Checking if your kit is complete...
Looks good
Writing Makefile for Peptide::Pubmed
cp lib/Peptide/DictionaryScientific.pm blib/lib/Peptide/DictionaryScientific.pm
cp lib/Peptide/DictionaryFrequent.pm blib/lib/Peptide/DictionaryFrequent.pm
cp lib/Peptide/NonSequence.pm blib/lib/Peptide/NonSequence.pm
cp lib/Peptide/Gene.pm blib/lib/Peptide/Gene.pm
cp lib/Peptide/DictionaryEnglish.pm blib/lib/Peptide/DictionaryEnglish.pm
cp lib/Peptide/DictionaryAbbreviations.pm blib/lib/Peptide/DictionaryAbbreviations.pm
cp lib/Peptide/Kmers.pm blib/lib/Peptide/Kmers.pm
cp lib/Peptide/Pubmed.pm blib/lib/Peptide/Pubmed.pm
cp lib/Peptide/Sequence.pm blib/lib/Peptide/Sequence.pm
Manifying blib/man3/Peptide::Kmers.3
Manifying blib/man3/Peptide::Pubmed.3
PERL_DL_NONLAZY=1 /home/cpanrun/tmp/5.10.0/bin/perl "-MExtUtils::Command::MM" "-e" "test_harness(1, 'blib/lib', 'blib/arch')" t/*.t
t/01load..........1..2
ok 1 - use Peptide::Pubmed;
ok 2 - use Peptide::Kmers;
ok
t/02parse_seq.....1..69
ok 1 - Peptide::Pubmed->new
ok 2 - parse_file
ok 3 - AbstNumAb
ok 4 - AbstNumAllCap
ok 5 - AbstNumBind
ok 6 - AbstNumDigest for year=1972
ok 7 - AbstNumMHC
ok 8 - AbstNumPeptide
ok 9 - AbstNumPhage
ok 10 - AbstNumProtease
ok 11 - WordAaSymbols X-proline-X-X-proline
ok 12 - WordAaSymbols GETRAPL
ok 13 - WordAlpha EYHH/YNK
ok 14 - is(WordIsDNA{'ACCCGTNA'}
ok 15 - is(WordIsDNA{'ACGTNACGTNW'}
ok 16 - is(WordIsDNA{'(T/C)CAAGG(T/C)C(A/G)'}
ok 17 - isnt(WordIsDNA{'ACCCGTNS'}
ok 18 - WordIsDNALen ACCCGTNS
ok 19 - isnt(WordIsDict{'GETRAPL'}
ok 20 - is(WordIsDict{'SELEX'}
ok 21 - is(WordIsDict{'SDSPAGE'}
ok 22 - is(WordIsDict{'VEGFRII'}
ok 23 - is(WordIsDict{'PATIENT'},
ok 24 - is(WordIsDict{'PATIENTS'}
ok 25 - is(WordIsDict{'(A/M)ART'}
ok 26 - is(WordIsDict{'HAART'}
ok 27 - is(WordIsDict{'TMHMM'}
ok 28 - is(WordIsDict{'FPL(C/H)PLC'}
ok 29 - WordIsDict AWGC DictionaryAbbreviations
ok 30 - WordIsDict AAAASF DictionaryFrequent
ok 31 - WordIsDict (IVGTT) DictionaryFrequent
ok 32 - WordIsDictLen FPLC/HPLC
ok 33 - WordIsDictLen HPLC
ok 34 - WordIsDictLen SDS-PAGE
ok 35 - isnt(WordIsGene{'GETRAPL'}
ok 36 - is(WordIsGene{'FVIII'}
ok 37 - is(WordIsGene{'IGF-II'}
ok 38 - is(WordIsGene{'MARCKS'}
ok 39 - WordIsGeneLen (GKLF/KLF4)
ok 40 - WordIsGeneLen N-WASP,
ok 41 - WordIsRoman HYNKIIIA
ok 42 - WordIsRomanLen HYNKIII
ok 43 - WordIsRomanLen HYNKIIIA
ok 44 - WordIsRomanLen HYNKXXVII
ok 45 - WordNumNotDegen X-proline-X-X-proline
ok 46 - WordNumDegen X-proline-X-X-proline
ok 47 - WordPropDNA ACGTNACGTNW
ok 48 - WordPropDegen X-proline-X-X-proline
ok 49 - WordPropDegen GETRAPL
ok 50 - WordPropProtein
ok 51 - WordScore EYHHYNK
ok 52 - WordScore GETRAPL
ok 53 - WordScore (GET),
ok 54 - WordScore RGDFV
ok 55 - WordScore X-proline-X-X-proline, degen > 0.1
ok 56 - WordScore X-proline-X-X-proline, degen < 0.9
ok 57 - WordScore N-Formyl-Met-Leu-Phe;
ok 58 - WordScore EYHH/YNK split sequence, potentially similar to abbreviations, etc
ok 59 - WordScore GXXXXXXG degen
ok 60 - WordScore (-Cys59-x-x-x-x-Cys64-) degen
ok 61 - WordScore PATIENT dict english
ok 62 - WordScore SDSPAGE dict sci
ok 63 - WordScore HYNKIIIA roman
ok 64 - WordScore ACCCGTNA all dna
ok 65 - WordScore FVIII gene
ok 66 - WordScore MOS/MEK/MAPK/RSK multiple genes
ok 67 - WordSeqLen X-proline-X-X-proline,
ok 68 - WordSubLenMax EYHH/YNK
ok 69 - WordSubLenMax EYHHYNK
ok
t/04kmers.........1..5
ok 1 - Peptide::Kmers->new
ok 2 - kmers
ok 3 - log_prop_kmers without maxtotal: all k-mers of text are processed
ok 4 - log_prop_kmers with maxtotal <= min * number of k-mers: no k-mers of text are processed
ok 5 - log_prop_kmers with maxtotal = min * number of k-mers + 1: only first min + 1 = 2 k-mers of text are processed
ok
t/05to_aa.........1..63
ok 1 - isnt to_aa1('BLACK'), 'LACK';; B is not valid 1 letter symbol
ok 2 - isnt to_aa1('XLAC'), 'XLACZ';; Z is not valid 1 letter symbol
ok 3 - to_aa1('GETRAPL'), 'GETRAPL';; only 1 letter symbols
ok 4 - to_aa1('SELEX'), 'SELEX';; scientific term that looks like peptide sequence; known bug
ok 5 - to_aa1('ACCCGTNA'), 'ACCCGTNA';; DNA that looks like peptide sequence; known bug
ok 6 - to_aa1('FVIII'), 'FVIII';; gene symbol that looks like peptide sequence; known bug
ok 7 - to_aa1('14RRVPTETRSSF24'), 'RRVPTETRSSF';; sequence with aa positions
ok 8 - to_aa1('TRDI-pY-ETD-pY-pY-RK'), 'TRDIYETDYYRK';; phospho-aa
ok 9 - to_aa1('MDWxxxxx(L/I)Fxx(L/F)'), 'MDWXXXXX(L/I)FXX(L/F)';; change x to X; keep (A/B/etc)
ok 10 - to_aa1('H(2)N-KLLKLLLKLLLKLLK-CO-Ph'), 'KLLKLLLKLLLKLLK';; delete terminal marks
ok 11 - to_aa1('TGWMDF-NH2'), 'TGWMDF';; delete terminal marks
ok 12 - to_aa1('VPVIAEKL-NH(2)'), 'VPVIAEKL';; delete terminal marks
ok 13 - to_aa1('(200)HACQ(219)'), 'HACQ';; change Y(n) to Y
ok 14 - to_aa1('[KKEKKKS-KKDKKAK(X)(17)KKKKKKKKAKEVELVSE]'), 'KKEKKKSKKDKKAKX';; delete digits; known bug: expected: X repeated 17 times
ok 15 - to_aa1('(Z-DEVD-FMK).'), 'DEVD';; delete FMK
ok 16 - to_aa1('C-(ELDKWA-G)4'), 'CELDKWAG';; change (ABC...) to ABC...
ok 17 - to_aa1('GVFFEL(I)VG'), 'GVFFELIVG';; change (Y) to Y; known bug. correct: GVFFE(L/I)VG
ok 18 - to_aa1('(PXXP/GXPXP)'), 'PXX(P/G)XPXP';; replace Y/Z with (Y/Z)
ok 19 - to_aa1('(PXXP/PXPXP)'), 'PXPXP';; do not allow repeats, eg Y/.../Y inside (); split on '/' instead
ok 20 - to_aa1('(PXXP/XXPXP)'), 'XXPXP';; do not allow X inside (); split on '/' instead
ok 21 - aa3_to_aa1('N\'-Ser-Ile-Leu-Pro-Tyr-ProTyr-C\''), 'SILPYPY';; remove terminal marks; handle separators: -, none
ok 22 - aa3_to_aa1('(acetyl-AspTrpLeu-amide)'), 'DWL';; remove terminal marks; handle separators: -, none
ok 23 - aa3_to_aa1('Gly>His>Asn>Arg'), 'GHNR';; handle separator: >
ok 24 - aa3_to_aa1('Glu,Pro,Dpr,Tyr-NH(2))(2)human'), 'EPXY';; handle separator: ,
ok 25 - aa3_to_aa1('cyclo(-Arg-Gly-Asp-dPhe-Val)'), 'RGDFV';; handle cyclic sequences and d-amino acids
ok 26 - aa3_to_aa1('Ac-cyclo(D-Lys-D-Ile-Leu-Asp-Val)'), 'KILDV';; handle d-amino acids
ok 27 - aa3_to_aa1('Asn-x-Glu-x-x-(aromatic)-x-x-Gly'), 'NXEXXXXG';; handle x; known bug: aromatic is deleted; expected: changed to X
ok 28 - aa3_to_aa1('Lys(epsilon-palmitoyl)-Phe-Phe'), 'KFF';; handle modified aa: delete modifications
ok 29 - aa3_to_aa1('(pGlu5-Arg-Pro)'), 'ERP';; handle phospho-aa
ok 30 - aa3_to_aa1('Phe-Ser*-Gly-Glu'), 'FSGE';; handle marked aa
ok 31 - aa3_to_aa1('benzyloxycarbonyl-Val-Ala-Asp-fluoromethylketone'), 'VAD';; handle modifications of aa which match 'x': delete them, delete x
ok 32 - a3_to_aa1('AspTrePheXxxAsxXxxXxxTrpAsp'), 'DFXXXXWD';; handle XxxXxx and typo:Tre
ok 33 - to_aa1('Pro-Pro-Xxx-Xxx-Tyr'), 'PPXXY';; handle Xxx-Xxx
ok 34 - to_aa1('Xaa-Pro-Yaa-Gln'), 'XPXQ';; handle Yaa
ok 35 - aa3_to_aa1('NAc-lys-gly-gln-OH'), 'KGQ';; handle lowercase 3 letter symbols
ok 36 - aa3_to_aa1('pglu-ile-gly-ala'), 'IGA';; handle phospho-lowercase 3 letter symbols: known bug: deleted pglu; expected: glu
ok 37 - aa3_to_aa1('(Arg-Glu(EDANS)-Ser-Gln)'), 'RESQ';; for 3 letter symbols, delete all non-3 letter symbols
ok 38 - aa3_to_aa1('beta-Mpa(beta-(CH2)5)(Bzl)-Tyr(Bzl)-Ile-Gln-Asn-Cys(Bzl)-Pro-Leu-Gly-NH2'), 'YIQNCPLG';; handle many modifications inside sequence with 3 letter symbols
ok 39 - aa3_to_aa1('Gly-Met(OX)-Ala'), 'GMA';; delete X if X = modification, not X= amino acid
ok 40 - aa3_to_aa1('Phe-Arg-(/)-Pro-Pro-(/)-Thr'), 'FRPPT';; delete (/)
ok 41 - aa3_to_aa1('Cys-X-Cys-X(3)-Cys'), 'CXCXXXC';; change X(n) to X repeated n times
ok 42 - aa3_to_aa1('Lys-Xaa(4)-Asn-Xaa(2)-His'), 'KXXXXNXXH';; change Xaa(n) to X repeated n times
ok 43 - aa3_to_aa1('[Phe-(Xaa)4-Ile-(Xaa)2-Leu]'), 'FXXXXIXXL';; change (Xaa)n to X repeated n times
ok 44 - aa3_to_aa1('Hyp)(4)-Ser-Hyp-Ser-(Hyp)(4)-Tyr'), 'XXXXSXSXXXXY';; change (Hyp)(n) to Xn to X repeated n times; disregard the nonmatching parens typo
ok 45 - aa3_to_aa1('(Pro-Pro-Gly)(n)'), 'PPG';; handle simple parens
ok 46 - aa3_to_aa1('cyclo-(Ala(1)-Pro(2)-Asp(3)-Glu(4))'), 'APDE';; change Y(n) to Y
ok 47 - aa3_to_aa1('Gly1-Val2-Thr3-Ser4'), 'GVTS';; handle Yn: change Yn to Y
ok 48 - aa3_to_aa1('(Pro-Hyp-Gly)(3)-Ile-Thr'), 'PXGIT';; change (ABC...)(n) to ABC...; known bug: expected: ABC... repeated n times
ok 49 - aa3_to_aa1('Thr-(125I-Tyr)-Thr'), 'TYT';; change (Y) to Y
ok 50 - aa3_to_aa1('Phe-(D-Trp)-Lys'), 'FWK';; change (Y) to Y
ok 51 - aa3_to_aa1('(Gly-Thr-Pro-(Ser?)-Lys),'), 'GTPSK';; change (Y) to Y
ok 52 - aa3_to_aa1('(Lys)-Lys-Gln'), 'KKQ';; change (Y) to Y at the beginning of the string
ok 53 - aa3_to_aa1('(Glu)(5)(Gly-Ala-Pro-Gly-Pro-Pro)(6)(Glu)(5)'), 'EGAPGPPE';; change (Y)(n) or (ABC...) to Y and ABC...; known bug: expected Y or ABC... repeated n times
ok 54 - aa3_to_aa1('Ac-(Pro)2-His-(Ala)2-His'), 'PHAH';; change (Y)n to Y; known bug: expected Y repeated n times
ok 55 - aa3_to_aa1('Cys-(Xaa)(3)-Lys/Arg-Arg-'), 'CXXX(K/R)R;; change A/B to (A/B)
ok 56 - aa3_to_aa1('(287SerLeuThrSerSer291/287AlaLeuAlaAlaAla291)'), 'SLTS(S/A)LAAA';; change A/B to (A/B): known bug: expected to split on '/' into 2 sequences
ok 57 - aa3_to_aa1('Gly-(Leu/Pro/Gln)-(Pro/Leu)-Leu'), 'G(L/P/Q)(P/L)L';; keep (A/B/...)
ok 58 - aa3_to_aa1('Val-Val-Asp/isoAsp-Ser-Ala-Tyr-Glu'), 'DSAYE';; do not allow repeats inside (), split on '/' instead
ok 59 - aa3_to_aa1('histidine-tryptophane-glycine-phenylalanine'), 'HWGF';; all full names
ok 60 - aa3_to_aa1('X-proline-X-X-proline'), 'XPXXP';; full names and Xs
ok 61 - aa3_to_aa1('methylcysteinylthreonylseryl-gamma-tert-butylglutamylvalylserine'), 'CTSEVS';; full names and full names with 'yl'
ok 62 - aa3_to_aa1('Asp-Glu-Val-L-aspartic acid'), 'DEVD';; full names and 3 letter symbols
ok 63 - aa3_to_aa1('N-acetyl-l-aspartyl-l-glutamyl-l-valyl-l-aspartyl-7-amino-4-methylcoumarin'), 'DEVD';; full names with 'yl' and numbers
ok
t/06abst_score....1..33
EYHHYNK RGD
ok 1 - get_seqs: default WordAbstScoreMin: EYHHYNK RGD
EYHHYNK RGD
EYHHYNK RGD ACCCGTNA VEGFRI
ok 2 - get_seqs: WordAbstScoreMin = -1: all
0.9301
Peptide sequences <mark>EYHHYNK</mark> and <mark>Arg-Gly-Asp,</mark> but not ACCCGTNA or VEGFRI.
ok 3 - get_abst AbstMtext
0.8443
EYHHYNK
EYHHYNK
0.8774
Arg-Gly-Asp,
RGD
ok 4 - get_words: WordSequence
ok 5 - empty input - no sequences
ok 6 - Peptide::Pubmed->new
ok 7 - parse_abstract empty Abstract
ok 8 - number of elements in words; unlimited number of words per abstract, empty Abstract
ok 9 - AbstScore empty Abstract
ok 10 - number of elements in words; exactly 1 word per abstract, empty Abstract
ok 11 - Word* vars = 0 or empty, empty Abstract
ok 12 - AbstScore undef input
ok 13 - Word* vars = 0 or empty, undef input
ok 14 - AbstLcAllText EYHHYNK
ok 15 - AbstMaxWordScore EYHHYNK
ok 16 - AbstMtext EYHHYNK
ok 17 - AbstNumAb EYHHYNK
ok 18 - AbstNumAllCap EYHHYNK
ok 19 - AbstNumBind EYHHYNK
ok 20 - AbstNumDigest EYHHYNK
ok 21 - AbstNumWords EYHHYNK
ok 22 - AbstNumMHC EYHHYNK
ok 23 - AbstNumPeptide EYHHYNK
ok 24 - AbstNumPhage EYHHYNK
ok 25 - AbstNumProtease EYHHYNK
ok 26 - AbstPropAllCap EYHHYNK
ok 27 - AbstScore EYHHYNK
ok 28 - number of elements in words; WordScoreMin => 1e-6 EYHHYNK
ok 29 - number of elements in words; exactly 1 word per abstract EYHHYNK
ok 30 - parse_file
ok 31 - print exactly 1 line per abstract: input = EYHHYNK, DNA (2 abstracts)
ok 32 - parse_abstract DNA
ok 33 - AbstScore DNA
ok
All tests successful.
Files=5, Tests=172,  8 wallclock secs ( 6.62 cusr +  0.83 csys =  7.45 CPU)
Installing /home/cpanrun/build/5.10.0/html/site/lib/Peptide/Pubmed.html
Installing /home/cpanrun/build/5.10.0/html/site/lib/Peptide/Kmers.html
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/DictionaryScientific.pm
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/Pubmed.pm
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/DictionaryEnglish.pm
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/Kmers.pm
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/DictionaryFrequent.pm
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/Gene.pm
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/NonSequence.pm
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/DictionaryAbbreviations.pm
Installing /home/cpanrun/build/5.10.0/site/lib/Peptide/Sequence.pm
Installing /home/cpanrun/build/5.10.0/site/man/man3/Peptide::Kmers.3
Installing /home/cpanrun/build/5.10.0/site/man/man3/Peptide::Pubmed.3
Appending installation info to /home/cpanrun/build/5.10.0/lib/perllocal.pod