正在加载图片...
第15卷第5期 智能系统学报 Vol.15 No.5 2020年9月 CAAI Transactions on Intelligent Systems Sep.2020 D0:10.11992/tis.201810005 网络出版地址:http:/kns.cnki.net/kcms/detail/23.1538.TP.20190516.2353.002.html 基于MCCA的座疮宏基因组数据辅助分析 孙梦茹,王瑜,何聪芬2,贾焱2,高学义1 (1.北京工商大学计算机与信息工程学院食品安全大数据技术北京市重点实验室,北京100048:2.北京工商 大学理学院中国轻工业化妆品重点实验室,北京100048) 摘要:座疮作为常见皮肤病之一,发病机制复杂,其中微生物定植在座疮发病中的作用是一个热点研究问 题。本文从宏基因组学的角度,利用机器学习方法分析痤疮宏基因组数据.包括痤疮患者的患病皮肤(diseased skin,DS)样本集和健康皮肤healthy skin,HS)样本集,以及正常对照组(normal control,.NC)样本集。为了同时分 析3组样本集以获得可以区分不同样本集的脂质,使用多重集典型相关分析(multi-set canonical correlation ana- lyss,MCCA)方法进行研究。实验结果可得到仅对某一样本集有显著影响的脂质,以及同时对3个样本集影响 程度不同的脂质,这些脂质可以作为判别皮肤状态的指标,用于辅助指导皮肤痤疮疾病的诊断、预后和治疗。 关键词:座疮;宏基因组学;面部皮肤:脂质:机器学习:多重集典型相关分析 中图分类号:TP391 文献标志码:A文章编号:1673-4785(2020)05-0972-06 中文引用格式:孙梦茹,王瑜,何聪芬,等.基于MCCA的痤疮宏基因组数据辅助分析J.智能系统学报,2020,15(5): 972-977. 英文引用格式:SUN Mengru,.WANG Yu,HE Congfen,et al.Assisted analysis of acne metagenomic sequencing data using multi-set canonical correlation analysis methods[Jl.CAAl transactions on intelligent systems,2020,15(5):972-977. Assisted analysis of acne metagenomic sequencing data using multi-set canonical correlation analysis methods SUN Mengru',WANG Yu',HE Congfen',JIA Yan',GAO Xueyi (1.Beijing Key Laboratory of Big Data Technology for Food Safety,School of Computer and Information Engineering,Beijing Tech- nology and Business University,Beijing 100048,China;2.Key Laboratory of Cosmetic of China National Light Industry,School of Science,Beijing Technology and Business University,Beijing 100048,China) Abstract:As one of the common skin diseases,the pathogenesis of acne is very complicated.The role of microbial col- onization in the pathogenesis of acne is an active research area.The purpose of this paper is to analyze acne metagenom- ic data,including sample sets of acne diseased skin(DS)and healthy skin(HS)as well as normal control (NC)by using machine learning from the perspective of macrogenomics.Multi-set canonical correlation analysis(MCCA)method is used to analyze the above three sample sets at the same time and to confirm the lipids that can distinguish these three sample sets.The results show that lipids that had a significant impact on only one set and those that had different im- pacts on the three sample sets respectively can be used as indicators to determine the skin status.Moreover,these lipids can be used to guide diagnosis,prognosis,and treatment of skin acne diseases. Keywords:acne;macrogenomics;facial skin;lipids;machine learning;multi-set canonical correlation analysis 痤疮是世界上最常见的皮肤病之一,表现为部、胸背部等皮脂溢出区,患者表现为粉刺、丘 一种毛囊皮脂腺的慢性炎症性,主要发生于面 疹、脓疱、囊肿、结节及萎缩性瘢痕等皮损,大约 收稿日期:2019-10-09.网络出版日期:2019-05-17. 会影响80%的青少年和青壮年山。痤疮普遍而且 基金项目:国家自然科学基金面上项目(61671028):北京市自 错误的被概括为只是患者经历的一个阶段,但对 然科学基金面上项目(4162018). 通信作者:王瑜.E-mail:wangyu(@btbu.edu.cn. 于一些人来说,座疮可以持续多年,不仅影响患DOI: 10.11992/tis.201810005 网络出版地址: http://kns.cnki.net/kcms/detail/23.1538.TP.20190516.2353.002.html 基于 MCCA 的痤疮宏基因组数据辅助分析 孙梦茹1 ,王瑜1 ,何聪芬2 ,贾焱2 ,高学义1 (1. 北京工商大学 计算机与信息工程学院 食品安全大数据技术北京市重点实验室,北京 100048; 2. 北京工商 大学 理学院 中国轻工业化妆品重点实验室,北京 100048) 摘 要:痤疮作为常见皮肤病之一,发病机制复杂,其中微生物定植在痤疮发病中的作用是一个热点研究问 题。本文从宏基因组学的角度,利用机器学习方法分析痤疮宏基因组数据,包括痤疮患者的患病皮肤 (diseased skin, DS) 样本集和健康皮肤 (healthy skin, HS) 样本集,以及正常对照组 (normal control, NC) 样本集。为了同时分 析 3 组样本集以获得可以区分不同样本集的脂质,使用多重集典型相关分析 (multi-set canonical correlation ana￾lysis, MCCA) 方法进行研究。实验结果可得到仅对某一样本集有显著影响的脂质,以及同时对 3 个样本集影响 程度不同的脂质,这些脂质可以作为判别皮肤状态的指标,用于辅助指导皮肤痤疮疾病的诊断、预后和治疗。 关键词:痤疮;宏基因组学;面部皮肤;脂质;机器学习;多重集典型相关分析 中图分类号:TP391 文献标志码:A 文章编号:1673−4785(2020)05−0972−06 中文引用格式:孙梦茹, 王瑜, 何聪芬, 等. 基于 MCCA 的痤疮宏基因组数据辅助分析 [J]. 智能系统学报, 2020, 15(5): 972–977. 英文引用格式:SUN Mengru, WANG Yu, HE Congfen, et al. Assisted analysis of acne metagenomic sequencing data using multi-set canonical correlation analysis methods[J]. CAAI transactions on intelligent systems, 2020, 15(5): 972–977. Assisted analysis of acne metagenomic sequencing data using multi-set canonical correlation analysis methods SUN Mengru1 ,WANG Yu1 ,HE Congfen2 ,JIA Yan2 ,GAO Xueyi1 (1. Beijing Key Laboratory of Big Data Technology for Food Safety, School of Computer and Information Engineering, Beijing Tech￾nology and Business University, Beijing 100048, China; 2. Key Laboratory of Cosmetic of China National Light Industry, School of Science, Beijing Technology and Business University, Beijing 100048, China) Abstract: As one of the common skin diseases, the pathogenesis of acne is very complicated. The role of microbial col￾onization in the pathogenesis of acne is an active research area. The purpose of this paper is to analyze acne metagenom￾ic data, including sample sets of acne diseased skin (DS) and healthy skin (HS) as well as normal control (NC) by using machine learning from the perspective of macrogenomics. Multi-set canonical correlation analysis (MCCA) method is used to analyze the above three sample sets at the same time and to confirm the lipids that can distinguish these three sample sets. The results show that lipids that had a significant impact on only one set and those that had different im￾pacts on the three sample sets respectively can be used as indicators to determine the skin status. Moreover, these lipids can be used to guide diagnosis, prognosis, and treatment of skin acne diseases. Keywords: acne; macrogenomics; facial skin; lipids; machine learning; multi-set canonical correlation analysis 痤疮是世界上最常见的皮肤病之一,表现为 一种毛囊皮脂腺的慢性炎症性,主要发生于面 部、胸背部等皮脂溢出区,患者表现为粉刺、丘 疹、脓疱、囊肿、结节及萎缩性瘢痕等皮损,大约 会影响 80% 的青少年和青壮年[1]。痤疮普遍而且 错误的被概括为只是患者经历的一个阶段,但对 于一些人来说,痤疮可以持续多年,不仅影响患 收稿日期:2019−10−09. 网络出版日期:2019−05−17. 基金项目:国家自然科学基金面上项目 (61671028);北京市自 然科学基金面上项目 (4162018). 通信作者:王瑜. E-mail:wangyu@btbu.edu.cn. 第 15 卷第 5 期 智 能 系 统 学 报 Vol.15 No.5 2020 年 9 月 CAAI Transactions on Intelligent Systems Sep. 2020
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有