Select 並使用 R 比較來自兩個數據幀的兩個元素

Question

我想使用兩個數據框計算兩種蛋白質之間的最短路徑。 例如，我想計算第一個列表中的第一個和秒列表中的第一個、第一個列表中的第一個和第二個列表中的第二個等的最短路徑。

structure(list(LAS1L = c("FKBP4", "RBM6", "UPF1", "SLC25A5", 
"DHX33", "ELAC2", "CCDC124", "RPS20", "CSDE1", "AKAP8L", "UTP18", 
"PTBP1", "DCN", "MATR3", "SAMD4A", "AQR", "STRAP", "SEC63", "BCLAF1", 
"TFB1M", "GRN", "ZCCHC8", "NSUN2", "SKIV2L2", "STAU2", "CTNNA1", 
"YTHDC2", "POLR2B", "TPR", "MAP4", "NOP16", "FAM120A", "R3HDM1", 
"PTCD2", "RRP12", "MRTO4", "THRAP3", "NOP58", "USP36", "MLL3", 
"PUM2", "MRPL43", "ZFR", "RC3H2", "ZC3H11A", "PARP12", "ALDH18A1", 
"CSDA", "CCAR1")), class = "data.frame", row.names = c(NA, -49L
))

structure(list(GNL3L = c("FMR1", "FRAXA", "UBA1", "CSTF2", "MECP2", 
"PHF6", "RBM10", "GSPT2", "SLC25A5", "EIF1AX", "NKRF", "RPS4X", 
"RBMX2", "HTATSF1", "LAS1L", "MBNL3", "HUWE1", "RPL10", "RPL15", 
"RBMX", "NONO", "RPGR", "UPF3B", "RBM3", "HNRNPH2", "UTP14A", 
"DKC1", "MEX3C", "DDX3X", "FLNA", "FAM120C")), class = "data.frame", row.names = c(NA, 
-31L))

到目前為止，我只是提出了這個問題。

sp<-shortest_path[protein1[,1],protein2[,1]]

最短路徑的輸入：

structure(c(0, 4, 6, 4, 4, 4, 4, 3, 3, 3, 5, 3, 5, 3, 3, 3, 4, 
3, 3, 3, 4, 0, 5, 4, 4, 4, 4, 3, 3, 3, 5, 3, 5, 3, 3, 3, 4, 3, 
3, 3, 6, 5, 0, 6, 4, 6, 5, 5, 5, 5, 7, 5, 6, 5, 5, 3, 6, 5, 5, 
5, 4, 4, 6, 0, 3, 3, 3, 3, 3, 3, 4, 3, 5, 3, 3, 3, 4, 3, 3, 3, 
4, 4, 4, 3, 0, 4, 3, 3, 3, 3, 4, 3, 5, 3, 3, 3, 4, 3, 3, 3, 4, 
4, 6, 3, 4, 0, 3, 3, 3, 3, 5, 3, 5, 3, 3, 3, 4, 3, 3, 3, 4, 4, 
5, 3, 3, 3, 0, 3, 3, 2, 3, 3, 5, 3, 3, 3, 4, 3, 3, 3, 3, 3, 5, 
3, 3, 3, 3, 0, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 2, 2, 3, 3, 5, 3, 
3, 3, 3, 2, 0, 2, 4, 2, 4, 2, 2, 2, 3, 2, 2, 2, 3, 3, 5, 3, 3, 
3, 2, 2, 2, 0, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 5, 5, 7, 4, 4, 5, 
3, 4, 4, 2, 0, 4, 6, 4, 4, 4, 5, 4, 4, 4, 3, 3, 5, 3, 3, 3, 3, 
2, 2, 2, 4, 0, 4, 2, 2, 2, 3, 2, 2, 2, 5, 5, 6, 5, 5, 5, 5, 4, 
4, 4, 6, 4, 0, 4, 4, 4, 5, 4, 4, 4, 3, 3, 5, 3, 3, 3, 3, 2, 2, 
2, 4, 2, 4, 0, 2, 2, 3, 2, 2, 2, 3, 3, 5, 3, 3, 3, 3, 2, 2, 2, 
4, 2, 4, 2, 0, 2, 3, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 4, 
2, 4, 2, 2, 0, 3, 2, 2, 2, 4, 4, 6, 4, 4, 4, 4, 3, 3, 3, 5, 3, 
5, 3, 3, 3, 0, 3, 3, 3, 3, 3, 5, 3, 3, 3, 3, 2, 2, 2, 4, 2, 4, 
2, 2, 2, 3, 0, 1, 2, 3, 3, 5, 3, 3, 3, 3, 2, 2, 2, 4, 2, 4, 2, 
2, 2, 3, 1, 0, 2, 3, 3, 5, 3, 3, 3, 3, 2, 2, 2, 4, 2, 4, 2, 2, 
2, 3, 2, 2, 0), .Dim = c(20L, 20L), .Dimnames = list(c("1810055G02Rik", 
"2810046L04Rik", "4922501C03Rik", "4930572J05Rik", "9830001H06Rik", 
"A1CF", "A2M", "AAGAB", "AATF", "ABCA1", "ABCA13", "ABCA2", "ABCA4", 
"ABCB1", "ABCB7", "ABCC2", "ABCC8", "ABCD1", "ABCD3", "ABCD4"
), c("1810055G02Rik", "2810046L04Rik", "4922501C03Rik", "4930572J05Rik", 
"9830001H06Rik", "A1CF", "A2M", "AAGAB", "AATF", "ABCA1", "ABCA13", 
"ABCA2", "ABCA4", "ABCB1", "ABCB7", "ABCC2", "ABCC8", "ABCD1", 
"ABCD3", "ABCD4")))

提前致謝！

Answer 1

也許你可以試試下面的代碼

outer(protein1$LAS1L, protein2$GNL3L, FUN = function(x, y) shortest_path[x, y])