1 January 2014 in BioMed Research International
Next-generation sequencing (NGS) technology has rapidly advanced and generated the massive data volumes. To align and map the NGS data, biologists often randomly select a number of aligners without concerning their suitable feature, high performance, and high accuracy as well as sequence variations and polymorphisms existing on reference genome. This study aims to systematically evaluate and compare the capability of multiple aligners for NGS data analysis. To explore this capability, we firstly performed alignment algorithms comparison and classification. We further used long-read and short-read datasets from both real-life andin silicoNGS data for comparative analysis and evaluation of these aligners focusing on three criteria, namely, application-specific alignment feature, computational performance, and alignment accuracy. Our study demonstrated the overall evaluation and comparison of multiple aligners for NGS data analysis. This serves as an important guiding resource for biologists to gain further insight into suitable selection of aligners for specific and broad applications.
11 November 2019 in IEEE Access
The application of reinforcement learning in industrial fields makes the safety problem of the agent a research hotspot. Traditional methods mainly alter the objective function and the exploration process of the agent to address the safety problem. Those methods, however, can hardly prevent the agent from falling into dangerous states because most of the methods ignore the damage caused by unsafe states. As a result, most solutions are not satisfactory. In order to solve the aforementioned problem, we come forward with a safe Q-learning method that is based on constrained Markov decision processes, adding safety constraints as prerequisites to the model, which improves standard Q-learning algorithm so that the proposed algorithm seeks for the optimal solution ensuring that the safety premise is satisfied. During the process of finding the solution in form of the optimal state-action value, the feasible space of the agent is limited to the safe space that guarantees the safety via the feasible space being filtered by constraints added to the action space. Because the traditional solution methods are not applicable to the safe Q-learning model as they tend to obtain local optimal solution, we take advantage of the Lagrange multiplier method to solve the optimal action that can be performed in the current state based on the premise of linearizing constraint functions, which not only improves the efficiency and accuracy of the algorithm, but also guarantees to obtain the global optimal solution. The experiments verify the effectiveness of the algorithm.
30 October 2019 in IEEE Access
5 May 2020 in Frontiers in Bioengineering and Biotechnology
Protein interactions play an essential role in studying living systems and life phenomena. A considerable amount of literature has been published on analyzing and predicting protein interactions, such as support vector machine method, homology-based method and similarity-based method, each has its pros and cons. Most existing methods for predicting protein interactions require prior domain knowledge, making it difficult to effectively extract protein features. Single method is dissatisfactory in predicting protein interactions, declaring the need for a comprehensive method that combines the advantages of various methods. On this basis, a deep ensemble learning method called EnAmDNN (Ensemble Deep Neural Networks with Attention Mechanism) is proposed to predict protein interactions which is an appropriate candidate for comprehensive learning, combining multiple models, and considering the advantages of various methods. Particularly, it encode protein sequences by the local descriptor, auto covariance, conjoint triad, pseudo amino acid composition and combine the vector representation of each protein in the protein interaction network. Then it takes advantage of the multi-layer convolutional neural networks to automatically extract protein features and construct an attention mechanism to analyze deep-seated relationships between proteins. We set up four different structures of deep learning models. In the ensemble learning model, second layer data sets are generated with five-fold cross validation from basic learners, then predict the protein interaction network by combining 16 models. Results on five independent PPI data sets demonstrate that EnAmDNN achieves superior prediction performance than other comparing methods.
1 September 2023 in Cell Reports
Current biochemical approaches have only identified the most well-characterized kinases for a tiny fraction of the phosphoproteome, and the functional assignments of phosphosites are almost negligible. Herein, we analyze the substrate preference catalyzed by a specific kinase and present a novel integrated deep neural network model named FuncPhos-SEQ for functional assignment of human proteome-level phosphosites. FuncPhos-SEQ incorporates phosphosite motif information from a protein sequence using multiple convolutional neural network (CNN) channels and network features from protein-protein interactions (PPIs) using network embedding and deep neural network (DNN) channels. These concatenated features are jointly fed into a heterogeneous feature network to prioritize functional phosphosites. Combined with a series of in vitro and cellular biochemical assays, we confirm that NADK-S48/50 phosphorylation could activate its enzymatic activity. In addition, ERK1/2 are discovered as the primary kinases responsible for NADK-S48/50 phosphorylation. Moreover, FuncPhos-SEQ is developed as an online server.
1 December 2021 in Expert Systems with Applications