Generate MSstatsTMT required input format for OpenMS output — OpenMStoMSstatsTMTFormat • MSstatsTMT

Convert OpenMS MSstatsTMT report into the required input format for MSstatsTMT.

OpenMStoMSstatsTMTFormat(
  input,
  useUniquePeptide = TRUE,
  rmPSM_withMissing_withinRun = FALSE,
  rmPSM_withfewMea_withinRun = TRUE,
  rmProtein_with1Feature = FALSE,
  summaryforMultiplePSMs = sum
)

Arguments

input	MSstatsTMT report from OpenMS
useUniquePeptide	TRUE(default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein.
rmPSM_withMissing_withinRun	TRUE will remove PSM with any missing value within each Run. Defaut is FALSE.
rmPSM_withfewMea_withinRun	only for rmPSM_withMissing_withinRun = FALSE. TRUE(default) will remove the features that have 1 or 2 measurements within each Run.
rmProtein_with1Feature	TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE.
summaryforMultiplePSMs	sum(default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value.

Value

input for proteinSummarization function

Examples

head(raw.om)
#>   RetentionTime          ProteinName                 PeptideSequence Charge
#> 1      2924.491 sp|P11679|K2C8_MOUSE .(TMT6plex)AEAETMYQIK(TMT6plex)      2
#> 2      2924.491 sp|P11679|K2C8_MOUSE .(TMT6plex)AEAETMYQIK(TMT6plex)      2
#> 3      2924.491 sp|P11679|K2C8_MOUSE .(TMT6plex)AEAETMYQIK(TMT6plex)      2
#> 4      2924.491 sp|P11679|K2C8_MOUSE .(TMT6plex)AEAETMYQIK(TMT6plex)      2
#> 5      2924.491 sp|P11679|K2C8_MOUSE .(TMT6plex)AEAETMYQIK(TMT6plex)      2
#> 6      2924.491 sp|P11679|K2C8_MOUSE .(TMT6plex)AEAETMYQIK(TMT6plex)      2
#>   Channel Condition BioReplicate   Run Mixture TechRepMixture Fraction
#> 1       1   Long_LF            1 1_1_3       1            1_1        3
#> 2       2   Long_LF            2 1_1_3       1            1_1        3
#> 3       3    Long_M            3 1_1_3       1            1_1        3
#> 4       6    Long_M            6 1_1_3       1            1_1        3
#> 5       5      Norm            5 1_1_3       1            1_1        3
#> 6       9      Norm            9 1_1_3       1            1_1        3
#>   Intensity
#> 1  5727.319
#> 2  6985.365
#> 3  4553.897
#> 4  5937.782
#> 5  5151.292
#> 6  6800.128
#>                                                                                                          Reference
#> 1 PAMI-176_Mouse_A-J_TMT_40ug_22pctACN_25cm_120min_20160223_OT.mzML_controllerType=0 controllerNumber=1 scan=11324
#> 2 PAMI-176_Mouse_A-J_TMT_40ug_22pctACN_25cm_120min_20160223_OT.mzML_controllerType=0 controllerNumber=1 scan=11324
#> 3 PAMI-176_Mouse_A-J_TMT_40ug_22pctACN_25cm_120min_20160223_OT.mzML_controllerType=0 controllerNumber=1 scan=11324
#> 4 PAMI-176_Mouse_A-J_TMT_40ug_22pctACN_25cm_120min_20160223_OT.mzML_controllerType=0 controllerNumber=1 scan=11324
#> 5 PAMI-176_Mouse_A-J_TMT_40ug_22pctACN_25cm_120min_20160223_OT.mzML_controllerType=0 controllerNumber=1 scan=11324
#> 6 PAMI-176_Mouse_A-J_TMT_40ug_22pctACN_25cm_120min_20160223_OT.mzML_controllerType=0 controllerNumber=1 scan=11324
input.om <- OpenMStoMSstatsTMTFormat(raw.om)
#> Joining, by = c("RetentionTime", "ProteinName", "PeptideSequence", "Charge", "Run", "Reference")
#> ** PSMs, that have all zero intensities across channels in each run, are removed.
#> Joining, by = c("RetentionTime", "ProteinName", "PeptideSequence", "Charge", "Run", "Reference")
#> ** 2 features have 1 or 2 intensities across runs are removed.
#> Joining, by = c("Run", "Channel")
#> ** PSMs have been aggregated to peptide ions.
#> ** For peptides overlapped between fractions of 2_2_2, use the fraction with maximal average abundance.
#> ** For peptides overlapped between fractions of 3_3_3, use the fraction with maximal average abundance.
#> ** Fractions belonging to same mixture have been combined.
head(input.om)
#>            ProteinName                           PeptideSequence Charge
#> 1 sp|O08663|MAP2_MOUSE .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR      2
#> 2 sp|O08663|MAP2_MOUSE .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR      2
#> 3 sp|O08663|MAP2_MOUSE .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR      2
#> 4 sp|O08663|MAP2_MOUSE .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR      2
#> 5 sp|O08663|MAP2_MOUSE .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR      2
#> 6 sp|O08663|MAP2_MOUSE .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR      2
#>                                           PSM Mixture TechRepMixture   Run
#> 1 .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR_2       1            1_1 1_1_1
#> 2 .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR_2       1            1_1 1_1_1
#> 3 .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR_2       1            1_1 1_1_1
#> 4 .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR_2       1            1_1 1_1_1
#> 5 .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR_2       1            1_1 1_1_1
#> 6 .(TMT6plex)GQEC(Carbamidomethyl)EYPPTQDGR_2       1            1_1 1_1_1
#>   Channel Condition BioReplicate Intensity
#> 1       1   Long_LF            1  18748.36
#> 2      10  Short_LF           10  15084.31
#> 3       2   Long_LF            2  19591.20
#> 4       3    Long_M            3  17800.54
#> 5       4  Short_LF            4  21316.78
#> 6       5      Norm            5  17607.60