DeepTrio: a ternary prediction system for protein–protein interaction using mask multiple parallel convolutional neural networks

Hu, Xiaotian; Feng, Cong; Zhou, Yincong; Harrison, Andrew; Chen, Ming

doi:10.1093/bioinformatics/btab737

Cited by 41 publications

(47 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent investigations have shown that many researchers use a convolutional network or graph convolutional neural network [ 50 ] combined with the 3D structure information of proteins to solve the problem of PPI prediction [ 51 ]. In the model evaluation, these methods have achieved good results.…”

Section: Resultsmentioning

confidence: 99%

SIPGCN: A Novel Deep Learning Model for Predicting Self-Interacting Proteins from Sequence Information Using Graph Convolutional Networks

Wang

Wong

et al. 2022

Biomedicines

View full text Add to dashboard Cite

Protein is the basic organic substance that constitutes the cell and is the material condition for the life activity and the guarantee of the biological function activity. Elucidating the interactions and functions of proteins is a central task in exploring the mysteries of life. As an important protein interaction, self-interacting protein (SIP) has a critical role. The fast growth of high-throughput experimental techniques among biomolecules has led to a massive influx of available SIP data. How to conduct scientific research using the massive amount of SIP data has become a new challenge that is being faced in related research fields such as biology and medicine. In this work, we design an SIP prediction method SIPGCN using a deep learning graph convolutional network (GCN) based on protein sequences. First, protein sequences are characterized using a position-specific scoring matrix, which is able to describe the biological evolutionary message, then their hidden features are extracted by the deep learning method GCN, and, finally, the random forest is utilized to predict whether there are interrelationships between proteins. In the cross-validation experiment, SIPGCN achieved 93.65% accuracy and 99.64% specificity in the human data set. SIPGCN achieved 90.69% and 99.08% of these two indicators in the yeast data set, respectively. Compared with other feature models and previous methods, SIPGCN showed excellent results. These outcomes suggest that SIPGCN may be a suitable instrument for predicting SIP and may be a reliable candidate for future wet experiments.

show abstract

Section: Resultsmentioning

confidence: 99%

SIPGCN: A Novel Deep Learning Model for Predicting Self-Interacting Proteins from Sequence Information Using Graph Convolutional Networks

Wang

Wong

et al. 2022

Biomedicines

View full text Add to dashboard Cite

show abstract

“…The protein representations are generated by retrieving the amino acid embeddings according to the indices provided by input sequences. NXTfusion [68] and DeepTrio [40] use this method to learn the protein representations for model input.…”

Section: Deep Learning Methodologymentioning

confidence: 99%

“…It is better for PPI prediction models to ensure a consistent prediction from arbitrarily ordered inputs(the featurization should be symmetric). Based on the above principle, the Siamese architecture [33] , [34] , [40] is usually employed, which contains two identical submodules sharing the same configuration and weights. In this section, we mainly describe the learning architectures adopted in the recently proposed deep learning methods for PPI prediction.…”

Section: Deep Learning Methodologymentioning

confidence: 99%

“…To avoid the overestimation caused by the highly homologous sequences, a nonredundant subset is built by commonly removing the proteins with an identity threshold of 40% [33] , [34] , [35] using the CD-HIT [38] , [39] software. Additionally, proteins with fewer than 50 amino acid residues are also removed in some studies [34] , [35] , [40] .…”

Section: Preliminarymentioning

confidence: 99%

“…This negative data construction method is based on the expected sparsity of the protein interactome. Another negative data construction method is to shuffle the protein sequences [21] , [40] . It has been proven that the possibility of the interaction can be deemed negligible if one sequence of a pair of interacting proteins is shuffled [44] .…”

Section: Preliminarymentioning

confidence: 99%

See 2 more Smart Citations

Deep learning frameworks for protein–protein interaction prediction

Feng²,

Ling³

et al. 2022

Computational and Structural Biotechnology Journal

Self Cite

View full text Add to dashboard Cite

Prediction of interactions between cell surface proteins by machine learning

Su,

Griffin,

Emmons

et al. 2023

Proteins

View full text Add to dashboard Cite

Cells detect changes in their external environments or communicate with each other through proteins on their surfaces. These cell surface proteins form a complicated network of interactions in order to fulfill their functions. The interactions between cell surface proteins are highly dynamic and, thus, challenging to detect using traditional experimental techniques. Here, we tackle this challenge using a computational framework. The primary focus of the framework is to develop new tools to identify interactions between domains in the immunoglobulin (Ig) fold, which is the most abundant domain family in cell surface proteins. These interactions could be formed between ligands and receptors from different cells or between proteins on the same cell surface. In practice, we collected all structural data on Ig domain interactions and transformed them into an interface fragment pair library. A high‐dimensional profile can then be constructed from the library for a given pair of query protein sequences. Multiple machine learning models were used to read this profile so that the probability of interaction between the query proteins could be predicted. We tested our models on an experimentally derived dataset that contains 564 cell surface proteins in humans. The cross‐validation results show that we can achieve higher than 70% accuracy in identifying the PPIs within this dataset. We then applied this method to a group of 46 cell surface proteins in Caenorhabditis elegans. We screened every possible interaction between these proteins. Many interactions recognized by our machine learning classifiers have been experimentally confirmed in the literature. In conclusion, our computational platform serves as a useful tool to help identify potential new interactions between cell surface proteins in addition to current state‐of‐the‐art experimental techniques. The tool is freely accessible for use by the scientific community. Moreover, the general framework of the machine learning classification can also be extended to study the interactions of proteins in other domain superfamilies.

show abstract

DeepTrio: a ternary prediction system for protein–protein interaction using mask multiple parallel convolutional neural networks

Cited by 41 publications

References 41 publications

SIPGCN: A Novel Deep Learning Model for Predicting Self-Interacting Proteins from Sequence Information Using Graph Convolutional Networks

SIPGCN: A Novel Deep Learning Model for Predicting Self-Interacting Proteins from Sequence Information Using Graph Convolutional Networks

Deep learning frameworks for protein–protein interaction prediction

Prediction of interactions between cell surface proteins by machine learning

Contact Info

Product

Resources

About