# 安装
metid 包能够用于 in-house 代谢物库构建,并可利用 MS2 spectra 进行代谢物鉴定。metid 自带数据库,来自于公共数据库的整合。
if(!require(remotes)){ | |
install.packages("remotes") | |
} | |
remotes::install_github("tidymass/metid") |
# 建库
# 构建内部库
# 质谱数据准备
将标准品原始质谱数据用 ProteoWizard 转换为 mzXM 格式.
# 标准品信息表
将标准品信息整理至 csv 格式表格中,参考如下。
共 11 列:“Lab.ID”, “Compound.name”, “mz”, “RT”, “CAS.ID”, “HMDB.ID”, “KEGG.ID”, “Formula”, “mz.pos”, “mz.neg”, “Submitter”。也可以添加更多的信息,如 “Family”, “Sub.pathway” 和 “Note”。
Lab.ID: 不可重复
mz: 化合物准确的 mass
RT: 保留时间,以秒为单位
mz.pos: 正离子模式下化合物的 mz,如 M+H。可设为 NA
mz.neg: 负离子模式下化合物的 mz,如 M-H。可设为 NA
Submitter: 个人或组织名称,可设为 NA
新建目录 database_construction
,将正离子数据放在 database_construction/POS
中,将负离子数据放在 database_construction/NEG
中,标准品信息表 metabolite.info_RPLC.csv
放在 database_construction
中。
注意:每个文件名必须包含碰撞能(collision energy),如 test_NCE25.mzXML
。
# 建库
library(metid) | |
datapath<-file.path("./database_construction") | |
mydb <- construct_database( | |
path = datapath, | |
version = "0.0.1", | |
metabolite.info.name = "metabolite.info_RPLC.csv", | |
source = "my lab", | |
link = "http://xxx.com", | |
creater = "someone", | |
email = "x@126.com", | |
rt = TRUE, # Do the metabolites have RT information or not? | |
mz.tol = 15, # m/z tolerance for the match between metabolites and precursor m/z of MS2 spectra. | |
rt.tol = 30, # RT tolerance for the match between metabolites and precursor m/z of MS2 spectra. | |
threads = 10 | |
) | |
# 保存数据库 | |
save(mydb, file="mydb") |
注意:保存时前后名字必须一样。
# 构建公共库
可将 msp 格式的数据库转换为 metid 数据库。目前有 bug:Error in `dplyr::select ()`: ! Can't subset columns that don't exist. ✖ Column `Name` doesn't exist.
bug 解决前可以下载已经构建好的公共库:Database provided for metid。
# MassBank
下载最新的 release MassBank_NIST.msp,将其放在当前目录下。
setwd("C:/Users/liu/Downloads") | |
library(metid) | |
massbank_database_2022.12.01 <- construct_mona_database( | |
file = "MassBank_NIST.msp", | |
path = ".", | |
version = "2022.12.01", | |
source = "MassBank", | |
link = "https://github.com/MassBank/MassBank-data/releases", | |
creater = "Hualin Liu", | |
email = "LHL371@126.com", | |
rt = FALSE, | |
threads = 15 | |
) | |
save(massbank_database_2022.12.01, file = "massbank_database_2022.12.01") |
# MoNA
下载对应数据库,如此处下载 LC-MS Spectra (153,242 spectra)
,截至 2023.04.16。
library(metid) | |
mona_database_2023.04.16 <- construct_mona_database( | |
file = "MoNA-export-LC-MS_Spectra.msp", | |
path = ".", | |
version = "2023.04.16", | |
source = "MoNA", | |
link = "https://mona.fiehnlab.ucdavis.edu/", | |
creater = "Hualin Liu", | |
email = "LHL371@126.com", | |
rt = FALSE, | |
threads = 10 | |
) | |
save(mona_database_2023.04.16, file = "mona_database_2023.04.16") |
# 参考
- Construct in-house MS2 datbase using metid
- Construct public MS2 datbase using metid
# 加关注
关注公众号 “生信之巅”。
敬告:使用文中脚本请引用本文网址,请尊重本人的劳动成果,谢谢!