0
$\begingroup$

I have to peptide output sample output i would give here ..

Sample A

dput(head(B5_ILS_Mus_PeptideSummary))
structure(list(N = c(1, 1, 1, 1, 1, 1), Unused = c(47.67, 47.67, 
47.67, 47.67, 47.67, 47.67), Total = c(47.67, 47.67, 47.67, 47.67, 
47.67, 47.67), `%Cov` = c(98.0000019073486, 98.0000019073486, 
98.0000019073486, 98.0000019073486, 98.0000019073486, 98.0000019073486
), `%Cov(50)` = c(86.0000014305115, 86.0000014305115, 86.0000014305115, 
86.0000014305115, 86.0000014305115, 86.0000014305115), `%Cov(95)` = c(86.0000014305115, 
86.0000014305115, 86.0000014305115, 86.0000014305115, 86.0000014305115, 
86.0000014305115), Accessions = c("sp|P20065|TYB4_MOUSE", "sp|P20065|TYB4_MOUSE", 
"sp|P20065|TYB4_MOUSE", "sp|P20065|TYB4_MOUSE", "sp|P20065|TYB4_MOUSE", 
"sp|P20065|TYB4_MOUSE"), Names = c("Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1"
), Used = c(NA, NA, NA, NA, NA, NA), Annotation = c(NA, NA, NA, 
NA, NA, NA), Contrib = c(2, 2, 2, 2, 2, 2), Conf = c(99.0000009536743, 
58.2899987697601, 97.5199997425079, 99.0000009536743, 98.9300012588501, 
73.7299978733063), Sequence = c("EKNPLPSKETIEQEKQAGES", "KKTETQEKNPLPSKETIEQEKQAGES", 
"KNPLPSKETIEQEKQAGES", "KTETQEKNPLPSKETIEQEKQAGES", "LKKTETQEKNPLPSKETIEQEKQAGES", 
"PLPSKETIEQEKQAGES"), Modifications = c(NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_), 
    ProteinModifications = c(NA_character_, NA_character_, NA_character_, 
    NA_character_, NA_character_, NA_character_), Cleavages = c(NA, 
    NA, NA, NA, NA, NA), dMass = c(-0.0625222995877266, 0.180465996265411, 
    -0.00865099020302296, -0.0651467964053154, -0.107698999345303, 
    -0.0186963994055986), `Obs MW` = c(2241.05004882813, 2956.67944335938, 
    2112.06127929688, 2828.3388671875, 3069.47534179688, 1869.91320800781
    ), `Obs m/z` = c(748.0239, 740.1771, 529.0226, 708.092, 768.3761, 
    624.3117), `Theor MW` = c(2241.11254882813, 2956.4990234375, 
    2112.06982421875, 2828.40405273438, 3069.5830078125, 1869.93200683594
    ), `Theor m/z` = c(748.044738769531, 740.132019042969, 529.024719238281, 
    708.108276367188, 768.403015136719, 624.317932128906), `Theor z` = c(3, 
    4, 4, 4, 4, 3), Sc = c(15, 8, 11, 21, 12, 10), Spectrum = c("1.1.1.372.12", 
    "1.1.1.339.6", "1.1.1.358.3", "1.1.1.355.16", "1.1.1.346.14", 
    "1.1.1.384.8"), `Acq Time` = c(4.2116, 3.539133, 3.91795, 
    3.867617, 3.68345, 4.45125), `Intensity (Peptide)` = c(3775.35, 
    110.58, 4374.93, 7285.52, 3073.51, 5776.43), PrecursorIntensityAcquisition = c(3626.33, 
    37.12, 4301.05, 7124.23, 2706.13, 5533.12), `Apex Time (Peptide)` = c(4.2, 
    3.59, 3.91, 3.85, 3.67, 4.44), `Elution Peak Width (Peptide)` = c(0.1, 
    0.06, 0.08, 0.1, 0.08, 0.08), MS2Counts = c(3077.868, 477.5326, 
    2262.827, 4694.357, 1759.267, 2618.842)), row.names = c(NA, 
-6L), class = c("tbl_df", "tbl", "data.frame"))

Sample B

dput(head(B6_ILS_mus_PeptideSummary))
structure(list(N = c(1, 1, 1, 1, 1, 1), Unused = c(82.41, 82.41, 
82.41, 82.41, 82.41, 82.41), Total = c(82.41, 82.41, 82.41, 82.41, 
82.41, 82.41), `%Cov` = c(100, 100, 100, 100, 100, 100), `%Cov(50)` = c(87.9999995231628, 
87.9999995231628, 87.9999995231628, 87.9999995231628, 87.9999995231628, 
87.9999995231628), `%Cov(95)` = c(86.0000014305115, 86.0000014305115, 
86.0000014305115, 86.0000014305115, 86.0000014305115, 86.0000014305115
), Accessions = c("sp|P20065|TYB4_MOUSE", "sp|P20065|TYB4_MOUSE", 
"sp|P20065|TYB4_MOUSE", "sp|P20065|TYB4_MOUSE", "sp|P20065|TYB4_MOUSE", 
"sp|P20065|TYB4_MOUSE"), Names = c("Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1", 
"Thymosin beta-4 OS=Mus musculus OX=10090 GN=Tmsb4x PE=1 SV=1"
), Used = c(NA, NA, NA, NA, NA, NA), Annotation = c(NA, NA, NA, 
NA, NA, NA), Contrib = c(2, 2, 2, 2, 2, 2), Conf = c(99.0000009536743, 
99.0000009536743, 99.0000009536743, 99.0000009536743, 94.4599986076355, 
99.0000009536743), Sequence = c("DKPDMAEIEKFDKSKLK", "EKNPLPSKETIEQEKQAGES", 
"ETQEKNPLPSKETIEQEKQAGES", "IEKFDKSKLKKTETQEKNPLPSKETIEQEKQAGES", 
"KKTETQEKNPLPSKETIEQEKQAGES", "KNPLPSKETIEQEK"), Modifications = c(NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_
), ProteinModifications = c(NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_), Cleavages = c(NA, 
NA, NA, NA, NA, NA), dMass = c(0.0129736997187138, -0.0542825013399124, 
-0.0299271997064352, -0.107947997748852, -0.0191929005086422, 
-0.0046052997931838), `Obs MW` = c(2021.06335449219, 2241.05834960938, 
2599.2314453125, 4045.01391601563, 2956.47973632813, 1639.87341308594
), `Obs m/z` = c(506.2731, 748.0267, 650.8151, 810.0101, 592.3032, 
547.6318), `Theor MW` = c(2021.05029296875, 2241.11254882813, 
2599.26123046875, 4045.12182617188, 2956.4990234375, 1639.87805175781
), `Theor m/z` = c(506.269866943359, 748.044738769531, 650.822631835938, 
810.031677246094, 592.307067871094, 547.63330078125), `Theor z` = c(4, 
3, 4, 5, 5, 3), Sc = c(11, 12, 12, 26, 10, 10), Spectrum = c("1.1.1.858.2", 
"1.1.1.621.5", "1.1.1.640.9", "1.1.1.643.4", "1.1.1.597.3", "1.1.1.604.4"
), `Acq Time` = c(8.74735, 4.069217, 4.43505, 4.4987, 3.615083, 
3.7369), `Intensity (Peptide)` = c(1798.16, 2856.36, 1278.57, 
5833.81, 758.71, 599.21), PrecursorIntensityAcquisition = c(1603.78, 
443.55, 1104.72, 5265.07, 484.03, 423.02), `Apex Time (Peptide)` = c(8.72, 
4.19, 4.39, 4.45, 3.55, 3.78), `Elution Peak Width (Peptide)` = c(0.14, 
0.12, 0.12, 0.37, 0.1, 0.08), MS2Counts = c(456.3906, 313.663, 
712.3438, 2748.186, 351.0362, 228.9387)), row.names = c(NA, -6L
), class = c("tbl_df", "tbl", "data.frame"))

Unlike genes expression where it can be intersected since i know the gene name or ensemble ID are consistent.

Here My objective is how many of the sequence are common or unique to these two condition.

In the accession column many ID are same but the differences are in the sequence column.

Is there any programmatic way of finding the elements that are common or different in both the conditions

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

merge(a, b, by = "Sequence") would "merge" the two tables (as the name suggests) based on the Sequence column. The caveat is that sequences have to be exactly the same to be considered "common to both samples", so even 1 aa difference would be missed.

Simplified output:

1       EKNPLPSKETIEQEKQAGES   1    47.67   47.67     98         86         86 sp|P20065|TYB4_MOUSE
2 KKTETQEKNPLPSKETIEQEKQAGES   1    47.67   47.67     98         86         86 sp|P20065|TYB4_MOUSE
Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.