diff --git a/data/phenotypes/pheno.allium.lilljebjorn.csv b/data/phenotypes/pheno.allium.lilljebjorn.csv deleted file mode 100644 index b7ea232..0000000 --- a/data/phenotypes/pheno.allium.lilljebjorn.csv +++ /dev/null @@ -1,196 +0,0 @@ -public_id,Subtype -Case_001,HeH -Case_002,t(12;21) -Case_003,t(12;21) -Case_004,ph-like -Case_005,ph-like -Case_006,t(12;21) -Case_007,11q23/MLL -Case_008,B-other -Case_009,B-other -Case_010,11q23/MLL -Case_011,B-other -Case_012,HeH -Case_013,t(12;21) -Case_014,HeH -Case_015,HeH -Case_016,HeH -Case_017,t(1;19) -Case_018,HeH -Case_019,HeH -Case_020,B-other -Case_021,HeH -Case_022,11q23/MLL -Case_023,HeH -Case_024,t(12;21) -Case_025,ph-like -Case_026,HeH -Case_027,HeH -Case_028,HeH -Case_029,HeH -Case_030,t(12;21) -Case_031,HeH -Case_032,t(12;21) -Case_033,t(12;21) -Case_034,ph-like -Case_035,DUX4-r -Case_036,HeH -Case_037,t(12;21) -Case_038,HeH -Case_039,B-other -Case_040,ph-like -Case_041,t(12;21) -Case_042,HeH -Case_043,t(9;22) -Case_044,HeH -Case_045,ph-like -Case_046,t(1;19) -Case_047,DUX4-r -Case_048,HeH -Case_049,HeH -Case_050,t(12;21) -Case_051,t(9;22) -Case_052,t(12;21) -Case_053,DUX4-r -Case_054,HeH -Case_055,HeH -Case_056,HeH -Case_057,t(12;21) -Case_058,11q23/MLL -Case_059,t(1;19) -Case_060,PAX5alt -Case_061,t(12;21) -Case_062,ph-like -Case_063,t(1;19) -Case_064,t(12;21)-like -Case_065,t(12;21) -Case_066,t(1;19) -Case_067,DUX4-r -Case_068,t(12;21)-like -Case_069,11q23/MLL -Case_070,ph-like -Case_071,t(12;21) -Case_072,B-other -Case_073,ph-like -Case_074,Hypo -Case_075,DUX4-r -Case_076,PAX5alt -Case_077,PAX5alt -Case_078,HeH -Case_079,t(9;22) -Case_080,t(12;21) -Case_081,B-other -Case_082,HeH -Case_083,t(1;19) -Case_084,t(12;21) -Case_085,t(12;21)-like -Case_086,HeH -Case_087,t(12;21) -Case_088,Hypo -Case_089,t(12;21) -Case_090,HeH -Case_091,t(12;21) -Case_092,t(12;21) -Case_093,t(12;21) -Case_094,B-other -Case_095,HeH -Case_096,HeH -Case_097,B-other -Case_098,B-other -Case_099,t(12;21) -Case_100,B-other -Case_101,HeH -Case_102,11q23/MLL -Case_103,B-other -Case_104,HeH -Case_105,t(12;21)-like -Case_106,HeH -Case_107,B-other -Case_108,HeH -Case_109,B-other -Case_110,HeH -Case_111,t(12;21)-like -Case_112,HeH -Case_113,HeH -Case_114,t(12;21) -Case_115,11q23/MLL -Case_116,B-other -Case_117,t(12;21) -Case_118,t(12;21) -Case_119,HeH -Case_120,11q23/MLL -Case_121,t(12;21) -Case_122,ph-like -Case_123,t(12;21) -Case_124,DUX4-r -Case_125,HeH -Case_126,t(12;21) -Case_127,11q23/MLL -Case_128,HeH -Case_129,t(12;21) -Case_130,HeH -Case_131,t(12;21) -Case_132,t(12;21) -Case_133,B-other -Case_134,t(12;21) -Case_135,11q23/MLL -Case_136,HeH -Case_137,HeH -Case_138,t(12;21) -Case_139,t(9;22) -Case_140,t(1;19) -Case_141,B-other -Case_142,t(12;21) -Case_143,t(12;21) -Case_144,ph-like -Case_145,ph-like -Case_146,HeH -Case_147,HeH -Case_148,HeH -Case_149,t(12;21) -Case_150,ph-like -Case_151,B-other -Case_152,11q23/MLL -Case_153,HeH -Case_154,t(9;22) -Case_155,t(12;21) -Case_156,ph-like -Case_157,t(1;19) -Case_158,HeH -Case_159,HeH -Case_160,t(1;19) -Case_161,ph-like -Case_162,HeH -Case_163,11q23/MLL -Case_164,HeH -Case_165,t(1;19) -Case_166,HeH -Case_167,11q23/MLL -Case_168,t(12;21) -Case_169,t(9;22) -Case_170,11q23/MLL -Case_171,t(12;21) -Case_172,B-other -Case_173,HeH -Case_174,DUX4-r -Case_175,HeH -Case_176,t(12;21)-like -Case_177,B-other -Case_178,t(12;21) -Case_179,DUX4-r -Case_180,t(12;21) -Case_181,iAMP21 -Case_182,HeH -Case_183,t(1;19) -Case_184,B-other -Case_185,HeH -Case_186,t(12;21) -Case_187,t(12;21) -Case_188,HeH -Case_189,t(12;21) -Case_190,t(12;21) -Case_191,HeH -Case_192,t(1;19) -Case_193,t(12;21) -Case_194,HeH -Case_195,t(1;19) diff --git a/data/phenotypes/pheno.allium.tran.csv b/data/phenotypes/pheno.allium.tran.csv deleted file mode 100644 index 7b9b60d..0000000 --- a/data/phenotypes/pheno.allium.tran.csv +++ /dev/null @@ -1,174 +0,0 @@ -public_id,Subtype -16-001,ETV6::RUNX1 -16-002,ETV6::RUNX1 -16-003,ETV6::RUNX1 -16-006,ETV6::RUNX1 -16-008,T-ALL -16-011,T-ALL -16-012,ETV6::RUNX1 -16-014,hyperdiploid -16-015,hyperdiploid -16-017,PAX5alt -16-021,TCF3::PBX1 -16-022,B-other -16-025,hyperdiploid -16-027,DUX4-r -16-029,DUX4-r -16-033,DUX4-r -16-035,T-ALL -16-037,B-other -16-038,KMT2A-r -16-039,PAX5alt -16-042,T-ALL -16-044,BCR::ABL-like -16-047,BCR::ABL-like -16-048,hyperdiploid -16-049,hyperdiploid -16-050,ETV6::RUNX1 -16-052,T-ALL -16-053,T-ALL -16-056,T-ALL -16-057,T-ALL -16-059,T-ALL -16-065,ETV6::RUNX1 -16-068,hypodiploid -16-070,ETV6::RUNX1 -16-074,ETV6::RUNX1 -16-076,ETV6::RUNX1 -16-077,BCR::ABL-like -16-082,MEF2D-r -16-086,B-other -16-089,ZNF384-r -16-090,hyperdiploid -16-092,ETV6::RUNX1 -16-094,ETV6::RUNX1 -16-095,T-ALL -16-098,T-ALL -16-099,KMT2A-r -16-100,ETV6::RUNX1 -16-102,BCR::ABL-like -16-103,hyperdiploid -16-104,T-ALL -16-105,DUX4-r -16-106,ETV6::RUNX1 -16-108,ETV6::RUNX1-like -16-114,T-ALL -16-115,ETV6::RUNX1 -16-116,KMT2A-r -16-129,hypodiploid -16-131,hyperdiploid -16-132,KMT2A-r -16-138,T-ALL -16-139,ETV6::RUNX1 -16-140,ETV6::RUNX1 -16-141,hyperdiploid -16-144,T-ALL -16-152,ETV6::RUNX1 -16-155,T-ALL -16-158,hyperdiploid -16-161,hyperdiploid -16-162,hyperdiploid -16-164,BCR::ABL-like -16-167,T-ALL -16-170,B-other -16-171,T-ALL -16-174,T-ALL -16-176,hyperdiploid -16-177,T-ALL -16-179,BCR::ABL-like -16-182,hyperdiploid -16-186,hyperdiploid -16-189,DUX4-r -16-191,T-ALL -16-192,TCF3::PBX1 -16-194,hyperdiploid -16-196,T-ALL -16-199,hyperdiploid -16-200,TCF3::PBX1 -16-201,T-ALL -16-202,B-other -16-204,B-other -16-205,TCF3::PBX1 -16-207,ZNF384-r -16-210,hyperdiploid -16-215,hyperdiploid -16-217,T-ALL -16-218,ZNF384-r -16-220,B-other -16-221,ETV6::RUNX1 -16-222,B-other -16-223,T-ALL -16-225,BCR::ABL-like -16-226,PAX5alt -16-227,T-ALL -16-229,TCF3::PBX1 -16-230,DUX4-r -16-231,PAX5alt -16-232,BCR::ABL-like -16-233,T-ALL -16-238,ETV6::RUNX1 -16-239,hyperdiploid -16-240,PAX5 P80R -16-241,T-ALL -16-242,hyperdiploid -16-243,ETV6::RUNX1 -16-244,T-ALL -16-245,T-ALL -16-249,hyperdiploid -16-252,T-ALL -16-253,BCR::ABL-like -16-256,T-ALL -16-257,hyperdiploid -16-258,TCF3::PBX1 -16-261,PAX5alt -16-265,B-other -16-266,iAMP21 -16-267,ETV6::RUNX1 -16-268,DUX4-r -16-269,PAX5alt -16-270,ZNF384-r -16-272,hyperdiploid -16-273,hyperdiploid -16-279,hyperdiploid -16-280,TCF3::PBX1 -16-282,hyperdiploid -16-284,DUX4-r -16-286,PAX5alt -16-287,hyperdiploid -16-291,"hyperdiploid,PAX5alt" -16-293,ETV6::RUNX1 -16-294,DUX4-r -16-295,hyperdiploid -16-296,T-ALL -16-302,hyperdiploid -16-304,ETV6::RUNX1 -16-306,hyperdiploid -16-312,ETV6::RUNX1 -16-315,hypodiploid -16-319,KMT2A-r -16-322,ETV6::RUNX1 -16-326,BCR::ABL-like -16-328,DUX4-r -16-335,hyperdiploid -16-338,hyperdiploid -16-339,hyperdiploid -16-340,T-ALL -16-341,"BCR::ABL1,iAMP21" -16-342,hyperdiploid -16-343,BCR::ABL-like -16-346,NUTM1-r -16-347,B-other -16-348,BCR::ABL1 -16-350,ETV6::RUNX1 -16-352,ETV6::RUNX1 -16-354,ETV6::RUNX1 -16-359,B-other -16-362,T-ALL -16-363,ETV6::RUNX1-like -16-364,B-other -16-367,T-ALL -16-372,B-other -16-373,T-ALL -16-374,hyperdiploid -16-376,BCR::ABL-like -16-378,B-other diff --git a/data/phenotypes/pheno.lilljebjorn.csv b/data/phenotypes/pheno.lilljebjorn.csv deleted file mode 100644 index c5a350b..0000000 --- a/data/phenotypes/pheno.lilljebjorn.csv +++ /dev/null @@ -1,196 +0,0 @@ -ID;Subtype -1;High hyperdiploidy -2;ETV6-RUNX1 -3;ETV6-RUNX1 -4;Ph-like -5;Ph-like -6;ETV6-RUNX1 -7;MLL -8;B-other, with fusion -9;B-other, with fusion -10;MLL -11;B-other, with fusion -12;High hyperdiploidy -13;ETV6-RUNX1 -14;High hyperdiploidy -15;High hyperdiploidy -16;High hyperdiploidy -17;TCF3-PBX1 -18;High hyperdiploidy -19;High hyperdiploidy -20;B-other, with fusion -21;High hyperdiploidy -22;MLL -23;High hyperdiploidy -24;ETV6-RUNX1 -25;Ph-like -26;High hyperdiploidy -27;High hyperdiploidy -28;High hyperdiploidy -29;High hyperdiploidy -30;ETV6-RUNX1 -31;High hyperdiploidy -32;ETV6-RUNX1 -33;ETV6-RUNX1 -34;Ph-like -35;DUX4-rearranged -36;High hyperdiploidy -37;ETV6-RUNX1 -38;High hyperdiploidy -39;B-other, with fusion -40;Ph-like -41;ETV6-RUNX1 -42;High hyperdiploidy -43;BCR-ABL1 -44;High hyperdiploidy -45;Ph-like -46;TCF3-PBX1 -47;DUX4-rearranged -48;High hyperdiploidy -49;High hyperdiploidy -50;ETV6-RUNX1 -51;BCR-ABL1 -52;ETV6-RUNX1 -53;DUX4-rearranged -54;High hyperdiploidy -55;High hyperdiploidy -56;High hyperdiploidy -57;ETV6-RUNX1 -58;MLL -59;TCF3-PBX1 -60;"dic(9;20)" -61;ETV6-RUNX1 -62;Ph-like -63;TCF3-PBX1 -64;ETV6-RUNX1-like -65;ETV6-RUNX1 -66;TCF3-PBX1 -67;DUX4-rearranged -68;ETV6-RUNX1-like -69;MLL -70;Ph-like -71;ETV6-RUNX1 -72;B-other, without fusion -73;Ph-like -74;Hypodiploid -75;DUX4-rearranged -76;"dic(9;20)" -77;"dic(9;20)" -78;High hyperdiploidy -79;BCR-ABL1 -80;ETV6-RUNX1 -81;B-other, with fusion -82;High hyperdiploidy -83;TCF3-PBX1 -84;ETV6-RUNX1 -85;ETV6-RUNX1-like -86;High hyperdiploidy -87;ETV6-RUNX1 -88;Hypodiploid -89;ETV6-RUNX1 -90;High hyperdiploidy -91;ETV6-RUNX1 -92;ETV6-RUNX1 -93;ETV6-RUNX1 -94;B-other, without fusion -95;High hyperdiploidy -96;High hyperdiploidy -97;B-other, with fusion -98;B-other, without fusion -99;ETV6-RUNX1 -100;B-other, with fusion -101;High hyperdiploidy -102;MLL -103;B-other, without fusion -104;High hyperdiploidy -105;ETV6-RUNX1-like -106;High hyperdiploidy -107;B-other, with fusion -108;High hyperdiploidy -109;B-other, with fusion -110;High hyperdiploidy -111;ETV6-RUNX1-like -112;High hyperdiploidy -113;High hyperdiploidy -114;ETV6-RUNX1 -115;MLL -116;B-other, with fusion -117;ETV6-RUNX1 -118;ETV6-RUNX1 -119;High hyperdiploidy -120;MLL -121;ETV6-RUNX1 -122;Ph-like -123;ETV6-RUNX1 -124;DUX4-rearranged -125;High hyperdiploidy -126;ETV6-RUNX1 -127;MLL -128;High hyperdiploidy -129;ETV6-RUNX1 -130;High hyperdiploidy -131;ETV6-RUNX1 -132;ETV6-RUNX1 -133;B-other, with fusion -134;ETV6-RUNX1 -135;MLL -136;High hyperdiploidy -137;High hyperdiploidy -138;ETV6-RUNX1 -139;BCR-ABL1 -140;TCF3-PBX1 -141;B-other, with fusion -142;ETV6-RUNX1 -143;ETV6-RUNX1 -144;Ph-like -145;Ph-like -146;High hyperdiploidy -147;High hyperdiploidy -148;High hyperdiploidy -149;ETV6-RUNX1 -150;Ph-like -151;B-other, with fusion -152;MLL -153;High hyperdiploidy -154;BCR-ABL1 -155;ETV6-RUNX1 -156;Ph-like -157;TCF3-PBX1 -158;High hyperdiploidy -159;High hyperdiploidy -160;TCF3-PBX1 -161;Ph-like -162;High hyperdiploidy -163;MLL -164;High hyperdiploidy -165;TCF3-PBX1 -166;High hyperdiploidy -167;MLL -168;ETV6-RUNX1 -169;BCR-ABL1 -170;MLL -171;ETV6-RUNX1 -172;B-other, with fusion -173;High hyperdiploidy -174;DUX4-rearranged -175;High hyperdiploidy -176;ETV6-RUNX1-like -177;B-other, with fusion -178;ETV6-RUNX1 -179;DUX4-rearranged -180;ETV6-RUNX1 -181;iAMP21 -182;High hyperdiploidy -183;TCF3-PBX1 -184;B-other, with fusion -185;High hyperdiploidy -186;ETV6-RUNX1 -187;ETV6-RUNX1 -188;High hyperdiploidy -189;ETV6-RUNX1 -190;ETV6-RUNX1 -191;High hyperdiploidy -192;TCF3-PBX1 -193;ETV6-RUNX1 -194;High hyperdiploidy -195;TCF3-PBX1 \ No newline at end of file diff --git a/predict.py b/predict.py index c00d90d..0efb33d 100644 --- a/predict.py +++ b/predict.py @@ -2,7 +2,7 @@ from src.allium.gex_classifier import GEXClassifier testX = pd.read_csv('/home/mariya/Data/tran/counts.allium.tran.csv', index_col="public_id") -pheno = pd.read_csv('/home/mariya/Development/allium/data/phenotypes/pheno.allium.tran.csv', index_col = "public_id") +pheno = pd.read_csv('/home/mariya/Data/tran/pheno.allium.tran.csv', index_col = "public_id") gc = GEXClassifier('v3') diff --git a/src/experiments/lilljebjorn/standardize_phenotypes.py b/src/experiments/lilljebjorn/standardize_phenotypes.py index 39982a6..4487bd2 100644 --- a/src/experiments/lilljebjorn/standardize_phenotypes.py +++ b/src/experiments/lilljebjorn/standardize_phenotypes.py @@ -3,7 +3,7 @@ import os # GEX data from Lilljebjorn et al. 2016 -path_to_data = '/Users/marly389/Data/lilljebjorn/' +path_to_data = '/home/mariya/Data/lilljebjorn/' input_file = f'{path_to_data}/pheno.lilljebjorn.csv' output_file = f'{path_to_data}/pheno.allium.lilljebjorn.csv' diff --git a/src/experiments/lilljebjorn/subtypes_to_allium.yml b/src/experiments/lilljebjorn/subtypes_to_allium.yml index e62c061..9321373 100644 --- a/src/experiments/lilljebjorn/subtypes_to_allium.yml +++ b/src/experiments/lilljebjorn/subtypes_to_allium.yml @@ -1,13 +1,13 @@ -High hyperdiploidy: HeH -ETV6-RUNX1: t(12;21) -Ph-like: ph-like -MLL: 11q23/MLL +High hyperdiploidy: hyperdiploid +ETV6-RUNX1: ETV6::RUNX1 +Ph-like: BCR::ABL1-like +MLL: KMT2A-r B-other, with fusion: B-other -TCF3-PBX1: t(1;19) +TCF3-PBX1: TCF3::PBX1 DUX4-rearranged: DUX4-r -BCR-ABL1: t(9;22) +BCR-ABL1: BCR::ABL1 dic(9;20): PAX5alt -ETV6-RUNX1-like: t(12;21)-like +ETV6-RUNX1-like: ETV6::RUNX1-like B-other, without fusion: B-other -Hypodiploid: Hypo +Hypodiploid: hypodiploid