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

Zhou, Guobing; Chen, M.; Ju, Chelsea J.‐T.; Jiang, Jiaxi; Wang, Z.; Wang, W.

doi:10.1101/2019.12.15.876953

Cited by 5 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mutations in proteins can affect protein conformation, folding, and stability, and can eventually influence protein–protein interactions and protein thermodynamics [ 60 ]. There are several observed mutations in the RBD of SARS-CoV-2 S glycoprotein that improve its infectivity and strengthen the viral binding interaction to ACE2 receptor [ 27 ].…”

Section: Discussionmentioning

confidence: 99%

Mutations of SARS-CoV-2 RBD May Alter Its Molecular Structure to Improve Its Infection Efficiency

Alaofi

Shahid

2021

Biomolecules

View full text Add to dashboard Cite

The receptor-binding domain (RBD) of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) mediates the viral–host interaction and is a target for most neutralizing antibodies. Nevertheless, SARS-CoV-2 RBD mutations pose a threat due to their role in host cell entry via the human angiotensin-converting enzyme 2 receptor that might strengthen SARS-CoV-2 infectivity, viral load, or resistance against neutralizing antibodies. To understand the molecular structural link between RBD mutations and infectivity, the top five mutant RBDs (i.e., N501Y, E484K L452R, S477N, and N439K) were selected based on their recorded case numbers. These mutants along with wild-type (WT) RBD were studied through all-atom molecular dynamics (MD) simulations of 100 ns. The principal component analysis and the free energy landscape were used too. Interestingly, N501Y, N439K, and E484K mutations were observed to increase the rigidity in some RBD regions while increasing the flexibility of the receptor-binding motif (RBM) region, suggesting a compensation of the entropy penalty. However, S477N and L452R RBDs were observed to increase the flexibility of the RBM region while maintaining similar flexibility in other RBD regions in comparison to WT RBD. Therefore, both mutations (especially S477N) might destabilize the RBD structure, as loose conformation compactness was observed. The destabilizing effect of S477N RBD was consistent with previous work on S477N mutation. Finally, the free energy landscape results showed that mutations changed WT RBD conformation while local minima were maintained for all mutant RBDs. In conclusion, RBD mutations definitely impact the WT RBD structure and conformation as well as increase the binding affinity to angiotensin-converting enzyme receptor.

show abstract

Section: Discussionmentioning

confidence: 99%

Mutations of SARS-CoV-2 RBD May Alter Its Molecular Structure to Improve Its Infection Efficiency

Alaofi

Shahid

2021

Biomolecules

View full text Add to dashboard Cite

show abstract

“…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.…”

Section: Resultsmentioning

confidence: 99%

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

Zhang

Chen

Bui

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Electronic health records (EHRs) contain both ordered and unordered chronologies of clinical events that occur during a patient encounter. However, during data preprocessing steps, many predictive models impose a predefined order on unordered clinical events sets (e.g., alphabetical, natural order from the chart, etc.), which is potentially incompatible with the temporal nature of the sequence and predictive task. To address this issue, we proposeDPSS, which seeks to capture each patient's clinical event records as sequences of event sets. Foreach clinical event set, we assume that the predictive model should be invariant to the order of concurrent events and thus employ a novel permutation sampling mechanism. This paper evaluates the use of this permuted sampling method given different data-driven models for predicting a heart failure (HF) diagnosis in sub-sequent patient visits. Experimental results using the MIMIC-III dataset show that the permutation sampling mechanism offers improved discriminative power based on the area under the receiver operating curve (AUROC) and precision-recall curve (pr-AUC) metrics as HF diagnosis prediction becomes more robust to different data ordering schemes.

show abstract

“…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-the-art performance on different datasets.…”

Section: Discussionmentioning

confidence: 99%

EpitopeVec: Linear Epitope Prediction Using Deep Protein Sequence Embeddings

Bahai

Asgari²,

Mofrad

et al. 2020

Preprint

View full text Add to dashboard Cite

MotivationB-cell epitopes (BCEs) play a pivotal role in the development of peptide vaccines, immunodiagnostic reagents, and antibody production, and thus generally in infectious disease prevention and diagnosis. Experimental methods used to determine BCEs are costly and time-consuming. It thus becomes essential to develop computational methods for the rapid identification of BCEs. Though several computational methods have been developed for this task, cross-testing of classifiers trained and tested on different datasets revealed their limitations, with accuracies of 51 to 53%.ResultsWe describe a new method called EpitopeVec, which utilizes residue properties, modified antigenicity scales, and a Protvec representation of peptides for linear BCE prediction with machine learning techniques. Evaluating on several large and small data sets, as well as cross-testing demonstrated an improvement of the state-of-the-art performances in terms of accuracy and AUC. Predictive performance depended on the type of antigen (viral, bacterial, eukaryote, etc.). In view of that, we also trained our method on a large viral dataset to create a linear viral BCE predictor.AvailablityThe software is available at https://github.com/hzi-bifo/epitope-prediction under the GPL3.0 license.Contactalice.mchardy@helmholtz-hzi.deSupplementary informationSupplementary data are available at Bioinformatics online.

show abstract

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

Cited by 5 publications

References 47 publications

Mutations of SARS-CoV-2 RBD May Alter Its Molecular Structure to Improve Its Infection Efficiency

Mutations of SARS-CoV-2 RBD May Alter Its Molecular Structure to Improve Its Infection Efficiency

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

EpitopeVec: Linear Epitope Prediction Using Deep Protein Sequence Embeddings

Contact Info

Product

Resources

About