Mutation effect estimation on protein–protein interactions using deep contextualized representation learning

Abstract

The functional impact of protein mutations is reflected on the alteration of conformation and thermodynamics of protein–protein interactions (PPIs). Quantifying the changes of two interacting proteins upon mutations is commonly carried out by computational approaches. Hence, extensive research efforts have been put to the extraction of energetic or structural features on proteins, followed by statistical learning methods to estimate the effects of mutations on PPI properties. Nonetheless, such features require extensive human labors and expert knowledge to obtain, and have limited abilities to reflect point mutations. We present an end-to-end deep learning framework, MuPIPR (Mutation Effects in Protein–protein Interaction PRediction Using Contextualized Representations), to estimate the effects of mutations on PPIs. MuPIPR incorporates a contextualized representation mechanism of amino acids to propagate the effects of a point mutation to surrounding amino acid representations, therefore amplifying the subtle change in a long protein sequence. On top of that, MuPIPR leverages a Siamese residual recurrent convolutional neural encoder to encode a wild-type protein pair and its mutation pair. Multi-layer perceptron regressors are applied to the protein pair representations to predict the quantifiable changes of PPI properties upon mutations. Experimental evaluations show that, with only sequence information, MuPIPR outperforms various state-of-the-art systems on estimating the changes of binding affinity for SKEMPI v1, and offers comparable performance on SKEMPI v2. Meanwhile, MuPIPR also demonstrates state-of-the-art performance on estimating the changes of buried surface areas. The software implementation is available at https://github.com/guangyu-zhou/MuPIPR.

Comparative molecular dynamics study of the receptor-binding domains in SARS-CoV-2 and SARS-CoV and the effects of mutations on the binding affinity

“…Investigating the effects of sequence variations in SARS‐CoV‐2 RBD is essential for the understanding of pathogenesis and the development of safe and effective prevention and treatment strategies for COVID-19, as through viral detection, vaccine design, and development of drugs (Zhou et al., 2020 ). One such study, gaining an insight into the basic aspects of thermodynamics and pharmacodynamics of the interaction between wild-type and mutated SARS‐CoV‐2 RBDs and its receptor in the host cell has been undertaken here.…”

“…In general, investigating the impact of mutations, particularly on the conformation of the interacting proteins, is essential because mutations in proteins can have a dramatic effect on the protein folding and stability. Also, mutations alter the kinetics and thermodynamics of protein-protein interactions (Zhou et al., 2020 ), and these mutations can be either selectively beneficial to the organism via evolution or straightforwardly detrimental (Jubb et al., 2017 ). Therefore, the study of the effect of mutations is essential for different biomedical applications, including personalized medicine stemming from disease-associated mutation analyses or highly specific drug design and remedial interventions.…”

Diagnostic Prediction with Sequence-of-sets Representation Learning for Clinical Events

“…For future work, we plan to extend DPSS to jointly model lab event sequences with medication and demographic information. We also seek to better support multi-disease prediction by incorporating structured label representations [14] and leveraging pre-training [34] to improve domain adaptation of DPSS.…”

EpitopeVec: Linear Epitope Prediction Using Deep Protein Sequence Embeddings

“…However, in our implementation, we proposed the scale's negative logarithm before normalization, improving its discriminative power. Sequence-based embeddings have been used successfully in protein functional/structural annotations tasks previously such as secondary structure prediction (Li and Yu, 2016;Asgari et al, 2019a), point mutations (Zhou et al, 2020), protein function prediction (Asgari and Mofrad, 2015;Zhou et al, 2019;Bonetta and Valentino, 2020), and predicting structural motifs (Liu et al, 2018). In this paper, we proposed the use of ProtVec embeddings and k-mers for linear BCE prediction improving state-of-theart performance on different datasets.…”