Whole-genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin-resistant tuberculosis

Rifampicin-resistant tuberculosis (RR-TB) remains a major global health challenge, with delayed sputum culture conversion (SCC) predicting poor treatment outcomes. This study integrated whole-genome sequencing (WGS) and machine learning to identify clinical and genomic determinants of SCC failure in...

Full description

Saved in:
Bibliographic Details
Main Authors: Qing Fang, Xiangchen Li, Yewei Lu, Junshun Gao, Yvette Wu, Yi Chen, Yang Che
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Cellular and Infection Microbiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fcimb.2025.1641385/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392350300733440
author Qing Fang
Xiangchen Li
Xiangchen Li
Yewei Lu
Junshun Gao
Yvette Wu
Yi Chen
Yang Che
author_facet Qing Fang
Xiangchen Li
Xiangchen Li
Yewei Lu
Junshun Gao
Yvette Wu
Yi Chen
Yang Che
author_sort Qing Fang
collection DOAJ
description Rifampicin-resistant tuberculosis (RR-TB) remains a major global health challenge, with delayed sputum culture conversion (SCC) predicting poor treatment outcomes. This study integrated whole-genome sequencing (WGS) and machine learning to identify clinical and genomic determinants of SCC failure in 150 RR-TB patients (2019–2023). Phenotypic and genotypic analysis revealed high rates of isoniazid resistance (74.0%) and rpoB mutations (97.3%, predominantly Ser450Leu), with 90% of strains belonging to Lineage 2 (Beijing family). While 64.7% achieved 2-month SCC, 18.0% remained culture-positive at 6 months. Univariate analysis linked 2-month SCC failure to smear positivity, resistance to isoniazid, amikacin, capreomycin, and levofloxacin, and pre-XDR-TB status, though only smear positivity (aOR=2.41, P=0.008) and levofloxacin resistance (aOR=2.83, P=0.003) persisted as independent predictors in multivariable analysis. A Random Forest model achieved robust prediction of SCC failure (AUC: 0.86 ± 0.06 at 2 months; 0.76 ± 0.10 at 6 months), identifying levofloxacin resistance (feature importance: 6.37), embB_p.Met306Ile (5.94), and smear positivity (5.12) as top 2-month predictors, while katG_p.Ser315Thr (4.85) and gyrA_p.Asp94Gly (3.43) dominated 6-month predictions. These findings underscore smear positivity, levofloxacin resistance, and specific resistance mutations as critical drivers of SCC failure, guiding targeted RR-TB treatment strategies.
format Article
id doaj-art-dc2d6c0b4da64c32af8a9b5e60fb7905
institution Kabale University
issn 2235-2988
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Cellular and Infection Microbiology
spelling doaj-art-dc2d6c0b4da64c32af8a9b5e60fb79052025-08-20T03:40:47ZengFrontiers Media S.A.Frontiers in Cellular and Infection Microbiology2235-29882025-08-011510.3389/fcimb.2025.16413851641385Whole-genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin-resistant tuberculosisQing Fang0Xiangchen Li1Xiangchen Li2Yewei Lu3Junshun Gao4Yvette Wu5Yi Chen6Yang Che7Departments of Pulmonary Medicine, The First Affiliated Hospital of Ningbo University, Ningbo, Zhejiang, ChinaJiaxing Key Laboratory of Clinical Laboratory Diagnostics and Translational Research, Affiliated Hospital of Jiaxing University, Jiaxing, Zhejiang, ChinaCosmos Wisdom Mass Spectrometry Center of Zhejiang University Medical School, Hangzhou, Zhejiang, ChinaCosmos Wisdom Mass Spectrometry Center of Zhejiang University Medical School, Hangzhou, Zhejiang, ChinaCosmos Wisdom Mass Spectrometry Center of Zhejiang University Medical School, Hangzhou, Zhejiang, ChinaFountain Valley School, Colorado Springs, CO, United StatesInstitute of Tuberculosis Prevention and Control, Ningbo Municipal Center for Disease Control and Prevention, Ningbo, Zhejiang, ChinaInstitute of Tuberculosis Prevention and Control, Ningbo Municipal Center for Disease Control and Prevention, Ningbo, Zhejiang, ChinaRifampicin-resistant tuberculosis (RR-TB) remains a major global health challenge, with delayed sputum culture conversion (SCC) predicting poor treatment outcomes. This study integrated whole-genome sequencing (WGS) and machine learning to identify clinical and genomic determinants of SCC failure in 150 RR-TB patients (2019–2023). Phenotypic and genotypic analysis revealed high rates of isoniazid resistance (74.0%) and rpoB mutations (97.3%, predominantly Ser450Leu), with 90% of strains belonging to Lineage 2 (Beijing family). While 64.7% achieved 2-month SCC, 18.0% remained culture-positive at 6 months. Univariate analysis linked 2-month SCC failure to smear positivity, resistance to isoniazid, amikacin, capreomycin, and levofloxacin, and pre-XDR-TB status, though only smear positivity (aOR=2.41, P=0.008) and levofloxacin resistance (aOR=2.83, P=0.003) persisted as independent predictors in multivariable analysis. A Random Forest model achieved robust prediction of SCC failure (AUC: 0.86 ± 0.06 at 2 months; 0.76 ± 0.10 at 6 months), identifying levofloxacin resistance (feature importance: 6.37), embB_p.Met306Ile (5.94), and smear positivity (5.12) as top 2-month predictors, while katG_p.Ser315Thr (4.85) and gyrA_p.Asp94Gly (3.43) dominated 6-month predictions. These findings underscore smear positivity, levofloxacin resistance, and specific resistance mutations as critical drivers of SCC failure, guiding targeted RR-TB treatment strategies.https://www.frontiersin.org/articles/10.3389/fcimb.2025.1641385/fullrifampicin-resistant tuberculosiswhole-genome sequencingsputum culture conversionmachine learningdrug resistance mutations
spellingShingle Qing Fang
Xiangchen Li
Xiangchen Li
Yewei Lu
Junshun Gao
Yvette Wu
Yi Chen
Yang Che
Whole-genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin-resistant tuberculosis
Frontiers in Cellular and Infection Microbiology
rifampicin-resistant tuberculosis
whole-genome sequencing
sputum culture conversion
machine learning
drug resistance mutations
title Whole-genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin-resistant tuberculosis
title_full Whole-genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin-resistant tuberculosis
title_fullStr Whole-genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin-resistant tuberculosis
title_full_unstemmed Whole-genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin-resistant tuberculosis
title_short Whole-genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin-resistant tuberculosis
title_sort whole genome sequencing and machine learning reveal key drivers of delayed sputum conversion in rifampicin resistant tuberculosis
topic rifampicin-resistant tuberculosis
whole-genome sequencing
sputum culture conversion
machine learning
drug resistance mutations
url https://www.frontiersin.org/articles/10.3389/fcimb.2025.1641385/full
work_keys_str_mv AT qingfang wholegenomesequencingandmachinelearningrevealkeydriversofdelayedsputumconversioninrifampicinresistanttuberculosis
AT xiangchenli wholegenomesequencingandmachinelearningrevealkeydriversofdelayedsputumconversioninrifampicinresistanttuberculosis
AT xiangchenli wholegenomesequencingandmachinelearningrevealkeydriversofdelayedsputumconversioninrifampicinresistanttuberculosis
AT yeweilu wholegenomesequencingandmachinelearningrevealkeydriversofdelayedsputumconversioninrifampicinresistanttuberculosis
AT junshungao wholegenomesequencingandmachinelearningrevealkeydriversofdelayedsputumconversioninrifampicinresistanttuberculosis
AT yvettewu wholegenomesequencingandmachinelearningrevealkeydriversofdelayedsputumconversioninrifampicinresistanttuberculosis
AT yichen wholegenomesequencingandmachinelearningrevealkeydriversofdelayedsputumconversioninrifampicinresistanttuberculosis
AT yangche wholegenomesequencingandmachinelearningrevealkeydriversofdelayedsputumconversioninrifampicinresistanttuberculosis