Structure-aware protein solubility prediction from sequence through graph convolutional network and predicted contact map

Chen, Jianwen; Zheng, Shuangjia; Zhao, Huiying; Yang, Yuedong

doi:10.1186/s13321-021-00488-1

Cited by 79 publications

(64 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Effective learning of protein structure remains a challenging task, even though 1DCNN [31], 2DCNN [32], 3DCNN [33], GNN and its variants [34,35] have been widely adopted. On the other hand, transformer [36] is well acknowledged as the most powerful neural network in modelling sequential data, such as natural language [37], drug SMILES [38] and protein sequence [39].…”

Section: Introductionmentioning

confidence: 99%

AlphaFold2-aware protein-DNA binding site prediction using graph transformer

Yuan

Chen

Rao

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

MotivationProtein-DNA interactions play crucial roles in the biological systems, and identifying protein-DNA binding sites is the first step for mechanistic understanding of various biological activities (such as transcription and repair) and designing novel drugs. How to accurately identify DNA-binding residues from only protein sequence remains a challenging task. Currently, most existing sequence-based methods only consider contextual features of the sequential neighbors, which are limited to capture spatial information.ResultsBased on the recent breakthrough in protein structure prediction by AlphaFold2, we propose an accurate predictor, GraphSite, for identifying DNA-binding residues based on the structural models predicted by AlphaFold2. Here, we convert the binding site prediction problem into a graph node classification task and employ a transformerbased variant model to take the protein structural information into account. By leveraging predicted protein structures and graph transformer, GraphSite substantially improves over the latest sequence-based and structure-based methods. The algorithm was further confirmed on the independent test set of 196 proteins, where GraphSite surpasses the state-of-the-art structure-based method by 12.3% in AUPR and 9.3% in MCC, respectively.Contactyangyd25@mail.sysu.edu.cn

show abstract

Section: Introductionmentioning

confidence: 99%

AlphaFold2-aware protein-DNA binding site prediction using graph transformer

Yuan

Chen

Rao

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…DM can efficiently represent contacted structural information by residue-pairwise distance matrix, which can be calculated by SPOT-Contact [ 117 ]. DM has been applied for protein profile prediction, such as solubility [ 118 ] and DTI [ 53 ].…”

Section: Model Inputs and Structure Encodingsmentioning

confidence: 99%

Protein–RNA interaction prediction with deep learning: structure matters

Wei

Chen

Zong

et al. 2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

Protein–RNA interactions are of vital importance to a variety of cellular activities. Both experimental and computational techniques have been developed to study the interactions. Because of the limitation of the previous database, especially the lack of protein structure data, most of the existing computational methods rely heavily on the sequence data, with only a small portion of the methods utilizing the structural information. Recently, AlphaFold has revolutionized the entire protein and biology field. Foreseeably, the protein–RNA interaction prediction will also be promoted significantly in the upcoming years. In this work, we give a thorough review of this field, surveying both the binding site and binding preference prediction problems and covering the commonly used datasets, features and models. We also point out the potential challenges and opportunities in this field. This survey summarizes the development of the RNA-binding protein–RNA interaction field in the past and foresees its future development in the post-AlphaFold era.

show abstract

“…Both of these methods work well, but there are still some drawbacks. A lot of end-to-end methods have been presented due to the development of deep learning techniques [ 11 ]. In order to get a better method.…”

Section: Introductionmentioning

confidence: 99%

“…Graph convolutional networks have achieved good results in other fields. Chen et al [ 11 ] presented a new method for structure-aware protein solubility prediction. The method predicts protein solubility by combining GCN with the predicted contact graph, and this method works well.…”

Section: Introductionmentioning

confidence: 99%

Predicting miRNA-disease associations via layer attention graph convolutional network model

Han

Zhu

Liu

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background MiRNA is a class of non-coding single-stranded RNA molecules with a length of approximately 22 nucleotides encoded by endogenous genes, which can regulate the expression of other genes. Therefore, it is very important to predict the associations between miRNA and disease. Predecessors developed a new prediction method of drug-disease association, and it achieved good results. Methods In this paper, we introduced the method of LAGCN to identify potential miRNA-disease associations. First, we integrate three associations into a heterogeneous network, such as the known miRNA-disease association, miRNA-miRNA similarities and disease-disease similarities, next we apply graph convolution network to learn the embedding of miRNA and disease. We use an attention mechanism to combine embedding from multiple convolution layers. Unobserved miRNA-disease associations are scored based on integrated embedding. Results After fivefold cross-validations, the value of AUC is reached 0.9091, which is higher than other prediction methods and baseline methods. Conclusions In this paper, we introduced the method of LAGCN to identify potential miRNA-disease associations. LAGCN has achieved good performance in predicting miRNA-disease associations, and it is superior to other association prediction methods and baseline methods.

show abstract

Structure-aware protein solubility prediction from sequence through graph convolutional network and predicted contact map

Cited by 79 publications

References 49 publications

AlphaFold2-aware protein-DNA binding site prediction using graph transformer

AlphaFold2-aware protein-DNA binding site prediction using graph transformer

Protein–RNA interaction prediction with deep learning: structure matters

Predicting miRNA-disease associations via layer attention graph convolutional network model

Contact Info

Product

Resources

About