Last active
April 15, 2016 12:01
-
-
Save abojchevski/ac4f681dfc2875a3a1801f3cbcbe502d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/home/abojchevski/anaconda3/bin/python /home/abojchevski/projects/nala/scripts/train.py --test_corpus tmVar_test --model_path_1 /home/abojchevski/Downloads/nala_BIEO_del_None_466744.bin --we | |
SpacyLemmatizer: INIT START | |
SpacyLemmatizer: INIT END | |
word embddings loaded with vocab size: 519819 | |
Running arguments: | |
crf_train_params = None | |
cv_fold = None | |
cv_n = None | |
delete_subclasses = [] | |
do_train = False | |
elastic_net = False | |
labeler = BIEO | |
model_name = None_BIEO_del_None | |
model_name_suffix = | |
model_path_1 = /home/abojchevski/Downloads/nala_BIEO_del_None_466744.bin | |
model_path_2 = None | |
nl = False | |
nl_features = None | |
nl_threshold = 0 | |
nl_window = False | |
output_folder = /tmp/tmpmke3wcpu | |
pruner = parts | |
ps_NL = False | |
ps_ST = False | |
ps_random = 0.0 | |
test_corpus = tmVar_test | |
training_corpus = None | |
use_feat_windows = True | |
validation = stratified | |
we_additive = 0 | |
we_model_location = None | |
we_multiplicative = 1 | |
we_params = {'multiplicative': 1, 'location': None, 'additive': 0} | |
word_embeddings = True | |
write_anndoc = False | |
None_BIEO_del_None | |
starting feature generator: <class 'nalaf.features.stemming.SpacyLemmatizer'> | |
starting feature generator: <class 'nalaf.features.simple.SentenceMarkerFeatureGenerator'> | |
starting feature generator: <class 'nala.features.tmvar.TmVarFeatureGenerator'> | |
starting feature generator: <class 'nala.features.tmvar.TmVarDictionaryFeatureGenerator'> | |
starting feature generator: <class 'nalaf.features.window.WindowFeatureGenerator'> | |
starting feature generator: <class 'nalaf.features.embeddings.WordEmbeddingsFeatureGenerator'> | |
test size: 166 | |
test: | |
pred: | |
subclass distribution: Counter({0: 445, 1: 17, 2: 2}) | |
num sentences: 1755 | |
test: c.737delC || p.Pro246HisfsX13 | |
pred: c.737delC || p.Pro246HisfsX13 | |
test: | |
pred: | |
test: Ex2+860G>C || S276T || rs2234671 || rs2234671 || rs2234671 | |
pred: S276T || rs2234671 || rs2234671 || rs2234671 at position Ex2+860G>C | |
test: | |
pred: | |
test: 3190C>T || Arg987Ter || Arg987Ter | |
pred: 3190C>T in exon 24 || Arg987Ter || Arg987Ter || replacement of an arginine residue at position 573 by termination codon | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: insertion of A between nucleotides 1900 and 1901, which resulted in a 3-nucleotide change within the Kozak sequence || single nucleotide insertion/deletion | |
test: | |
pred: | |
test: c.104delT || p.Val35AlafsX25 | |
pred: c.104delT || p.Val35AlafsX25 || panel of 262,000 single nucleotide polymorphism || premature termination codon | |
test: | |
pred: | |
test: rs16754 || rs16754 | |
pred: All exon 7 mutations were frameshift mutations || including the insertion within codon 313 and codon 314 || rs16754 || rs16754 single nucleotide polymorphism was G | |
test: | |
pred: | |
test: c.130G>A || c.130G>A || p.V44M | |
pred: D13S1316 || D13S1316 || D13S175 || D13S175 || c.130G>A || c.130G>A || non-conservative substitution of valine-to-methionine at codon 44 || p.V44M | |
test: | |
pred: | |
test: | |
pred: 4G/5G || single base pair guanine insertion/deletion polymorphism (4G/5G) | |
test: | |
pred: 13-bp deletion in the 3' untranslated region | |
test: CD +90 del 13 bp || IVSII-1 (G > A) || IVSII-1 (G > A) | |
pred: 13-bp deletion || 13-bp deletion at nucleotide 90 downstream of the termination codon || 13-bp deletion in the 3' UTR || 13-bp deletion in the 3' UTR || CD +90 del 13 bp || G > A || G > A | |
test: | |
pred: single base pair substitution activates a 10-base downstream cryptic splice acceptor site in exon 12 | |
test: c.1706-1715del.ATCTCCTCAG || c.1706-2 A>T || p.(Asp569Valfs*93) | |
pred: 10-base deletion from the beginning of exon 12 || Asp569Valfs || c.1706-1715del || c.1706-2 A>T || deletion generates a frameshift and a premature termination codon (c.1991-1993 | |
test: Arg399Gln | |
pred: Arg399Gln | |
test: Arg399Gln || Arg399Gln || Arg399Gln || Arg399Gln || rs25487 | |
pred: Arg or Arg || Arg versus Arg || Arg versus Arg || Arg399Gln || Arg399Gln || Arg399Gln || Arg399Gln || rs25487 | |
test: | |
pred: | |
test: | |
pred: C35322C || C35322C || C35322T || deletion at 5063 || substitution of C to T at 33468 in exon 8 | |
test: | |
pred: | |
test: A1762T || E164D || G1764A || G1896A || G1899A || I195M || L180M || L180M || M204V || M204V || V173L || V173L | |
pred: A1762T || G1764A || G1896A || G1899A || rtL180M || rtL180M + rtM204V || rtM204V || rtV173L || rtV173L || sE164D || sI195M | |
test: | |
pred: | |
test: c.263C>T || c.263C>T || p.Ala88Val || p.Ala88Val || p.Asp50Asn | |
pred: c.263C>T || c.263C>T || leading to a substitution of alanine for valine at position 88 || p.Ala88Val || p.Ala88Val || p.Asp50Asn | |
test: | |
pred: | |
test: | |
pred: C to T substitution at a polymorphic site 13 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: Arg158 Pro | |
pred: Arg158 Pro | |
test: | |
pred: G to C at codon 158 of exon 4 || amino acid substitution of arginine residue for the proline residue at position 158 of apoE | |
test: | |
pred: | |
test: c.410+5 G/A || c.69delC | |
pred: c.410+5 G/A || c.69delC | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: G303E || c.908G>A | |
pred: G303E || c.908G>A within exon 8 || substitution of the amino acid glycine at position 303 | |
test: | |
pred: | |
test: I597T || T>C | |
pred: I597T || heterozygous T>C nucleotide substitution on exon 14 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: -1240 L/S || -521 C/T || -521 C/T || -521C/T || -616C/G | |
pred: -120 bp duplication, -616C/G | |
test: | |
pred: | |
test: | |
pred: | |
test: delta32 | |
pred: | |
test: | |
pred: | |
test: -1021C/T | |
pred: | |
test: rs1611115 || rs1800587 | |
pred: rs1611115 || rs1800587 | |
test: | |
pred: | |
test: c.-17T>C || c.171T>C || c.465G>T || c.465G>T || p.Glu155Asp | |
pred: c.-17T>C || c.171T>C || c.465G>T || c.465G>T || p.Glu155Asp | |
test: | |
pred: | |
test: | |
pred: | |
test: 10034C>T | |
pred: fibrinogen gamma 10034C>T | |
test: 10034C>T || 10034C>T || rs2066865 | |
pred: FGG 10034 T || FGG 10034C>T || FGG 10034C>T || rs2066865 | |
test: | |
pred: | |
test: rs20551 || rs525549 || rs5758222 || rs6589664 || rs6589664 || rs7286979 | |
pred: rs20551 || rs525549 || rs5758222 || rs6589664 || rs6589664 || rs7286979 | |
test: | |
pred: | |
test: | |
pred: lack of CDKN2A | |
test: | |
pred: | |
test: c.2554+1G>T | |
pred: c.2554+1G>T || deletion of amino acids 809-852 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: c.2515_2519delAAGTT | |
pred: c.2515_2519delAAGTT | |
test: | |
pred: | |
test: C119Y || C119Y || c.356G>A || rs13267 | |
pred: C119Y || c.356G>A || leading to amino acid substitution C119Y || rs13267 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: IVS3 + 18C > T || IVS3 + 18C > T || c.1546_1547insC | |
pred: IVS3 + 18C > T || c.1546_1547insC || single nucleotide polymorphism (SNP) in intron 3 (IVS3 + 18C > T) | |
test: | |
pred: | |
test: (G-->A) at nucleotide position 2141 | |
pred: (G-->A) at nucleotide position 2141 (exon 8), which resulted in substitution of arginine by glutamine at amino acid position 714 || replacement of arginine by glutamine at position 714 | |
test: | |
pred: | |
test: R68C || rs4112788 || rs4112788 | |
pred: R68C || rs4112788 || rs4112788 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: codon 104 G --> A | |
pred: nondeletional mutation Hb Sallanches (alpha 2 codon 104 G --> A) | |
test: | |
pred: | |
test: rs10954213 || rs10954213 || rs10954213 || rs2004640 || rs2070197 | |
pred: rs10954213 || rs10954213 || rs10954213 || rs2004640 || rs2070197 | |
test: | |
pred: | |
test: p.C152G || p.D157fsX158 || p.E180K || p.R194S || p.S173fsX174 | |
pred: D157fsX158 || p.C152G || p.E180K || p.R194S | |
test: Ser326Cys | |
pred: Ser326Cys | |
test: rs1052133 || rs1052133 || rs1052133 | |
pred: rs1052133 || rs1052133 || rs1052133 || substitution of the amino acid at codon 326 from Ser to Cys | |
test: | |
pred: | |
test: c.263 G>C || c.264 C>A | |
pred: c.263 G>C || c.264 C>A || substitution from cytosine to adenine at position 264 || substitution from guanine to cytosine at position 263 of the nucleotide sequence | |
test: | |
pred: | |
test: G>A substitution at nucleotide 893 || R298Q || rs16864880 | |
pred: G>A substitution at nucleotide 893 || R298Q || rs16864880 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: 672 insertion sequence 6110 | |
test: | |
pred: G 14 bp insertion/deletion polymorphism | |
test: rs16375 | |
pred: 14 bp insertion/deletion polymorphism || 14 bp insertion/deletion polymorphism || G 14 bp deletion/insertion polymorphism || rs16375 | |
test: | |
pred: | |
test: rs2236624 || rs35320474 || rs3761422 || rs5751876 | |
pred: rs2236624 || rs35320474 || rs3761422 || rs5751876 | |
test: | |
pred: | |
test: | |
pred: deletion of a termination-codon-containing region | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: c.1558-1559insA || c.507G>T || c.867G>T || c.897G>T || p.E169stop || p.E299stop || p.G289stop || p.S522fs 525stop | |
pred: c.1558-1559insA || c.507G>T || c.867G>T || c.897G>T || p.E169stop || p.E299stop || p.G289stop || p.S522fs 525stop | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: G-669A || Glu98X || Leu203fsX15 || Ser863Asn | |
pred: (Glu98X) and a missense single nucleotide substitution in exon 12 (Ser863Asn) || G-669A || Leu203fsX15 || deletion of TG at the nucleotide position 608-609 in exon 5 || nonsense mutation at the nucleotide position 292 in exon 3 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: Deletion/Deletion (DD) | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: A 11666C || A 1166C || A 1166C | |
pred: A 11666C || A 1166C || A 1166C | |
test: R58fs | |
pred: R58fs | |
test: R58fs || c.342delA || p.Arg58fs || p.R58fs | |
pred: R58fs || p.Arg58fs || single nucleotide deletion c.342delA, located in exon 3, which resulted in a frameshift at amino acid position 58 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: SRO of deletion (10-Mb or less) at 11q23 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: rs12329760 | |
pred: rs12329760 | |
test: | |
pred: | |
test: 118-119insA || 125-126insAA || 46delS || A442V || A6V || E359K || E359K || P163S || P407Q || S429T || c.1146+25insA | |
pred: 118-119insA || 125-126insAA || 46delS || A442V || A6V || E359K || E359K || P163S || P407Q || S429T || c.1146+25insA in exon 6 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: R1858X || Y1854X || Y1854X | |
pred: C to G transversion (Y1854X) || R1858X || Y1854X | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: c.2068-4T>A | |
pred: 7-bp deletion in exon 21 and a base insertion in exon 26 || c.2068-4T>A || nonsense mutation in exon 19 || nonsense mutation in exon 24 | |
test: L1503R | |
pred: L1503R | |
test: L1503Q || L1503R || L1503R || L1503R || T-->G transversion at nucleotide 4508 | |
pred: L1503Q || L1503R || L1503R || heterozygous T-->G transversion at nucleotide 4508 || substitution of L1503R | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: c.1570+2T>C || c.360+1G>C || c.360+1G>C || c.520delC || c.681dupA || c.899+1G>T || c.956delC || p.Arg153X | |
pred: 956delC || c.1570+2T>C || c.360+1G>C || c.360+1G>C || c.520delC || c.681dupA || c.899+1G>T || p.Arg153X | |
test: | |
pred: | |
test: | |
pred: deletion of 13q14 || deletion of 13q14 || deletion of ATM (11q22) || deletion of TP53 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: A/G transition -1,071 bp || D541E || D541E || K294E || R462Q || R462Q | |
pred: 20 bp insertion/deletion polymorphism 1,109 bp upstream of the initiation codon || D541E || D541E || G transition -1,071 bp from the transcriptional start site || K294E || R462Q || R462Q | |
test: | |
pred: | |
test: M200V || P29S | |
pred: M200V || P29S || replacement of a non-polar amino acid (proline) with a polar amino acid (serine) at position 29 | |
test: | |
pred: | |
test: 25*G>A || Ala88Thr || Ser424Ser || Tyr428Tyr || c.1272C>T || c.1284T>C || c.262G>A || c.97GCC[9]+[10] | |
pred: Ala88Thr || G>A substitution in the 3'-untranslated region || Ser424Ser || Tyr428Tyr || c.1272C>T || c.1284T>C || c.262G>A || duplication of GCC (c.97GCC[9]+[10]) || extra alanine within exon 1 | |
overlapping subclasses do not match 0 1 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: -1082(G/A) || G/A | |
pred: polymorphic nucleotide A at position -1082 | |
test: IVS1-1G>C | |
pred: IVS1-1G>C | |
test: G > C || IVS1-1G > A || IVS1-1G > C || IVS1-1G > C || IVS1-1G > C | |
pred: G > C || IVS1-1G > A || IVS1-1G > C || IVS1-1G > C substitution || IVS1-1G > C substitution of exon 1 | |
overlapping subclasses do not match 0 2 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: g.ORF15 + 652-653delAG || g.ORF15 + 652-653delAG | |
pred: -653delAG || -653delAG || heterozygous AG-deletion at nucleotide 652 and 653 | |
test: | |
pred: | |
test: Delta32 || Delta32 || Delta32 || Delta32 | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: rs2648875 || rs2720709 || rs2720709 | |
pred: rs2648875 || rs2720709 || rs2720709 | |
test: V175M | |
pred: V175M | |
test: Val175Met || Val175Met || Val175Met || Val175Met || Val175Met || Val175Met || Val175Met | |
pred: Val175Met || Val175Met || Val175Met || Val175Met || Val175Met || Val175Met || Val175Met | |
test: | |
pred: | |
test: A149P || A174D || N334K | |
pred: A149P || A174D || Delta4E4 || N334K | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: 6bINS || 6bINS || 6bINS || 6bINS || 6bINS | |
pred: 6bINS || 6bINS || 6bINS || 6bINS || 6bINS | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: in-frame deletion | |
test: | |
pred: | |
test: -1282G>A || -2084G>C | |
pred: -1282G>A || -2084G>C | |
test: | |
pred: | |
test: | |
pred: p53 codon 72 || p53 codon 72 genotype | |
test: | |
pred: | |
test: c.2633+1G>C || c.2633+1G>C || p.Ser555Leu || r.2521_2634del | |
pred: 1 skipping the entire exon 22 || c.2633+1G>C || c.2633+1G>C || p.Ser555Leu || r.2521_2634del || substitution of serine by leucine at amino acid position 555 | |
test: | |
pred: | |
test: c.2406C-->A | |
pred: c.2406C-->A | |
test: | |
pred: | |
test: 1858C/T || 1858C/T || 2250G/C | |
pred: premature termination codon after exon 17 | |
test: | |
pred: | |
test: | |
pred: C-to-T || C-to-T single nucleotide substitution | |
test: | |
pred: | |
test: -863C > A || -863C > A || C > A substitution at position -863 | |
pred: C > A substitution at position -863 || allele of the TNFA-863C > A | |
overlapping subclasses do not match 0 1 | |
test: Tyr1306Cys | |
pred: Tyr1306Cys | |
test: Tyr1306Cys || Tyr1306Cys | |
pred: Tyr1306Cys || Tyr1306Cys | |
test: G1103R | |
pred: G1103R | |
test: G1103R | |
pred: G1103R | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: Arg260His || Ser263Phe || Ser290/Ala291fs || Ser413Leu || Tyr547fs || Tyr69X || Val414Phe || c.1642_1644dupA || c.2045-1G > A || c.210T > G || c.791C > T || c.892_895dupG | |
pred: (c.1642_1644dupA) and at codonTyr547fs || (c.892_895dupG) at codons Ser290/Ala291fs || Arg260His || Ser263Phe || Ser413Leu || Tyr69X || Val414Phe || c.2045-1G > A || c.210T > G || c.791C > T || single base 'G' duplication | |
overlapping subclasses do not match 0 1 | |
overlapping subclasses do not match 0 2 | |
test: | |
pred: | |
test: | |
pred: 30-bp deletion || codon: 346-355 | |
test: | |
pred: deletion of cDNA nucleotide 81 | |
test: | |
pred: nt 81G deletion | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: single-nucleotide insertion or deletion | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: deletion of chromosome 14q32.33 | |
test: | |
pred: | |
test: EX6-96A>G || F302fsX39 || G346R || I38fsX19 || IVS12+4A>G || IVS12+6T>A || IVS4+3G>C || L367L || Q267E || Q267H || R111X || R157I || R157K || R243Q || R400K || R413P || S349A || T200fsX6 || Y154H || Y356X | |
pred: EX6-96A>G || F302fsX39 || G346R || I38fsX19 || IVS12+4A>G || IVS12+6T>A || IVS4+3G>C || L367L || Q267E || Q267H || R111X || R157I || R157K || R243Q || R400K || R413P || S349A || T200fsX6 || Y154H || Y356X | |
test: | |
pred: | |
test: A --> G transition at 127 position || Asn --> Ser substitution at codon 127 || Asn127Ser || G --> A transition at 1032 position || Gly --> Asp change at codon 322 || Gly322Asp || Gly322Asp || Gly322Asp | |
pred: A --> G transition at 127 position producing an Asn --> Ser substitution at codon 127 (the Asn127Ser || G --> A transition at 1032 position || Gly --> Asp change at codon 322 || Gly/Gly phenotype of the Gly322Asp || Gly322Asp || the Gly322Asp polymorphism | |
overlapping subclasses do not match 0 1 | |
overlapping subclasses do not match 0 1 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: K386T || S482X | |
pred: 15-bp deletion in exon 7 || 15-bp deletion that included the 3' splice site for exon 7 || K386T || S482X || deletion mutation in exon 7 | |
test: | |
pred: | |
test: A467T || A467T || A467T || A467T || A467T || E873-TAG || E873stop || E873stop || E873stop || E873stop | |
pred: A467T || A467T || A467T || A467T || A467T || E873-TAG || E873stop || E873stop || E873stop || E873stop || premature termination codon (TAG) in exon 17 || threonine to alanine substitution at a highly conserved site in exon 7 | |
test: | |
pred: | |
test: IVS2-58_55insT | |
pred: IVS2-58_55insT || insertion in IVS2 | |
test: | |
pred: | |
test: Arg792Gly || Arg792Gly | |
pred: A to G transition at nucleotide +79 of exon 41 || Arg792Gly || Arg792Gly substitution is located at the Y-position of Gly-X-Y || converted the codon for arginine at amino acid 792 to a codon for glycine | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: V175M || V175M || V175M || V175M | |
pred: Met/Met at residue 175 || V175M || V175M || V175M || V175M | |
test: | |
pred: | |
test: C-->T | |
pred: heterozygous C-->T single-nucleotide substitution, 16 nt upstream of the putative translation initiation site | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: rs5393 | |
pred: rs5393 | |
test: | |
pred: | |
test: | |
pred: deletion of about 1.4 kb including exon 3 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: c.1044_1049delTTCTGGinsACACT || c.113-1G>A || c.345_372del28 || c.360_363delCAAA || c.532T>C || c.612T>G || c.799+2T>A || c.841_842delAC || c.851T>C || c.865delC || p.A150P || p.A175D || p.C178R || p.L284P || p.N335K || p.R60X || p.Y204X || p.Y204X | |
pred: c.1044_1049delTTCTGGinsACACT || c.113-1G>A || c.345_372del28 || c.360_363delCAAA || c.532T>C || c.612T>G || c.799+2T>A || c.841_842delAC || c.851T>C || c.865delC || p.A150P || p.A175D || p.C178R || p.L284P || p.N335K || p.R60X || p.Y204X || p.Y204X | |
test: | |
pred: | |
test: 157delMTTTVP || 157delMTTTVP || rs2277025 | |
pred: 1 insertion/deletion polymorphism || 157delMTTTVP || 157delMTTTVP || rs2277025 | |
test: | |
pred: | |
test: A1053G || C3026T || C934A || G1915T/A || G529A || T2005C/A | |
pred: A1053G || C3026T || C934A || G1915T/A || G529A || T2005C/A | |
test: | |
pred: | |
test: rs1639679 | |
pred: rs1639679 | |
test: | |
pred: | |
test: ACG-->AAG substitution in codon 420 || GAT-->GAG | |
pred: GAT-->GAG substitution replaces aspartic acid by glutamic acid in codon 416; and ACG-->AAG substitution in codon 420 leads to an exchange of threonine for lysine | |
overlapping subclasses do not match 0 1 | |
overlapping subclasses do not match 1 0 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: 217_218insC || 217_218insC || A207D || A207D || A49T || A49T || G158R || G158R || G183S || G183S || G196S || G196S || IVS3+1G>A || IVS3+1G>A || Q126R || Q126R || Q126R || R246W || R266W || V89L || del418T || del642T || del642T | |
pred: 217_218insC plus the A49T || A207D || A207D || A49T || G158R || G158R || G183S || G183S || G196S || G196S || IVS3+1G>A || IVS3+1G>A || Q126R || Q126R || Q126R || R246W || R266W || V89L || and the insertion of a cytosine (217_218insC) || del418T || del642T || del642T || single nucleotide deletion | |
overlapping subclasses do not match 0 2 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: 222insT || 835del18 || 912delTA || D418D || GAC/GAT || L89R || P291A || Q536X || R171Q | |
pred: 222insT || D418D || L89R || P291A || Q536X, exon 10 || R171Q || one frameshift deletion (912delTA, exon 5), one in-frame deletion (835del18, exon 4) | |
overlapping subclasses do not match 0 1 | |
test: L490R || V561X | |
pred: L490R || V561X | |
test: 1469T->G || 1665delC || C282Y || I238M || I238M || L490R || L490R || L490R || V561X || V561X | |
pred: 1469T->G || 1665delC || 594-597 deletion || 714C-> || C282Y || I238M || I238M || L490R || L490R || L490R || V561X || V561X | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: A>G polymorphism at position -670 | |
pred: single nucleotide A>G polymorphism at position -670 | |
test: | |
pred: ) to guanine (G) substitution at position -670 | |
test: | |
pred: | |
test: 203G > A || N372H || N372H || N372H || N372H || N372H | |
pred: 203G > A || N372H || N372H || N372H || N372H || nonconservative amino acid substitution polymorphism N372H | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: E29K || E29K || Glu29 to Lys || g.3907G >A | |
pred: E29K || E29K || F7 gene deletion || codon for Glu29 to Lys || g.3907G >A | |
overlapping subclasses do not match 2 1 | |
test: | |
pred: | |
test: | |
pred: A guanine insertion (2G) polymorphism at nucleotide -1607 | |
test: | |
pred: | |
test: | |
pred: T to C substitution at position 1833 || all males were heterozygous in nucleotides 1678, 1694, 1699, 1708 and 1825 || exon 12 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: IVS10 + 4G | |
pred: A to G substitution denoted IVS10 + 4G | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: G-->A substitution at codon 1763 || I1762A || V1763M || V1764M | |
pred: G-->A substitution at codon 1763, which changed a valine (GTG) to a methionine (ATG) || I1762A || V1763M || V1764M | |
test: | |
pred: | |
test: 1188-A/C | |
pred: bp insertion/deletion | |
test: | |
pred: | |
test: Delta30 || Delta30 || Delta30 || Delta30 || Delta30 || Delta30 || Delta30 || Delta30 || Delta30 | |
pred: Delta30 || rDEN2Delta30-4995 || rDEN2Delta30-4995 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: 1091 C > T || G71R || G71R || G71R || G71R || P229Q || P364L || P364L || P364L || Y486D || Y486D || Y486D | |
pred: 1091 C > T || G71R || G71R || G71R || G71R || P229Q || P364L || P364L || P364L || Y486D || Y486D || Y486D | |
test: | |
pred: | |
test: Tyr246X | |
pred: Tyr246X || premature stop codon at the 246 residue || substitution of cytosine (C) for guanine (G) at codon 246 in exon 6 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: resulting from the loss of repeat units 7 | |
test: | |
pred: | |
test: 5504delA || 5504delA || 6573 + 1G > C || 6573 + 1G > C | |
pred: 5504delA || 5504delA || 6573 + 1G > C || 6573 + 1G > C || deletion mutation || intron 81 || single-nucleotide deletion within exon 64 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: C435G || del 329C | |
pred: C435G || del 329C || single-nucleotide deletion at position 329 | |
test: | |
pred: | |
test: 1242G>T || 1780C>A || 1780C>A || 2068G>C || 2068G>C || 2084G>A || 9 +1G>T | |
pred: 1242G>T || 1780C>A || 1780C>A || 2068G>C in exon 11 || 2084G>A || C insertion in exon 14 between positions 2505-2511 || GGCC insertion at exon 8 (1277) and a nucleotide substitution in exon 11 (2068G>C) || homozygous GGCC insertion at exon 8 || intron 9 +1G>T | |
overlapping subclasses do not match 0 1 | |
overlapping subclasses do not match 0 1 | |
overlapping subclasses do not match 0 2 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: D16S2622 || D16S475 || D16S523 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: C270T | |
pred: C270T | |
test: C270T | |
pred: C270T | |
test: | |
pred: | |
test: +142C/G || +142C/G || +355G/T || +355G/T || -1001C/T || -1001C/T || -1001C/T || -13C/T || -13C/T || -13C/T || -263G/A || -263G/A || -263G/A | |
pred: G-C-C-G of -1001C/T, -263G | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: A/C1166 || A/C1166 || A/C1166 || T/C-344 || T/C-344 || T/C-344 || T/C704 || T/C704 || T/C704 | |
pred: A/C1166 || A/C1166 || C allele of AGT T/C704, the A allele of AT1 A/C1166 || T/C-344 || T/C-344 || T/C-344 || T/C704 || T/C704 | |
overlapping subclasses do not match 0 1 | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: 620-621del in cDNA || C877T in cDNA | |
pred: C877T || deletion (620-621del | |
test: | |
pred: | |
test: | |
pred: | |
test: | |
pred: | |
test: -866 promoter (G/A) || A55V || Ala55Val | |
pred: nonsynonymous (Ala55Val or A55V) single-nucleotide polymorphism in exon 4 | |
overlapping subclasses do not match 0 1 | |
test: c.399_402del AGAG | |
pred: c.399_402del AGAG | |
test: c.399_402delAGAG || c.399_402delAGAG || c.399_402delAGAG || c.399_402delAGAG || c.399_402delAGAG | |
pred: 4-bp deletion in exon 3 || c.399_402delAGAG || c.399_402delAGAG || c.399_402delAGAG || c.399_402delAGAG || c.399_402delAGAG | |
test: C-174G || G-308A | |
pred: C-174G || G-308A | |
test: C-174G || G-308A || G-308A | |
pred: C-174C || C-174C || C-174G || G-308A || G-308A || G-308G | |
test: | |
pred: | |
test: | |
pred: G to C substitution at position -174 | |
test: | |
pred: | |
test: | |
pred: deletion of KLF5 | |
test: 3020insC | |
pred: 3020insC frameshift mutation | |
test: 3020insC || 3020insC || 3020insC || 3020insC | |
pred: 3020insC || 3020insC || 3020insC || 3020insC || cytosine insertion at position 3020 of exon 11 | |
test: | |
pred: | |
test: | |
pred: | |
crf_train_params = None | |
cv_fold = None | |
cv_n = None | |
delete_subclasses = [] | |
do_train = False | |
elastic_net = False | |
labeler = BIEO | |
model_name = None_BIEO_del_None | |
model_name_suffix = | |
model_path_1 = /home/abojchevski/Downloads/nala_BIEO_del_None_466744.bin | |
model_path_2 = None | |
nl = False | |
nl_features = None | |
nl_threshold = 0 | |
nl_window = False | |
output_folder = /tmp/tmpmke3wcpu | |
pruner = parts | |
ps_NL = False | |
ps_ST = False | |
ps_random = 0.0 | |
test_corpus = tmVar_test | |
training_corpus = None | |
use_feat_windows = True | |
validation = stratified | |
we_additive = 0 | |
we_model_location = None | |
we_multiplicative = 1 | |
we_params = {'multiplicative': 1, 'location': None, 'additive': 0} | |
word_embeddings = True | |
write_anndoc = False | |
# class tp fp fn fp_ov fn_ov match P P_SE R R_SE F F_SE match P P_SE R R_SE F F_SE | |
0 338 81 107 58 69 e 0.8067 0.0024 0.7596 0.0033 0.7824 0.0027 o 0.9529 0.0012 0.9245 0.0021 0.9384 0.0013 | |
1 7 93 10 8 10 e 0.0700 0.0025 0.4118 0.0111 0.1197 0.0048 o 0.2273 0.0044 1.0000 0.0000 0.3704 0.0051 | |
2 0 14 2 2 2 e 0.0000 0.0000 0.0000 0.0000 nan nan o 0.2500 0.0098 1.0000 0.0000 0.4000 0.0220 | |
TOTAL 345 188 119 68 81 e 0.6473 0.0026 0.7435 0.0029 0.6921 0.0025 o 0.8046 0.0021 0.9286 0.0020 0.8621 0.0016 | |
Process finished with exit code 0 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment