Prediction of human-virus protein-protein interactions through a sequence embedding-based machine learning method

Yang, Xiaodi; Yang, Shiping; Li, Qinmengge; Wuchty, Stefan; Zhang, Ziding

doi:10.1016/j.csbj.2019.12.005

Cited by 114 publications

(167 citation statements)

References 53 publications

Supporting

Mentioning

158

Contrasting

Order By: Relevance

“…human) PPI prediction. To compare with the existing sequence-based methods for both intra-and inter-species PPI prediction, we evaluated DeepViral and RCNN (Chen et al, 2019), a recent method designed for intra-species prediction, on an existing dataset (Eid et al, 2016) that has been used to evaluate a number of PHI prediction methods (Yang et al, 2020;Alguwaizani et al, 2018;Zhou et al, 2018). The respective model performances and implementation details are shown in Supplementary Table 1.…”

Section: Embedding Features Of Viruses and Human Proteins From Phenotmentioning

confidence: 99%

“…We compared DeepViral with two existing state-of-the-art methods based on protein sequences: Doc2Vec + RF (Yang et al, 2020), a recent method predicting for virus-human interactions; and RCNN (Chen et al, 2019), a recent deep learning based method for intra-species (e.g., human) PPI prediction. To adapt Doc2Vec + RF on our dataset, we used the pretrained Doc2Vec model provided by the authors and the same parameters for the random forest model for training.…”

Section: Phenotypes Improve Prediction For Novel Virusesmentioning

confidence: 99%

“…Existing PHI prediction methods for novel viruses typically utilize protein sequence features of the interacting proteins (Eid et al, 2016;Zhou et al, 2018;Alguwaizani et al, 2018;Yang et al, 2020). While protein functions have been shown to predict intra-species (e.g., human) i i "output" -2020/8/12 -19:24 -page 2 -#2 i i i i i i PPIs (Guzzi et al, 2011;Jain and Bader, 2010;Pesquita et al, 2009) and such protein specific features exist for some extensively studied pathogens, such as Mycobacterium tuberculosis (Huo et al, 2015) and HIV (Mukhopadhyay et al, 2014), for most pathogens, these features are rare and expensive to obtain.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DeepViral: infectious disease phenotypes improve prediction of novel virus–host interactions

Liu-Wei

Kafkas

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Motivation: Infectious diseases from novel viruses are becoming a major public health concern. Fast identification of virus-host interactions can reveal mechanistic insights of infectious diseases and shed light on potential treatments and drug discoveries. Current computational prediction methods for novel viruses are based only on protein sequences. Yet, it is not clear to what extent other important features, such as the symptoms caused by the viruses, could contribute to a predictor. Disease phenotypes (i.e., symptoms) are readily accessible from clinical diagnosis and we hypothesize that they may act as a potential proxy and an additional source of information for the underlying molecular interactions between the pathogens and hosts. Results: We developed DeepViral, a deep learning method that predicts potential protein-protein interactions between human and viruses. First, human proteins and viruses were embedded in a shared space using their associated phenotypes, functions, taxonomic classification, as well as formalized background knowledge from biomedical ontologies. By extending a sequence learning model with phenotype features, our model can not only significantly improve over previous sequence-based approaches for inter-species interaction prediction, but also identify pathways of viral targets under a realistic experimental setup for novel viruses. Availability:https://github.com/bio-ontology-research-group/DeepViral Contact:

show abstract

Section: Embedding Features Of Viruses and Human Proteins From Phenotmentioning

confidence: 99%

Section: Phenotypes Improve Prediction For Novel Virusesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DeepViral: infectious disease phenotypes improve prediction of novel virus–host interactions

Liu-Wei

Kafkas

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Also, the researchers have little knowledge of the molecular biology of SARS-CoV2 infection [16]. In the present state of art, viral infection mechanism is not fully understood though various proteinprotein interactions (PPIs) of virus and host are known [17,18]. So identifying interactions between the SARS-CoV2 virus proteins and host proteins helps understand the mechanism of viral infection and develop treatments and vaccines [19].…”

Section: Introductionmentioning

confidence: 99%

Spatial Distribution of Amino Acids of the SARS-CoV2 Proteins

Hassan¹,

Rout²

2020

Preprint

View full text Add to dashboard Cite

The world is now undergoing through a global emergency due to COVID-19 which needs immediate remedies in order to strengthen the healthcare facility to save the nations. Looking towards to the remedies, research on different aspects including the genomic and proteomic level characterizations of the SARS-CoV2 are necessarily important. In this present study, the spatial representation/composition of twenty amino acids across the primary protein sequences of SARS-CoV2 have been looked into through different parameters viz. Shannon entropy, Hurst exponent in order to fetch the autocorrelation and amount of information over the spatial representations. Also frequency distribution of each of the amino acids over the protein sequences have been chalked out.

show abstract

“…Everyday our world is now experiencing the pandemic side of the COVID-19 which certainly questing for in depth knowledge of the virus and its infection mechanism and other aspects. In the present state of art, viral infection mechanism is not fully understood though various proteinprotein interactions (PPIs) of virus and host are known [17,18]. So identifying interactions between the SARS-CoV2 virus proteins and host proteins helps understand the mechanism of viral infection and develop treatments and vaccines [19].…”

Section: Introductionmentioning

confidence: 99%