Predicting annotated HIV-1-Human PPIs using a biclustering approach to association rule mining

Ray, Sumanta; Mukhopadhyay, Anirban; Maulik, Ujjwal

doi:10.1109/eait.2012.6407854

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the construction of the negative samples is a problem that must be overcome in the PHI prediction with supervised methods. Some studies present data mining methods which use only positive samples to build a prediction model (Mukhopadhyay et al, 2010;Mondal et al, 2012;Ray et al, 2012). Since the data mining methods use only positive samples, the model fails to predict negative interactions and so they have risk of high false positive rate.…”

Section: Background and Preliminariesmentioning

confidence: 99%

Prediction of host-pathogen protein interactions by extended network model

2021

View full text Add to dashboard Cite

Knowledge of the pathogen-host interactions between the species is essentialin order to develop a solution strategy against infectious diseases. In vitro methods take extended periods of time to detect interactions and provide very few of the possible interaction pairs. Hence, modelling interactions between proteins has necessitated the development of computational methods. The main scope of this paper is integrating the known protein interactions between thehost and pathogen organisms to improve the prediction success rate of unknown pathogen-host interactions. Thus, the truepositive rate of the predictions was expected to increase.In order to perform this study extensively, encoding methods and learning algorithms of several proteins were tested. Along with human as the host organism, two different pathogen organisms were used in the experiments. For each combination of protein-encoding and prediction method, both the original prediction algorithms were tested using only pathogen-host interactions and the same methodwas testedagain after integrating the known protein interactions within each organism. The effect of merging the networks of pathogen-host interactions of different species on the prediction performance of state-of-the-art methods was also observed. Successwas measured in terms of Matthews correlation coefficient, precision, recall, F1 score, and accuracy metrics. Empirical results showed that integrating the host and pathogen interactions yields better performance consistently in almost all experiments.

show abstract

Section: Background and Preliminariesmentioning

confidence: 99%

Prediction of host-pathogen protein interactions by extended network model

2021

View full text Add to dashboard Cite

show abstract

“…Constructing negative class is not straightforward due to the fact that there is no experimentally verified non-interacting pair. This has motivated some studies to overcome this problem by removing the need for negative data through using alternative methods (Mukhopadhyay et al, 2010 , 2012 , 2014 ; Mondal et al, 2012 ; Ray et al, 2012 ). They integrate bi-clustering with association rule mining, utilizing only positive samples to predict virus-human interactions.…”

Section: Machine Learning and Data Mining Based Approachesmentioning

confidence: 99%

“…Since there is no available verified non-interacting PPI to be used for training the model, selecting negative data remains as a challenge for PPI prediction. Some studies try to circumvent the obstacle by using methods which do not require negative samples (Ray et al, 2012 ). However, ignoring non-interacting patterns may increase the rate of false positives (Mei, 2013 ).…”

Section: Machine Learning and Data Mining Based Approachesmentioning

confidence: 99%

Computational approaches for prediction of pathogen-host protein-protein interactions

2015

View full text Add to dashboard Cite

Infectious diseases are still among the major and prevalent health problems, mostly because of the drug resistance of novel variants of pathogens. Molecular interactions between pathogens and their hosts are the key parts of the infection mechanisms. Novel antimicrobial therapeutics to fight drug resistance is only possible in case of a thorough understanding of pathogen-host interaction (PHI) systems. Existing databases, which contain experimentally verified PHI data, suffer from scarcity of reported interactions due to the technically challenging and time consuming process of experiments. These have motivated many researchers to address the problem by proposing computational approaches for analysis and prediction of PHIs. The computational methods primarily utilize sequence information, protein structure and known interactions. Classic machine learning techniques are used when there are sufficient known interactions to be used as training data. On the opposite case, transfer and multitask learning methods are preferred. Here, we present an overview of these computational approaches for predicting PHI systems, discussing their weakness and abilities, with future directions.

show abstract