand. Several hominoid dental specimens from Pasalar display similar microscopic wear to the two types of acid erosion and the abrasion caused by the medium-sized sands.