ddply 的第二次迭代改变了第一次迭代的结果

【问题标题】：second iteration of ddply changes result of first iterationddply 的第二次迭代改变了第一次迭代的结果
【发布时间】：2016-10-07 12:01:33
【问题描述】：

我正在尝试运行 ddply 来计算第 1 列和第 2 列中每个元素的出现次数。所以我使用 ddply 两次：

1) 当我第一次运行操作时，它会创建我期望的值

xx <- ddply(
    xx, "Annotated.Sequence", transform, 
    PSMPerPep = length(Annotated.Sequence)
)

2) 但是，当我第二次在不同的列上运行相同的操作时，它不仅会创建一个包含错误数字的列，而且它还设法更改了第一列中的数字。有什么建议么？ 

xx <- ddply(
    xx, "Protein.Accessions", transform, 
    PSMPerProt = length(Protein.Accessions)
)

xx <- structure(list(Annotated.Sequence = c("ACDLPAWVHFPDTER", "ACIGDTLCQK", 
"ACIGDTLCQK", "ADEEFFAK", "AENPGISFGQVGK", "AETLYEGPSDDPFCTAIR", 
"AETLYEGPSDDPFCTAIR", "AFDDESVQK", "AILGATNPLQSAPGTIR", "AILGATNPLQSAPGTIR", 
"AIVNATTHYNDPVK", "AKGDNDPLDVCEIGEK", "ALALLEDEER", "ALALLEDEER", 
"ALALLEDEER", "ALALLEDEER", "APVGNPEGADKPNKK", "APVVQQPAPSFK", 
"AQPPEAGPQGLHDLGR", "AQPPEAGPQGLHDLGR", "AQPPEAGPQGLHDLGR", "ASTGEEYTAETDPGVQSVK", 
"ASTSTSAPASTPSPSSK", "ATGTTIVTDTGEFEQIAK", "AVANVNDIIAPALIK", 
"AVANVNDIIAPALIK", "AVANVNDIIAPALIK", "AVANVNDIIAPALIK", "AVASSGQELSVEER", 
"AYLAENDPDSVEAFEK", "AYLAENDPDSVEAFEK", "CLANLRPLLDSGTMGTK", 
"CLANLRPLLDSGTMGTK", "DDDHNGHIDFITAASNLR", "DDGYGGGYGGGRPDDR", 
"DDLFNTNASIVR", "DFNTGSANAAADAGGEDIPDLVDQKFDDVE", "DFPQLDSQLPK", 
"DLFDYAQEK", "DLFDYAQEK", "DLQELIAEGNTK", "DNDSYGSSNRR", "DNDSYGSSNRR", 
"DQANDGLSSALLILYLDSAR", "DQANDGLSSALLILYLDSAR", "DQANDGLSSALLILYLDSAR", 
"DVGADGQPTEELK", "DVYEDELVPVFEAVGR", "DVYEDELVPVFEAVGR", "DVYEDELVPVFEAVGR", 
"DVYEDELVPVFEAVGR", "DVYEDELVPVFEAVGR", "EADTNNDGEIDIQEFTSLLAAK", 
"EADTNNDGEIDIQEFTSLLAAK", "EDFTLLDFINAVK", "EDFTLLDFINAVK", "EEEQEEEEDAEK", 
"EFILEQHNK", "EGETETEGAATATAAATEAK", "EGTIPTDYEQATGLQR", "EGTIPTDYEQATGLQR", 
"EIFDNVNSEFNVALK", "EIFISNITQANPGIVTCLENHPHK", "ELIEPAEGEEVDEDAEPQYR", 
"ELIEPAEGEEVDEDAEPQYR", "ELNNYEIRPGR", "ELNNYEIRPGR", "EPTPSIASDISLPIATQELR", 
"EPTPSIASDISLPIATQELR", "EPTPSIASDISLPIATQELR", "EPTPSIASDISLPIATQELR", 
"EPTPSIASDISLPIATQELR", "EPTPSIASDISLPIATQELR", "EPTPSIASDISLPIATQELR", 
"ERLLDEWFTLDEVPK", "ERPPDHQHSAQVK", "ESDEFIAEK", "ESNPADGRENLQSIEDR", 
"ETIEPAVR", "FDLNEPLHLSFLQNAAK", "FGGGRPDDR", "FRQELTSLADVYINDAFGTAHR", 
"FVSEVAGTNPVNENVPVVGGHSGVTIVPLLSQTK", "FWQTYSSAEEVLQK", "GANTHLSTFSFTK", 
"GAPGVAADVSHVPTNSTVK", "GAPGVAADVSHVPTNSTVK", "GATYGKPTNQGVNQLK", 
"GDNDPLDVCEIGEK", "GEGEGGELPGVTPYPNENELIK", "GEVTASGDDLVIDGHK", 
"GEVTASGDDLVIDGHK", "GFDSAEGLQTSGLHVQGQK", "GGDVSSTTYDA", "GGNDYEIYNDPR", 
"GGVIMDVVNADQAK", "GIFGYGYETPSAIQQR", "GISELGIYPAVDPLDSK", "GMITVTDPDLIEK", 
"GNPTVEVDFTTDK", "GNPTVEVDFTTDK", "GSGHSNTVR", "GTDEANGATEFDR", 
"GTEVNDTGAPISVPVGR", "GTEVNDTGAPISVPVGR", "GTQFGLQTPGSR", "GTQFGLQTPGSR", 
"GWDISLTNNYGK", "GWTQWYDLTEDGTRPQAMT", "GWTQWYDLTEDGTRPQAMT", 
"HEGGFGGGRPDDR", "HIANISNAK", "HNDDEQYVWESNAGGK", "HSEFVAYPIQLVVTK", 
"HVVFGEVTDGLDIVK", "HVVFGEVTDGLDIVK", "HVVFGEVTDGLDIVK", "IADSGLTALSYTQELRPGVK", 
"IADSGLTALSYTQELRPGVK", "IDEFLLSLDGTPNK", "IDEFLLSLDGTPNK", "IEEELGSEAIYAGK", 
"IEEELGSEAIYAGK", "IEEELGSEAIYAGK", "IESFGSGSGATSK", "IHFIEAQDLQGK", 
"IIPAIATTTATVSGLVALEMIK", "IIAAVPNASDVAVCSSR", "ILENSEGGR", "IPRDVYEDELVPVFEAVGR", 
"IQEFKPSNK", "IQIVGDDLTVTNPTR", "ISPSDQSSTVISASWDK", "ISPSDQSSTVISASWDK", 
"ISSNPNPVVQMSVGHK", "ISSNPNPVVQMSVGHK", "ISSNPNPVVQMSVGHK", "ISSNPNPVVQMSVGHK", 
"ISSNPNPVVQMSVGHK", "ISSNPNPVVQMSVGHK", "IVDMSTSK", "IVIEESGQL", 
"IVSDWSNIVVAYEPVWAIGTGLAATPEDAEETHK", "IVTGVNPQSAVK", "IWCFGPDGNGPNLVVDQTK", 
"KAEDEEEDEGEIDETGLDPK", "KIESCGTSSGTPSASVVIEESGEAEK", "KIESFGSGSGATSK", 
"KLEDLSPSTHNMEVPNVSR", "KLQINLVVEDALVSLDDLQAAVEEDEDHVQSTDIAAMQK", 
"KPNVGCQQDSEELLK", "KPNVGCQQDSEELLK", "KPNVGCQQDSEELLK", "KPNVGCQQDSEELLK", 
"KPNVGCQQDSEELLK", "KPTATTETCAVAAVSAAYEQDAK", "KREEILEEIAK", 
"KYDVVVIGGGPGGYVAAIK", "LADYLINVGY", "LEWLTLMPNASNLDK", "LEWLTLMPNASNLDK", 
"LFCDFGDEFEVLDTTGEEPK", "LFCDFGDEFEVLDTTGEEPK", "LFCDFGDEFEVLDTTGEEPK", 
"LFCDFGDEFEVLDTTGEEPK", "LGANAILGVSLAAANAAAAAQGIPLYK", "LGIHEDAQNR", 
"LISWYDNEYGYSTR", "LLGVCCSVDNCR", "LLYGHLDDPHNQEIER", "LLYNDYVSNPSK", 
"LQSENFTYEIVK", "LRDQAINNAQR", "LSHVSTGGGASLELLEGK", "LTGGEDNQYGIPK", 
"LVEALCNEPEEK", "LVEDPQIVAPFMDK", "LWDLETGETTQR", "LWDLETGETTQR", 
"MGHAGAIVAGGK", "MLIFEDVISGDELLSDAYDVK", "MLIFEDVISGDELLSDAYDVK", 
"MPIGDSLFDEAGAK", "MQLVQESEEK", "MQLVQESEEK", "MQLVQESEEK", "NCFLNLAIPIVVFTETTEVRKTK", 
"NDREFNGIIAQTTNDNITEAGK", "NFALLGVGTSK", "NGDQDLVLEVAQHLGENTVR", 
"NLIAFSEDGSDPYVR", "NLIAFSEDGSDPYVR", "NLIAFSEDGSDPYVR", "NLIAFSEDGSDPYVR", 
"NLIAFSEDGSDPYVR", "NLIAFSEDGSDPYVR", "NLIAFSEDGSDPYVR", "NQAALNPK", 
"NVPGVETASVK", "NWSQCVELAR", "QAFDDAVADLETLSEDSYK", "QATFPGVQMK", 
"QATFPGVQMK", "QDVIITALDNVEAR", "QDVIITALDNVEAR", "QDVIITALDNVEAR", 
"QEEEEEEK", "QGDNEIEGLTDTTVPK", "QLENGTTLGQSPLGQIQLTIR", "RAGELTQEELER", 
"REAQLCVLCDSVTEESIIK", "RERPPDHQHSAQVK", "RERPPDHQHSAQVK", "RERPPDHQHSAQVK", 
"RISTVGELNDLFADK", "RISTVGELNDLFADK", "RQENLAK", "RQGTSPDTMR", 
"SEPLPTEEEK", "SFGQFNPGCVER", "SFGQFNPGCVER", "SFGQFNPGCVER", 
"SFGQFNPGCVER", "SFGQFNPGCVER", "SGETEDTFIADLSVGLR", "SGLAEGYSYTDANK", 
"SGLAEGYSYTDANK", "SGQAAFGNMCR", "SGYTLPSNIISNTDVTR", "SHMSGSPGPGGSNTAPSTPVIGGSDKPGMEEK", 
"SIDDSVAQIIG", "SINPNYTPVPVPETK", "SIVPSGASTGVHEALELR", "SLQDIIAILGMDELSEADK", 
"SNETGILDAIK", "SSSSLLASPGHISVK", "STGDDNEVAEEEEADVEFTPVVQLDK", 
"STAAEELANTFGYK", "SVEQIDDCPAGNIIGLVGIDQFLLK", "SYTAADATLK", 
"SAAGTYVVFGEAK", "TAEDVIAAFECN", "TASGNIIPSSTGAAK", "TASGNIIPSSTGAAK", 
"TASGNIIPSSTGAAK", "TCNVLVAIEQQSPDIAQGLHYEK", "TCYNCGK", "TGQFGWSANMER", 
"TGTPLFSSHMLDLSEETDDENIATCAK", "TGYSMVQENGQR", "TGYSMVQENGQR", 
"THGPQIK", "TKQTILIAHYPSGVQPGEATTLVEK", "TLNPVFDQSFDFSVSLPEVQR", 
"TLNPVFDQSFDFSVSLPEVQRR", "TLNPVFDQSFDFSVSLPEVQRR", "TLTTVQGVPNEYDLK", 
"TLTTVQGVPNEYDLKK", "TVEDDHPIPEDVHENYQNTVAEFASR", "VATLYDMIDHQDATNLDDK", 
"VCPTTETIYNDEFYTK", "VCPTTETIYNDEFYTK", "VCPTTETIYNDEFYTK", "VDFNVPLDGK", 
"VDVGQQPLR", "VEEPLGSYAPNTIDKPFYER", "VEQEAEQQIHK", "VHADQTPEDLDMDDGDTIEAHR", 
"VHLVAIDIFTGK", "VIITAPSADAPMFVVGVNEDK", "VIITAPSADAPMFVVGVNEDK", 
"VITSSAR", "VNLDTDCQYAYLTGIR", "VNLDTDCQYAYLTGIRDYVTNK", "VNSAVVTCPAYFNDAQR", 
"VVDLLEHVAK", "VVDLLEHVAK", "VVDLLEHVAK", "VVNDTFGIEEGLMTTVHSITATQK", 
"VVQTDETAR", "WAGNANELNAGYAADGYAR", "WVVIGDENFGEGSSR", "YGGPPPGWEGPHPQR", 
"YGIEPTMVVQGVK", "YGQSAGNVGDEGGVAPDIK", "YHIEEEGSSK", "YHIEEEGSSK", 
"YKGEVTASGDDLVIDGHK", "YLDQVLDHQR", "YQALSDPSQLESEPELFIR", "YQCVVLTEMK", 
"YVDEQVAAAEADAPPEAK", "YVECSALTQR", "YVHGGNVLIDPTAK", "YAATPANPAK", 
"YAATPANPAK", "AAADYAPNAAVCIISNPVNSTVPIVAEVFK", "AAADYAPNAAVCIISNPVNSTVPIVAEVFK", 
"AAIRDPNPVVFLENEIAYGETFK", "AAVEEGILPGGGTALIK"), Protein.Accessions = c("HS_A0FGR8", 
"HS_A0AVT1", "HS_A0AVT1", "CA_Q9URB4", "CA_Q9UVL1", "CA_Q5A0M4", 
"CA_Q5A0M4", "CA_Q5A397", "CA_Q5AG68", "CA_Q5AG68", "CA_Q5AIA6", 
"CA_P83777", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", 
"CA_Q9URB4", "CA_Q9Y7F0", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", 
"CA_Q5A017", "CA_Q5AGX8", "CA_Q5A017", "CA_P30575", "CA_P30575", 
"CA_P30575", "CA_P30575", "CA_O42766", "CA_Q5A860", "CA_Q5A860", 
"HS_A0AVT1", "HS_A0AVT1", "HS_A0AVT1", "CA_Q5A4I4", "CA_Q5AMP4", 
"CA_Q59TU0", "CA_P83775", "CA_Q9URB4", "CA_Q9URB4", "CA_Q5ANH5", 
"CA_Q59X49", "CA_Q59X49", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", 
"CA_Q5AL30", "HS_A0AV96", "HS_A0AV96", "HS_A0AV96", "HS_A0AV96", 
"HS_A0AV96", "CA_Q59Q76", "CA_Q59Q76", "HS_A0AVT1", "HS_A0AVT1", 
"CA_Q59N01", "CA_Q5AGD1", "CA_Q59S96", "CA_Q5ALV5", "CA_Q5ALV5", 
"CA_Q5AF03", "HS_A0AVT1", "CA_Q96VB9", "CA_Q96VB9", "HS_A0AV96", 
"HS_A0AV96", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", 
"HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", 
"CA_Q9P940", "CA_Q59QN7", "HS_A0FGR8", "HS_A0AVT1", "CA_Q5A4I4", 
"CA_P46273", "CA_Q5AMP4", "HS_A0AVT1", "HS_A0FGR8", "CA_Q5AMP4", 
"CA_Q5AMP4", "CA_Q5A6R1", "CA_P83777", "CA_Q59P14", "CA_Q5ADM7", 
"CA_Q5ADM7", "CA_Q5A786", "CA_Q5AKV3", "CA_P31353", "CA_Q5AIA6", 
"CA_P87206", "CA_Q59UR7", "HS_A0AVT1", "CA_P30575", "CA_P30575", 
"CA_P46614", "CA_Q59LS1", "CA_Q59UR7", "CA_Q59UR7", "CA_Q59MR4", 
"CA_Q59MR4", "CA_P28870", "HS_A0FGR8", "HS_A0FGR8", "CA_Q5A4I4", 
"CA_P30575", "CA_P46598", "CA_P46598", "CA_P22011", "CA_P22011", 
"CA_P22011", "CA_P83781", "CA_P83781", "CA_P30575", "CA_P30575", 
"CA_P30575", "CA_P30575", "CA_P30575", "CA_P22011", "HS_A0FGR8", 
"HS_A0AVT1", "CA_O42817", "CA_P83784", "HS_A0AV96", "HS_A0AVT1", 
"CA_P30575", "CA_P83774", "CA_P83774", "HS_A0FGR8", "HS_A0FGR8", 
"HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "CA_O94083", 
"CA_P22011", "CA_Q9P940", "CA_Q5AF03", "CA_Q5A0M4", "CA_Q5ANP2", 
"CA_Q5ALM6", "CA_P22011", "CA_O94083", "CA_Q5A652", "HS_A0AVT1", 
"HS_A0AVT1", "HS_A0AVT1", "HS_A0AVT1", "HS_A0AVT1", "CA_P46614", 
"HS_A0AV96", "CA_Q59RQ6", "CA_Q5A786", "HS_A0FGR8", "HS_A0FGR8", 
"HS_A0AVT1", "HS_A0AVT1", "HS_A0AVT1", "HS_A0AVT1", "CA_P30575", 
"CA_P46598", "CA_Q5ADM7", "HS_A0AV96", "CA_P82611", "CA_Q5A3Z7", 
"CA_P83775", "CA_Q59RJ3", "CA_P46273", "CA_P83774", "CA_Q5ADQ6", 
"CA_P25997", "CA_P83774", "CA_P83774", "CA_Q5A8X6", "CA_Q5A860", 
"CA_Q5A860", "CA_P46273", "HS_A0A0B4J2F0", "HS_A0A0B4J2F0", "HS_A0A0B4J2F0", 
"HS_A0AVT1", "CA_Q5AK04", "HS_A0AVT1", "CA_Q59UR7", "HS_A0FGR8", 
"HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", 
"HS_A0FGR8", "CA_Q5A397", "CA_Q59ZX4", "HS_A0AVT1", "CA_O42766", 
"CA_P83779", "CA_P83779", "HS_A0AVT1", "HS_A0AVT1", "HS_A0AVT1", 
"CA_Q5A795", "CA_Q5AMI6", "HS_A0FGR8", "CA_Q5AFQ0", "CA_Q5ADQ6", 
"HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", "CA_P83779", "CA_P83779", 
"CA_Q5A2U8", "CA_Q59W54", "CA_Q5A5F2", "HS_A0AV96", "HS_A0AV96", 
"HS_A0AV96", "HS_A0AV96", "HS_A0AV96", "CA_P30575", "CA_P53698", 
"CA_P53698", "CA_Q59ZX4", "CA_Q59ZX4", "HS_A0FGR8", "CA_P83775", 
"CA_P83779", "CA_P30575", "CA_Q59UR7", "CA_Q59RD8", "HS_A0FGR8", 
"CA_Q5AAL2", "CA_Q59SM9", "CA_Q5A0M4", "HS_A0AVT1", "CA_Q5ANP2", 
"CA_Q5AF03", "CA_Q5ADM7", "CA_Q5ADM7", "CA_Q5ADM7", "CA_Q59W67", 
"CA_Q59YJ9", "CA_P46598", "CA_Q9URB4", "HS_A0AV96", "HS_A0AV96", 
"CA_P83775", "CA_Q5A786", "HS_A0FGR8", "HS_A0FGR8", "HS_A0FGR8", 
"CA_Q59LQ6", "CA_Q59LQ6", "CA_Q5A7T3", "CA_Q5A5A0", "HS_A0AVT1", 
"HS_A0AVT1", "HS_A0AVT1", "CA_P46273", "HS_A0FGR8", "CA_Q5AND4", 
"CA_Q5A389", "CA_Q59W54", "CA_O94083", "CA_Q5ADM7", "CA_Q5ADM7", 
"CA_Q5A5P4", "CA_Q9URB4", "CA_Q9URB4", "CA_P83784", "CA_Q5ADM7", 
"CA_Q5ADM7", "CA_Q5ADM7", "CA_Q5ADM7", "HS_A0AVT1", "CA_P83779", 
"CA_P82611", "HS_A0AV96", "HS_A0AVT1", "CA_P30575", "CA_P46273", 
"CA_P46273", "CA_Q5ADM7", "CA_Q59TE0", "CA_P46598", "HS_A0AVT1", 
"CA_Q5A0Z9", "CA_P0CY33", "CA_O93827", "CA_Q59TE0", "CA_Q59TE0", 
"CA_Q5AMP4", "CA_Q5AMP4", "CA_Q5A5V6", "CA_O74261"), PSMPerPep = c(1L, 
2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 4L, 4L, 4L, 4L, 1L, 
1L, 3L, 3L, 3L, 1L, 1L, 1L, 4L, 4L, 4L, 4L, 1L, 2L, 2L, 2L, 2L, 
1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 3L, 3L, 3L, 1L, 5L, 5L, 
5L, 5L, 5L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 
2L, 2L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 
1L, 3L, 3L, 3L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 2L, 2L, 6L, 6L, 6L, 6L, 6L, 6L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 5L, 5L, 5L, 5L, 5L, 1L, 1L, 1L, 1L, 2L, 2L, 
4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
2L, 2L, 1L, 2L, 2L, 1L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 7L, 7L, 7L, 
7L, 7L, 7L, 7L, 1L, 1L, 1L, 1L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 
1L, 1L, 3L, 3L, 3L, 2L, 2L, 1L, 1L, 1L, 5L, 5L, 5L, 5L, 5L, 1L, 
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 
1L, 1L, 1L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 
1L, 1L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L)), .Names = c("Annotated.Sequence", 
"Protein.Accessions", "PSMPerPep"), row.names = c(NA, -300L), class = "data.frame")

【问题讨论】：

  • 你确定它会改变结果吗？我认为它只会改变顺序

标签： r plyr


【解决方案1】：
  1. 一些主要的 R IDE 会遇到像您所做的 dput() 这样的长行问题（即像 @nrussell 所做的那样在未来更适当地格式化它）
  2. 您只是查看修改后的列还是整行，因为 ddply 并不能保证您以相同的顺序返回内容

即：

head(xx)
##   Annotated.Sequence Protein.Accessions PSMPerPep
## 1    ACDLPAWVHFPDTER          HS_A0FGR8         1
## 2         ACIGDTLCQK          HS_A0AVT1         2
## 3         ACIGDTLCQK          HS_A0AVT1         2
## 4           ADEEFFAK          CA_Q9URB4         1
## 5      AENPGISFGQVGK          CA_Q9UVL1         1
## 6 AETLYEGPSDDPFCTAIR          CA_Q5A0M4         2

yy <- plyr::ddply(xx, "Annotated.Sequence", transform,
            PSMPerPep = length(Annotated.Sequence))
y1 <- yy

head(yy)
##               Annotated.Sequence Protein.Accessions PSMPerPep
## 1 AAADYAPNAAVCIISNPVNSTVPIVAEVFK          CA_Q5AMP4         2
## 2 AAADYAPNAAVCIISNPVNSTVPIVAEVFK          CA_Q5AMP4         2
## 3        AAIRDPNPVVFLENEIAYGETFK          CA_Q5A5V6         1
## 4              AAVEEGILPGGGTALIK          CA_O74261         1
## 5                ACDLPAWVHFPDTER          HS_A0FGR8         1
## 6                     ACIGDTLCQK          HS_A0AVT1         2
yy <- plyr::ddply(yy, "Protein.Accessions", transform,
            PSMPerProt = length(Protein.Accessions))

head(yy)
##    Annotated.Sequence Protein.Accessions PSMPerPep PSMPerProt
## 1      AVASSGQELSVEER          CA_O42766         1          2
## 2 QAFDDAVADLETLSEDSYK          CA_O42766         1          2
## 3   IIAAVPNASDVAVCSSR          CA_O42817         1          1
## 4   AAVEEGILPGGGTALIK          CA_O74261         1          1
## 5      YVHGGNVLIDPTAK          CA_O93827         1          1
## 6            IVDMSTSK          CA_O94083         1          3

head(dplyr::arrange(y1, Annotated.Sequence))
##               Annotated.Sequence Protein.Accessions PSMPerPep
## 1 AAADYAPNAAVCIISNPVNSTVPIVAEVFK          CA_Q5AMP4         2
## 2 AAADYAPNAAVCIISNPVNSTVPIVAEVFK          CA_Q5AMP4         2
## 3        AAIRDPNPVVFLENEIAYGETFK          CA_Q5A5V6         1
## 4              AAVEEGILPGGGTALIK          CA_O74261         1
## 5                ACDLPAWVHFPDTER          HS_A0FGR8         1
## 6                     ACIGDTLCQK          HS_A0AVT1         2

head(dplyr::arrange(yy, Annotated.Sequence))
##               Annotated.Sequence Protein.Accessions PSMPerPep PSMPerProt
## 1 AAADYAPNAAVCIISNPVNSTVPIVAEVFK          CA_Q5AMP4         2          6
## 2 AAADYAPNAAVCIISNPVNSTVPIVAEVFK          CA_Q5AMP4         2          6
## 3        AAIRDPNPVVFLENEIAYGETFK          CA_Q5A5V6         1          1
## 4              AAVEEGILPGGGTALIK          CA_O74261         1          1
## 5                ACDLPAWVHFPDTER          HS_A0FGR8         1         50
## 6                     ACIGDTLCQK          HS_A0AVT1         2         35

head(dplyr::arrange(xx, Annotated.Sequence))
##               Annotated.Sequence Protein.Accessions PSMPerPep
## 1 AAADYAPNAAVCIISNPVNSTVPIVAEVFK          CA_Q5AMP4         2
## 2 AAADYAPNAAVCIISNPVNSTVPIVAEVFK          CA_Q5AMP4         2
## 3        AAIRDPNPVVFLENEIAYGETFK          CA_Q5A5V6         1
## 4              AAVEEGILPGGGTALIK          CA_O74261         1
## 5                ACDLPAWVHFPDTER          HS_A0FGR8         1
## 6                     ACIGDTLCQK          HS_A0AVT1         2

您可以转到dplyr 并执行以下操作：

library(dplyr)

xx %>%
  group_by(Annotated.Sequence) %>%
  mutate(PSMPerPep = n()) %>%
  group_by(Protein.Accessions) %>%
  mutate(PSMPerProt = n()) %>%
  ungroup()
## # A tibble: 300 × 4
##    Annotated.Sequence Protein.Accessions PSMPerPep PSMPerProt
##                 <chr>              <chr>     <int>      <int>
## 1     ACDLPAWVHFPDTER          HS_A0FGR8         1         50
## 2          ACIGDTLCQK          HS_A0AVT1         2         35
## 3          ACIGDTLCQK          HS_A0AVT1         2         35
## 4            ADEEFFAK          CA_Q9URB4         1          7
## 5       AENPGISFGQVGK          CA_Q9UVL1         1          1
## 6  AETLYEGPSDDPFCTAIR          CA_Q5A0M4         2          4
## 7  AETLYEGPSDDPFCTAIR          CA_Q5A0M4         2          4
## 8           AFDDESVQK          CA_Q5A397         1          2
## 9   AILGATNPLQSAPGTIR          CA_Q5AG68         2          2
## 10  AILGATNPLQSAPGTIR          CA_Q5AG68         2          2
## # ... with 290 more rows

这也保留了原始的xx Annotated.Sequence 顺序。

【讨论】：

    猜你喜欢
    • 1970-01-01
    • 2023-04-02
    • 1970-01-01
    • 2016-04-13
    • 1970-01-01
    • 2013-10-24
    • 1970-01-01
    • 1970-01-01
    • 2020-07-02
    相关资源
    最近更新 更多
    热门标签
    Java Python linux javascript Mysql C# Docker 算法 前端 SpringBoot Redis Vue spring 设计模式 .net core .net kubernetes c++ 数据库 数据结构 大数据 js 机器学习 微服务 Android Go 程序员 面试 JVM ASP.net core 云原生 人工智能 后端 PHP git CSS golang k8s Nginx Django mybatis 深度学习 多线程 React 架构 devops 爬虫 云计算 Spring Boot LeetCode