" Bacteria_phyla"列有70个级别,但有24,364行。如何组合匹配的水平,以便我有70个门和每个门相关的正确序列读数?
示例数据:
structure(list(taxa.P = structure(c(7L, 61L, 51L, 27L, 51L, 25L,
18L, 51L, 51L, 51L, 22L, 51L, 51L, 7L, 51L), .Label = c(" p__",
" p__[Caldithrix]", " p__[Parvarchaeota]", " p__[Thermi]", " p__AC1",
" p__Acidobacteria", " p__Actinobacteria", " p__AD3", " p__AncK6",
" p__Armatimonadetes", " p__Bacteroidetes", " p__BHI80-139",
" p__BRC1", " p__Caldithrix", " p__CD12", " p__Chlamydiae", " p__Chlorobi",
" p__Chloroflexi", " p__Crenarchaeota", " p__Cyanobacteria",
" p__Elusimicrobia", " p__Euryarchaeota", " p__FCPU426", " p__Fibrobacteres",
" p__Firmicutes", " p__Fusobacteria", " p__Gemmatimonadetes",
" p__GN02", " p__GN04", " p__GOUTA4", " p__H-178", " p__Hyd24-12",
" p__Kazan-3B-28", " p__KSB3", " p__LCP-89", " p__LD1", " p__Lentisphaerae",
" p__MVS-104", " p__NC10", " p__Nitrospirae", " p__NKB19", " p__OD1",
" p__OP1", " p__OP11", " p__OP3", " p__OP8", " p__OP9", " p__PAUC34f",
" p__Planctomycetes", " p__Poribacteria", " p__Proteobacteria",
" p__SAR406", " p__SBR1093", " p__SC4", " p__Spirochaetes", " p__SR1",
" p__Tenericutes", " p__TM6", " p__TM7", " p__TPD-58", " p__Verrucomicrobia",
" p__VHS-B3-43", " p__WPS-2", " p__WS1", " p__WS2", " p__WS3",
" p__WS5", " p__WWE1", " p__ZB3", "k__Bacteria"), class = "factor"),
total_phyla = c(1, 5, 65, 33, 1, 19, 13, 48, 1, 1, 1, 5,
3, 1, 32)), .Names = c("taxa.P", "total_phyla"), row.names = c(NA,
15L), class = "data.frame")