小柯机器人

科学家利用机器学习和群体遗传学对肿瘤进行亚克隆重建
2020-09-04 16:00

英国癌症研究所Andrea Sottoriva、伦敦玛丽女王大学Trevor A. Graham等研究人员,合作利用机器学习和群体遗传学对肿瘤进行亚克隆重建。2020年9月2日,《自然—遗传学》发表了这一最新研究成果。

研究人员表示,大多数癌症基因组数据是从由癌症亚群以及正常细胞混合物组成的大量样本中产生的。基于机器学习的亚克隆重建方法旨在分离样品中的那些亚群并推断其进化历史。但是,当前的方法完全是数据驱动的,并且与进化论无关。
 
研究人员证明,如果不考虑进化,则会在分析中发生系统性错误,并且对同一肿瘤进行多次采样会加剧这种错误。研究人员提出了一种基于模型的肿瘤亚克隆重建方法,称为MOBSTER,它将机器学习与理论性群体遗传学相结合。使用来自不同队列的2606个样本的公共全基因组测序数据、新数据和综合验证,研究人员表明,在单样本、多区域和纵向数据中,该方法比当前技术更可靠、更准确。这种方法最大程度地减少了非进化方法的混杂因素,从而可以更准确地绘制出人类癌症的进化史。
 
附:英文原文

Title: Subclonal reconstruction of tumors by using machine learning and population genetics

Author: Giulio Caravagna, Timon Heide, Marc J. Williams, Luis Zapata, Daniel Nichol, Ketevan Chkhaidze, William Cross, George D. Cresswell, Benjamin Werner, Ahmet Acar, Louis Chesler, Chris P. Barnes, Guido Sanguinetti, Trevor A. Graham, Andrea Sottoriva

Issue&Volume: 2020-09-02

Abstract: Most cancer genomic data are generated from bulk samples composed of mixtures of cancer subpopulations, as well as normal cells. Subclonal reconstruction methods based on machine learning aim to separate those subpopulations in a sample and infer their evolutionary history. However, current approaches are entirely data driven and agnostic to evolutionary theory. We demonstrate that systematic errors occur in the analysis if evolution is not accounted for, and this is exacerbated with multi-sampling of the same tumor. We present a novel approach for model-based tumor subclonal reconstruction, called MOBSTER, which combines machine learning with theoretical population genetics. Using public whole-genome sequencing data from 2,606 samples from different cohorts, new data and synthetic validation, we show that this method is more robust and accurate than current techniques in single-sample, multiregion and longitudinal data. This approach minimizes the confounding factors of nonevolutionary methods, thus leading to more accurate recovery of the evolutionary history of human cancers. MOBSTER is an approach for subclonal reconstruction of tumors from cancer genomics data on the basis of models that combine machine learning with evolutionary theory, thus leading to more accurate evolutionary histories of tumors.

DOI: 10.1038/s41588-020-0675-5

Source: https://www.nature.com/articles/s41588-020-0675-5

Nature Genetics:《自然—遗传学》,创刊于1992年。隶属于施普林格·自然出版集团,最新IF:41.307
官方网址:https://www.nature.com/ng/
投稿链接:https://mts-ng.nature.com/cgi-bin/main.plex


本期文章:《自然—遗传学》:Online/在线发表

分享到:

0