Enhancing selection of alcohol consumption-associated genes by random forest.

Machine learning methods have been used in identifying omics markers for a variety of phenotypes. We aimed to examine whether a supervised machine learning algorithm can improve identification of alcohol-associated transcriptomic markers. In this study, we analysed array-based, whole-blood derived expression data for 17 873 gene transcripts in 5508 Framingham Heart Study participants. By using the Boruta algorithm, a supervised random forest (RF)-based feature selection method, we selected twenty-five alcohol-associated transcripts. In a testing set (30 % of entire study participants), AUC (area under the receiver operating characteristics curve) of these twenty-five transcripts were 0·73, 0·69 and 0·66 for non-drinkers v. moderate drinkers, non-drinkers v. heavy drinkers and moderate drinkers v. heavy drinkers, respectively. The AUC of the selected transcripts by the Boruta method were comparable to those identified using conventional linear regression models, for example, AUC of 1958 transcripts identified by conventional linear regression models (false discovery rate < 0·2) were 0·74, 0·66 and 0·65, respectively. With Bonferroni correction for the twenty-five Boruta method-selected transcripts and three CVD risk factors (i.e. at P < 6·7e-4), we observed thirteen transcripts were associated with obesity, three transcripts with type 2 diabetes and one transcript with hypertension. For example, we observed that alcohol consumption was inversely associated with the expression of DOCK4, IL4R, and SORT1, and DOCK4 and SORT1 were positively associated with obesity, and IL4R was inversely associated with hypertension. In conclusion, using a supervised machine learning method, the RF-based Boruta algorithm, we identified novel alcohol-associated gene transcripts.

Liquid-like polymer-based self-cleaning coating for effective prevention of liquid foods contaminations.

Liquid food containers commonly suffer from inevitable contamination and even biofilm formation due to the adhesion of food residuals or saliva, which requires detergents to clean. Although previously reported superhydrophobic and omniphobic coatings can resist the adhesion of liquids, the requirements of specific nanostructures or infused lubricants limit their applications in food containers. Here, by grafting smooth glass containers with "liquid like" polydimethylsiloxane brushes, we developed a unique approach for preparing a slippery coating that could exhibit highly robust repellency to various liquid foods. The coating was highly transparent and did not induce a significant alteration of the smooth surface. The "liquid like" coating could effectively prevent the adhesion of various liquid foods and inhibit the formation of bacterial biofilms, without the use of detergents for cleaning. Moreover, this coating could resist mechanical damage from friction, and displayed high biocompatibility with biological cells. The slipperiness, smoothness, robustness and biocompatibility of the "liquid like" coating was highly beneficial to practical applications as self-cleaning glass container, which has been challenging to achieve by conventional superhydrophobic or omniphobic coatings. Our study introduced a versatile strategy to functionalize biocompatible surfaces for food containers which reduced the contamination of residues and the use of detergents, and may be beneficial to human and environmental health.