added unicode to parser

Author: bkellman

example_data/paper_epo/output_data/paper_epo_glycan_glycoct_dict.json

@@ -1,3 +1 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5fbe64633463ffeadd898b4d028995f4edadeb62b06716c9f6412404194ebef1
-size 883
+{"18": "st3gal4.st3gal6", "14": "st3gal3", "31": "EPO259.mgat2.st3gal4.st3gal6.", "33": "EPO263.mgat2.st3gal4.st3gal6.magt4A.mgat4B.mgat5.", "25": "EPO174.mgat2.", "24": "EPO143.mgat4C.", "21": "st3gal4.st3gal6.mgat4a.mgat4b.mgat5", "23": "EPO48.mgat3.", "22": "KI_ST6GalNAc1.st3gal4.st3gal6.mgat4a.mgat4b.mgat5", "19": "KI_ST6GalNAc1.st3gal4.st3gal6", "27": "EPO275.B3gnt8.", "11": "B4GalT1.B4GalT3", "5": "mgat4A.mgat4B.mgat5", "9": "B4GalT4", "32": "EPO261.mgat2.mgat4A.mgat4B.mgat5.", "28": "EPO78.mgat4B.", "3": "mgat4A.mgat4B", "12": "B3gnt1", "13": "B3gnt2", "20": "B3gnt2.mgat4a.mgat4b.mgat5", "17": "st3gal3.st3gal4", "29": "EPO104.mgat5B.", "10": "B4GalT1.B4GalT2", "34": "EPO266.fut8.", "16": "st3gal6", "30": "EPO127.mgat1.", "1": "WT", "26": "EPO200.B4galt1.B4galt2.B4galt3.", "7": "B4GalT2", "6": "B4GalT1", "15": "st3gal4", "4": "mgat5", "8": "B4GalT3", "2": "mgat4A"}

example_data/paper_epo/output_data/paper_epo_glycan_substructure_glycoct_dict.json

@@ -1,3 +1 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:40ee7ff6475fd3d5aa97a86ec45a384a08f8c00fc10203af375501d33de29861
-size 5893
+{"4": {"2244": "G04483SK", "2967": "G17689DH", "2605": "G30460NZ", "3416": "G54338PJ", "3777": "G76812VG", "4226": "G56516KW"}, "20": {"2244": "G04483SK", "2605": "G30460NZ", "2967": "G17689DH", "1836": "G80858MF"}, "32": {"2605": "2605.2", "1795": "G12398HZ", "2156": "G39439UR"}, "26": {"2326": "G00176HZ", "2646": "2646.1", "2081": "G80393PG", "1836": "G80858MF", "2892": "G79412GP"}, "5": {"2244": "G04483SK", "2605": "G30460NZ", "3416": "3416.1", "2967": "G17689DH"}, "3": {"2244": "G04483SK", "4675": "4675.1", "3416": "3416.3", "3777": "G76812VG", "3055": "G88127MB", "4226": "G56516KW", "2693": "G07568IR"}, "13": {"4226": "G86696LV", "4587": "4587.1", "2605": "G30460NZ", "3416": "G54338PJ", "3777": "G76812VG", "3055": "3055.1", "3865": "3865.1"}, "19": {"5037": "G49604DB", "2081": "G80393PG", "2967": "G17689DH", "5486": "5486.1", "3504": "G10292TC", "4226": "G86696LV", "4675": "G09280JF", "1836": "G80858MF", "3416": "G54338PJ", "2605": "G30460NZ", "3055": "3055.1", "3865": "3865.1"}, "16": {"2285": "G03445UI", "5037": "G49604DB", "3143": "G20924UR", "2081": "G80393PG", "3504": "G10292TC", "3592": "G75308SV", "2040": "G58667NI", "4226": "G86696LV", "4675": "G09280JF", "2244": "G04483SK", "2489": "G10691MJ", "4314": "G16873YG", "1836": "G80858MF", "1591": "G07483YN", "3416": "G54338PJ", "3055": "3055.1", "3865": "3865.1", "2693": "G07568IR"}, "28": {"2244": "G04483SK", "4675": "4675.1", "2967": "G17689DH", "3777": "G76812VG", "3416": "G54338PJ", "2605": "G30460NZ", "3055": "3055.1", "4226": "G56516KW"}, "11": {"2326": "G00176HZ", "3457": "3457.1", "2081": "G80393PG", "1836": "G80858MF", "1591": "G07483YN", "4022": "G80264ZA", "2646": "2646.1", "2892": "G79412GP", "3212": "3212.1"}, "30": {"1754": "1754.1", "1375": "G60415BS", "1580": "G49721VX"}, "15": {"4402": "4402.1", "2244": "G04483SK", "2489": "G10691MJ", "3143": "G20924UR", "3953": "3953.1", "3592": "G75308SV", "3504": "G10292TC", "2939": "G37597FW", "2693": "G07568IR"}, "31": {"2244": "G52428MJ", "2967": "2967.1", "1591": "G07483YN", "2156": "G39439UR", "1795": "G12398HZ", "2605": "2605.1", "2693": "2693.1"}, "1": {"2244": "G04483SK", "5037": "G49604DB", "4226": "G86696LV", "2967": "G17689DH", "4587": "4587.1", "3416": "G54338PJ", "2605": "G30460NZ", "5486": "5486.1", "3865": "3865.1"}, "25": {"2401": "2401.1", "2967": "2967.1", "1591": "G07483YN", "2156": "G39439UR", "1795": "G12398HZ", "2605": "2605.1", "3416": "3416.2"}, "23": {"2244": "G04483SK", "4587": "4587.1", "5037": "G49604DB", "2967": "G17689DH", "3777": "G76812VG", "3416": "G54338PJ", "2605": "G30460NZ", "5486": "5486.1", "4226": "G86696LV"}, "21": {"2244": "G04483SK", "4041": "G90130AG", "3143": "G54953LX", "1836": "G80858MF", "2605": "G30460NZ", "3592": "3592.1", "2040": "G58667NI", "2693": "2693.2"}, "12": {"2285": "G03445UI", "5037": "G49604DB", "2967": "G17689DH", "2081": "G80393PG", "3953": "3953.1", "3504": "G10292TC", "2040": "G58667NI", "3777": "G76812VG", "4226": "G86696LV", "2244": "G04483SK", "2489": "G10691MJ", "4314": "G16873YG", "1836": "G80858MF", "4587": "4587.1", "3416": "G54338PJ", "2605": "G30460NZ", "3055": "3055.1", "3865": "3865.1", "2693": "G07568IR"}, "17": {"4402": "4402.1", "2489": "G10691MJ", "4041": "4041.1", "3953": "3953.1", "2040": "G58667NI", "3504": "G10292TC", "4851": "4851.1", "2244": "G04483SK", "4490": "4490.1", "3592": "G75308SV", "2693": "G07568IR", "2939": "G37597FW", "3143": "G20924UR"}, "14": {"2244": "G04483SK", "5037": "G49604DB", "4226": "G86696LV", "4587": "4587.1", "3416": "G54338PJ", "2605": "G30460NZ", "3055": "3055.1", "3865": "3865.1"}, "33": {"2244": "2244.1", "3143": "3143.1", "1795": "G12398HZ", "2605": "2605.2", "3055": "3055.2", "2693": "2693.3"}, "29": {"4587": "4587.1", "5037": "G49604DB", "2967": "G17689DH", "2605": "G30460NZ", "3416": "G54338PJ", "3777": "G76812VG", "4226": "G86696LV"}, "18": {"2244": "G04483SK", "2489": "G10691MJ", "3388": "G88966ZO", "3143": "G20924UR", "4041": "4041.1", "3592": "G75308SV", "2040": "G58667NI", "2939": "G37597FW", "2693": "G07568IR"}, "9": {"5486": "5486.1", "5037": "G49604DB", "2967": "G17689DH", "3777": "G76812VG", "3416": "G54338PJ", "4587": "4587.1", "4226": "G86696LV"}, "34": {"3603": "G05098FE", "5312": "5312.1", "4052": "G99891PR", "4862": "G85809SI", "2792": "G39764AC", "4413": "G05203UQ", "3242": "G39813YP"}, "7": {"4675": "G09280JF", "2244": "G04483SK", "4587": "4587.1", "5037": "G49604DB", "4226": "G86696LV", "2967": "G17689DH", "3777": "G76812VG", "3416": "G54338PJ", "2605": "G30460NZ", "5486": "5486.1", "3865": "3865.1"}, "6": {"5037": "G49604DB", "2081": "G80393PG", "4587": "4587.1", "3457": "3457.1", "4226": "G86696LV", "2892": "G79412GP", "2530": "G79457WN", "3096": "G40242TG", "2326": "G00176HZ", "1836": "G80858MF", "1591": "G07483YN", "4022": "G80264ZA", "3777": "G76812VG"}, "27": {"2244": "G04483SK", "4587": "4587.1", "5037": "G49604DB", "2967": "G17689DH", "3777": "G76812VG", "3416": "G54338PJ", "2605": "G30460NZ", "5486": "5486.1", "4226": "G86696LV"}, "2": {"2244": "G04483SK", "5037": "G49604DB", "4226": "G86696LV", "2967": "G17689DH", "4587": "4587.1", "3416": "G54338PJ", "2605": "G30460NZ", "3865": "3865.1"}, "10": {"5037": "G49604DB", "3661": "3661.1", "2081": "G80393PG", "2734": "G00536FZ", "3457": "3457.1", "4226": "G86696LV", "2892": "G79412GP", "2530": "G79457WN", "3096": "G40242TG", "2326": "G00176HZ", "1836": "G80858MF", "1591": "G07483YN", "4022": "G80264ZA", "4587": "4587.1", "3865": "3865.1"}, "8": {"4675": "G09280JF", "5486": "5486.1", "4587": "4587.1", "5037": "G49604DB", "4226": "G86696LV", "2967": "G17689DH", "3777": "G76812VG", "3416": "G54338PJ", "2605": "G30460NZ", "3865": "3865.1"}, "22": {"2401": "G23295TF", "2605": "G30460NZ", "2967": "G17689DH", "1836": "G80858MF"}, "24": {"5486": "5486.1", "4587": "4587.1", "5037": "G49604DB", "2967": "G17689DH", "3777": "G76812VG", "3416": "G54338PJ", "2605": "G30460NZ", "4226": "G86696LV"}}

example_data/paper_epo/output_data/paper_epo_glycan_substructure_occurance_dict.json

@@ -1,3 +1 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:be6d034b6f03cf274eeca2c7fc411c7aff96c5b99491b258759a03c2cc9c44ea
-size 3834
+{"LSTc": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\n6b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n7s:n-acetyl\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(4+1)5d\n5:5o(6+2)6d\n6:6d(5+1)7n\n", "LNT": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n", "LSTb": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\n6b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n7s:n-acetyl\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:3o(6+2)6d\n6:6d(5+1)7n\n", "FDSLNH": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:a-lgal-HEX-1:5|6:d\n6b:b-dgal-HEX-1:5\n7b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n8s:n-acetyl\n9b:b-dglc-HEX-1:5\n10s:n-acetyl\n11b:b-dgal-HEX-1:5\n12b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n13s:n-acetyl\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:3o(4+1)6d\n6:6o(6+2)7d\n7:7d(5+1)8n\n8:2o(6+1)9d\n9:9d(2+1)10n\n10:9o(4+1)11d\n11:11o(6+2)12d\n12:12d(5+1)13n\n", "LNFP III": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:a-lgal-HEX-1:5|6:d\n6b:b-dgal-HEX-1:5\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:3o(4+1)6d\n", "2'FL": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:a-lgal-HEX-1:5|6:d\nLIN\n1:1o(4+1)2d\n2:2o(2+1)3d\n", "LNFP I": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\n6b:a-lgal-HEX-1:5|6:d\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:5o(2+1)6d\n", "LNFP II": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\n6b:a-lgal-HEX-1:5|6:d\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:3o(4+1)6d\n", "LNnT": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(4+1)5d\n", "3FL": "RES\n1b:x-dglc-HEX-1:5\n2b:a-lgal-HEX-1:5|6:d\n3b:b-dgal-HEX-1:5\nLIN\n1:1o(3+1)2d\n2:1o(4+1)3d\n", "DFLNT": "RES\n1b:x-dglc-HEX-1:5\n2b:a-lgal-HEX-1:5|6:d\n3b:b-dgal-HEX-1:5\n4b:b-dglc-HEX-1:5\n5s:n-acetyl\n6b:b-dgal-HEX-1:5\n7b:a-lgal-HEX-1:5|6:d\nLIN\n1:1o(3+1)2d\n2:1o(4+1)3d\n3:3o(3+1)4d\n4:4d(2+1)5n\n5:4o(3+1)6d\n6:4o(4+1)7d\n", "DSLNH": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\n6b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n7s:n-acetyl\n8b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n9s:n-acetyl\n10b:b-dglc-HEX-1:5\n11s:n-acetyl\n12b:b-dgal-HEX-1:5\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:5o(3+2)6d\n6:6d(5+1)7n\n7:3o(6+2)8d\n8:8d(5+1)9n\n9:2o(6+1)10d\n10:10d(2+1)11n\n11:10o(4+1)12d\n", "DFLNH": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:a-lgal-HEX-1:5|6:d\n6b:b-dgal-HEX-1:5\n7b:b-dglc-HEX-1:5\n8s:n-acetyl\n9b:a-lgal-HEX-1:5|6:d\n10b:b-dgal-HEX-1:5\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:3o(4+1)6d\n6:2o(6+1)7d\n7:7d(2+1)8n\n8:7o(3+1)9d\n9:7o(4+1)10d\n", "FLNH": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\n6b:a-lgal-HEX-1:5|6:d\n7b:b-dglc-HEX-1:5\n8s:n-acetyl\n9b:b-dgal-HEX-1:5\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:5o(2+1)6d\n6:2o(6+1)7d\n7:7d(2+1)8n\n8:7o(4+1)9d\n", "3'SL": "RES\n1b:b-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n4s:n-acetyl\nLIN\n1:1o(4+1)2d\n2:2o(3+2)3d\n3:3d(5+1)4n\n", "DSLNT": "RES\n1b:x-dglc-HEX-1:5\n2b:b-dgal-HEX-1:5\n3b:b-dglc-HEX-1:5\n4s:n-acetyl\n5b:b-dgal-HEX-1:5\n6b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n7s:n-acetyl\n8b:a-dgro-dgal-NON-2:6|1:a|2:keto|3:d\n9s:n-acetyl\nLIN\n1:1o(4+1)2d\n2:2o(3+1)3d\n3:3d(2+1)4n\n4:3o(3+1)5d\n5:5o(3+2)6d\n6:6d(5+1)7n\n7:3o(6+2)8d\n8:8d(5+1)9n\n"}