Icons / Logo / Facebook Created with Sketch. Icons / Logo / Google Created with Sketch. Icons / Logo / ORCID Created with Sketch. Branding/Logomark minus Citation Combined Shape Icon/Bookmark-empty Icon/Copy Icon/Collection Icon/Close Copy 7 no author result Created with Sketch. Icon/Back Created with Sketch. Match!

HIV-1 tropism prediction by the XGboost and HMM methods

Published on Dec 1, 2019in Scientific Reports 4.01
· DOI :10.1038/s41598-019-46420-4
Xiang Chen (THU: Tsinghua University), Zhi-Xin Wang19
Estimated H-index: 19
(THU: Tsinghua University),
Xian-Ming Pan (THU: Tsinghua University)
Human Immunodeficiency Virus 1 (HIV-1) co-receptor usage, called tropism, is associated with disease progression towards AIDS. Furthermore, the recently developed and developing drugs against co-receptors CCR5 or CXCR4 open a new thought for HIV-1 therapy. Thus, knowledge about tropism is critical for illness diagnosis and regimen prescription. To improve tropism prediction accuracy, we developed two novel methods, the extreme gradient boosting based XGBpred and the hidden Markov model based HMMpred. Both XGBpred and HMMpred achieved higher specificities (72.56% and 72.09%) than the state-of-the-art methods Geno2pheno (61.6%) and G2p_str (68.60%) in a 10-fold cross validation test at the same sensitivity of 93.73%. Moreover, XGBpred had more outstanding performances (with AUCs 0.9483, 0.9464) than HMMpred (0.8829, 0.8774) on the Hivcopred and Newdb (created in this work) datasets containing larger proportions of hard-to-predict dual tropic samples in the X4-using tropic samples. Therefore, we recommend the use of our novel method XGBpred to predict tropism. The two methods and datasets are available via http://spg.med.tsinghua.edu.cn:23334/XGBpred/. In addition, our models identified that positions 5, 11, 13, 18, 22, 24, and 25 were correlated with HIV-1 tropism.
  • References (45)
  • Citations (0)
Published on Aug 1, 2018in Bioinformatics 4.53
Hannah F Löchel1
Estimated H-index: 1
(University of Marburg),
Mona Riemenschneider7
Estimated H-index: 7
+ 1 AuthorsDominik Heider (University of Marburg)
Published on Aug 1, 2016in Scientific Reports 4.01
Hui-Shuang Shen1
Estimated H-index: 1
Jason Yin1
Estimated H-index: 1
+ 4 AuthorsXian-Ming Pan1
Estimated H-index: 1
AIDS has claimed millions of lives worldwide and continues to be a pressing public health issue. To combat HIV replication in an infected individual, anti-retroviral therapies (ARTs) have been designed to target essential proteins in the replication cycle of HIV. The replication cycle is comprised of several steps. To successfully enter a cell, the viral gp120 protein first binds to its primary cellular CD4 receptor protein. This induces a series of conformational changes in the gp120 protein, e...
Published on Jul 1, 2016in Pediatric Infectious Disease Journal 2.32
Allison L. Agwu17
Estimated H-index: 17
Tzy-Jyun Yao18
Estimated H-index: 18
(ICSCI: Kennedy Krieger Institute)
+ 5 AuthorsRussell B. Van Dyke32
Estimated H-index: 32
Background: Perinatally HIV-infected (PHIV) children and youth are often heavily treatment-experienced, with resultant antiretroviral resistance and limited treatment options. For those with virologic failure (VF), new agents such as CCR5 (R5) antagonists may be useful; however, reports of R5 antagonist susceptibility in children have mostly relied on genotypic testing, which may not accurately reflect the phenotypic tropism of the viral populations. We characterized phenotypic coreceptor usage ...
Published on Apr 1, 2016in Scientific Reports 4.01
Mona Riemenschneider7
Estimated H-index: 7
Kieran Cashin9
Estimated H-index: 9
(Burnet Institute)
+ 6 AuthorsDominik Heider16
Estimated H-index: 16
(TUM: Technische Universität München)
Antiretroviral treatment of Human Immunodeficiency Virus type-1 (HIV-1) infections with CCR5-antagonists requires the co-receptor usage prediction of viral strains. Currently available tools are mostly designed based on subtype B strains and thus are in general not applicable to non-B subtypes. However, HIV-1 infections caused by subtype B only account for approximately 11% of infections worldwide. We evaluated the performance of several sequence-based algorithms for co-receptor usage prediction...
Published on Oct 2, 2015in Critical Reviews in Microbiology 5.70
George Panos5
Estimated H-index: 5
Dionysios C. Watson8
Estimated H-index: 8
AbstractHIV-1 entry begins with viral envelope glycoprotein gp120 interacting with host-cell CD4 and an entry coreceptor (mainly chemokine receptors CCR5 or CXCR4). Inhibitors of particular coreceptors are being developed in order to exploit this step of cellular infection. However, effectiveness of these drugs requires matching of the administered therapeutic to coreceptor use by the viral variants infecting each patient. Patient viruses may use only CCR5 (R5), only CXCR4 (X4) or both (D/M). Mo...
Published on Dec 1, 2014in Biodata Mining 2.30
Dominik Heider16
Estimated H-index: 16
(University of Duisburg-Essen),
Jan Nikolaj Dybowski1
Estimated H-index: 1
(University of Duisburg-Essen)
+ 1 AuthorsDaniel Hoffmann26
Estimated H-index: 26
(University of Duisburg-Essen)
Background Human Immunodeficiency Virus 1 enters host cells through interaction of its V3 loop (which is part of the gp120 protein) with the host cell receptor CD4 and one of two co-receptors, namely CCR5 or CXCR4. Entry inhibitors binding the CCR5 co-receptor can prevent viral entry. As these drugs are only available for CCR5-using viruses, accurate prediction of this so-called co-receptor tropism is important in order to ensure an effective personalized therapy. With the development of next-ge...
Published on Jun 6, 2013in Infectious Disease Reports
Hassan M. Naif2
Estimated H-index: 2
(Nahrain University)
Over the past three decades of intense research on the contribution of viral and host factors determining the variability in HIV-1 infection outcome, HIV pathogenesis is still a fascinating topic that requires further study. An understanding of the exact mechanism of how these factors influencing HIV pathogenesis is critical to the development of effective strate- gies to prevent infection. Significant progress has been made in identifying the role of CCR5 (R5) and CXCR4 (X4) HIV strains in dise...
Published on Apr 15, 2013in PLOS ONE 2.78
Ravi Kumar8
Estimated H-index: 8
(CSIR: Council of Scientific and Industrial Research),
Gajendra P. S. Raghava51
Estimated H-index: 51
(CSIR: Council of Scientific and Industrial Research)
Background HIV-1 infects the host cell by interacting with the primary receptor CD4 and a coreceptor CCR5 or CXCR4. Maraviroc, a CCR5 antagonist binds to CCR5 receptor. Thus, it is important to identify the coreceptor used by the HIV strains dominating in the patient. In past, a number of experimental assays and in-silico techniques have been developed for predicting the coreceptor tropism. The prediction accuracy of these methods is excellent when predicting CCR5(R5) tropic sequences but is rel...
Published on Mar 21, 2013in PLOS Computational Biology
Katarzyna Bozek12
Estimated H-index: 12
(MPG: Max Planck Society),
Thomas Lengauer67
Estimated H-index: 67
(MPG: Max Planck Society)
+ 2 AuthorsFrancisco S. Domingues24
Estimated H-index: 24
The relationship of HIV tropism with disease progression and the recent development of CCR5-blocking drugs underscore the importance of monitoring virus coreceptor usage. As an alternative to costly phenotypic assays, computational methods aim at predicting virus tropism based on the sequence and structure of the V3 loop of the virus gp120 protein. Here we present a numerical descriptor of the V3 loop encoding its physicochemical and structural properties. The descriptor allows for structure-bas...
Published on Sep 1, 2012in Current Opinion in Hiv and Aids 4.27
Martin Obermeier1
Estimated H-index: 1
Jori Symons8
Estimated H-index: 8
Annemarie M. J. Wensing28
Estimated H-index: 28
Cited By0