Homology-based prediction of interactions between proteins using Averaged One-Dependence Estimators

Murakami, Yoichi; Mizuguchi, Kenji

doi:10.1186/1471-2105-15-213

Cited by 77 publications

(43 citation statements)

References 46 publications

(87 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Besides these machine learning models, some other models have also been adopted for PPIs prediction, including K-Nearest Neighbors [44], Decision Tree [45], Random Forest [46], Homology Detection Approaches [47]. All these models aim to get a better understanding of PPIs inner mechanism.…”

Section: )mentioning

confidence: 99%

Towards Data Analytics of Pathogen-Host Protein-Protein Interaction: A Survey

Chen

Shen

Wang

et al. 2016

2016 IEEE International Congress on Big Data (BigData Congress)

View full text Add to dashboard Cite

Abstract"Big Data" is immersed in many disciplines, including computer vision, economics, online resources, bioinformatics and so on. Increasing researches are conducted on data mining and machine learning for uncovering and predicting related domain knowledge. Protein-protein interaction is one of the main areas in bioinformatics as it is the basis of the biological functions. However, most pathogen-host protein-protein interactions, which would be able to reveal much more infectious mechanisms between pathogen and host, are still up for further investigation. Considering a decent feature representation of pathogen-host proteinprotein interactions (PHPPI), currently there is not a well structured database for research purposes, not even for infection mechanism studies for different species of pathogens. In this paper, we will survey the PHPPI researches and construct a public PHPPI dataset by ourselves for future research. It results in an utterly big and imbalanced data set associated with high dimension and large quantity. Several machine learning methodologies are also discussed in this paper to imply possible analytics solutions in near future. This paper contributes to a new, yet challenging, research area in applying data analytic technologies in bioinformatics, by learning and predicting pathogen-host protein-protein interactions. Abstract-"Big Data" is immersed in many disciplines, including computer vision, economics, online resources, bioinformatics and so on. Increasing researches are conducted on data mining and machine learning for uncovering and predicting related domain knowledge. Protein-protein interaction is one of the main areas in bioinformatics as it is the basis of the biological functions. However, most pathogen-host proteinprotein interactions, which would be able to reveal much more infectious mechanisms between pathogen and host, are still up for further investigation. Considering a decent feature representation of pathogen-host protein-protein interactions (PHPPI), currently there is not a well structured database for research purposes, not even for infection mechanism studies for different species of pathogens. In this paper, we will survey the PHPPI researches and construct a public PHPPI dataset by ourselves for future research. It results in an utterly big and imbalanced data set associated with high dimension and large quantity. Several machine learning methodologies are also discussed in this paper to imply possible analytics solutions in near future. This paper contributes to a new, yet challenging, research area in applying data analytic technologies in bioinformatics, by learning and predicting pathogen-host proteinprotein interactions.

show abstract

Section: )mentioning

confidence: 99%

Towards Data Analytics of Pathogen-Host Protein-Protein Interaction: A Survey

Chen

Shen

Wang

et al. 2016

2016 IEEE International Congress on Big Data (BigData Congress)

View full text Add to dashboard Cite

show abstract

“…El modelamiento de proteínas por homología es útil para conocer la estructura de una proteína desconocida empleando moldes que han sido generados por muchos años de investigación mediante técnicas como la cristalografía. Esta técnica resulta ser muy buena para conocer la especificidad, función y regiones conservadas de una proteína (Zhang, 2008;Murakami & Mizuguchi, 2014). La generación de una proteína por homología permite visualizar estructuras secundarias como α-hélices y hojas-β.…”

Section: Introductionunclassified

Modelamiento de Glicosil hidrolasas de la familia Ustilaginaceae empleando el servidor en línea SWISS-MODEL

et al. 2018

View full text Add to dashboard Cite

En este trabajo se realizó la búsqueda de 20 secuencias proteicas de la familia Ustilaginaceae en la base de datos de NCBI para su posterior modelamiento. El modelamiento de estas proteínas utilizando el servidor en línea SWISS-MODEL permitió apreciar las regiones conservadas en 17 proteínas a través de la presencia de estructuras secundarias como α-hélices y hojas-β, sin embargo tres de ellas no presentaron similitud estructural con el resto de las proteínas. Se sugiere realizar estudios sobre la composición de los aminoácidos del sitio activo y sobre la región del péptido señal, así como llevar a cabo un análisis filogenético de las proteínas con mayor similitud.

show abstract

“…Homology-based prediction is one of the most common approaches to predict host-pathogen PPIs. These approaches have been extensively used to infer intraspecies interactions [10,11,18] as well as host-pathogen PPIs [13][14][15]19]. These methods assume that interactions between proteins in one species can be transferred to homolog proteins in another species (interologs).…”

Section: Introductionmentioning

confidence: 99%

An integrative method to unravel the host-parasite interactome: an orthology-based approach

Cuesta-Astroz

Santos

Oliveira

et al. 2017

Preprint

View full text Add to dashboard Cite

The study of molecular host-parasite interactions is essential to understand parasitic infection and adaptation within the host system. As well, prevention and treatment of infectious diseases require clear understanding of the molecular crosstalk between parasites and their hosts. As yet, experimental large-scale identification of host-parasite molecular interactions remains challenging and the use of in silico predictions becomes then necessary. Here, we propose a computational integrative approach to predict host-parasite protein-protein interaction (PPI) networks resulting from the infection of human by 12 different parasites. We used an orthology-based method to transfer high-confidence intraspecies interactions obtained from the STRING database to the corresponding inter-species protein pairs in the host-parasite system. To reduce the number of spurious predictions, our approach uses either the parasites predicted secretome and membrane proteins or only the secretome depending on whether they are uni-or multicellular respectively. Besides, the host proteome is filtered for proteins expressed in selected cellular localizations and tissues supporting the parasites growth. We evaluated the inferred interactions by analyzing the enriched biological processes and pathways in the predicted networks and their association to known parasitic invasion and evasion mechanisms. The resulting PPI networks were compared across parasites to identify common mechanisms that may define a global pathogenic hallmark. The predicted PPI networks can be visualized and downloaded at http://orthohpi.jensenlab.org. Author SummaryA protein-protein interaction (PPI) network is a collection of interactions between proteins from one or more organisms. Host-parasite PPIs are key to understanding the biology of different parasitic diseases, since predicting PPIs enable to know more about the parasite invasion, infection and persist. Our understanding of PPIs between host and parasites is still . CC-BY 4.0 International license peer-reviewed) is the author/funder. It is made available under a The copyright holder for this preprint (which was not . http://dx.doi.org/10.1101/147868 doi: bioRxiv preprint first posted online 3 very limited, as no many systematic experimental studies have so far been performed.Efficacy of treatments for parasitic diseases is limited and in many cases parasites evolve resistance. Thus, there is an urgent need to develop novel drugs or vaccines for these neglected diseases, and thus interest in the functions and interactions of proteins associated with parasitism processes. Here we developed an in silico method to shed light on the interactome in twelve human parasites by combining an orthology based strategy and integrating, domain-domain interaction data, sub-cellular localization and to give a spatial context, we only took in to account those human tissues that support the parasite´s tropism.Here we show that is possible to identify relevant interactions across different parasites and their human h...

show abstract

Homology-based prediction of interactions between proteins using Averaged One-Dependence Estimators

Cited by 77 publications

References 46 publications

Towards Data Analytics of Pathogen-Host Protein-Protein Interaction: A Survey

Towards Data Analytics of Pathogen-Host Protein-Protein Interaction: A Survey

Modelamiento de Glicosil hidrolasas de la familia Ustilaginaceae empleando el servidor en línea SWISS-MODEL

An integrative method to unravel the host-parasite interactome: an orthology-based approach

Contact Info

Product

Resources

About