Machine-learning techniques for the prediction of protein–protein interactions

Sarkar, Debasree; Saha, Sudipto

doi:10.1007/s12038-019-9909-z

Cited by 65 publications

(44 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To this end, a support vector machine (SVM) based machine learning (ML) approach was used to differentiate and classify samples based on their antibody response to three target antigens (S1, S1S2, and Nuc). ML approaches have been used extensively for classification and diagnosis when data from multiple biomarkers or targets is available ( Sarkar and Saha, 2019 ; Uddin et al, 2019 ). SVM software (LibSVM) ( Chang and Lin, 2011 ) was trained using GC-FP data from serum samples ( Table 1 ).…”

Section: Resultsmentioning

confidence: 99%

Multiplexed detection and quantification of human antibody response to COVID-19 infection using a plasmon enhanced biosensor platform

Cady

Tokranova

Minor

et al. 2021

Biosensors and Bioelectronics

View full text Add to dashboard Cite

The 2019 SARS CoV-2 (COVID-19) pandemic has illustrated the need for rapid and accurate diagnostic tests. In this work, a multiplexed grating-coupled fluorescent plasmonics (GC-FP) biosensor platform was used to rapidly and accurately measure antibodies against COVID-19 in human blood serum and dried blood spot samples. The GC-FP platform measures antibody-antigen binding interactions for multiple targets in a single sample, and has 100% selectivity and sensitivity (n = 23) when measuring serum IgG levels against three COVID-19 antigens (spike S1, spike S1S2, and the nucleocapsid protein). The GC-FP platform yielded a quantitative, linear response for serum samples diluted to as low as 1:1600 dilution. Test results were highly correlated with two commercial COVID-19 antibody tests, including an enzyme linked immunosorbent assay (ELISA) and a Luminex-based microsphere immunoassay. To demonstrate test efficacy with other sample matrices, dried blood spot samples (n = 63) were obtained and evaluated with GC-FP, yielding 100% selectivity and 86.7% sensitivity for diagnosing prior COVID-19 infection. The test was also evaluated for detection of multiple immunoglobulin isotypes, with successful detection of IgM, IgG and IgA antibody-antigen interactions. Last, a machine learning approach was developed to accurately score patient samples for prior COVID-19 infection, using antibody binding data for all three COVID-19 antigens used in the test.

show abstract

Section: Resultsmentioning

confidence: 99%

Multiplexed detection and quantification of human antibody response to COVID-19 infection using a plasmon enhanced biosensor platform

Cady

Tokranova

Minor

et al. 2021

Biosensors and Bioelectronics

View full text Add to dashboard Cite

show abstract

“…These include the use of statistical and contact potentials [7][8][9][10] , design of novel sampling schemes, 11,12 generation of weighted energy or score functions, [13][14][15][16] and employment of supervised machine learning techniques. [17][18][19][20][21] Additionally, within the Rosetta Modelling Suite, new sampling schemes, designed to mimic protein motions observed in solution, have afforded increased predictive accuracy. 11,22 Though these methods have shown some notable success, there is still a need for a single, generalizable, and facile approach capable of accurately predicting ΔΔG's of mutations at protein/protein interfaces.…”

mentioning

confidence: 99%

Rosetta Custom Score Functions Accurately Predict ΔΔG of Mutations at Protein-Protein Interfaces Using Machine Learning

Shringari

Giannakoulias

Ferrie

et al. 2020

Preprint

View full text Add to dashboard Cite

Protein-protein interfaces play essential roles in a variety of biological processes and many therapeutic molecules are targeted at these interfaces. However, accurate predictions of the effects of interfacial mutations to identify "hotspots" have remained elusive despite the myriad of modeling and machine learning methods tested. Here, for the first time, we demonstrate that nonlinear reweighting of energy terms from Rosetta, through the use of machine learning, exhibits improved predictability of ΔΔG values associated with interfacial mutations.

show abstract

“…The main hypothesis of this method is that two interacting proteins may co-express under specific phenotypes. Proteins with high similar expression patterns might interact as the co-expressed genes or proteins tend to be involved in the same pathways and biological processes (Wolfe et al 2005 (Sarkar & Saha 2019). The selection of ML-based method depends on the input protein features, and the accuracies of the predicted PPIs were higher when more than one feature was included into the analysis (Tahir & Hayat 2017;Chen et al 2019b).…”

Section: Computational Approachesmentioning

confidence: 99%

Protein–protein interaction network: an emerging tool for understanding fish disease in aquaculture

Waiho

Afiqah‐Aleng

Iryani

et al. 2020

Reviews in Aquaculture

View full text Add to dashboard Cite

Protein-protein interactions (PPIs) play integral roles in a wide range of biological processes that regulate the overall growth, development, physiology and disease in living organisms. With the advancement of high-throughput sequencing technologies, increasing numbers of PPI networks are being predicted and annotated, and these contribute greatly towards the understanding of pathogenesis and the discovery of novel drug targets for the treatment of diseases. The use of this tool is gaining popularity in the identification, understanding and treatment of diseases in humans and plants. Due to the importance of aquaculture in tackling the global food crisis by producing cheap and high-quality protein source, the maintenance of the overall health status of aquaculture species is essential. With the increasing omics data on aquaculture species, the PPI network is an emerging tool for fish health maintenance. In this review, we first introduce the concept of PPI network, how they are discovered and their general application. Then, the current status of aquaculture and disease in aquaculture are discussed. The different applications of PPI network in aquaculture fish disease management such as biomarker identification, mechanism prediction, understanding of host-pathogen interaction, understanding of pathogen co-infection interaction, and potential development of vaccines and treatments are subsequently highlighted. It is hoped that this emerging tool-PPI networkwould deepen our understanding of the pathogenesis of various diseases and hasten the prevention and treatment processes in aquaculture species.

show abstract

Machine-learning techniques for the prediction of protein–protein interactions

Cited by 65 publications

References 104 publications

Multiplexed detection and quantification of human antibody response to COVID-19 infection using a plasmon enhanced biosensor platform

Multiplexed detection and quantification of human antibody response to COVID-19 infection using a plasmon enhanced biosensor platform

Rosetta Custom Score Functions Accurately Predict ΔΔG of Mutations at Protein-Protein Interfaces Using Machine Learning

Protein–protein interaction network: an emerging tool for understanding fish disease in aquaculture

Contact Info

Product

Resources

About