Search

DNA-binding proteins play a vital role in cellular processes. It is an extremely urgent to develop a high-throughput method for efficiently identifying DNA-binding proteins. According to the current research situation, some methods in machine learning and deep learning show excellent computational speed and accuracy, which are worthy of application. In this work, a novel predictor was proposed to predict DNA binding proteins called UMAP-DBP. Firstly, the feature extraction of primary protein sequence was realized based on physicochemical distance transformation, Profile-based auto-cross covariance and General series correlation pseudo amino acid composition. Secondly, uniform manifold approximation and projection (UMAP) and feature importance score methods were used for feature selection; there is a progressive relationship between them. Finally, the Adaboost operation engine with jackknife test were adopted for predicting DNA-binding proteins. For the jackknife test on the BP1075 and BP594, we obtained an overall accuracy of 82.97% and 82.14%, Cohen's kappa (CK) of 0.66 and 0.64, respectively. The results illustrate that a feasible method has been developed for predicting DNA-binding proteins by UMAP and Adaboost. This is the first study in which UMAP has been successfully applied to identify DNA-binding proteins. All the datasets and codes are accessible at https://github.com/Wang-Jinyue/UMAP-DBP. [ABSTRACT FROM AUTHOR]

The IEEE 802.11ax standard defined a set of new specifications to improve spectrum efficiency, power efficiency, and reliability of future wireless local area networks (WLANs). Among these specifications, the uplink multi-user multiple-input, multiple-output (MU-MIMO) remedies the uplink shortcomings of existing WLANs and enables high-efficiency uplink transmissions. This paper considers the problem of adaptive modulation and coding (AMC) for uplink MU-single-input, multiple-output (MU-SIMO) in the upcoming WLANs. Our target is to select the appropriate modulation and coding scheme (MCS) for the existing users so as to maximize the throughput and at the same time guarantee that all users can satisfy a frame error constraint. We adopt a deep learning approach to tackle this problem. We propose to let the access point (AP) leverage the estimated channel state information (CSI) of all users along with the estimated noise standard deviation as the input features to a deep convolutional neural network (DCNN) that is trained to perform AMC. Simulation results reveal that the proposed DCNN for the uplink MU-SIMO AMC outperforms rival machine learning techniques such as fully-connected deep neural network (DNN), k-nearest neighbors (KNN), support vector machines (SVM), Gaussian Naive Bayes (GNB), and random forest (RF) in terms of the throughput and the frame error rate (FER). [ABSTRACT FROM AUTHOR]