fix HXB2 reference in all.fasta

tests/expected-results-edgy/blast.csv

@@ -1,7 +1,7 @@
 qseqid,sseqid,sgi,qlen,slen,length,qstart,qend,sstart,send,evalue,bitscore,pident,nident,sstrand,btop
-Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9719,9719,1,9718,1,9719,0.0,13866,99.949,9714,plus,5770-T291TC2358CTCA743GA552
-Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9719,634,1,634,9086,9719,0.0,885,98.738,626,plus,23CA83AG55GT3TA7AG5CT44AG63AG343
-Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9719,634,9085,9718,1,634,0.0,882,98.580,625,plus,23AC57GA25GA55TG3AT7GA5TC44GA63GA343
-Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9719,9719,1,9718,9719,1,0.0,13866,99.949,9714,minus,552CT743GTGA2358AG291-A5770
-Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9719,634,9085,9718,9719,9086,0.0,885,98.738,626,minus,343TC63TC44GA5TC7AT3CA55TC83GT23
-Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9719,634,1,634,634,1,0.0,882,98.580,625,minus,343CT63CT44AG5CT7TA3AC55CT25CT57TG23
+Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9718,9718,1,9718,1,9718,0.0,13882,100.000,9718,plus,9718
+Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9718,634,9085,9718,1,634,0.0,882,98.580,625,plus,23AC57GA25GA55TG3AT7GA5TC44GA63GA343
+Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9718,634,1,634,9085,9718,0.0,882,98.580,625,plus,23CA57AG25AG55GT3TA7AG5CT44AG63AG343
+Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9718,9718,1,9718,9718,1,0.0,13882,100.000,9718,minus,9718
+Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9718,634,1,634,634,1,0.0,882,98.580,625,minus,343CT63CT44AG5CT7TA3AC55CT25CT57TG23
+Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,0,9718,9718,634,9085,9718,9718,9085,0.0,882,98.580,625,minus,343TC63TC44GA5TC7AT3CA55TC25TC57GT23

tests/expected-results-edgy/errors.json

@@ -1,26 +1,4 @@
 {
-    "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455": [
-        {
-            "sequence_name": "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455",
-            "error": "FrameshiftInOrf",
-            "message": "Smaller ORF vpr at 5558-5843 contains out of frame indels that impact 75 positions."
-        },
-        {
-            "sequence_name": "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455",
-            "error": "InsertionInOrf",
-            "message": "Smaller ORF nef at 8796-9417 can have maximum insertions 90, got 249"
-        }
-    ],
-    "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED": [
-        {
-            "sequence_name": "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED [REVERSED]",
-            "error": "FrameshiftInOrf",
-            "message": "Smaller ORF vpr at 5558-5843 contains out of frame indels that impact 75 positions."
-        },
-        {
-            "sequence_name": "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED [REVERSED]",
-            "error": "InsertionInOrf",
-            "message": "Smaller ORF nef at 8796-9417 can have maximum insertions 90, got 249"
-        }
-    ]
+    "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455": [],
+    "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED": []
 }

tests/expected-results-edgy/holistic.json

@@ -4,23 +4,23 @@
         "hypermutation_probablility": 0.0,
         "inferred_subtype": "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455",
         "blast_matched_qlen": 9718,
-        "blast_sseq_coverage": 1.1304660973351168,
+        "blast_sseq_coverage": 1.130479522535501,
         "blast_qseq_coverage": 1.130479522535501,
         "blast_sseq_orfs_coverage": 1.0,
         "orfs_start": 789,
-        "orfs_end": 8795,
+        "orfs_end": 8794,
         "blast_n_conseqs": 3
     },
     "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455.BUT.REVERSED": {
         "qlen": 9718,
         "hypermutation_probablility": 0.0,
         "inferred_subtype": "Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455",
         "blast_matched_qlen": 9718,
-        "blast_sseq_coverage": 1.1304660973351168,
+        "blast_sseq_coverage": 1.130479522535501,
         "blast_qseq_coverage": 1.130479522535501,
         "blast_sseq_orfs_coverage": 1.0,
         "orfs_start": 789,
-        "orfs_end": 8795,
+        "orfs_end": 8794,
         "blast_n_conseqs": 3
     }
 }

tests/expected-results-large-csv/holistic.csv

@@ -1,42 +1,42 @@
 seqid,qlen,hypermutation_probablility,inferred_subtype,blast_matched_qlen,blast_sseq_coverage,blast_qseq_coverage,blast_sseq_orfs_coverage,orfs_start,orfs_end,blast_n_conseqs
-KX505501.1,1997,0.7087072014754221,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,1997,0.2498199403230785,1.2158237356034052,0.17661753684736448,789,8795,4
-MN691959,9493,0.19593905853945925,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9493,1.0816956477003807,1.1086063415148004,1.0,789,8795,3
-MN692074,4178,0.36378645339477633,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,4178,0.5041670953801831,1.1728099569171853,0.41144141893579816,789,8795,4
-MN692145,9689,0.1661041079701131,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9689,1.1304660973351168,1.1271545051088863,1.0,789,8795,3
-MN090335,9069,0.1754017863888554,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9069,0.9842576396748637,1.0603153600176425,1.0003747189607795,789,8795,3
-MN090376,8985,0.026007919521734202,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,8985,0.9784957300133759,1.0604340567612687,0.9943792155883088,789,8795,3
-MK115581.1,9495,0.6897199265079494,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9495,0.9870357032616525,1.0046340179041602,1.0,789,8795,2
-MK115690.1,9689,0.05065930954004094,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9689,0.988167506945159,0.9949427185468056,1.0,789,8795,2
-MK115571.1,9394,0.8012585672082311,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9394,0.9866241382858318,1.0113902490951672,1.0,789,8795,2
-MK115514.1,9382,0.6458974386368621,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9382,0.9864183557979216,1.0173736943082499,1.0,789,8795,2
-MK115488.1,9623,0.6511896911074662,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9623,1.0255170285008746,1.0325262392185388,1.0,789,8795,6
-MK115030.1,9126,0.031598631869680704,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9126,0.9940323078506019,1.0655270655270654,1.0,789,8795,3
-MK115498.1,9461,0.8339748776671196,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9461,0.9866241382858318,1.0080329774865235,1.0,789,8795,2
-MK115211.1,9032,0.11689558806708,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9032,0.9950612202901533,1.0598981399468557,1.0,789,8795,3
+KX505501.1,1997,0.7087072014754221,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,1997,0.2498456472525211,1.2158237356034052,0.17663960024984385,789,8794,4
+MN691959,9493,0.19667690182893238,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9493,1.0817040543321672,1.1086063415148004,1.0,789,8794,3
+MN692074,4178,0.36378645339477633,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,4178,0.5042189750977567,1.1728099569171853,0.4114928169893816,789,8794,4
+MN692145,9689,0.1672411051048176,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9689,1.130479522535501,1.1271545051088863,1.0,789,8794,3
+MN090335,9069,0.1771850809736527,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9069,0.9842560197571517,1.0603153600176425,1.0003747657713928,789,8794,3
+MN090376,8985,0.026415767987601813,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,8985,0.9784935171846059,1.0604340567612687,0.9943785134291068,789,8794,3
+MK115581.1,9495,0.6919440876652894,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9495,0.987034369211772,1.0046340179041602,1.0,789,8794,2
+MK115690.1,9689,0.051230576250981485,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9689,1.004630582424367,1.0113530808132933,1.0,789,8794,3
+MK115571.1,9394,0.8029570594372466,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9394,0.9866227618851615,1.0113902490951672,1.0,789,8794,2
+MK115514.1,9382,0.6482462132632603,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9382,0.9864169582218564,1.0173736943082499,1.0,789,8794,2
+MK115488.1,9623,0.6534999185838631,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9623,1.0255196542498457,1.0325262392185388,1.0,789,8794,6
+MK115030.1,9126,0.032014462397289556,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9126,0.994031693764149,1.0655270655270654,1.0,789,8794,3
+MK115498.1,9461,0.83547963060225,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9461,0.9866227618851615,1.0080329774865235,1.0,789,8794,2
+MK115211.1,9032,0.11818291879607423,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9032,0.995060712080675,1.0598981399468557,1.0,789,8794,3
 MK115158.1,9143,0.002572269807584293,Ref.47_BF.ES.08.P1942.GQ372987,9143,0.9921577414295317,0.9699223449633599,1.0,234,8212,1
-MK114705.1,9411,0.14449377496074622,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9411,1.0980553554892478,1.122622463075125,1.0,789,8795,6
-MK114856.1,9477,1.0,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9477,1.0485646671468258,1.0812493405085997,1.0,789,8795,4
-MK115009.1,9207,1.0,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9207,0.9965016977055252,1.0590854784403172,1.0,789,8795,3
-MK115387.1,9136,0.5412311092694289,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9136,0.9796275336968824,1.040936952714536,1.0,789,8795,2
-MK115491.1,9422,0.8951015182445495,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9422,1.003704084782385,1.0299299511780937,1.0,789,8795,2
+MK114705.1,9411,0.14584270737492833,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9411,1.098065445564931,1.122622463075125,1.0,789,8794,6
+MK114856.1,9477,1.0,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9477,1.0485696645400289,1.0812493405085997,1.0,789,8794,4
+MK115009.1,9207,1.0,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9207,0.9965013377238114,1.0590854784403172,1.0,789,8794,3
+MK115387.1,9136,0.5436355526687852,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9136,0.9796254373327845,1.040936952714536,1.0,789,8794,2
+MK115491.1,9422,0.8961809048805741,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9422,1.0037044659394938,1.0299299511780937,1.0,789,8794,2
 MK116110.1,8967,0.07021438897893317,Ref.B.TH.90.BK132.AY173951,8967,0.9957759004001778,0.9972119995539199,0.998622244488978,140,8124,3
-MK115527.1,9481,0.7689834393883834,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9481,0.986727029529787,1.0056956017297753,1.0,789,8795,2
-MK114997.1,9055,0.054959132555391754,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9055,0.9784957300133759,1.0516841524019878,1.0,789,8795,2
-MK115518.1,9537,0.6385326595592609,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9537,0.9847720958946393,0.9996854356715948,1.0,789,8795,3
-MK115065.1,9214,0.033517722768753644,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9214,1.0080255170285009,1.069459518124593,1.0,789,8795,6
-MK115464.1,9663,1.0,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9663,0.9838460746990431,0.9893407844354756,1.0,789,8795,2
-MK115530.1,9544,0.5789377103398377,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9544,0.9866241382858318,0.9992665549036044,1.0,789,8795,2
-MK115520.1,9589,0.5200353682902832,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9589,0.9787015125012861,0.987902805297737,1.012115913065201,789,8795,3
-MK115503.1,9617,0.4263025132504157,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9617,0.9870357032616525,0.9953207861079338,1.0,789,8795,2
-MK115570.1,9485,0.738578434638724,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9485,0.9866241382858318,1.0057986294148655,1.0,789,8795,2
-MK115509.1,9353,0.7866198309713798,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9353,0.9866241382858318,1.0197797498128942,1.0,789,8795,2
-MK115702.1,9098,0.14401391767451666,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9098,0.987447268237473,1.0596834469114091,1.019860104921309,789,8795,4
-MK115095.1,9137,1.0,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9137,0.9907397880440375,1.060085367188355,1.0,789,8795,2
-MK115490.1,9347,0.8863248655310947,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9347,0.9848749871385946,1.0204343639670483,1.0,789,8795,3
-MK115576.1,9266,0.818189227062389,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9266,0.9917687004835889,1.0342110943233327,1.0,789,8795,3
-OQ092466,9686,0.3876036547663967,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9686,1.1015536577837226,1.1192442700805285,1.0,789,8795,3
+MK115527.1,9481,0.770862998910788,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9481,0.9867256637168141,1.0056956017297753,1.0,789,8794,2
+MK114997.1,9055,0.05560625344150194,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9055,0.9784935171846059,1.0516841524019878,1.0,789,8794,2
+MK115518.1,9537,0.6408152618300496,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9537,0.9847705289154147,0.9996854356715948,1.0,789,8794,3
+MK115065.1,9214,0.033954952452739495,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9214,1.0080263428689031,1.069459518124593,1.0,789,8794,6
+MK115464.1,9663,1.0,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9663,0.9838444124305412,0.9893407844354756,1.0,789,8794,2
+MK115530.1,9544,0.5812621948015355,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9544,0.9866227618851615,0.9992665549036044,1.0,789,8794,2
+MK115520.1,9589,0.5225247969864292,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9589,0.9786993208479111,0.987902805297737,1.0121174266083697,789,8794,3
+MK115503.1,9617,0.42870398270204335,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9617,0.987034369211772,0.9953207861079338,1.0,789,8794,2
+MK115570.1,9485,0.7406166892211931,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9485,0.9866227618851615,1.0057986294148655,1.0,789,8794,2
+MK115509.1,9353,0.7883768413537747,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9353,0.9866227618851615,1.0197797498128942,1.0,789,8794,2
+MK115702.1,9098,0.1454272422215308,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9098,0.9874459765383824,1.0596834469114091,1.0198625858838226,789,8794,4
+MK115095.1,9137,1.0,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9137,0.9907388351512657,1.060085367188355,1.0,789,8794,2
+MK115490.1,9347,0.8875203448314265,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9347,0.9848734307470673,1.0204343639670483,1.0,789,8794,3
+MK115576.1,9266,0.8197662757563093,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9266,0.9917678534677917,1.0342110943233327,1.0,789,8794,3
+OQ092466,9686,0.3858261890626,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9686,1.1015641078411196,1.1192442700805285,1.0,789,8794,3
 OQ092463,9605,0.21628713708846803,Ref.B.TH.90.BK132.AY173951,9605,1.0529124055135617,0.9884435190005205,1.0,140,8124,2
 OQ092465,9659,0.02412789935966586,Ref.28_BF.BR.99.BREPM12817.DQ085874,9659,1.0429696287964005,0.9620043482762191,1.0,200,8208,2
-OQ092462,9714,0.10777665573070194,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9714,1.130671879823027,1.1301214741610048,1.0,789,8795,3
+OQ092462,9714,0.10883643311676816,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9714,1.1306853261988064,1.1301214741610048,1.0,789,8794,3
 OQ092464,9556,0.006887768010151674,Ref.28_BF.BR.99.BREPM12817.DQ085874,9556,1.0427446569178853,0.9678735872750105,1.0,200,8208,2
-OQ092467,9936,0.6416537859942263,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9936,1.1308776623109373,1.0962157809983897,1.0,789,8795,3
+OQ092467,9936,0.6438715160567257,Ref.B.FR.83.HXB2_LAI_IIIB_BRU.K03455,9936,1.1308911298621116,1.0962157809983897,1.0,789,8794,3