Using decision tree learning to predict the responsiveness of hepatitis C patients to drug treatment
| Autor: | Masashi Mizokami, Shigeru Takasaki, Yoshihiro Kawamura |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2012 |
| Předmět: |
Oncology
medicine.medical_specialty RBV ribavirin Genome-wide association study Hepatitis C virus Rebavirin Single-nucleotide polymorphism Bioinformatics medicine.disease_cause General Biochemistry Genetics and Molecular Biology Article chemistry.chemical_compound MM both major genotypes GDI Gini diversity index Internal medicine Het one major and one minor genotype Genotype medicine GWAS genome-wide association study Chronic hepatitis C genotype 1 Sustained virologic response NVR null virologic response business.industry Ribavirin Decision tree learning PEG-IFN-α pegylated interferon α Hepatitis C Odds ratio Pegylated interferon α medicine.disease mm both minor genotypes Single nucleotide polymorphism SVR sustained virologic response chemistry Null virologic response HCV hepatitis C virus SNPs single nucleotide polymorphisms business OR Odds ratio |
| Zdroj: | FEBS Open Bio |
| ISSN: | 2211-5463 |
| Popis: | Highlights ► We modeled drug responses using decision tree learning based on SNPs in a genome-wide association study. ► We can predict the drug responses of a new patient with HCV genotype 1. ► Responsiveness to pegylated interferon α (PEG-IFN-α) plus rebavirin (RBV) treatment was predicted. ► We can predict with 93% probability whether a new patient with HCV genotype 1 will be helped by drug treatment. The recommended treatment for patients with chronic hepatitis C, pegylated interferon α (PEG-IFN-α) plus rebavirin (RBV), does not provide a sustained virologic response in all patients, especially those with hepatitis C virus (HCV) genotype 1. It is therefore important to predict whether or not a new patient with HCV genotype 1 will be cured by the recommended treatment. We propose a prediction method for a new patient using a decision tree learning model based on SNPs evaluated in a genome-wide association study. By the decision tree learning for 142 Japanese patients with HCV genotype 1 (78 with null virologic response and 64 with virologic response), we can predict with high probability (93%) whether or not a new patient with HCV will be helped by the recommended treatment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text