Reciprocal Perspective for Improved Protein-Protein Interaction Prediction

Dick, Kevin; Green, James R.

doi:10.1038/s41598-018-30044-1

Cited by 26 publications

(34 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Incorporating the original landscape generation complexity, O L , we determine that the modified landscape generation complexity, ′ O L , is: Hence, we confirm the assertions from (14) and (16). Since φ +  m n, generally, the new landscape generation algorithm is expected to be considerably faster at a rate proportional to the size of the proteomes of the organisms involved in the PPI prediction schema.…”

Section: Pipe a B A B A Bsupporting

confidence: 58%

“…Finally, high-throughput predictors have enabled the prediction of the comprehensive set of all possible interactions that has given rise to context: the ability to appraise a given PPI prediction relative to all possible interactions. Applying the Reciprocal Perspective for PPI (RP-PPI) cascaded machine learning layer to these data has led to significantly improved predictive performance in the face of extreme class imbalance 16 . As a meta-method applicable to any PPI predictor, here we looked to additionally validate RP-PPI for use in cross-species prediction schemas.…”

Section: Increasing Scale and Complexity Of Prediction Schemasmentioning

confidence: 99%

“…See section "Comparison to the Reciprocal perspective. The RP-PPI meta-method, as described in 16 , is a cascaded machine learning layer which leverages context-based features to improve the classification performance of PPI predictors. We applied it to each of the interactomes generated in this work.…”

Section: Evolutionary Distance Relation To Classification Performancementioning

confidence: 99%

See 2 more Smart Citations

PIPE4: Fast PPI Predictor for Comprehensive Inter- and Cross-Species Interactomes

Dick

Samanfar

Barnes

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

The need for larger-scale and increasingly complex protein-protein interaction (PPI) prediction tasks demands that state-of-the-art predictors be highly efficient and adapted to inter-and cross-species predictions. Furthermore, the ability to generate comprehensive interactomes has enabled the appraisal of each PPI in the context of all predictions leading to further improvements in classification performance in the face of extreme class imbalance using the Reciprocal Perspective (RP) framework. We here describe the PIPE4 algorithm. Adaptation of the PIPE3/MP-PIPE sequence preprocessing step led to upwards of 50x speedup and the new Similarity Weighted Score appropriately normalizes for window frequency when applied to any inter-and cross-species prediction schemas. Comprehensive interactomes for three prediction schemas are generated: (1) cross-species predictions, where Arabidopsis thaliana is used as a proxy to predict the comprehensive Glycine max interactome, (2) interspecies predictions between Homo sapiens-HIV1, and (3) a combined schema involving both cross-and inter-species predictions, where both Arabidopsis thaliana and Caenorhabditis elegans are used as proxy species to predict the interactome between Glycine max (the soybean legume) and Heterodera glycines (the soybean cyst nematode). Comparing PIPE4 with the state-of-the-art resulted in improved performance, indicative that it should be the method of choice for complex PPI prediction schemas. The elucidation of protein-protein interaction (PPI) networks is central to molecular biology research. Necessary to producing mechanistic models of cellular processes, PPI networks additionally contribute to challenges such as the prediction of gene function 1-3 , identification of disease genes 4 , and pharmaceutical discovery 5,6. Computational PPI prediction techniques have been developed to supplement and guide wet-laboratory experimental work. The last decade has seen increased computational demand in both scale and complexity of PPI predictors. Predicting comprehensive interactomes (the set of all possible pairwise PPIs in or between proteomes) has only recently become possible with the advent of high-performance computing infrastructure and algorithmic optimizations. While methodologically diverse in their implementation, PPI prediction tools generally exploit information from the set of known PPIs (previously confirmed using classical wet-laboratory techniques) to determine whether any two query proteins will physically interact. The utility and scalability of any one method is subject to the information it leverages. Structure-based methods, at one extreme, require the three-dimensional (3D) characterization of each protein and therefore suffer from low coverage of the proteome. While useful to determining highly specific PPI networks, many methods require template-based modelling which tend to be computationally taxing 7-9. Furthermore, even with complete 3D structural information of each protein in an organism's proteome, the computational time comp...

show abstract

Section: Pipe a B A B A Bsupporting

confidence: 58%

Section: Increasing Scale and Complexity Of Prediction Schemasmentioning

confidence: 99%

Section: Evolutionary Distance Relation To Classification Performancementioning

confidence: 99%

See 1 more Smart Citation

PIPE4: Fast PPI Predictor for Comprehensive Inter- and Cross-Species Interactomes

Dick

Samanfar

Barnes

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, these similarity measures in Table 1 are directly used as indices of link prediction. There are different reasons for the selection of their similarity measure, respectively, such as Preferential Attachment (Barabâsi et al, 2002), Resource Allocation , and Reciprocal Relationship (Dick and Green, 2018), etc. The index we are going to propose is still network-based, but there are two differences between our method and the previous ones in Table 1:…”

Section: Why Jaccard Similarity?mentioning

confidence: 99%

Protein Interface Complementarity and Gene Duplication Improve Link Prediction of Protein-Protein Interaction Network

et al. 2020

View full text Add to dashboard Cite

Protein-protein interactions are the foundations of cellular life activities. At present, the already known protein-protein interactions only account for a small part of the total. With the development of experimental and computing technology, more and more PPI data are mined, PPI networks are more and more dense. It is possible to predict protein-protein interaction from the perspective of network structure. Although there are many high-throughput experimental methods to detect protein-protein interactions, the cost of experiments is high, time-consuming, and there is a certain error rate meanwhile. Network-based approaches can provide candidates of protein pairs for high-throughput experiments and improve the accuracy rate. This paper presents a new link prediction approach "Sim" for PPI networks from the perspectives of proteins' complementary interfaces and gene duplication. By integrating our approach "Sim" with the state-of-art network-based approach "L3," the prediction accuracy and robustness are improved.

show abstract

“…These one-to-all score curves are based on the underlying assumption that we expect true SARS-CoV-2 vs. human PPIs to be rare, such that the vast majority of prediction scores should fall below the decision threshold. Furthermore, by also plotting the one-to-all curves for each human protein, we can apply the same local decision logic to the reciprocal perspective (while not performed here, this analysis forms the basis of the Reciprocal Perspective method) [16].…”

Section: Determining An Appropriate Per-protein Decision Thresholdmentioning

confidence: 99%

Computational Prediction of the Comprehensive SARS-CoV-2 vs. Human Interactome to Guide the Design of Therapeutics

Dick

Green

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Understanding the disease pathogenesis of the novel coronavirus, denoted SARS-CoV-2, is critical to the development of anti-SARS-CoV-2 therapeutics. The global propagation of the viral disease, denoted COVID-19 ("coronavirus disease 2019"), has unified the scientific community in searching for possible inhibitory small molecules or polypeptides. Given the known interaction between the human ACE2 ("Angiotensin-converting enzyme 2") protein and the SARS-CoV virus (responsible for the coronavirus outbreak circa. 2003), considerable focus has been directed towards the putative interaction between the SARS-CoV-2 Spike protein and ACE2. However, a more holistic understanding of the SARS-CoV-2 vs. human inter-species interactome promises additional putative protein-protein interactions (PPI) that may be considered targets for the development of inhibitory therapeutics.To that end, we leverage two state-of-the-art, sequence-based PPI predictors (PIPE4 & SPRINT) capable of generating the comprehensive SARS-CoV-2 vs. human interactome, comprising approximately 285,000 pairwise predictions. Of these, we identify the high-scoring subset of human proteins predicted to interact with each of the 14 SARS-CoV-2 proteins by both methods, comprising 279 highconfidence putative interactions involving 225 human proteins. Notably, the Spike-ACE2 interaction was the highest ranked for both the PIPE4 and SPRINT predictors, corroborating existing evidence for this PPI. Furthermore, the PIPE-Sites algorithm was used to predict the putative subsequence that might mediate each interaction and thereby inform the design of inhibitory polypeptides intended to disrupt the corresponding host-pathogen interactions.We hereby publicly release the comprehensive set of PPI predictions and their corresponding PIPE-Sites landscapes in the following DataVerse repository: 10.5683/SP2/JZ77XA. All data and metadata are released under a CC-BY 4.0 licence. The information provided represents theoretical modeling only and caution should be exercised in its use. It is intended as a resource for the scientific community at large in furthering our understanding of SARS-CoV-2. : bioRxiv preprint Promisingly, many computational approaches have been rapidly deployed to increase our understanding of SARS-CoV-2, including protein function, three-dimensional (3D) protein structures, and possible target regions for small inhibitory molecules [2,3]. Through the use of publication preprint platforms, this information can be immediately disseminated, albeit, with the disclaimer of "non-peer-reviewed" research. Two notable examples include the use of DeepMind's recently published AplhaFold protein structure predictor [2] to predict the 3D protein structure of each of the SARS-CoV-2 proteins, and the use of the SUMMIT high-performance computing (HPC) infrastructure to perform large-scale virtual docking simulations as a form of high-throughput screening to identify small inhibitory molecules [3]. Given that the Spike protein from the original SARS coronavirus, SARS-CoV, is ...

show abstract

Reciprocal Perspective for Improved Protein-Protein Interaction Prediction

Cited by 26 publications

References 42 publications

PIPE4: Fast PPI Predictor for Comprehensive Inter- and Cross-Species Interactomes

PIPE4: Fast PPI Predictor for Comprehensive Inter- and Cross-Species Interactomes

Protein Interface Complementarity and Gene Duplication Improve Link Prediction of Protein-Protein Interaction Network

Computational Prediction of the Comprehensive SARS-CoV-2 vs. Human Interactome to Guide the Design of Therapeutics

Contact Info

Product

Resources

About