A novel model for improving the prediction accuracy of the new heating station

In recent years, many computational models have been designed to detect essential proteins based on protein-protein interaction (PPI) networks. However, due to the incompleteness of PPI networks, the prediction accuracy of these models is still not satisfactory. In this manuscript, a novel key target convergence sets based prediction model (KTCSPM) is proposed to identify essential proteins. In KTCSPM, a weighted PPI network and a weighted (Domain-Domain Interaction) network are constructed first based on known PPIs and PDIs downloaded from benchmark databases. And then, by integrating these two kinds of networks, a novel weighted PDI network is built. Next, through assigning a unique key target convergence set (KTCS) for each node in the weighted PDI network, an improved method based on the random walk with restart is designed to identify essential proteins. Finally, in order to evaluate the predictive effects of KTCSPM, it is compared with 12 competitive state-of-the-art models, and experimental results show that KTCSPM can achieve better prediction accuracy. Considering the satisfactory predictive performance achieved by KTCSPM, it indicates that KTCSPM might be a good supplement to the future research on prediction of essential proteins.

Download Full-text

Prediction of Four Kinds of Simple Supersecondary Structures in Protein by Using Chemical Shifts

The Scientific World JOURNAL ◽

10.1155/2014/978503 ◽

2014 ◽

Vol 2014 ◽

pp. 1-5 ◽

Cited By ~ 1

Author(s):

Feng Yonge

Keyword(s):

Nuclear Magnetic Resonance ◽

Amino Acid ◽

Prediction Accuracy ◽

Cross Validation ◽

Chemical Shifts ◽

Amino Acid Sequences ◽

Quadratic Discriminant Analysis ◽

Combined Use ◽

Accuracy Of Prediction ◽

Novel Model

Knowledge of supersecondary structures can provide important information about its spatial structure of protein. Some approaches have been developed for the prediction of protein supersecondary structure. However, the feature used by these approaches is primarily based on amino acid sequences. In this study, a novel model is presented to predict protein supersecondary structure by use of chemical shifts (CSs) information derived from nuclear magnetic resonance (NMR) spectroscopy. Using these CSs as inputs of the method of quadratic discriminant analysis (QD), we achieve the overall prediction accuracy of 77.3%, which is competitive with the same method for predicting supersecondary structures from amino acid compositions in threefold cross-validation. Moreover, our finding suggests that the combined use of different chemical shifts will influence the accuracy of prediction.

Download Full-text

Incorporating Synonym for Lexical Sememe Prediction: An Attention-Based Model

Applied Sciences ◽

10.3390/app10175996 ◽

2020 ◽

Vol 10 (17) ◽

pp. 5996

Author(s):

Xiaojun Kang ◽

Bing Li ◽

Hong Yao ◽

Qingzhong Liang ◽

Shengwen Li ◽

...

Keyword(s):

Natural Language Processing ◽

Language Processing ◽

Prediction Accuracy ◽

Word Embedding ◽

Commonsense Knowledge ◽

Proposed Model ◽

Series Of Experiments ◽

And Performance ◽

Novel Model

Sememe is the smallest semantic unit for describing real-world concepts, which improves the interpretability and performance of Natural Language Processing (NLP). To maintain the accuracy of the sememe description, its knowledge base needs to be continuously updated, which is time-consuming and labor-intensive. Sememes predictions can assign sememes to unlabeled words and are valuable work for automatically building and/or updating sememeknowledge bases (KBs). Existing methods are overdependent on the quality of the word embedding vectors, it remains a challenge for accurate sememe prediction. To address this problem, this study proposes a novel model to improve the performance of sememe prediction by introducing synonyms. The model scores candidate sememes from synonyms by combining distances of words in embedding vector space and derives an attention-based strategy to dynamically balance two kinds of knowledge from synonymous word set and word embedding vector. A series of experiments are performed, and the results show that the proposed model has made a significant improvement in the sememe prediction accuracy. The model provides a methodological reference for commonsense KB updating and embedding of commonsense knowledge.

Download Full-text