Improve NL Definer
juanmirocks opened this issue · comments
Stats of changes:
- nala_training: 144 total changes, 69 from ST to sth else, 75 SS to NL
- IDP4: 52 total changes, 23 from ST to sth else, 29 SS to NL
Stats before:
nala_tr 501 1769 1010 0.571 595 0.336 164 0.093 759 0.429 147975
IDP4 159 3337 3137 0.940 147 0.044 53 0.016 200 0.060 442515
Final stats after:
nala_tr 501 1769 941 0.532 691 0.391 137 0.077 828 0.468 -1
IDP4 159 3337 3114 0.933 192 0.058 31 0.009 223 0.067 -1
Modified algorithm will produce the following changes:
Corpus #docs #ann #ST %ST #NL %NL #SS %SS #NL+SS %NL+SS #tokens
4 2 codon 392 (Gly----Asp) mutation +++++++++++++++++++++++++++ SS -> NL
4 2 Lys substitution for Glu102 +++++++++++++++++++++++++++ SS -> NL
5 4 Deletion of the C-terminal +++++++++++++++++++++++++++ SS -> NL
5 3 (p.G2D) at the N-terminus +++++++++++++++++++++++++++ SS -> NL
3 2 deletion of p75(NTR) +++++++++++++++++++++++++++ SS -> NL
6 2 eliminating codons 487-489 (Asp-Ser-Phe) @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 2 mutation of Tyr-838 +++++++++++++++++++++++++++ SS -> NL
3 2 mutation at Tyr-615 +++++++++++++++++++++++++++ SS -> NL
3 2 total gene deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 2 arginine-141 to serine substitution +++++++++++++++++++++++++++ SS -> NL
4 2 arginine-141 to serine substitution +++++++++++++++++++++++++++ SS -> NL
3 2 mutations at Arg885 +++++++++++++++++++++++++++ SS -> NL
4 3 point mutation at Cys93 +++++++++++++++++++++++++++ SS -> NL
3 2 heterozygous missense 3035G>T @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 1 synonymous 696T>C *************************** ST -> SS
2 1 missense Glu285Ala *************************** ST -> SS
3 1 somatic 16-bp deletion *************************** ST -> SS
4 2 serine 749 is phosphorylated @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 2 Ser58 to Glu substitution +++++++++++++++++++++++++++ SS -> NL
2 2 deletion of +++++++++++++++++++++++++++ SS -> NL
2 2 deletion of +++++++++++++++++++++++++++ SS -> NL
2 2 deletion of +++++++++++++++++++++++++++ SS -> NL
2 2 deletion of +++++++++++++++++++++++++++ SS -> NL
2 2 deletion of +++++++++++++++++++++++++++ SS -> NL
4 3 Deletion of chromosome 11q23 +++++++++++++++++++++++++++ SS -> NL
4 1 codon 98 GAT-->GTT, Asp-->Val *************************** ST -> SS
3 1 codon 92, TAC-->TAT *************************** ST -> SS
4 2 codon 177, CAA-->TAA, Gln-->termination @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 1 codon 173 (CTA-->CGA) *************************** ST -> SS
3 1 Val/Met genotype *************************** ST -> SS
3 1 Val/Met genotype *************************** ST -> SS
4 2 156 in exon 5 +++++++++++++++++++++++++++ SS -> NL
4 1 one 1-bp insertion (251-insA-252) *************************** ST -> SS
4 1 9-bp deletion (del 192-200) *************************** ST -> SS
3 2 deletion of Phe52 +++++++++++++++++++++++++++ SS -> NL
4 2 deletion of aa 51/52 +++++++++++++++++++++++++++ SS -> NL
4 3 mutation at codon 692 +++++++++++++++++++++++++++ SS -> NL
4 3 Mutation in codon 713 +++++++++++++++++++++++++++ SS -> NL
3 2 mutation (codon 665Asp) +++++++++++++++++++++++++++ SS -> NL
4 2 deletes a BglII site @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 1 intron 21, G(+1)A *************************** ST -> SS
3 1 intron 25, G(+5)C *************************** ST -> SS
3 1 intron 26, T(+2)A *************************** ST -> SS
4 3 Mutations at codons 717 +++++++++++++++++++++++++++ SS -> NL
4 3 mutation at codon 693 +++++++++++++++++++++++++++ SS -> NL
4 2 C to T substitution +++++++++++++++++++++++++++ SS -> NL
4 3 mutations at codon 717 +++++++++++++++++++++++++++ SS -> NL
4 3 mutation at codon 717 +++++++++++++++++++++++++++ SS -> NL
4 3 variant at codon 717 +++++++++++++++++++++++++++ SS -> NL
4 3 mutation in codon 717 +++++++++++++++++++++++++++ SS -> NL
2 2 deletion of +++++++++++++++++++++++++++ SS -> NL
2 1 knock-out *************************** ST -> SS
3 2 Uba domain-deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 1 HP1 box deletion *************************** ST -> SS
3 1 Asp 296 mutants *************************** ST -> SS
4 2 substitution of histidine 238 +++++++++++++++++++++++++++ SS -> NL
3 1 Ala 238 mutant *************************** ST -> SS
4 4 Truncating the intracellular tail @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 3 Deleting the carboxy terminus @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
5 0 polyglutamine (poly-Q) repeat expansion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 1 486-bp deletion *************************** ST -> SS
4 3 altering the COOH terminus @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
5 4 removal of the pro-domain +++++++++++++++++++++++++++ SS -> NL
2 2 deletion of +++++++++++++++++++++++++++ SS -> NL
3 1 introduced Cys 131 *************************** ST -> SS
3 2 Mutation of Lys-269 +++++++++++++++++++++++++++ SS -> NL
3 2 N-terminal deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 2 Mutation of arginine 78 +++++++++++++++++++++++++++ SS -> NL
4 3 removal of the methionine +++++++++++++++++++++++++++ SS -> NL
3 2 lacking exon 15 @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 2 without exon 15 @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 1 marker D7S636 *************************** ST -> SS
3 2 Substitution to Lys +++++++++++++++++++++++++++ SS -> NL
3 2 substitution to Glu +++++++++++++++++++++++++++ SS -> NL
3 2 Mutation at Thr-668 +++++++++++++++++++++++++++ SS -> NL
2 1 ACO1 deletion *************************** ST -> SS
4 3 mutation at codon 178 +++++++++++++++++++++++++++ SS -> NL
4 2 deletion of 1.6 kb +++++++++++++++++++++++++++ SS -> NL
4 2 mutation at base 1258 +++++++++++++++++++++++++++ SS -> NL
3 1 985A-to-G *************************** ST -> SS
3 1 985A-to-G *************************** ST -> SS
3 1 DG91/C92, 6-bp deletion *************************** ST -> SS
2 1 Glu137 deletion *************************** ST -> SS
5 2 G/A in codon 407 +++++++++++++++++++++++++++ SS -> NL
3 2 mutation at Ser557 +++++++++++++++++++++++++++ SS -> NL
5 4 Deletion of the N-terminal +++++++++++++++++++++++++++ SS -> NL
4 3 Single mutation of Ser-28 +++++++++++++++++++++++++++ SS -> NL
4 1 Phe- or Gly-706 mutant *************************** ST -> SS
4 1 Phe- and Gly-706 mutant *************************** ST -> SS
2 1 Phe-706 mutant *************************** ST -> SS
2 1 Gly-706 mutant *************************** ST -> SS
2 1 Gly-807 mutant *************************** ST -> SS
2 1 Phe-807 mutant *************************** ST -> SS
2 1 Knock-down *************************** ST -> SS
2 1 knock-down *************************** ST -> SS
5 5 deletion of amino-terminal sequences +++++++++++++++++++++++++++ SS -> NL
4 2 substitution at position 387 +++++++++++++++++++++++++++ SS -> NL
3 2 substitution of W-282 +++++++++++++++++++++++++++ SS -> NL
2 2 removal of +++++++++++++++++++++++++++ SS -> NL
4 2 Mutation of FAK Tyr-925 +++++++++++++++++++++++++++ SS -> NL
4 2 lysine-304 to glutamate substitution +++++++++++++++++++++++++++ SS -> NL
4 2 lys329 to glu mutation +++++++++++++++++++++++++++ SS -> NL
2 1 missense ala305-->glu *************************** ST -> SS
4 1 4-bp deletions (32 deltaT *************************** ST -> SS
2 1 deltaT deletion *************************** ST -> SS
2 1 the 625G-->A *************************** ST -> SS
2 1 625A-1147T allele *************************** ST -> SS
2 1 511C-625A allele *************************** ST -> SS
3 2 511C-625A variant allele @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 2 single 778 C>T substitution +++++++++++++++++++++++++++ SS -> NL
3 2 deletion of S232 +++++++++++++++++++++++++++ SS -> NL
4 2 Mutation of serine 253 +++++++++++++++++++++++++++ SS -> NL
4 2 substitution of cysteine 245 +++++++++++++++++++++++++++ SS -> NL
2 1 Glis2 deletion *************************** ST -> SS
3 2 Mutation of Lys-426 +++++++++++++++++++++++++++ SS -> NL
4 2 mutation of tyrosine 876 +++++++++++++++++++++++++++ SS -> NL
3 2 deleted C1 domain +++++++++++++++++++++++++++ SS -> NL
2 1 UIM-deletion *************************** ST -> SS
4 2 deletion of this motif +++++++++++++++++++++++++++ SS -> NL
4 2 deletion of aa 527-534 +++++++++++++++++++++++++++ SS -> NL
4 2 deletion and loss of +++++++++++++++++++++++++++ SS -> NL
3 3 deletion of the +++++++++++++++++++++++++++ SS -> NL
4 2 mutations at arginine 303 +++++++++++++++++++++++++++ SS -> NL
3 2 Deletion of Ile663 +++++++++++++++++++++++++++ SS -> NL
3 2 Deletion of MK5 +++++++++++++++++++++++++++ SS -> NL
3 2 Substitution of 3K +++++++++++++++++++++++++++ SS -> NL
3 2 deletion of exon4 +++++++++++++++++++++++++++ SS -> NL
4 2 one insertion mutation (698insC) +++++++++++++++++++++++++++ SS -> NL
5 4 lacking the C-terminal extension @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 1 Asn113 mutant *************************** ST -> SS
2 1 Asn113 mutant *************************** ST -> SS
2 1 Asn79 mutant *************************** ST -> SS
2 1 Asn79 mutant *************************** ST -> SS
2 1 Ala204 mutant *************************** ST -> SS
3 2 single phenylalanine deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
5 1 one-base deletion (C344fs/ter) @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 3 chromosome 2q37.3 terminal deletions @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 3 Absence of exon 5 +++++++++++++++++++++++++++ SS -> NL
4 2 skipping of exon 5 +++++++++++++++++++++++++++ SS -> NL
4 2 scrambled sequence [A beta(25-35)scram] @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 2 Mutation of Arg-115 +++++++++++++++++++++++++++ SS -> NL
4 1 Ala- and Asp-115 mutant *************************** ST -> SS
2 2 trinucleotide deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 1 3-bp deletion *************************** ST -> SS
*** 144 69
nala_tr 501 1769 941 0.532 691 0.391 137 0.077 828 0.468 -1
21:56:02|jmcejuela|nala$ python scripts/get_corpus_stats.py IDP4
Corpus #docs #ann #ST %ST #NL %NL #SS %SS #NL+SS %NL+SS #tokens
3 1 15.32 Mb deletion *************************** ST -> SS
4 3 deletion of the entire +++++++++++++++++++++++++++ SS -> NL
4 2 deletion of exons 10-16 +++++++++++++++++++++++++++ SS -> NL
5 2 heterozygous C-to-G transversion +++++++++++++++++++++++++++ SS -> NL
5 2 heterozygous C-to-G change +++++++++++++++++++++++++++ SS -> NL
4 2 alanine substitution of Asp-233 +++++++++++++++++++++++++++ SS -> NL
2 1 truncation 229-233Delta *************************** ST -> SS
4 2 mutation within codon 355 +++++++++++++++++++++++++++ SS -> NL
3 2 deletion of ARS607 +++++++++++++++++++++++++++ SS -> NL
3 2 Deletion of ARS607 +++++++++++++++++++++++++++ SS -> NL
3 2 Deletion of REV1 +++++++++++++++++++++++++++ SS -> NL
3 2 deletion of rev1 +++++++++++++++++++++++++++ SS -> NL
3 2 ARS607, was deleted +++++++++++++++++++++++++++ SS -> NL
3 2 Deletion of ARS607 +++++++++++++++++++++++++++ SS -> NL
3 2 deletion of ARS607 +++++++++++++++++++++++++++ SS -> NL
3 2 deleted the REV1 +++++++++++++++++++++++++++ SS -> NL
6 2 C-terminal SeCys-Gly dipeptide deleted +++++++++++++++++++++++++++ SS -> NL
4 2 loss of exon 13 +++++++++++++++++++++++++++ SS -> NL
4 2 loss of exon 12 +++++++++++++++++++++++++++ SS -> NL
4 2 Deletion of PxVxL motif +++++++++++++++++++++++++++ SS -> NL
4 2 Lys9 to alanine substitution +++++++++++++++++++++++++++ SS -> NL
4 2 Asp277 residue to Ala +++++++++++++++++++++++++++ SS -> NL
3 2 Substitution of Arg29 +++++++++++++++++++++++++++ SS -> NL
3 2 Deletion of ZF1-2 +++++++++++++++++++++++++++ SS -> NL
4 3 deletion of the ZF2-4 +++++++++++++++++++++++++++ SS -> NL
3 2 deletion of ZF1-2 +++++++++++++++++++++++++++ SS -> NL
2 2 complete deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 2 complete deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 3 single large deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 3 deletions at chromosome 3p14.1 +++++++++++++++++++++++++++ SS -> NL
4 3 single large 3p14.1p13 deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 1 3p14.1 deletions *************************** ST -> SS
2 1 3p14.1p13 deletion *************************** ST -> SS
2 1 3p14.1p13 deletion *************************** ST -> SS
5 2 C-terminal 20 a.a. deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 2 C-terminal deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
5 2 20 a.a. N-terminal deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
5 2 42 a.a. N-terminal deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 3 4 amino acid deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 2 17p11.2 duplication or deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 3 amino acid substitution N71Y +++++++++++++++++++++++++++ SS -> NL
4 3 amino acid substitution T164A +++++++++++++++++++++++++++ SS -> NL
3 3 4-amino acid deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
4 2 12-bp cDNA fragment deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 3 4-amino acid deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 3 15-amino acid insertion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
3 3 4-amino acid deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 1 deletion p.G3891_Q4020 *************************** ST -> SS
3 2 Trp153 to termination +++++++++++++++++++++++++++ SS -> NL
3 3 54-amino acid deletion @@@@@@@@@@@@@@@@@@@@@@@@@@@ ST -> NL
2 1 S323-to-I *************************** ST -> SS
4 2 SNP in codon 24 +++++++++++++++++++++++++++ SS -> NL
*** 52 23
IDP4 159 3337 3114 0.933 192 0.058 31 0.009 223 0.067 -1