To Improve Protein Sequence Profile Prediction through Image Captioning on Pairwise Residue Distance Map

By Sheng Chen, Zhe Sun, Zifeng Liu, Xun Liu, Y. Chong, Yutong Lu, Huiying Zhao, Yuedong Yang. 2019

61 citations recorded by the source corpus.

Protein sequence profile prediction aims to generate multiple sequences from structural information to advance the protein design. Protein sequence profile can be computationally predicted by energy-based method or fragment-based methods. By integrating these methods with neural networks, our previous method, SPIN2 has achieved a sequence recovery rate of 34%. However, SPIN2 employed only one dimensional (1D) structural properties that are not sufficient to represent 3D structures. In this study, we represented 3D structures by 2D maps of pairwise residue distances. and developed a new method (SPROF) to predict protein sequence profile based on an image captioning learning frame. To our best knowledge, this is the first method to employ 2D distance map for predicting protein properties. SPROF achieved 39.8% in sequence recovery of residues on the independent test set, representing a 5.2% improvement over SPIN2. We also found the sequence recovery increased with the number of their neighbored residues in 3D structural space, indicating that our method can effectively learn long range information from the 2D distance map. Thus, such network architecture using 2D distance map is expected to be useful for other 3D structure-based applications, such as binding site prediction, protein function prediction, and protein interaction prediction.

Subfields: Computer Vision and Pattern Recognition, Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

Learning inverse folding from millions of predicted structures (2022, methodology): “More recently, convolution-based deep learning methods have also been applied to predict amino acid propensities given the surrounding local structural environments (Anand-Achim et al., 2021; Boomsma & Frellsen, 2017; Shroff et al., 2020; Li et al., 2020; Qi & Zhang, 2020; Zhang et al., 2020; Chen e”
Learning from Protein Structure with Geometric Vector Perceptrons (2020, neutral): “Recovery % GVP-GNN 44.9 DenseCPD (Qi & Zhang, 2020) 50.7 ProDCoNN (Zhang et al., 2019) 40.7 SBROF (Chen et al., 2019) 39.2 SPIN2 (O’Connell et al., 2018) 33.6 Wang’s model (Wang et al., 2018) 33.0 ProteinSolver (Strokach et al., 2020) 30.8 SPIN (Li et al., 2014) 30.3 Rosetta 30.0”
Generative Models for Graph-Based Protein Design (2019, background): “Recently [8, 9, 14] proposed neural network-based models for sequences given 3D structure, where the amino acids are modeled independently of one another.”
AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB (2022, methodology): “The 2D CNN-based SPROF (Chen et al., 2019) extracts structural features from the distance matrix, and improves the accuracy to 39.8%.”