Identification of KRAS mutation-associated gut microbiota in colorectal cancer and construction of predictive machine learning model

作者：Zigui Huang, Xiaoliang Huang, Yili Huang, Kunmei Liang, Lei Chen, Chuzhuo Zhong, Yingxin Chen, Chuanbin Chen, Zhen Wang, Fuhai He, Mingjian Qin, Chenyan Long, Binzhe Tang, Yongqi Huang, Yongzhi Wu, Xianwei Mo, Weizhong Tang, Jungang Liu · 发表于：Microbiology Spectrum · 年份：2024 · DOI：10.1128/spectrum.02720-23 · 被引用次数：21 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Gut microbiota and health、Colorectal Cancer Treatments and Studies

ABSTRACT Gut microbiota has demonstrated an increasingly important role in the onset and development of colorectal cancer (CRC). Nonetheless, the association between gut microbiota and KRAS mutation in CRC remains enigmatic. We conducted 16S rRNA sequencing on stool samples from 94 CRC patients and employed the linear discriminant analysis effect size algorithm to identify distinct gut microbiota between KRAS mutant and KRAS wild-type CRC patients. Transcriptome sequencing data from nine CRC patients were transformed into a matrix of immune infiltrating cells, which was then utilized to explore KRAS mutation-associated biological functions, including Gene Ontology items and Kyoto Encyclopedia of Genes and Genomes pathways. Subsequently, we analyzed the correlations among these KRAS mutation-associated gut microbiota, host immunity, and KRAS mutation-associated biological functions. At last, we developed a predictive random forest (RF) machine learning model to predict the KRAS mutation status in CRC patients, based on the gut microbiota associated with KRAS mutation. We identified a total of 26 differential gut microbiota between both groups. Intriguingly, a significant positive correlation was observed between Bifidobacterium spp. and mast cells, as well as between Bifidobacterium longum and chemokine receptor CX3CR1. Additionally, we also observed a notable negative correlation between Bifidobacterium and GOMF:proteasome binding. The RF model constructed using the KRAS muta...