Machine-learning based patient classification using Hepatitis B virus full-length genome quasispecies from Asian and European cohorts

AbstractChronic infection with Hepatitis B virus (HBV) is a major risk factor for the development of advanced liver disease including fibrosis, cirrhosis, and hepatocellular carcinoma (HCC). The relative contribution of virological factors to disease progression has not been fully defined and tools aiding the deconvolution of complex patient virus profiles is an unmet clinical need. Variable viral mutant signatures develop within individual patients due to the low-fidelity replication of the viral polymerase creating ‘quasispecies’ populations. Here we present the first comprehensive survey of the diversity of HBV quasispecies through ultra-deep sequencing of the complete HBV genome across two distinct European and Asian patient populations. Seroconversion to the HBV e antigen (HBeAg) represents a critical clinical waymark in infected individuals. Using a machine learning approach, a model was developed to determine the viral variants that accurately classify HBeAg status. Serial surveys of patient quasispecies populations and advanced analytics will facilitate clinical decision support for chronic HBV infection and direct therapeutic strategies through improved patient stratification.

Download Full-text

Quasispecies Pattern of Hepatitis B Virus Predicts Hepatocellular Carcinoma Using Deep-Sequencing and Machine Learning

SSRN Electronic Journal ◽

10.2139/ssrn.3582725 ◽

2020 ◽

Author(s):

Shipeng Chen ◽

Zihan Zhang ◽

Ying Wang ◽

Meng Fang ◽

Jun Zhou ◽

...

Keyword(s):

Machine Learning ◽

Hepatocellular Carcinoma ◽

Hepatitis B Virus ◽

Hepatitis B ◽

Deep Sequencing ◽

B Virus

Download Full-text

Predicting hepatitis B virus–positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning

Nature Medicine ◽

10.1038/nm843 ◽

2003 ◽

Vol 9 (4) ◽

pp. 416-423 ◽

Cited By ~ 574

Author(s):

Qing-Hai Ye ◽

Lun-Xiu Qin ◽

Marshonna Forgues ◽

Ping He ◽

Jin Woo Kim ◽

...

Keyword(s):

Gene Expression ◽

Machine Learning ◽

Hepatitis B Virus ◽

Hepatitis B ◽

Gene Expression Profiling ◽

Expression Profiling ◽

Supervised Machine Learning ◽

Hepatocellular Carcinomas ◽

B Virus

Download Full-text

Analysis of the full-length genome of hepatitis B virus in the serum and cerebrospinal fluid of a patient with acute hepatitis B and transverse myelitis

Journal of Clinical Virology ◽

10.1016/j.jcv.2008.01.002 ◽

2008 ◽

Vol 41 (4) ◽

pp. 301-304 ◽

Cited By ~ 11

Author(s):

Jun Inoue ◽

Yoshiyuki Ueno ◽

Takayuki Kogure ◽

Futoshi Nagasaki ◽

Osamu Kimura ◽

...

Keyword(s):

Cerebrospinal Fluid ◽

Hepatitis B Virus ◽

Hepatitis B ◽

Acute Hepatitis ◽

Transverse Myelitis ◽

Full Length ◽

B Virus ◽

Acute Hepatitis B ◽

Full Length Genome

Download Full-text

Analysis of hepatitis B virus infection in blood sera using Raman spectroscopy and machine learning

Photodiagnosis and Photodynamic Therapy ◽

10.1016/j.pdpdt.2018.05.010 ◽

2018 ◽

Vol 23 ◽

pp. 89-93 ◽

Cited By ~ 22

Author(s):

Saranjam Khan ◽

Rahat Ullah ◽

Asifullah Khan ◽

Ruby Ashraf ◽

Hina Ali ◽

...

Keyword(s):

Machine Learning ◽

Raman Spectroscopy ◽

Hepatitis B Virus ◽

Virus Infection ◽

Hepatitis B ◽

Hepatitis B Virus Infection ◽

B Virus

Download Full-text

A Noninvasive Prediction Model for Hepatitis B Virus Disease in Patients with HIV: Based on the Population of Jiangsu, China

BioMed Research International ◽

10.1155/2021/6696041 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Yi Yin ◽

Mingyue Xue ◽

Lingen Shi ◽

Tao Qiu ◽

Derun Xia ◽

...

Keyword(s):

Machine Learning ◽

Hepatitis B Virus ◽

Hepatitis B ◽

Decision Tree ◽

Learning Model ◽

Heterosexual Transmission ◽

Adaboost Algorithm ◽

Machine Learning Model ◽

B Virus ◽

Homosexual Transmission

Objective. To establish a machine learning model for identifying patients coinfected with hepatitis B virus (HBV) and human immunodeficiency virus (HIV) through two sexual transmission routes in Jiangsu, China. Methods. A total of 14197 HIV cases transmitted by homosexual and heterosexual routes were recruited. After data processing, 12469 cases (HIV and HBV, 1033; HIV, 11436) were left for further analysis, including 7849 cases with homosexual transmission and 4620 cases with heterosexual transmission. Univariate logistic regression was used to select variables with significant P value and odds ratio for multivariable analysis. In homosexual transmission and heterosexual transmission groups, 10 and 6 variables were selected, respectively. For identifying HIV individuals coinfected with HBV, a machine learning model was constructed with four algorithms, including Decision Tree, Random Forest, AdaBoost with decision tree (AdaBoost), and extreme gradient boosting decision tree (XGBoost). The detective value of each variable was calculated using the optimal machine learning algorithm. Results. AdaBoost algorithm showed the highest efficiency in both transmission groups (homosexual transmission group: accuracy = 0.928 , precision = 0.915 , recall = 0.944 , F − 1 = 0.930 , and AUC = 0.96 ; heterosexual transmission group: accuracy = 0.892 , precision = 0.881 , recall = 0.905 , F − 1 = 0.893 , and AUC = 0.98 ). Calculated by AdaBoost algorithm, the detective value of PLA was the highest in homosexual transmission group, followed by CR, AST, HB, ALT, TBIL, leucocyte, age, marital status, and treatment condition; in the heterosexual transmission group, the detective value of PLA was the highest (consistent with the condition in the homosexual group), followed by ALT, AST, TBIL, leucocyte, and symptom severity. Conclusions. The univariate logistics regression combined with the AdaBoost algorithm could accurately screen the risk factors of HBV in HIV coinfection without invasive testing. Further studies are needed to evaluate the utility and feasibility of this model in various settings.

Download Full-text

Complete genome sequence of a divergent strain of Tibetan frog hepatitis B virus associated to concave-eared torrent frogOdorrana tormota

10.1101/506550 ◽

2018 ◽

Author(s):

Humberto J. Debat ◽

Terry Fei Fan Ng

Keyword(s):

Hepatitis B Virus ◽

Hepatitis B ◽

Host Range ◽

Broad Host Range ◽

Sequencing Data ◽

Pairwise Identity ◽

B Virus ◽

Organ Specific ◽

Full Length Genome ◽

Divergent Strain

AbstractThe familyHepadnaviridaeis characterized by partially dsDNA circular viruses of approximately 3.2 kb, which are reverse transcribed from RNA intermediates. Hepadnaviruses (HBVs) have a broad host range which includes humans (Hepatitis B virus), other mammals (genusOrthohepadnavirus), and birds (Avihepadnavirus). HBVs host specificity has been expanded by reports of new viruses infecting fish, amphibians, and reptiles. The tibetan frog hepatitis B virus (TFHBV) was recently discovered inNanorana parkeri(FamilyDicroglossidae) from Tibet. To increase understanding of hepadnavirus in amphibian host, we identified the full-length genome of a divergent strain TFHBV-Ot associated to the concave-eared torrent frogOdorrana tormota(FamilyRanidae) from China by searching deep sequencing data. TFHBV-Ot shared the genomic organization and a 76.6% overall genome nucleotide identity to the prototype TFHBV associated toN. parkeri(TFHBV-Np). TFHBV-Ot amino acid pairwise identity with TFHBV-Np predicted gene products ranged between 63.9% and 77.9%. Multiple tissue/organ specific RNAseq datasets suggest a broad tropism of TFHBV including muscles, gonads and brains. In addition, we provide for the first time evidence of virus derived small RNA from an amphibian hepadnavirus, tentatively enriched in 19-20 nt species and cytidine as first base. The results presented here expand the genetic diversity and the host range of TFHBV toRanidaefrogs, and warrant investigation on hepadnaviral infection of amphibian brains.

Download Full-text

Genetic Diversity of the Hepatitis B Virus Subgenotypes in Brazil

Viruses ◽

10.3390/v11090860 ◽

2019 ◽

Vol 11 (9) ◽

pp. 860 ◽

Cited By ~ 3

Author(s):

Barbara V. Lago ◽

Marcia P. do Espirito-Santo ◽

Vanessa D. Costa ◽

Vanessa A. Marques ◽

Livia M. Villar ◽

...

Keyword(s):

Genetic Diversity ◽

Hepatitis B Virus ◽

Hepatitis B ◽

Human Migration ◽

Serum Samples ◽

Comprehensive Overview ◽

Geographical Regions ◽

B Virus ◽

Full Length Genome ◽

Brazilian Studies

Hepatitis B virus (HBV) subgenotypes may be related to clinical outcomes and response to antiviral therapy. Most Brazilian studies on HBV subgenotypes are restricted to some regions and to specific population groups. Here, we provide an insight about genetic diversity of HBV subgenotypes in 321 serum samples from all five geographical regions, providing a representative overview of their circulation among chronic carriers. Overall, HBV/A1 was the most prevalent subgenotype, being found as the major one in all regions except in South Brazil. Among HBV/D samples, subgenotype D3 was the most prevalent, found in 51.5%, followed by D2 (27.3%) and D4 (21.2%). D2 and D3 were the most prevalent subgenotypes in South region, with high similarity with European strains. D4 was found in North and Northeast region and clustered with strains from Cape Verde and India. For HBV/F, the most frequent subgenotype was F2 (84.1%), followed by F4 (10.1%) and F1 (5.8%), closely related with strains from Venezuela, Argentina and Chile, respectively. Phylogeographic analyses were performed using an HBV full-length genome obtained from samples infected with genotypes rarely found in Brazil (B, C, and E). According to Bayesian inference, HBV/B2 and HBV/C2 were probably introduced in Brazil through China, and HBV/E from Guinea, all of them mostly linked to recent events of human migration. In conclusion, this study provided a comprehensive overview of the current circulation of HBV subgenotypes in Brazil. Our findings might contribute to a better understand of the dynamics of viral variants, to establish a permanent molecular surveillance on the introduction and dispersion patterns of new strains and, thus, to support public policies to control HBV dissemination in Brazil.

Download Full-text