我在R中有一个数据框，每行都有一个唯一的＆＃34; X＆＃34;和＆＃34; Y＆＃34;位置（如图像中的像素）。在处理期间，数据帧被合并多次，现在rownames已被加扰。我需要第一个数据框中的原始rownames才能继续处理数据。例如：
>head(dr1)
X Y RA1_Mix1_25Apr14.cel_MEAN RA2_Mix1_25Apr14.cel_MEAN
1 0 0 5707 8141
2 1 0 259 318
3 2 0 5005 7749
4 3 0 193 253
5 4 0 112 94
6 5 0 305 237
RA3_Mix1_25Apr14.cel_MEAN CTR1_Mix1_21Feb14.cel_MEAN
1 8375 7123
2 281 215
3 7824 6309
4 183 168
5 61 96
6 177 120
CTR2_Mix1_21Feb14.cel_MEAN CTR3_Mix1_21Feb14.cel_MEAN
1 8216 6726
2 382 197
3 7234 7333
4 248 284
5 100 69
6 259 193
> # Add UnitNames to X and Y from the filtered scm file.
> dr1.1 <- merge(dr1, scm2, by=c("X", "Y"), all.x=TRUE)
>
> # Add annotation from the ann file pulled form scheme.
> dr1.2 <- merge(dr1.1, ann, all.x=TRUE)
> head(dr1.2)
UNIT_ID X Y RA1_Mix1_25Apr14.cel_MEAN RA2_Mix1_25Apr14.cel_MEAN
1 -23 503 1054 35 30
2 -23 330 922 41 32
3 -23 332 1385 41 30
4 -23 348 178 44 36
5 -23 372 1135 51 35
6 -23 879 1585 55 35
RA3_Mix1_25Apr14.cel_MEAN CTR1_Mix1_21Feb14.cel_MEAN
1 41 37
2 31 37
3 30 33
4 37 39
5 40 45
6 28 30
CTR2_Mix1_21Feb14.cel_MEAN CTR3_Mix1_21Feb14.cel_MEAN ProbeLength Mask
1 34 41 25 -2
2 37 30 25 -2
3 27 31 25 -2
4 39 50 25 -2
5 39 39 25 -2
6 35 33 25 -2
EXON_ID PROBESET_ID TranscriptClusterID GeneName GeneSymbol GeneAccession
1 -23 -23 NA <NA> <NA> <NA>
2 -23 -23 NA <NA> <NA> <NA>
3 -23 -23 NA <NA> <NA> <NA>
4 -23 -23 NA <NA> <NA> <NA>
5 -23 -23 NA <NA> <NA> <NA>
6 -23 -23 NA <NA> <NA> <NA>
EntrezID Chromosome Cytoband Start Stop Strand CrossHybridization
1 NA <NA> <NA> NA NA <NA> NA
2 NA <NA> <NA> NA NA <NA> NA
3 NA <NA> <NA> NA NA <NA> NA
4 NA <NA> <NA> NA NA <NA> NA
5 NA <NA> <NA> NA NA <NA> NA
6 NA <NA> <NA> NA NA <NA> NA
ProbesetType
1 <NA>
2 <NA>
3 <NA>
4 <NA>
5 <NA>
6 <NA>
> erccs1_ln_rn <- c("AFFX-ERCC-00171_st", "AFFX-ERCC-00136_st", "AFFX-ERCC-00003_st", "AFFX-ERCC-00009_st", "AFFX-ERCC-00108_st", "AFFX-ERCC-00145_st", "AFFX-ERCC-00042_st", "AFFX-ERCC-00043_st", "AFFX-ERCC-00111_st", "AFFX-ERCC-00116_st", "AFFX-ERCC-00022_st", "AFFX-ERCC-00060_st", "AFFX-ERCC-00076_st", "AFFX-ERCC-00092_st", "AFFX-ERCC-00035_st", "AFFX-ERCC-00044_st", "AFFX-ERCC-00095_st", "AFFX-ERCC-00112_st", "AFFX-ERCC-00131_st", "AFFX-ERCC-00025_st", "AFFX-ERCC-00051_st", "AFFX-ERCC-00062_st", "AFFX-ERCC-00071_st", "AFFX-ERCC-00079_st", "AFFX-ERCC-00162_st", "AFFX-ERCC-00165_st", "AFFX-ERCC-00019_st", "AFFX-ERCC-00053_st", "AFFX-ERCC-00078_st", "AFFX-ERCC-00084_st", "AFFX-ERCC-00144_st", "AFFX-ERCC-00054_st", "AFFX-ERCC-00059_st", "AFFX-ERCC-00099_st", "AFFX-ERCC-00126_st", "AFFX-ERCC-00148_st", "AFFX-ERCC-00163_st", "AFFX-ERCC-00170_st", "AFFX-ERCC-00034_st", "AFFX-ERCC-00085_st", "AFFX-ERCC-00154_st", "AFFX-ERCC-00157_st", "AFFX-ERCC-00160_st")
> erccs1_linear <- dr1.2[dr1.2$GeneName %in% erccs1_ln_rn, ]
> head(erccs1_linear)
UNIT_ID X Y RA1_Mix1_25Apr14.cel_MEAN RA2_Mix1_25Apr14.cel_MEAN
18090 76 991 123 957 595
18091 76 1362 1345 6336 4770
18092 76 846 745 1443 719
18093 76 1153 1419 298 163
18094 76 429 1242 10413 9262
18095 76 489 759 5537 4239
RA3_Mix1_25Apr14.cel_MEAN CTR1_Mix1_21Feb14.cel_MEAN
18090 611 2959
18091 4732 8408
18092 885 2365
18093 155 785
18094 9438 13124
18095 4133 8646
CTR2_Mix1_21Feb14.cel_MEAN CTR3_Mix1_21Feb14.cel_MEAN ProbeLength Mask
18090 2205 1202 25 32
18091 7400 5700 25 32
18092 1703 705 25 32
18093 714 310 25 32
18094 12012 10879 25 32
18095 7842 5544 25 32
EXON_ID PROBESET_ID TranscriptClusterID GeneName GeneSymbol
18090 76 76 17883608 AFFX-ERCC-00003_st <NA>
18091 76 76 17883608 AFFX-ERCC-00003_st <NA>
18092 76 76 17883608 AFFX-ERCC-00003_st <NA>
18093 76 76 17883608 AFFX-ERCC-00003_st <NA>
18094 76 76 17883608 AFFX-ERCC-00003_st <NA>
18095 76 76 17883608 AFFX-ERCC-00003_st <NA>
GeneAccession EntrezID Chromosome Cytoband Start Stop Strand
18090 17883608 -1 <NA> <NA> 0 0 ?
18091 17883608 -1 <NA> <NA> 0 0 ?
18092 17883608 -1 <NA> <NA> 0 0 ?
18093 17883608 -1 <NA> <NA> 0 0 ?
18094 17883608 -1 <NA> <NA> 0 0 ?
18095 17883608 -1 <NA> <NA> 0 0 ?
CrossHybridization ProbesetType
18090 0 control->affx
18091 0 control->affx
18092 0 control->affx
18093 0 control->affx
18094 0 control->affx
18095 0 control->affx
所以现在我只需要收集＆＃39; X＆＃39;和＆＃39; Y＆＃39;来自＆＃39; erccs1_linear＆＃39;的值数据框并从dr1获取rownames的向量以进行进一步的数据分析。非常感谢任何建议或反馈！