From 39b5d2ff41322c3f45a0c0fa7549a75f634d4237 Mon Sep 17 00:00:00 2001
From: Schneider Leo <leo.schneider@etu.ec-lyon.fr>
Date: Thu, 20 Feb 2025 16:32:57 +0100
Subject: [PATCH] fix

---
 ...oriv_fluoroquinolones_conta_human_sang.csv | 136 ------------------
 diann_lib_processing.py                       |   1 +
 2 files changed, 1 insertion(+), 136 deletions(-)

diff --git a/data/spectral_lib/1-240711_ident_resistance_idbioriv_fluoroquinolones_conta_human_sang.csv b/data/spectral_lib/1-240711_ident_resistance_idbioriv_fluoroquinolones_conta_human_sang.csv
index 1187f3a..0d396eb 100644
--- a/data/spectral_lib/1-240711_ident_resistance_idbioriv_fluoroquinolones_conta_human_sang.csv
+++ b/data/spectral_lib/1-240711_ident_resistance_idbioriv_fluoroquinolones_conta_human_sang.csv
@@ -523,7 +523,6 @@
 13908,AAGADFIGEDDLVAK,0,holdout
 13944,AAGADFIGEDDLVAR,0,holdout
 13980,AAGADFVGEDDLVAK,0,holdout
-14016,AAGADFVGEDDLVAKINDGWLDFDVXXXXR,0,holdout
 14040,AAGADFVGEDELVAK,0,holdout
 14076,AAGADFVGEEDLVAK,0,holdout
 14112,AAGADIVGAEDFVDEIAK,0,holdout
@@ -2157,7 +2156,6 @@
 56918,ADIHPNYRDVVFHDVTSDFK,0,holdout
 56954,ADIHPNYVEIDATCSCGNVIK,0,holdout
 56990,ADIHPNYVEIDATCSCGNVIKTR,0,holdout
-57014,ADIHPNYVEIDATXSXGN,0,holdout
 57050,ADIHPQYDAIEATCSCGNVIK,0,holdout
 57086,ADIHPQYDAIEATCSCGNVIKTR,0,holdout
 57110,ADIHPTYEAIEATCSCGNVIK,0,holdout
@@ -2173,7 +2171,6 @@
 57346,ADISSVYTVTGPLYERDMGK,0,holdout
 57382,ADISSVYTVTGPLYERD-OxM-GK,0,holdout
 57418,ADITDIK,0,holdout
-57430,ADITDIKTILXTEK,0,holdout
 57466,ADITDIKTILYTEK,0,holdout
 57502,ADITINR,0,holdout
 57513,ADITINRK,0,holdout
@@ -7941,7 +7938,6 @@
 202657,ALEERPAQENDQK,0,holdout
 202693,ALEERPVQEDDQK,0,holdout
 202729,ALEERPVQEDEQK,0,holdout
-202765,ALEERPXQEEGQK,0,holdout
 202801,ALEESNYELEGK,0,holdout
 202825,ALEESNYELEGKIK,0,holdout
 202861,ALEGAIR,0,holdout
@@ -13142,7 +13138,6 @@
 335629,ATDKIYYTHSMYPGGLK,0,holdout
 335665,ATDKIYYTHS-OxM-YPGGLK,0,holdout
 335701,ATDKIYYTHSNHPGGLK,0,holdout
-335737,ATDKIYYTHSXXXXXXXQVNFVLK,0,holdout
 335761,ATDKSFVEK,0,holdout
 335773,ATDKVYYHHSNHPGGLTAR,0,holdout
 335809,ATDKVYYR,0,holdout
@@ -13803,8 +13798,6 @@
 353392,ATTYSI-OxM-SIEER,0,holdout
 353428,ATTYSIMSVEER,0,holdout
 353452,ATTYSI-OxM-SVEER,0,holdout
-353488,ATTYSIMSXEER,0,holdout
-353524,ATTYSI-OxM-SXEER,0,holdout
 353560,ATVAALKFTK,0,holdout
 353584,ATVAALR,0,holdout
 353593,ATVAALRFTASAK,0,holdout
@@ -13883,8 +13876,6 @@
 355807,ATVGVVGNEQHSLINWGKAGR,0,holdout
 355843,ATVGVVGNEQQSLVNLGK,0,holdout
 355879,ATVGVVGNEQQSLVNLGKAGR,0,holdout
-355915,ATVIGLIXGK,0,holdout
-355939,ATVIGLIXGKVK,0,holdout
 355963,ATVIRHGETLR,0,holdout
 355987,ATVIYEGER,0,holdout
 355999,ATVIYEGERVAIQNK,0,holdout
@@ -14339,8 +14330,6 @@
 366832,AVEVPEQTAYR,0,holdout
 366856,AVEVPEQTAYRTLR,0,holdout
 366892,AVEVQANGGNA,0,holdout
-366904,AVEXGVK,0,holdout
-366914,AVEXGVKEVVFDR,0,holdout
 366950,AVEYIR,0,holdout
 366958,AVEYIRIGLSGTSQR,0,holdout
 366994,AVFAALQDK,0,holdout
@@ -14636,7 +14625,6 @@
 374172,AVKNFTEVHPDYGSHIQALLDK,0,holdout
 374208,AVKNNTPIR,0,holdout
 374220,AVKPNLQK,0,holdout
-374232,AVKPNLXK,0,holdout
 374244,AVKPSDK,0,holdout
 374255,AVKPTEK,0,holdout
 374266,AVKQLWFDR,0,holdout
@@ -15412,7 +15400,6 @@
 393182,AWWLKDQAEGR,0,holdout
 393206,AWYAGWEFYVDER,0,holdout
 393242,AWYAGWEFYVDERVLIPR,0,holdout
-393278,AXVXGL,0,holdout
 393287,AYAEGNQDSEVVSEIK,0,holdout
 393323,AYAEGNQDSEVVSEIKK,0,holdout
 393359,AYAEMIAEAK,0,holdout
@@ -15468,7 +15455,6 @@
 394826,AYEEAETVTGVINGKVK,0,holdout
 394862,AYEEAETVVGVINGK,0,holdout
 394898,AYEEAETVVGVINGKVK,0,holdout
-394934,AYEEKATVIGLIXGK,0,holdout
 394970,AYEENETVVGIINGK,0,holdout
 395006,AYEENETVVGIINGKVK,0,holdout
 395042,AYEEQATVIGIINGK,0,holdout
@@ -20605,7 +20591,6 @@
 531521,DIEIRVEGNEVTLHR,0,holdout
 531557,DIEIRVEGSEVTLHR,0,holdout
 531593,DIEIRVEGTEITLHR,0,holdout
-531629,DIEIRVEGTEITXHR,0,holdout
 531665,DIEIRVEGTELTLHR,0,holdout
 531701,DIEIRVEGTEVTLHR,0,holdout
 531737,DIEKMEANGTFEVLPK,0,holdout
@@ -22635,8 +22620,6 @@
 585652,DMVTQAD-OxM-VELADQAGFLQLLTRLVNR,0,holdout
 585676,DMVTRCNNVGVR,0,holdout
 585700,D-OxM-VTRCNNVGVR,0,holdout
-585724,DMXXSXDALE,0,holdout
-585748,D-OxM-XXSXDALE,0,holdout
 585772,DMYKVGDVVEVK,0,holdout
 585796,D-OxM-YKVGDVVEVK,0,holdout
 585832,DMYNSGGLWDK,0,holdout
@@ -26463,7 +26446,6 @@
 685021,EAKELVDGAPT-OxM-IK,0,holdout
 685057,EAKELVDGAPTVLK,0,holdout
 685093,EAKELVDGAPTVVK,0,holdout
-685129,EAKELVDGAPXVXK,0,holdout
 685165,EAKELVDNGGVIK,0,holdout
 685189,EAKELVDNTPK,0,holdout
 685213,EAKELVEGAPK,0,holdout
@@ -26674,7 +26656,6 @@
 690125,EALTTIEEVLA,0,holdout
 690149,EALTVGQEVTVK,0,holdout
 690173,EALTVGQEVTVKVLDVNADAER,0,holdout
-690209,EALTVGQEVTVKVLDVXAXAER,0,holdout
 690233,EALVKGNPPIYR,0,holdout
 690257,EALVKR,0,holdout
 690266,EALVNKYYNLR,0,holdout
@@ -28297,8 +28278,6 @@
 732135,EEILALATLPNR,0,holdout
 732159,EEILALATLPNREGLLSMLLSVLQAPVR,0,holdout
 732183,EEILALATLPNREGLLS-OxM-LLSVLQAPVR,0,holdout
-732207,EEILALATLPNREGLLXMLLSVLQAPVR,0,holdout
-732231,EEILALATLPNREGLLX-OxM-LLSVLQAPVR,0,holdout
 732255,EEILAQAK,0,holdout
 732266,EEILAQAKENEK,0,holdout
 732302,EEILRILAR,0,holdout
@@ -29772,10 +29751,6 @@
 770598,EGLLS-OxM-LLSVLQAPVRNVAYAVK,0,holdout
 770634,EGLLSQLASVLQAPVR,0,holdout
 770670,EGLLSQLASVLQAPVRDFALVVK,0,holdout
-770706,EGLLXMLLSVLQAPVR,0,holdout
-770742,EGLLX-OxM-LLSVLQAPVR,0,holdout
-770778,EGLLXMLLSVLQAPVRNVALAVK,0,holdout
-770802,EGLLX-OxM-LLSVLQAPVRNVALAVK,0,holdout
 770826,EGLPAEEAEALK,0,holdout
 770850,EGLPAEEAEALKAAIEEAGGSAELK,0,holdout
 770886,EGLPKEEAEALK,0,holdout
@@ -29823,8 +29798,6 @@
 772081,EGLYHIVNVEVNDAVALNEFDRLSK,0,holdout
 772105,EGLYHIVNVEVNDDVALK,0,holdout
 772141,EGLYHIVNVEVNDDVALKEFDR,0,holdout
-772165,EGLYHIVXVEANDDAALK,0,holdout
-772201,EGLYHIVXVEANDDAALKEFDR,0,holdout
 772225,EGLYHVINVEAEDATALNEFDR,0,holdout
 772249,EGLYHVINVEAEDATALNEFDRLSK,0,holdout
 772273,EGLYHVINVETEDATALNEFDR,0,holdout
@@ -30227,8 +30200,6 @@
 782299,EGVVRVICSAEPR,0,holdout
 782335,EGVVRVLCSDPK,0,holdout
 782359,EGVVVKTLAAK,0,holdout
-782383,EGVXXAEAEEIK,0,holdout
-782419,EGVXXAEAEEIKXK,0,holdout
 782455,EGVYAQVR,0,holdout
 782467,EGVYAQVRLR,0,holdout
 782491,EGVYHLIECEAEDAAGIDEFNR,0,holdout
@@ -31787,7 +31758,6 @@
 822745,EKQSEAA,0,holdout
 822757,EKSADELK,0,holdout
 822769,EKSAQQLNEQLLGLLR,0,holdout
-822805,EKSAQQLNXQLL,0,holdout
 822841,EKSDIPGGSK,0,holdout
 822853,EKSEETEATEATEE,0,holdout
 822889,EKSEETEATEE,0,holdout
@@ -33264,8 +33234,6 @@
 860876,ELVDGAPTVLKEGVAAAEAEEIK,0,holdout
 860912,ELVDGAPTVVK,0,holdout
 860936,ELVDGAPTVVKEGVATAEAEEIK,0,holdout
-860972,ELVDGAPXVXK,0,holdout
-860996,ELVDGAPXVXKEGVXXAEAEEIK,0,holdout
 861020,ELVDNAPK,0,holdout
 861032,ELVDNAPKVIK,0,holdout
 861056,ELVDNGGVIK,0,holdout
@@ -33356,8 +33324,6 @@
 863524,ELWEQGHSLRDAAIEAAR,0,holdout
 863560,ELWGPCVLLCLFSLLTQVTAETPTPK,0,holdout
 863584,ELWGPCVLLCLFSLLTQVTAETPTPKAK,0,holdout
-863608,ELXXXVSLSLK,0,holdout
-863644,ELXXXVSLSLKATTPGPWDGVEQK,0,holdout
 863668,ELYDFLK,0,holdout
 863679,ELYDFLKTEK,0,holdout
 863703,ELYEVEVAK,0,holdout
@@ -34896,7 +34862,6 @@
 905024,EQLIFPEVNYDNVDK,0,holdout
 905060,EQLIFPEVNYDNVDKVR,0,holdout
 905096,EQLIVELYSK,0,holdout
-905120,EQLIXXXXNNC,0,holdout
 905156,EQLKAVMDDFAAFVEK,0,holdout
 905192,EQLKAV-OxM-DDFAAFVEK,0,holdout
 905228,EQLKDIEVEVSAK,0,holdout
@@ -35732,8 +35697,6 @@
 926657,ESLPLIVFLRNR,0,holdout
 926693,ESLPLVVFLR,0,holdout
 926717,ESLPLVVFLRNR,0,holdout
-926753,ESLPLXVFLR,0,holdout
-926777,ESLPLXVFLRNR,0,holdout
 926813,ESLRTLGLR,0,holdout
 926825,ESLVEGHPK,0,holdout
 926837,ESLVEGHPKYEPQLLSTHDK,0,holdout
@@ -36271,8 +36234,6 @@
 940612,ETNIANFDASVEVAFRLGIDTR,0,holdout
 940648,ETNIIEIAQSLNVSQK,0,holdout
 940684,ETNIIEIAQSLNVSQKQVEK,0,holdout
-940720,ETNIIEIAQSLNVSXK,0,holdout
-940756,ETNIIEIAQSLNVSXKQVEK,0,holdout
 940792,ETNLNIK,0,holdout
 940804,ETNLNIKR,0,holdout
 940816,ETNMPVDMR,0,holdout
@@ -44210,8 +44171,6 @@
 1144680,GALVSIDAGK,0,holdout
 1144692,GALVSIDAGKATTYSIMSIEER,0,holdout
 1144728,GALVSIDAGKATTYSI-OxM-SIEER,0,holdout
-1144764,GALVSIDAGKATTYSIMSXEER,0,holdout
-1144800,GALVSIDAGKATTYSI-OxM-SXEER,0,holdout
 1144836,GALVSIDNGK,0,holdout
 1144848,GALVSIDNGKATTYSIMSIEER,0,holdout
 1144884,GALVSIDNGKATTYSI-OxM-SIEER,0,holdout
@@ -51765,7 +51724,6 @@
 1341236,GNYTLGVKEQLIFPEISFDDVDK,0,holdout
 1341260,GNYTLGVKEQLIFPEISYDDVDK,0,holdout
 1341284,GNYTLGVKEQLIFPEVDYDLVDK,0,holdout
-1341308,GNYTLGVKEQLIXXXXNNC,0,holdout
 1341344,GNYTLGVR,0,holdout
 1341356,GNYTLGVREQLIFPEIDFDNVDK,0,holdout
 1341380,GNYTMGITEQLIFPEIDYDK,0,holdout
@@ -60065,7 +60023,6 @@
 1555219,IANGDFVHYPNEK,0,holdout
 1555255,IANGEEVK,0,holdout
 1555267,IANGEEVKIGVPFVDGGVIK,0,holdout
-1555303,IANHKAXVXGL,0,holdout
 1555327,IANIEVLR,0,holdout
 1555339,IANIEVLRR,0,holdout
 1555363,IANKSIHAMASR,0,holdout
@@ -60620,7 +60577,6 @@
 1568861,IDLATGKISDFIK,0,holdout
 1568897,IDLATGKISEFIK,0,holdout
 1568933,IDLATGKITDFLK,0,holdout
-1568969,IDLATGKIXSFIK,0,holdout
 1569005,IDLAVGDVVK,0,holdout
 1569017,IDLAVGDVVKTWR,0,holdout
 1569053,IDLDAKLVAENIAR,0,holdout
@@ -64541,7 +64497,6 @@
 1669175,ILKIMGYHGLER,0,holdout
 1669211,ILKI-OxM-GYHGLER,0,holdout
 1669247,ILKINVDR,0,holdout
-1669259,ILKLAXGYYGAK,0,holdout
 1669283,ILKLGPR,0,holdout
 1669294,ILKLMK,0,holdout
 1669303,ILKL-OxM-K,0,holdout
@@ -65672,8 +65627,6 @@
 1698622,INDGWLDFDVVVATPDMMGKIGR,0,holdout
 1698646,INDGWLDFDVVVATPD-OxM-MGKIGR,0,holdout
 1698670,INDGWLDFDVVVATPDM-OxM-GKIGR,0,holdout
-1698694,INDGWLDFDVXXXXR,0,holdout
-1698730,INDGWLDFDVXXXXRSK,0,holdout
 1698766,INDGWMDFDVVVATPDMMGK,0,holdout
 1698802,INDGW-OxM-DFDVVVATPDMMGK,0,holdout
 1698838,INDGWMDFDVVVATPD-OxM-MGK,0,holdout
@@ -68914,7 +68867,6 @@
 1780515,IVESATRTGAEVAGPIPLPTER,0,holdout
 1780551,IVESATRTGAQIAGPIPLPTER,0,holdout
 1780587,IVESATRTGAQVAGPIPLPTER,0,holdout
-1780623,IVESATRTGAQVAGXIPLPTER,0,holdout
 1780659,IVESATRTGAQVVGPIPLPTER,0,holdout
 1780695,IVESRLPESVR,0,holdout
 1780719,IVETAAR,0,holdout
@@ -69585,8 +69537,6 @@
 1798389,IWYHTFYNELRVAPDEHPILLTEAPLNPK,0,holdout
 1798413,IWYLTLK,0,holdout
 1798423,IWYLTLKER,0,holdout
-1798447,IXSFIK,0,holdout
-1798456,IXSFIKFDTGR,0,holdout
 1798480,IYAGENVGR,0,holdout
 1798492,IYAGENVGRGGDDTLFAK,0,holdout
 1798528,IYAGKDDLPR,0,holdout
@@ -69862,9 +69812,6 @@
 1805938,IYYTHSNHPGGLKQISAGELR,0,holdout
 1805974,IYYTHSNHPGGLKQITAGELR,0,holdout
 1806010,IYYTHSNHPGGLKSISAGELR,0,holdout
-1806046,IYYTHSXXXXXXXQVNFVLK,0,holdout
-1806070,IYYTHSXXXXXXXQVNFVLKMQYV,0,holdout
-1806094,IYYTHSXXXXXXXQVNFVLK-OxM-QYV,0,holdout
 1806118,KAAAEAR,0,holdout
 1806128,KAAAFVR,0,holdout
 1806137,KAAAILK,0,holdout
@@ -69950,7 +69897,6 @@
 1807716,KADIHPNYEAVAVTCSCGNK,0,holdout
 1807752,KADIHPNYR,0,holdout
 1807776,KADIHPNYVEIDATCSCGNVIK,0,holdout
-1807812,KADIHPNYVEIDATXSXGN,0,holdout
 1807848,KADIHPQYDAIEATCSCGNVIK,0,holdout
 1807884,KADIHPTYEAIEATCSCGNVIK,0,holdout
 1807920,KADININR,0,holdout
@@ -75452,7 +75398,6 @@
 1934055,KVTVHK,0,holdout
 1934065,KVTVQNLVIAQVLPEQNVILVK,0,holdout
 1934101,KVTVYDEVEK,0,holdout
-1934125,KVTXAIK,0,holdout
 1934137,KVTYSSGHVTLSAENK,0,holdout
 1934173,KVVADIAGVPAQINIAEVR,0,holdout
 1934209,KVVADLAGVPAQINIAEVR,0,holdout
@@ -75955,7 +75900,6 @@
 1945632,LAAGDVIEGKVK,0,holdout
 1945656,LAAGDVIEGTVK,0,holdout
 1945680,LAAGDVIEGTVKR,0,holdout
-1945704,LAAGDVIEGTXXXXITFT,0,holdout
 1945740,LAAGDVVEGK,0,holdout
 1945752,LAAGDVVEGKVK,0,holdout
 1945776,LAAGDVVTGK,0,holdout
@@ -75999,10 +75943,6 @@
 1946556,LAAPSHW-OxM-LDKLSGTYAPK,0,holdout
 1946592,LAAPSHWMLDKLSGTYAPR,0,holdout
 1946628,LAAPSHW-OxM-LDKLSGTYAPR,0,holdout
-1946664,LAAPSHWMLXK,0,holdout
-1946688,LAAPSHW-OxM-LXK,0,holdout
-1946712,LAAPSHWMLXKLSGTYAPR,0,holdout
-1946748,LAAPSHW-OxM-LXKLSGTYAPR,0,holdout
 1946784,LAAQIKK,0,holdout
 1946796,LAAQKLPITTK,0,holdout
 1946820,LAAQKLPVK,0,holdout
@@ -76808,7 +76748,6 @@
 1967223,LANGFYVTRAK,0,holdout
 1967247,LANGVKIR,0,holdout
 1967259,LANHKACVK,0,holdout
-1967271,LANHKAXVK,0,holdout
 1967295,LANIDLNR,0,holdout
 1967307,LANIDLNRK,0,holdout
 1967331,LANIEVEVSAK,0,holdout
@@ -77284,8 +77223,6 @@
 1979022,LAW-OxM-AVNK,0,holdout
 1979034,LAWMAVNKGDEK,0,holdout
 1979058,LAW-OxM-AVNKGDEK,0,holdout
-1979082,LAXGYYGAK,0,holdout
-1979094,LAXGYYGAKHILFR,0,holdout
 1979130,LAYAAVAIADK,0,holdout
 1979154,LAYAAVAIADKK,0,holdout
 1979178,LAYATVAIADK,0,holdout
@@ -77345,7 +77282,6 @@
 1980609,LAYEIQDFREGLYHIVNVEANDDVALK,0,holdout
 1980633,LAYEIQDFREGLYHIVNVEANEDLALK,0,holdout
 1980657,LAYEIQDFREGLYHIVNVEVNDDVALK,0,holdout
-1980681,LAYEIQDFREGLYHIVXVEANDDAALK,0,holdout
 1980705,LAYEIQK,0,holdout
 1980716,LAYEIQKK,0,holdout
 1980728,LAYEIQKMR,0,holdout
@@ -77936,8 +77872,6 @@
 1996478,LDLSAGVDVEIK,0,holdout
 1996502,LDLSAGVDVEIKL,0,holdout
 1996526,LDLSAGVDVEIKVQ,0,holdout
-1996562,LDLXSGVDIEIK,0,holdout
-1996598,LDLXSGVDIEIKL,0,holdout
 1996634,LDLYGK,0,holdout
 1996643,LDLYGKVDGLHYFSDNK,0,holdout
 1996679,LDLYITVK,0,holdout
@@ -78868,8 +78802,6 @@
 2021235,LEKLDIATGETVEFDQVL-OxM-VANGEDIK,0,holdout
 2021259,LEKLELATGATVEFDSVLMVVNGEDVK,0,holdout
 2021283,LEKLELATGATVEFDSVL-OxM-VVNGEDVK,0,holdout
-2021307,LEKLELATGATVEFDSXLMVVNGEDVK,0,holdout
-2021331,LEKLELATGATVEFDSXL-OxM-VVNGEDVK,0,holdout
 2021355,LEKLELATGSTVEFDSVLMIVNGEDIK,0,holdout
 2021379,LEKLELATGSTVEFDSVL-OxM-IVNGEDIK,0,holdout
 2021403,LEKLFSK,0,holdout
@@ -78904,8 +78836,6 @@
 2022048,LELAQYREVAAFAQFGSDLDAATQQLLSR,0,holdout
 2022072,LELATGATVEFDSVLMVVNGEDVK,0,holdout
 2022096,LELATGATVEFDSVL-OxM-VVNGEDVK,0,holdout
-2022120,LELATGATVEFDSXLMVVNGEDVK,0,holdout
-2022144,LELATGATVEFDSXL-OxM-VVNGEDVK,0,holdout
 2022168,LELATGEAVTFDR,0,holdout
 2022204,LELATGEAVTFDRVLLIGNGDDVK,0,holdout
 2022228,LELATGSTVEFDSVLMIVNGEDIK,0,holdout
@@ -81512,9 +81442,6 @@
 2090131,LIDIINPTQKTVEAL-OxM-K,0,holdout
 2090167,LIDIITPTQK,0,holdout
 2090191,LIDIITPTQKTVDALSR,0,holdout
-2090227,LIDIIXPTQK,0,holdout
-2090251,LIDIIXPTQKTVDALMK,0,holdout
-2090287,LIDIIXPTQKTVDAL-OxM-K,0,holdout
 2090323,LIDIKQTIR,0,holdout
 2090347,LIDILDPTPK,0,holdout
 2090371,LIDILDPTPKTVDALMR,0,holdout
@@ -81562,8 +81489,6 @@
 2091654,LIDIVSPTPQTVDSL-OxM-R,0,holdout
 2091690,LIDIVSPTPQTVDSLMRLDLPSGVDIEIK,0,holdout
 2091714,LIDIVSPTPQTVDSL-OxM-RLDLPSGVDIEIK,0,holdout
-2091738,LIDIVSPTPQTVDSLMRLDLXSGVDIEIK,0,holdout
-2091762,LIDIVSPTPQTVDSL-OxM-RLDLXSGVDIEIK,0,holdout
 2091786,LIDIYSSTAK,0,holdout
 2091810,LIDIYSSTAKTVDALMK,0,holdout
 2091846,LIDIYSSTAKTVDAL-OxM-K,0,holdout
@@ -87327,7 +87252,6 @@
 2239062,LSGTYAPR,0,holdout
 2239074,LSGTYAPRASAGPHK,0,holdout
 2239110,LSGTYAPRPSAGPHK,0,holdout
-2239146,LSGTYAPRPSAGPHXLR,0,holdout
 2239182,LSGVYAPR,0,holdout
 2239194,LSGVYAPRPSTGPHK,0,holdout
 2239230,LSHEIMDAANNTGASVR,0,holdout
@@ -87394,7 +87318,6 @@
 2240605,LSKAVNSIA,0,holdout
 2240617,LSKEDIER,0,holdout
 2240629,LSKELQAAQAR,0,holdout
-2240653,LSKELXXXVSLSLK,0,holdout
 2240689,LSKG-OxM-R,0,holdout
 2240697,LSKGYFGAK,0,holdout
 2240709,LSKIEVAK,0,holdout
@@ -90037,8 +89960,6 @@
 2305844,LWVEIESIKK,0,holdout
 2305868,LWWLDLK,0,holdout
 2305877,LWWLDLKSGAQATWTELPWPHEK,0,holdout
-2305901,LXYALCGR,0,holdout
-2305912,LXYALCGREVK,0,holdout
 2305936,LYAAISSR,0,holdout
 2305945,LYAAISSRPGQSGR,0,holdout
 2305981,LYACISSR,0,holdout
@@ -90598,8 +90519,6 @@
 2319430,-OxM-ADIQDTTETPQNFSTSTPETDAVEAAPR,0,holdout
 2319454,MADITDIK,0,holdout
 2319466,-OxM-ADITDIK,0,holdout
-2319478,MADITDIKTILXTEK,0,holdout
-2319514,-OxM-ADITDIKTILXTEK,0,holdout
 2319550,MADITDIKTILYTEK,0,holdout
 2319586,-OxM-ADITDIKTILYTEK,0,holdout
 2319622,MADKGIIDK,0,holdout
@@ -94220,10 +94139,6 @@
 2404716,-OxM-ETNIIEIAQSLNVSQK,0,holdout
 2404752,METNIIEIAQSLNVSQKQVEK,0,holdout
 2404788,-OxM-ETNIIEIAQSLNVSQKQVEK,0,holdout
-2404824,METNIIEIAQSLNVSXK,0,holdout
-2404860,-OxM-ETNIIEIAQSLNVSXK,0,holdout
-2404896,METNIIEIAQSLNVSXKQVEK,0,holdout
-2404932,-OxM-ETNIIEIAQSLNVSXKQVEK,0,holdout
 2404968,METRNLR,0,holdout
 2404980,-OxM-ETRNLR,0,holdout
 2404992,METSHNQELVATILEDNVANELQTIQDFLR,0,holdout
@@ -96558,8 +96473,6 @@
 2463239,-OxM-KADIHPNYR,0,holdout
 2463263,MKADIHPNYVEIDATCSCGNVIK,0,holdout
 2463287,-OxM-KADIHPNYVEIDATCSCGNVIK,0,holdout
-2463311,MKADIHPNYVEIDATXSXGN,0,holdout
-2463347,-OxM-KADIHPNYVEIDATXSXGN,0,holdout
 2463383,MKADIHPQYDAIEATCSCGNVIK,0,holdout
 2463407,-OxM-KADIHPQYDAIEATCSCGNVIK,0,holdout
 2463431,MKADIHPTYEAIEATCSCGNVIK,0,holdout
@@ -98191,8 +98104,6 @@
 2504114,-OxM-LSGCFSTNNLFSNFVHSTR,0,holdout
 2504150,MLSGCFSTNNLFSNFVHSTRFK,0,holdout
 2504174,-OxM-LSGCFSTNNLFSNFVHSTRFK,0,holdout
-2504198,MLSKELXXXVSLSLK,0,holdout
-2504234,-OxM-LSKELXXXVSLSLK,0,holdout
 2504270,MLSPKR,0,holdout
 2504277,-OxM-LSPKR,0,holdout
 2504286,MLSQESLR,0,holdout
@@ -104877,8 +104788,6 @@
 2673391,MVVRQPLELVEMTEK,0,holdout
 2673427,-OxM-VVRQPLELVEMTEK,0,holdout
 2673463,MVVRQPLELVE-OxM-TEK,0,holdout
-2673499,MVVRQPLELVXLTDK,0,holdout
-2673535,-OxM-VVRQPLELVXLTDK,0,holdout
 2673571,MVVRQPLVLTENAESFDIK,0,holdout
 2673607,-OxM-VVRQPLVLTENAESFDIK,0,holdout
 2673643,MVVRQPMELVDMVEK,0,holdout
@@ -108960,7 +108869,6 @@
 2781158,NKPTFTPHLDTGDFVIVINADK,0,holdout
 2781194,NKPTFTPHTDTGDFVIVINADK,0,holdout
 2781230,NKPTFTPHTDTGDFVIVINAEK,0,holdout
-2781266,NKPTFTPHTDTGDFVIVIXAEK,0,holdout
 2781290,NKPTFTPHVDTGDFVIVINADQVK,0,holdout
 2781314,NKPTFTPHVDTGDHVIIINAEK,0,holdout
 2781350,NKPTFTPNVDCGDFVIVINAEK,0,holdout
@@ -111767,7 +111675,6 @@
 2855213,NRLSNEAK,0,holdout
 2855225,NRLSSEAK,0,holdout
 2855237,NRLVHR,0,holdout
-2855248,NRLXYALCGR,0,holdout
 2855272,NRMDVFSQNMFCAGHPSLK,0,holdout
 2855308,NR-OxM-DVFSQNMFCAGHPSLK,0,holdout
 2855344,NRMDVFSQN-OxM-FCAGHPSLK,0,holdout
@@ -117520,7 +117427,6 @@
 2998576,PNLQVTTLVVNGSPIKVK,0,holdout
 2998612,PNLSYIIGK,0,holdout
 2998624,PNLSYIIGKDTWVEHWPEEDECQDEENQK,0,holdout
-2998648,PNLXKVTVLIDGK,0,holdout
 2998684,PNLYLHSLGCNK,0,holdout
 2998708,PNLYLHSLGCNKNLVDSEIMLGR,0,holdout
 2998732,PNLYLHSLGCNKNLVDSEI-OxM-LGR,0,holdout
@@ -118179,8 +118085,6 @@
 3015073,PSAENPQGAIVEKEAPIHASNVQVLDK,0,holdout
 3015097,PSAGNNSLYR,0,holdout
 3015121,PSAGPHKLR,0,holdout
-3015133,PSAGPHXLR,0,holdout
-3015145,PSAGPHXLRESLPLXVFLR,0,holdout
 3015181,PSAGTGVMLALVSDNTVPFALSLVDSATEK,0,holdout
 3015205,PSAGTGV-OxM-LALVSDNTVPFALSLVDSATEK,0,holdout
 3015229,PSAKISYAR,0,holdout
@@ -118713,8 +118617,6 @@
 3028937,PTFTPHTDTGDFVIVINAEK,0,holdout
 3028973,PTFTPHTDTGDFVIVINAEKIK,0,holdout
 3029009,PTFTPHTDTGDFVIVINAEKVK,0,holdout
-3029045,PTFTPHTDTGDFVIVIXAEK,0,holdout
-3029081,PTFTPHTDTGDFVIVIXAEKVK,0,holdout
 3029105,PTFTPHVDTGDFVIVINADQVK,0,holdout
 3029141,PTFTPHVDTGDFVIVINADQVKLTGK,0,holdout
 3029165,PTFTPHVDTGDHVIIINAEK,0,holdout
@@ -119696,8 +119598,6 @@
 3054697,PWVSLPK,0,holdout
 3054708,PWVSLPKGK,0,holdout
 3054720,PWWERYQPVSYK,0,holdout
-3054756,PXQEEGQK,0,holdout
-3054768,PXQEEGQKEEK,0,holdout
 3054804,PYAEECYSGNVAFLEGWYVVPSAR,0,holdout
 3054828,PYAEECYSGNVAFLEGWYVVPSARR,0,holdout
 3054852,PYAEKLITHAK,0,holdout
@@ -119939,7 +119839,6 @@
 3061351,QAADAVAEEAVRAGQYFINHR,0,holdout
 3061387,QAADAVAEEAVRSGQYFINHR,0,holdout
 3061423,QAADAVAEEAVRSGQYYINHR,0,holdout
-3061459,QAADAVAEEAVRSXQYFINHR,0,holdout
 3061495,QAADAVK,0,holdout
 3061507,QAADAVKDEAER,0,holdout
 3061531,QAADAVKEEAER,0,holdout
@@ -125287,8 +125186,6 @@
 3200662,QPLELVE-OxM-LEKLDLYITVK,0,holdout
 3200698,QPLELVEMTEK,0,holdout
 3200722,QPLELVE-OxM-TEK,0,holdout
-3200746,QPLELVXLTDK,0,holdout
-3200770,QPLELVXLTDKLDLYITVK,0,holdout
 3200806,QPLKEIMGNSQVLNALSPR,0,holdout
 3200842,QPLKEI-OxM-GNSQVLNALSPR,0,holdout
 3200878,QPLKEIMGNSSVLNSLSPR,0,holdout
@@ -127030,7 +126927,6 @@
 3244430,QVVGEVAAKIR,0,holdout
 3244454,QVVGKDTDTVTFLVSK,0,holdout
 3244490,QVVGKDTDTVTYLVSK,0,holdout
-3244526,QVVGKXXXXDADINDFVK,0,holdout
 3244562,QVVGQFAAVVR,0,holdout
 3244586,QVVGQFAAVVRSVR,0,holdout
 3244622,QVVGQMAAEIR,0,holdout
@@ -127667,7 +127563,6 @@
 3259748,RAVEGTSYEVLK,0,holdout
 3259772,RAVEHIPAAYLTHQAWQGEFDFYVDER,0,holdout
 3259796,RAVEQAGITK,0,holdout
-3259820,RAVEXGVK,0,holdout
 3259832,RAVEYIR,0,holdout
 3259844,RAVGIWHCGSCMK,0,holdout
 3259880,RAVGIWHCGSC-OxM-K,0,holdout
@@ -129160,8 +129055,6 @@
 3293461,RLAAPHHWLLDK,0,holdout
 3293497,RLAAPSHWMLDK,0,holdout
 3293533,RLAAPSHW-OxM-LDK,0,holdout
-3293569,RLAAPSHWMLXK,0,holdout
-3293605,RLAAPSHW-OxM-LXK,0,holdout
 3293641,RLAASTADVGVATADLFPR,0,holdout
 3293677,RLAASVVGVGK,0,holdout
 3293701,RLAAYLMLMGSPSQSDISK,0,holdout
@@ -129338,7 +129231,6 @@
 3297547,RLIDIIEPTQK,0,holdout
 3297571,RLIDIINPTQK,0,holdout
 3297595,RLIDIITPTQK,0,holdout
-3297619,RLIDIIXPTQK,0,holdout
 3297643,RLIDIK,0,holdout
 3297650,RLIDILDPTPK,0,holdout
 3297674,RLIDILEPTNK,0,holdout
@@ -131399,8 +131291,6 @@
 3348076,RWVTYEMP-OxM-PGR,0,holdout
 3348112,RWVVLTNEAAG,0,holdout
 3348136,RWYVVDATDVPLGR,0,holdout
-3348172,RXAQQGL,0,holdout
-3348183,RXXXXPEINFDDVDK,0,holdout
 3348219,RYAAIGDIIK,0,holdout
 3348243,RYAAVGDIIK,0,holdout
 3348267,RYADLESR,0,holdout
@@ -132237,7 +132127,6 @@
 3369574,SAQQLNEQLLELLRDQFNLR,0,holdout
 3369610,SAQQLNEQLLGLLR,0,holdout
 3369646,SAQQLNEQLLGLLRDQFNLR,0,holdout
-3369682,SAQQLNXQLL,0,holdout
 3369706,SAQRNALLR,0,holdout
 3369718,SAQRYK,0,holdout
 3369729,SAQSNLIHSNK,0,holdout
@@ -132251,8 +132140,6 @@
 3369981,SARAIQAAFFYLEPR,0,holdout
 3370017,SARDMR,0,holdout
 3370028,SARD-OxM-R,0,holdout
-3370037,SARDMXXSXDALE,0,holdout
-3370073,SARD-OxM-XXSXDALE,0,holdout
 3370109,SAREAGVTMR,0,holdout
 3370133,SAREAGVT-OxM-R,0,holdout
 3370157,SAREAGVYMR,0,holdout
@@ -142133,8 +142020,6 @@
 3620752,SWYVIDATDVVLGRLAVEAAK,0,holdout
 3620788,SWYYDK,0,holdout
 3620795,SWYYDKK,0,holdout
-3620804,SXQYFINHR,0,holdout
-3620828,SXQYFINHRWLGGTLTNWGTIQK,0,holdout
 3620852,SYAAEIAHNVSSK,0,holdout
 3620876,SYAAEIAHNVSSKNR,0,holdout
 3620912,SYAAEIASSVSSR,0,holdout
@@ -144848,8 +144733,6 @@
 3692831,TGAQVAGPVPLPTER,0,holdout
 3692867,TGAQVAGPVPLPTERSLYTIIR,0,holdout
 3692903,TGAQVAGPVPLPTERSVFTIIR,0,holdout
-3692939,TGAQVAGXIPLPTER,0,holdout
-3692975,TGAQVAGXIPLPTERSLYTIIR,0,holdout
 3693011,TGAQVCGPIPMPTR,0,holdout
 3693047,TGAQVCGPIP-OxM-PTR,0,holdout
 3693083,TGAQVCGPIPMPTRIER,0,holdout
@@ -146218,8 +146101,6 @@
 3728801,TILRYGSSSPVEVSK,0,holdout
 3728837,TILSNQTVDIPNNVEVSLK,0,holdout
 3728873,TILSNQTVDIPNNVEVSLKGR,0,holdout
-3728909,TILXTEK,0,holdout
-3728916,TILXTEKSLNLQEQGVVVIQTSPK,0,holdout
 3728940,TILYTEK,0,holdout
 3728948,TILYTEKSLNLQEQGVVVIQTSPK,0,holdout
 3728972,TILYTEKTLGLQEQGVVVIQTSPK,0,holdout
@@ -149799,7 +149680,6 @@
 3820064,TSRSLHGLSR,0,holdout
 3820088,TSRVLVFAR,0,holdout
 3820112,TSRVLVFAVGER,0,holdout
-3820136,TSRVLVFXXXXADQQIR,0,holdout
 3820172,TSRVVVIAR,0,holdout
 3820184,TSSCCVTNNLQASLK,0,holdout
 3820220,TSSCCVTNNLQASLKSCPR,0,holdout
@@ -154727,8 +154607,6 @@
 3948121,VEGTEITLHRPNDSK,0,holdout
 3948157,VEGTEITVVR,0,holdout
 3948181,VEGTEITVVRPNDSK,0,holdout
-3948217,VEGTEITXHR,0,holdout
-3948241,VEGTEITXHRPNDSK,0,holdout
 3948277,VEGTELTLHR,0,holdout
 3948301,VEGTELTLHRPNDSK,0,holdout
 3948337,VEGTELTLHRPNDTK,0,holdout
@@ -159276,8 +159154,6 @@
 4063538,VLDVNPEEHRLSLSIK,0,holdout
 4063574,VLDVNPEENR,0,holdout
 4063598,VLDVNPEENRLSLSIK,0,holdout
-4063634,VLDVXAXAER,0,holdout
-4063658,VLDVXAXAERVSLSIK,0,holdout
 4063694,VLDWLAK,0,holdout
 4063704,VLDWLAKGAQPSDTVR,0,holdout
 4063740,VLDWLGK,0,holdout
@@ -160126,7 +160002,6 @@
 4085835,VLNSAIANAENNFGLEK,0,holdout
 4085871,VLNSAVANAENNFGLDK,0,holdout
 4085907,VLNSAVANAENNFGLEK,0,holdout
-4085943,VLNSAVANAENNFGLXXXXIAILTFTPNK,0,holdout
 4085967,VLNSAVANAENNFSLDR,0,holdout
 4086003,VLNSLR,0,holdout
 4086009,VLNSLRTAK,0,holdout
@@ -160517,9 +160392,6 @@
 4095631,VLVFHK,0,holdout
 4095641,VLVFHKK,0,holdout
 4095653,VLVFKK,0,holdout
-4095663,VLVFXXXXADQQIR,0,holdout
-4095699,VLVFXXXXADQQIRGAMVLPNGTGK,0,holdout
-4095723,VLVFXXXXADQQIRGA-OxM-VLPNGTGK,0,holdout
 4095747,VLVGRVVSDK,0,holdout
 4095771,VLVHTQIR,0,holdout
 4095783,VLVHTQIRK,0,holdout
@@ -165304,8 +165176,6 @@
 4219461,VTWAPPPSIDLTNFLVRYSPVK,0,holdout
 4219485,VTWDQVR,0,holdout
 4219493,VTWDQVREIAETK,0,holdout
-4219529,VTXAIK,0,holdout
-4219538,VTXAIKR,0,holdout
 4219550,VTYARK,0,holdout
 4219558,VTYCPTEPGNYIINIK,0,holdout
 4219594,VTYCPTEPGNYIINIKFADQHVPGSPFSVK,0,holdout
@@ -168793,12 +168663,6 @@
 4311864,WYVVDATDVPLGRLSTVVASVLR,0,holdout
 4311888,WYVVDATGYTLGR,0,holdout
 4311924,WYVVDATGYTLGRLSSEIAK,0,holdout
-4311960,XAQQGL,0,holdout
-4311970,XKLEEAGASVTLK,0,holdout
-4312006,XXXXDADINDFVK,0,holdout
-4312042,XXXXDADINDFVKVGEVLDVLVLR,0,holdout
-4312066,XXXXPEINFDDVDK,0,holdout
-4312102,XXXXPEINFDDVDKTR,0,holdout
 4312138,YAADLHNLVVK,0,holdout
 4312162,YAADLHNLVVKNK,0,holdout
 4312198,YAAELHLVHWNTK,0,holdout
diff --git a/diann_lib_processing.py b/diann_lib_processing.py
index 53594b1..483c773 100644
--- a/diann_lib_processing.py
+++ b/diann_lib_processing.py
@@ -63,6 +63,7 @@ def extract_sequence(data_frame):
     df_pred.columns = ['sequence']
     df_pred['sequence']=df_pred['sequence'].map(lambda x:x.replace('M(UniMod:35)','-OxM-'))
     df_pred['remove']=df_pred['sequence'].map((lambda x : 'U' in x))
+    df_pred['remove'] = df_pred['sequence'].map((lambda x: 'X' in x))
     df_pred = df_pred[df_pred['remove']==False]
     df_pred = df_pred[['sequence']]
     df_pred['irt_scaled']=0
-- 
GitLab