[med-svn] [Git][med-team/biojava-live][master] 6 commits: Excluding files under non-free SWISS-PROT license
Pierre Gruet (@pgt)
gitlab at salsa.debian.org
Fri Apr 8 21:26:46 BST 2022
Pierre Gruet pushed to branch master at Debian Med / biojava-live
Commits:
c7cbcc87 by Pierre Gruet at 2022-04-08T20:42:05+02:00
Excluding files under non-free SWISS-PROT license
- - - - -
9d168d9b by Pierre Gruet at 2022-04-08T20:42:28+02:00
New upstream version 1.9.5+dfsg
- - - - -
30c4d8d5 by Pierre Gruet at 2022-04-08T20:42:40+02:00
Update upstream source from tag 'upstream/1.9.5+dfsg'
Update to upstream version '1.9.5+dfsg'
with Debian dir b4c352b06936a4a9a6eb7c7efdf757014da3a7b7
- - - - -
9cb8732a by Pierre Gruet at 2022-04-08T20:44:21+02:00
Updating changelog
- - - - -
06d3236e by Pierre Gruet at 2022-04-08T21:21:04+02:00
Removing two tests relying on data with non-free SWISS-PROT license
- - - - -
257884d2 by Pierre Gruet at 2022-04-08T22:26:23+02:00
Upload to NEW, targetting experimental
- - - - -
7 changed files:
- − core/src/test/resources/AAC4_HUMAN.sp
- − core/src/test/resources/org/biojava/bio/program/indexdb/part1.swiss
- − core/src/test/resources/org/biojava/bio/program/indexdb/part2.swiss
- debian/changelog
- debian/copyright
- debian/patches/omit_tests_with_problematic_data.patch
- debian/watch
Changes:
=====================================
core/src/test/resources/AAC4_HUMAN.sp deleted
=====================================
@@ -1,201 +0,0 @@
-ID AAC4_HUMAN STANDARD; PRT; 911 AA.
-AC O43707; O76048;
-DT 16-OCT-2001 (Rel. 40, Created)
-DT 16-OCT-2001 (Rel. 40, Last sequence update)
-DT 10-OCT-2003 (Rel. 42, Last annotation update)
-DE Alpha-actinin 4 (Non-muscle alpha-actinin 4) (F-actin cross linking
-DE protein).
-GN ACTN4.
-OS Homo sapiens (Human).
-OC Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi;
-OC Mammalia; Eutheria; Primates; Catarrhini; Hominidae; Homo.
-OX NCBI_TaxID=9606;
-RN [1]
-RP SEQUENCE OF 4-911 FROM N.A.
-RX MEDLINE=98177166; PubMed=9508771;
-RA Honda K., Yamada T., Endo R., Ino Y., Gotoh M., Tsuda H., Yamada Y.,
-RA Chiba H., Hirohashi S.;
-RT "Actinin-4, a novel actin-bundling protein associated with cell
-RT motility and cancer invasion.";
-RL J. Cell Biol. 140:1383-1393(1998).
-RN [2]
-RP ERRATUM.
-RA Honda K., Yamada T., Endo R., Ino Y., Gotoh M., Tsuda H., Yamada Y.,
-RA Chiba H., Hirohashi S.;
-RL J. Cell Biol. 143:276-276(1998).
-RN [3]
-RP SEQUENCE FROM N.A.
-RC TISSUE=Neuroblastoma;
-RX MEDLINE=20120478; PubMed=10656685;
-RA Nikolopoulos S.N., Spengler B.A., Kisselbach K., Evans A.E.,
-RA Biedler J.L., Ross R.A.;
-RT "The human non-muscle alpha-actinin protein encoded by the ACTN4 gene
-RT suppresses tumorigenicity of human neuroblastoma cells.";
-RL Oncogene 19:380-386(2000).
-RN [4]
-RP SEQUENCE FROM N.A.
-RC TISSUE=Placenta;
-RX MEDLINE=22388257; PubMed=12477932;
-RA Strausberg R.L., Feingold E.A., Grouse L.H., Derge J.G.,
-RA Klausner R.D., Collins F.S., Wagner L., Shenmen C.M., Schuler G.D.,
-RA Altschul S.F., Zeeberg B., Buetow K.H., Schaefer C.F., Bhat N.K.,
-RA Hopkins R.F., Jordan H., Moore T., Max S.I., Wang J., Hsieh F.,
-RA Diatchenko L., Marusina K., Farmer A.A., Rubin G.M., Hong L.,
-RA Stapleton M., Soares M.B., Bonaldo M.F., Casavant T.L., Scheetz T.E.,
-RA Brownstein M.J., Usdin T.B., Toshiyuki S., Carninci P., Prange C.,
-RA Raha S.S., Loquellano N.A., Peters G.J., Abramson R.D., Mullahy S.J.,
-RA Bosak S.A., McEwan P.J., McKernan K.J., Malek J.A., Gunaratne P.H.,
-RA Richards S., Worley K.C., Hale S., Garcia A.M., Gay L.J., Hulyk S.W.,
-RA Villalon D.K., Muzny D.M., Sodergren E.J., Lu X., Gibbs R.A.,
-RA Fahey J., Helton E., Ketteman M., Madan A., Rodrigues S., Sanchez A.,
-RA Whiting M., Madan A., Young A.C., Shevchenko Y., Bouffard G.G.,
-RA Blakesley R.W., Touchman J.W., Green E.D., Dickson M.C.,
-RA Rodriguez A.C., Grimwood J., Schmutz J., Myers R.M.,
-RA Butterfield Y.S.N., Krzywinski M.I., Skalska U., Smailus D.E.,
-RA Schnerch A., Schein J.E., Jones S.J.M., Marra M.A.;
-RT "Generation and initial analysis of more than 15,000 full-length
-RT human and mouse cDNA sequences.";
-RL Proc. Natl. Acad. Sci. U.S.A. 99:16899-16903(2002).
-RN [5]
-RP SEQUENCE OF 1-170 FROM N.A.
-RA Ottenwaelder B., Obermaier B., Mewes H.-W., Gassenhuber J.,
-RA Wiemann S.;
-RL Submitted (FEB-2000) to the EMBL/GenBank/DDBJ databases.
-RN [6]
-RP SEQUENCE OF 1-218 FROM N.A.
-RA Isogai T., Otsuki T., Sugiyama T.;
-RL Submitted (OCT-2000) to the EMBL/GenBank/DDBJ databases.
-RN [7]
-RP VARIANTS FSGS1 GLU-255; ILE-259 AND PRO-262.
-RC TISSUE=Lymphocytes;
-RX MEDLINE=20164321; PubMed=10700177;
-RA Kaplan J.M., Kim S.H., North K.N., Rennke H., Correia L.A.,
-RA Tong H.-Q., Mathis B.J., Rodriguez-Perez J.-C., Allen P.G.,
-RA Beggs A.H., Pollak M.R.;
-RT "Mutations in ACTN4, encoding alpha-actinin-4, cause familial focal
-RT segmental glomerulosclerosis.";
-RL Nat. Genet. 24:251-256(2000).
-CC -!- FUNCTION: F-ACTIN CROSS-LINKING PROTEIN WHICH IS THOUGHT TO ANCHOR
-CC ACTIN TO A VARIETY OF INTRACELLULAR STRUCTURES. THIS IS A BUNDLING
-CC PROTEIN.
-CC -!- SUBUNIT: HOMODIMER, ANTIPARALLEL (BY SIMILARITY).
-CC -!- SUBCELLULAR LOCATION: NUCLEAR AND CYTOPLASMIC. COLOCALIZES WITH
-CC ACTIN STRESS FIBERS. NUCLEAR TRANSLOCATION CAN BE INDUCED BY THE
-CC PI3 KINASE INHIBITOR WORTMANNIN OR BY CYTOCHALASIN D. EXCLUSIVELY
-CC LOCALIZED IN THE NUCLEUS IN A LIMITED NUMBER OF CELL LINES (BREAST
-CC CANCER CELL LINE MCF7, ORAL FLOOR CANCER IMC2, AND BLADDER CANCER
-CC KU7).
-CC -!- TISSUE SPECIFICITY: WIDELY EXPRESSED.
-CC -!- DISEASE: CYTOPLASMIC LOCALIZATION OF ACTN4 MAY BE ASSOCIATED WITH
-CC CANCER METASTASES DUE TO ENHANCED CELL MOTILITY.
-CC -!- DISEASE: DEFECTS IN ACTN4 ARE THE CAUSE OF FOCAL SEGMENTAL
-CC GLOMERULOSCLEROSIS 1 (FSGS1) [MIM:603278], A COMMON RENAL LESION
-CC CHARACTERIZED BY INCREASED URINARY PROTEIN EXCRETION AND
-CC DECREASING KIDNEY FUNCTION. RENAL INSUFFICIENCY OFTEN PROGRESSES
-CC TO END-STAGE RENAL FAILURE, A HIGHLY MORBID STATE REQUIRING EITHER
-CC DIALYSIS THERAPY OR KIDNEY TRANSPLANTATION. FSGS IS DEFINED BY THE
-CC PRESENCE OF SEGMENTAL SCLEROSIS IN GLOMERULI, AND IS SEEN IN ALL
-CC ETHNIC GROUPS, ALTHOUGH IT IS PARTICULARLY COMMON IN INDIVIDUALS
-CC OF AFRICAN DESCENT. FSGS OCCURS AS AN ISOLATED PRIMARY CONDITION
-CC OR SECONDARY TO DISORDERS AS HIV INFECTION, OBESITY, HYPERTENSION
-CC AND DIABETES. FSGS MAY ALSO BE INHERITED AS A MENDELIAN TRAIT.
-CC -!- SIMILARITY: CONTAINS 1 ACTIN-BINDING DOMAIN.
-CC -!- SIMILARITY: CONTAINS 2 CALPONIN-HOMOLOGY (CH) DOMAINS.
-CC -!- SIMILARITY: CONTAINS 2 EF-HAND CALCIUM-BINDING DOMAINS.
-CC -!- SIMILARITY: CONTAINS 4 SPECTRIN REPEATS.
-CC -!- CAUTION: REF.3 SEQUENCE DIFFERS FROM THAT SHOWN BY A HIGH NUMBER
-CC OF FRAMESHIFTS, SOME OF WHICH WE HAVE CORRECTED. THE REMAINING
-CC SEQUENCE CONFLICTS INCLUDE BOTH SMALL FRAMESHIFTS AS WELL AS POINT
-CC CHANGES. THEY ARE PROBABLY SEQUENCING ERRORS WHEN COMPARED WITH
-CC THE OTHER MAMMALIAN SEQUENCES.
-CC --------------------------------------------------------------------------
-CC This SWISS-PROT entry is copyright. It is produced through a collaboration
-CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
-CC the European Bioinformatics Institute. There are no restrictions on its
-CC use by non-profit institutions as long as its content is in no way
-CC modified and this statement is not removed. Usage by and for commercial
-CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
-CC or send an email to license at isb-sib.ch).
-CC --------------------------------------------------------------------------
-DR EMBL; D89980; BAA24447.1; ALT_INIT.
-DR EMBL; U48734; AAC17470.1; ALT_FRAME.
-DR EMBL; BC005033; AAH05033.1; -.
-DR EMBL; AL047603; -; NOT_ANNOTATED_CDS.
-DR EMBL; AU118403; -; NOT_ANNOTATED_CDS.
-DR HSSP; Q01082; 1BKR.
-DR Genew; HGNC:166; ACTN4.
-DR MIM; 604638; -.
-DR MIM; 603278; -.
-DR GO; GO:0015629; C:actin cytoskeleton; TAS.
-DR GO; GO:0005737; C:cytoplasm; TAS.
-DR GO; GO:0005634; C:nucleus; TAS.
-DR GO; GO:0005200; F:structural constituent of cytoskeleton; TAS.
-DR GO; GO:0006928; P:cell motility; TAS.
-DR GO; GO:0007125; P:invasive growth; TAS.
-DR InterPro; IPR001589; Actbind_actnin.
-DR InterPro; IPR001715; Calponin-like.
-DR InterPro; IPR002048; EF-hand.
-DR InterPro; IPR002017; Spectrin.
-DR Pfam; PF00307; CH; 2.
-DR Pfam; PF00036; efhand; 2.
-DR Pfam; PF00435; spectrin; 4.
-DR ProDom; PD000012; EF-hand; 1.
-DR SMART; SM00033; CH; 2.
-DR SMART; SM00054; EFh; 2.
-DR SMART; SM00150; SPEC; 3.
-DR PROSITE; PS00018; EF_HAND; 1.
-DR PROSITE; PS00019; ACTININ_1; 1.
-DR PROSITE; PS00020; ACTININ_2; 1.
-DR PROSITE; PS50021; CH; 2.
-KW Actin-binding; Calcium-binding; Repeat; Multigene family;
-KW Disease mutation; Nuclear protein.
-FT DOMAIN 1 269 ACTIN-BINDING (BY SIMILARITY).
-FT DOMAIN 50 154 CH 1.
-FT DOMAIN 163 269 CH 2.
-FT DOMAIN 177 192 POLYPHOSPHOINOSITIDE (PIP2)-BINDING
-FT (POTENTIAL).
-FT REPEAT 293 403 SPECTRIN 1.
-FT REPEAT 413 518 SPECTRIN 2.
-FT REPEAT 528 639 SPECTRIN 3.
-FT REPEAT 649 752 SPECTRIN 4.
-FT CA_BIND 778 789 EF-HAND 1 (POTENTIAL).
-FT CA_BIND 819 830 EF-HAND 2 (POTENTIAL).
-FT DOMAIN 19 26 POLY-GLY.
-FT VARIANT 255 255 K -> E (in FSGS1).
-FT /FTId=VAR_010378.
-FT VARIANT 259 259 T -> I (in FSGS1).
-FT /FTId=VAR_010379.
-FT VARIANT 262 262 S -> P (in FSGS1).
-FT /FTId=VAR_010380.
-FT CONFLICT 60 60 C -> S (IN REF. 3).
-FT CONFLICT 124 124 V -> I (IN REF. 3).
-FT CONFLICT 164 164 S -> L (IN REF. 4).
-FT CONFLICT 276 276 T -> TET (IN REF. 3).
-FT CONFLICT 292 294 EHL -> CSTS (IN REF. 3).
-FT CONFLICT 359 360 TL -> SV (IN REF. 3).
-FT CONFLICT 476 476 I -> S (IN REF. 3).
-FT CONFLICT 526 526 I -> II (IN REF. 3).
-FT CONFLICT 536 536 R -> P (IN REF. 3).
-FT CONFLICT 645 645 Q -> QQ (IN REF. 3).
-FT CONFLICT 673 674 GR -> A (IN REF. 3).
-FT CONFLICT 850 850 A -> T (IN REF. 3).
-FT CONFLICT 859 859 MISSING (IN REF. 3).
-FT CONFLICT 891 893 AVP -> GVR (IN REF. 3).
-SQ SEQUENCE 911 AA; 104854 MW; 461580C3F22937D1 CRC64;
- MVDYHAANQS YQYGPSSAGN GAGGGGSMGD YMAQEDDWDR DLLLDPAWEK QQRKTFTAWC
- NSHLRKAGTQ IENIDEDFRD GLKLMLLLEV ISGERLPKPE RGKMRVHKIN NVNKALDFIA
- SKGVKLVSIG AEEIVDGNAK MTLGMIWTII LRFAIQDISV EETSAKEGLL LWCQRKTAPY
- KNVNVQNFHI SWKDGLAFNA LIHRHRPELI EYDKLRKDDP VTNLNNAFEV AEKYLDIPKM
- LDAEDIVNTA RPDEKAIMTY VSSFYHAFSG AQKAETAANR ICKVLAVNQE NEHLMEDYEK
- LASDLLEWIR RTIPWLEDRV PQKTIQEMQQ KLEDFRDYRR VHKPPKVQEK CQLEINFNTL
- QTKLRLSNRP AFMPSEGKMV SDINNGWQHL EQAEKGYEEW LLNEIRRLER LDHLAEKFRQ
- KASIHEAWTD GKEAMLKHRD YETATLSDIK ALIRKHEAFE SDLAAHQDRV EQIAAIAQEL
- NELDYYDSHN VNTRCQKICD QWDALGSLTH SRREALEKTE KQLEAIDQLH LEYAKRAAPF
- NNWMESAMED LQDMFIVHTI EEIEGLISAH DQFKSTLPDA DREREAILAI HKEAQRIAES
- NHIKLSGSNP YTTVTPQIIN SKWEKVQQLV PKRDHALLEE QSKQQSNEHL RRQFASQANV
- VGPWIQTKME EIGRISIEMN GTLEDQLSHL KQYERSIVDY KPNLDLLEQQ HQLIQEALIF
- DNKHTNYTME HIRVGWEQLL TTIARTINEV ENQILTRDAK GISQEQMQEF RASFNHFDKD
- HGGALGPEEF KACLISLGYD VENDRQGEAE FNRIMSLVDP NHSGLVTFQA FIDFMSRETT
- DTDTADQVIA SFKVLAGDKN FITAEELRRE LPPDQAEYCI ARMAPYQGPD AVPGALDYKS
- FSTALYGESD L
-//
=====================================
core/src/test/resources/org/biojava/bio/program/indexdb/part1.swiss deleted
=====================================
@@ -1,149 +0,0 @@
-ID 104K_THEPA STANDARD; PRT; 924 AA.
-AC P15711;
-DT 01-APR-1990 (Rel. 14, Created)
-DT 01-APR-1990 (Rel. 14, Last sequence update)
-DT 01-AUG-1992 (Rel. 23, Last annotation update)
-DE 104 kDa microneme-rhoptry antigen.
-OS Theileria parva.
-OC Eukaryota; Alveolata; Apicomplexa; Piroplasmida; Theileriidae;
-OC Theileria.
-OX NCBI_TaxID=5875;
-RN [1]
-RP SEQUENCE FROM N.A.
-RC STRAIN=MUGUGA;
-RX MEDLINE=90158697; PubMed=1689460;
-RA Iams K.P., Young J.R., Nene V., Desai J., Webster P., Ole-Moiyoi O.K.,
-RA Musoke A.J.;
-RT "Characterisation of the gene encoding a 104-kilodalton microneme-
-RT rhoptry protein of Theileria parva.";
-RL Mol. Biochem. Parasitol. 39:47-60(1990).
-CC -!- SUBCELLULAR LOCATION: IN MICRONEME/RHOPTRY COMPLEXES.
-CC -!- DEVELOPMENTAL STAGE: SPOROZOITE ANTIGEN.
-CC --------------------------------------------------------------------------
-CC This SWISS-PROT entry is copyright. It is produced through a collaboration
-CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
-CC the European Bioinformatics Institute. There are no restrictions on its
-CC use by non-profit institutions as long as its content is in no way
-CC modified and this statement is not removed. Usage by and for commercial
-CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
-CC or send an email to license at isb-sib.ch).
-CC --------------------------------------------------------------------------
-DR EMBL; M29954; AAA18217.1; -.
-DR PIR; A44945; A44945.
-KW Antigen; Sporozoite; Repeat.
-FT DOMAIN 1 19 HYDROPHOBIC.
-FT DOMAIN 905 924 HYDROPHOBIC.
-SQ SEQUENCE 924 AA; 103625 MW; 289B4B554A61870E CRC64;
- MKFLILLFNI LCLFPVLAAD NHGVGPQGAS GVDPITFDIN SNQTGPAFLT AVEMAGVKYL
- QVQHGSNVNI HRLVEGNVVI WENASTPLYT GAIVTNNDGP YMAYVEVLGD PNLQFFIKSG
- DAWVTLSEHE YLAKLQEIRQ AVHIESVFSL NMAFQLENNK YEVETHAKNG ANMVTFIPRN
- GHICKMVYHK NVRIYKATGN DTVTSVVGFF RGLRLLLINV FSIDDNGMMS NRYFQHVDDK
- YVPISQKNYE TGIVKLKDYK HAYHPVDLDI KDIDYTMFHL ADATYHEPCF KIIPNTGFCI
- TKLFDGDQVL YESFNPLIHC INEVHIYDRN NGSIICLHLN YSPPSYKAYL VLKDTGWEAT
- THPLLEEKIE ELQDQRACEL DVNFISDKDL YVAALTNADL NYTMVTPRPH RDVIRVSDGS
- EVLWYYEGLD NFLVCAWIYV SDGVASLVHL RIKDRIPANN DIYVLKGDLY WTRITKIQFT
- QEIKRLVKKS KKKLAPITEE DSDKHDEPPE GPGASGLPPK APGDKEGSEG HKGPSKGSDS
- SKEGKKPGSG KKPGPAREHK PSKIPTLSKK PSGPKDPKHP RDPKEPRKSK SPRTASPTRR
- PSPKLPQLSK LPKSTSPRSP PPPTRPSSPE RPEGTKIIKT SKPPSPKPPF DPSFKEKFYD
- DYSKAASRSK ETKTTVVLDE SFESILKETL PETPGTPFTT PRPVPPKRPR TPESPFEPPK
- DPDSPSTSPS EFFTPPESKR TRFHETPADT PLPDVTAELF KEPDVTAETK SPDEAMKRPR
- SPSEYEDTSP GDYPSLPMKR HRLERLRLTT TEMETDPGRM AKDASGKPVK LKRSKSFDDL
- TTVELAPEPK ASRIVVDDEG TEADDEETHP PEERQKTEVR RRRPPKKPSK SPRPSKPKKP
- KKPDSAYIPS ILAILVVSLI VGIL
-//
-ID 108_LYCES STANDARD; PRT; 102 AA.
-AC Q43495;
-DT 15-JUL-1999 (Rel. 38, Created)
-DT 15-JUL-1999 (Rel. 38, Last sequence update)
-DT 15-JUL-1999 (Rel. 38, Last annotation update)
-DE Protein 108 precursor.
-OS Lycopersicon esculentum (Tomato).
-OC Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
-OC Spermatophyta; Magnoliophyta; eudicotyledons; core eudicots;
-OC Asteridae; lamiids; Solanales; Solanaceae; Solanum.
-OX NCBI_TaxID=4081;
-RN [1]
-RP SEQUENCE FROM N.A.
-RC STRAIN=CV. VF36; TISSUE=ANTHER;
-RX MEDLINE=94143497; PubMed=8310077;
-RA Chen R., Smith A.G.;
-RT "Nucleotide sequence of a stamen- and tapetum-specific gene from
-RT Lycopersicon esculentum.";
-RL Plant Physiol. 101:1413-1413(1993).
-CC -!- TISSUE SPECIFICITY: STAMEN- AND TAPETUM-SPECIFIC.
-CC -!- SIMILARITY: BELONGS TO THE A9 / FIL1 FAMILY.
-CC --------------------------------------------------------------------------
-CC This SWISS-PROT entry is copyright. It is produced through a collaboration
-CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
-CC the European Bioinformatics Institute. There are no restrictions on its
-CC use by non-profit institutions as long as its content is in no way
-CC modified and this statement is not removed. Usage by and for commercial
-CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
-CC or send an email to license at isb-sib.ch).
-CC --------------------------------------------------------------------------
-DR EMBL; Z14088; CAA78466.1; -.
-DR InterPro; IPR003612; AAI.
-DR InterPro; IPR001768; Try/amyl_inhbtr.
-DR Pfam; PF00234; tryp_alpha_amyl; 1.
-DR SMART; SM00499; AAI; 1.
-KW Signal.
-FT SIGNAL 1 30 POTENTIAL.
-FT CHAIN 31 102 PROTEIN 108.
-FT DISULFID 41 77 BY SIMILARITY.
-FT DISULFID 51 66 BY SIMILARITY.
-FT DISULFID 67 92 BY SIMILARITY.
-FT DISULFID 79 99 BY SIMILARITY.
-SQ SEQUENCE 102 AA; 10576 MW; CFBAA1231C3A5E92 CRC64;
- MASVKSSSSS SSSSFISLLL LILLVIVLQS QVIECQPQQS CTASLTGLNV CAPFLVPGSP
- TASTECCNAV QSINHDCMCN TMRIAAQIPA QCNLPPLSCS AN
-//
-ID 10KD_VIGUN STANDARD; PRT; 75 AA.
-AC P18646;
-DT 01-NOV-1990 (Rel. 16, Created)
-DT 01-NOV-1990 (Rel. 16, Last sequence update)
-DT 16-OCT-2001 (Rel. 40, Last annotation update)
-DE 10 kDa protein precursor (Clone PSAS10).
-OS Vigna unguiculata (Cowpea).
-OC Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
-OC Spermatophyta; Magnoliophyta; eudicotyledons; core eudicots; Rosidae;
-OC eurosids I; Fabales; Fabaceae; Papilionoideae; Phaseoleae; Vigna.
-OX NCBI_TaxID=3917;
-RN [1]
-RP SEQUENCE FROM N.A.
-RC TISSUE=COTYLEDON;
-RX MEDLINE=91355865; PubMed=2103443;
-RA Ishibashi N., Yamauchi D., Miniamikawa T.;
-RT "Stored mRNA in cotyledons of Vigna unguiculata seeds: nucleotide
-RT sequence of cloned cDNA for a stored mRNA and induction of its
-RT synthesis by precocious germination.";
-RL Plant Mol. Biol. 15:59-64(1990).
-CC -!- FUNCTION: THIS PROTEIN IS REQUIRED FOR GERMINATION.
-CC -!- SIMILARITY: BELONGS TO THE PLANT DEFENSIN FAMILY.
-CC --------------------------------------------------------------------------
-CC This SWISS-PROT entry is copyright. It is produced through a collaboration
-CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
-CC the European Bioinformatics Institute. There are no restrictions on its
-CC use by non-profit institutions as long as its content is in no way
-CC modified and this statement is not removed. Usage by and for commercial
-CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
-CC or send an email to license at isb-sib.ch).
-CC --------------------------------------------------------------------------
-DR EMBL; X16877; CAA34760.1; -.
-DR PIR; S11156; S11156.
-DR InterPro; IPR002118; Gamma-thionin.
-DR InterPro; IPR003614; Knot1.
-DR Pfam; PF00304; Gamma-thionin; 1.
-DR ProDom; PD002594; Gamma-thionin; 1.
-DR SMART; SM00505; Knot1; 1.
-DR PROSITE; PS00940; GAMMA_THIONIN; 1.
-KW Germination; Signal.
-FT SIGNAL 1 24 POTENTIAL.
-FT CHAIN 25 75 10 KDA PROTEIN.
-FT DISULFID 31 75 BY SIMILARITY.
-FT DISULFID 42 63 BY SIMILARITY.
-FT DISULFID 48 69 BY SIMILARITY.
-FT DISULFID 52 71 BY SIMILARITY.
-SQ SEQUENCE 75 AA; 8523 MW; 6D72D9D238CF7650 CRC64;
- MEKKSIAGLC FLFLVLFVAQ EVVVQSEAKT CENLVDTYRG PCFTTGSCDD HCKNKEHLLS
- GRCRDDVRCW CTRNC
-//
=====================================
core/src/test/resources/org/biojava/bio/program/indexdb/part2.swiss deleted
=====================================
@@ -1,164 +0,0 @@
-ID 110K_PLAKN STANDARD; PRT; 296 AA.
-AC P13813;
-DT 01-JAN-1990 (Rel. 13, Created)
-DT 01-JAN-1990 (Rel. 13, Last sequence update)
-DT 01-FEB-1994 (Rel. 28, Last annotation update)
-DE 110 kDa antigen (PK110) (Fragment).
-OS Plasmodium knowlesi.
-OC Eukaryota; Alveolata; Apicomplexa; Haemosporida; Plasmodium.
-OX NCBI_TaxID=5850;
-RN [1]
-RP SEQUENCE FROM N.A.
-RX MEDLINE=88039002; PubMed=2444886;
-RA Perler F.B., Moon A.M., Qiang B.Q., Meda M., Dalton M., Card C.,
-RA Schmidt-Ullrich R., Wallach D., Lynch J., Donelson J.E.;
-RT "Cloning and characterization of an abundant Plasmodium knowlesi
-RT antigen which cross reacts with Gambian sera.";
-RL Mol. Biochem. Parasitol. 25:185-193(1987).
-CC --------------------------------------------------------------------------
-CC This SWISS-PROT entry is copyright. It is produced through a collaboration
-CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
-CC the European Bioinformatics Institute. There are no restrictions on its
-CC use by non-profit institutions as long as its content is in no way
-CC modified and this statement is not removed. Usage by and for commercial
-CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
-CC or send an email to license at isb-sib.ch).
-CC --------------------------------------------------------------------------
-DR EMBL; M19152; AAA29471.1; -.
-DR PIR; A54527; A54527.
-KW Malaria; Antigen; Repeat.
-FT NON_TER 1 1
-FT DOMAIN 131 296 13.5 X 12 AA TANDEM REPEATS OF E-E-T-Q-K-
-FT T-V-E-P-E-Q-T.
-SQ SEQUENCE 296 AA; 34077 MW; B0D7CD175C7A3625 CRC64;
- FNSNMLRGSV CEEDVSLMTS IDNMIEEIDF YEKEIYKGSH SGGVIKGMDY DLEDDENDED
- EMTEQMVEEV ADHITQDMID EVAHHVLDNI THDMAHMEEI VHGLSGDVTQ IKEIVQKVNV
- AVEKVKHIVE TEETQKTVEP EQIEETQNTV EPEQTEETQK TVEPEQTEET QNTVEPEQIE
- ETQKTVEPEQ TEEAQKTVEP EQTEETQKTV EPEQTEETQK TVEPEQTEET QKTVEPEQTE
- ETQKTVEPEQ TEETQKTVEP EQTEETQKTV EPEQTEETQN TVEPEPTQET QNTVEP
-//
-ID 11S3_HELAN STANDARD; PRT; 493 AA.
-AC P19084;
-DT 01-NOV-1990 (Rel. 16, Created)
-DT 01-NOV-1990 (Rel. 16, Last sequence update)
-DT 30-MAY-2000 (Rel. 39, Last annotation update)
-DE 11S globulin seed storage protein G3 precursor (Helianthinin G3).
-GN HAG3.
-OS Helianthus annuus (Common sunflower).
-OC Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
-OC Spermatophyta; Magnoliophyta; eudicotyledons; core eudicots;
-OC Asteridae; campanulids; Asterales; Asteraceae; Asteroideae;
-OC Heliantheae; Helianthus.
-OX NCBI_TaxID=4232;
-RN [1]
-RP SEQUENCE FROM N.A.
-RX MEDLINE=89232734; PubMed=2469623;
-RA Vonder Haar R.A., Allen R.D., Cohen E.A., Nessler C.L., Thomas T.L.;
-RT "Organization of the sunflower 11S storage protein gene family.";
-RL Gene 74:433-443(1988).
-CC -!- FUNCTION: THIS IS A SEED STORAGE PROTEIN.
-CC -!- SUBUNIT: HEXAMER; EACH SUBUNIT IS COMPOSED OF AN ACIDIC AND A
-CC BASIC CHAIN DERIVED FROM A SINGLE PRECURSOR AND LINKED BY A
-CC DISULFIDE BOND.
-CC -!- SIMILARITY: BELONGS TO THE 11S SEED STORAGE PROTEIN (GLOBULINS)
-CC FAMILY.
-CC --------------------------------------------------------------------------
-CC This SWISS-PROT entry is copyright. It is produced through a collaboration
-CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
-CC the European Bioinformatics Institute. There are no restrictions on its
-CC use by non-profit institutions as long as its content is in no way
-CC modified and this statement is not removed. Usage by and for commercial
-CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
-CC or send an email to license at isb-sib.ch).
-CC --------------------------------------------------------------------------
-DR EMBL; M28832; AAA33374.1; -.
-DR PIR; JA0089; JA0089.
-DR InterPro; IPR000459; Seedstore_11s.
-DR Pfam; PF00190; Cupin; 2.
-DR PRINTS; PR00439; 11SGLOBULIN.
-DR PROSITE; PS00305; 11S_SEED_STORAGE; 1.
-KW Seed storage protein; Multigene family; Signal.
-FT SIGNAL 1 20
-FT CHAIN 21 305 ACIDIC CHAIN.
-FT CHAIN 306 493 BASIC CHAIN.
-FT DISULFID 103 312 INTERCHAIN (ACIDIC-BASIC) (POTENTIAL).
-FT DOMAIN 23 35 GLN-RICH.
-FT DOMAIN 111 127 GLN/GLY-RICH.
-FT DOMAIN 191 297 GLN-RICH.
-SQ SEQUENCE 493 AA; 55687 MW; A007B6F99D189AB5 CRC64;
- MASKATLLLA FTLLFATCIA RHQQRQQQQN QCQLQNIEAL EPIEVIQAEA GVTEIWDAYD
- QQFQCAWSIL FDTGFNLVAF SCLPTSTPLF WPSSREGVIL PGCRRTYEYS QEQQFSGEGG
- RRGGGEGTFR TVIRKLENLK EGDVVAIPTG TAHWLHNDGN TELVVVFLDT QNHENQLDEN
- QRRFFLAGNP QAQAQSQQQQ QRQPRQQSPQ RQRQRQRQGQ GQNAGNIFNG FTPELIAQSF
- NVDQETAQKL QGQNDQRGHI VNVGQDLQIV RPPQDRRSPR QQQEQATSPR QQQEQQQGRR
- GGWSNGVEET ICSMKFKVNI DNPSQADFVN PQAGSIANLN SFKFPILEHL RLSVERGELR
- PNAIQSPHWT INAHNLLYVT EGALRVQIVD NQGNSVFDNE LREGQVVVIP QNFAVIKRAN
- EQGSRWVSFK TNDNAMIANL AGRVSASAAS PLTLWANRYQ LSREEAQQLK FSQRETVLFA
- PSFSRGQGIR ASR
-//
-ID 11SB_CUCMA STANDARD; PRT; 480 AA.
-AC P13744;
-DT 01-JAN-1990 (Rel. 13, Created)
-DT 01-JAN-1990 (Rel. 13, Last sequence update)
-DT 15-JUN-2002 (Rel. 41, Last annotation update)
-DE 11S globulin beta subunit precursor.
-OS Cucurbita maxima (Pumpkin) (Winter squash).
-OC Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
-OC Spermatophyta; Magnoliophyta; eudicotyledons; core eudicots; Rosidae;
-OC eurosids I; Cucurbitales; Cucurbitaceae; Cucurbita.
-OX NCBI_TaxID=3661;
-RN [1]
-RP SEQUENCE FROM N.A.
-RC STRAIN=CV. KUROKAWA AMAKURI NANKIN;
-RX MEDLINE=88166744; PubMed=2450746;
-RA Hayashi M., Mori H., Nishimura M., Akazawa T., Hara-Nishimura I.;
-RT "Nucleotide sequence of cloned cDNA coding for pumpkin 11-S globulin
-RT beta subunit.";
-RL Eur. J. Biochem. 172:627-632(1988).
-RN [2]
-RP SEQUENCE OF 22-30 AND 297-302.
-RA Ohmiya M., Hara I., Mastubara H.;
-RT "Pumpkin (Cucurbita sp.) seed globulin IV. Terminal sequences of the
-RT acidic and basic peptide chains and identification of a pyroglutamyl
-RT peptide chain.";
-RL Plant Cell Physiol. 21:157-167(1980).
-CC -!- FUNCTION: THIS IS A SEED STORAGE PROTEIN.
-CC -!- SUBUNIT: HEXAMER; EACH SUBUNIT IS COMPOSED OF AN ACIDIC AND A
-CC BASIC CHAIN DERIVED FROM A SINGLE PRECURSOR AND LINKED BY A
-CC DISULFIDE BOND.
-CC -!- SIMILARITY: BELONGS TO THE 11S SEED STORAGE PROTEIN (GLOBULINS)
-CC FAMILY.
-CC --------------------------------------------------------------------------
-CC This SWISS-PROT entry is copyright. It is produced through a collaboration
-CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
-CC the European Bioinformatics Institute. There are no restrictions on its
-CC use by non-profit institutions as long as its content is in no way
-CC modified and this statement is not removed. Usage by and for commercial
-CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
-CC or send an email to license at isb-sib.ch).
-CC --------------------------------------------------------------------------
-DR EMBL; M36407; AAA33110.1; -.
-DR PIR; S00366; FWPU1B.
-DR InterPro; IPR000459; Seedstore_11s.
-DR Pfam; PF00190; Cupin; 2.
-DR PRINTS; PR00439; 11SGLOBULIN.
-DR PROSITE; PS00305; 11S_SEED_STORAGE; 1.
-KW Seed storage protein; Signal; Pyrrolidone carboxylic acid.
-FT SIGNAL 1 21
-FT CHAIN 22 480 11S GLOBULIN BETA SUBUNIT.
-FT CHAIN 22 296 GAMMA CHAIN (ACIDIC).
-FT CHAIN 297 480 DELTA CHAIN (BASIC).
-FT MOD_RES 22 22 PYRROLIDONE CARBOXYLIC ACID.
-FT DISULFID 124 303 INTERCHAIN (GAMMA-DELTA) (POTENTIAL).
-FT CONFLICT 27 27 S -> E (IN REF. 2).
-FT CONFLICT 30 30 E -> S (IN REF. 2).
-SQ SEQUENCE 480 AA; 54625 MW; BCD8A83DD1AED93C CRC64;
- MARSSLFTFL CLAVFINGCL SQIEQQSPWE FQGSEVWQQH RYQSPRACRL ENLRAQDPVR
- RAEAEAIFTE VWDQDNDEFQ CAGVNMIRHT IRPKGLLLPG FSNAPKLIFV AQGFGIRGIA
- IPGCAETYQT DLRRSQSAGS AFKDQHQKIR PFREGDLLVV PAGVSHWMYN RGQSDLVLIV
- FADTRNVANQ IDPYLRKFYL AGRPEQVERG VEEWERSSRK GSSGEKSGNI FSGFADEFLE
- EAFQIDGGLV RKLKGEDDER DRIVQVDEDF EVLLPEKDEE ERSRGRYIES ESESENGLEE
- TICTLRLKQN IGRSVRADVF NPRGGRISTA NYHTLPILRQ VRLSAERGVL YSNAMVAPHY
- TVNSHSVMYA TRGNARVQVV DNFGQSVFDG EVREGQVLMI PQNFVVIKRA SDRGFEWIAF
- KTNDNAITNL LAGRVSQMRM LPLGVLSNMY RISREEAQRL KYGQQEMRVL SPGRSQGRRE
-//
=====================================
debian/changelog
=====================================
@@ -1,6 +1,6 @@
-biojava-live (1:1.9.5-1) experimental; urgency=medium
+biojava-live (1:1.9.5+dfsg-1) experimental; urgency=medium
- * New upstream version 1.9.5
+ * New upstream version 1.9.5+dfsg
* Building new libbiojava1.9-java package, replacing and conflicting with
libbiojava1.7-java
* Removing obsolete get-orig-source target in d/rules
@@ -20,8 +20,11 @@ biojava-live (1:1.9.5-1) experimental; urgency=medium
* Excluding tests with problematic data
* Use secure URI in Homepage field.
* Marking the doc package as Multi-Arch: foreign
+ * Removing files under non-free SWISS-PROT license, thanks to
+ Thorsten Alteholz for pointing this out
+ * Skipping two tests relying on removed files with non-free license
- -- Pierre Gruet <pgt at debian.org> Mon, 28 Mar 2022 21:18:49 +0200
+ -- Pierre Gruet <pgt at debian.org> Fri, 08 Apr 2022 21:21:13 +0200
biojava-live (1:1.7.1-9) unstable; urgency=medium
=====================================
debian/copyright
=====================================
@@ -1,6 +1,9 @@
Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
Upstream-Name: BioJava
Source: http://www.biojava.org/download/source
+Files-Excluded: core/src/test/resources/org/biojava/bio/program/indexdb/part?.swiss
+ core/src/test/resources/AAC4_HUMAN.sp
+Comment: Those files are under non-free SWISS-PROT license.
Files: *
Copyright: 1999-2008 the Individual authors who contributed the code,
=====================================
debian/patches/omit_tests_with_problematic_data.patch
=====================================
@@ -2,9 +2,11 @@ Description: omitting tests needing datasets from the Internet
- The tests in Genbank* and Genpept* apparently look for data on the Internet.
- The test in SeqIOToolsTests strangely fails although it works if I run the
class on my computer from the installed package.
+ - Two more tests rely on data with non-free SWISS-PROT license, which we
+ removed when repacking.
Author: Pierre Gruet <pgt at debian.org>
Forwarded: not-needed
-Last-Update: 2022-02-27
+Last-Update: 2022-04-08
--- a/core/src/test/java/org/biojava/bio/seq/io/SeqIOToolsTest.java
+++ b/core/src/test/java/org/biojava/bio/seq/io/SeqIOToolsTest.java
@@ -26,6 +28,24 @@ Last-Update: 2022-02-27
/******* test readEmblNucleotide **********/
+@@ -306,7 +306,7 @@
+
+ /******* test readSwissProt **********/
+
+- // get access to the test file
++ /*// get access to the test file
+ System.out.println("Testing SP read");
+ System.out.println("Testing SP read");
+ inputS = this.getClass().getResourceAsStream("/AAC4_HUMAN.sp");
+@@ -335,7 +335,7 @@
+ }
+ catch (Exception ex) {
+ fail(ex.getMessage());
+- }
++ }*/
+
+ }
+
--- a/pom.xml
+++ b/pom.xml
@@ -136,6 +136,9 @@
@@ -38,3 +58,23 @@ Last-Update: 2022-02-27
</configuration>
</plugin>
<plugin>
+--- a/core/src/test/java/org/biojava/bio/program/indexdb/IndexToolsTest.java
++++ b/core/src/test/java/org/biojava/bio/program/indexdb/IndexToolsTest.java
+@@ -165,7 +165,7 @@
+ assertEquals(557, seq6.length());
+ }
+
+- public void testIndexSwissprot() throws Exception
++ /*public void testIndexSwissprot() throws Exception
+ {
+ File [] files = getDBFiles(new String [] { "part1.swiss",
+ "part2.swiss" });
+@@ -185,7 +185,7 @@
+ assertEquals(493, seq5.length());
+ Sequence seq6 = db.getSequence("11SB_CUCMA");
+ assertEquals(480, seq6.length());
+- }
++ }*/
+
+ private File [] getDBFiles(String [] fileNames) throws Exception
+ {
=====================================
debian/watch
=====================================
@@ -1,4 +1,5 @@
version=4
-opts=filenamemangle=s/.+\/biojava-legacy-(\d\S*)\.tar\.gz/biojava-legacy-$1\.tar\.gz/ \
+opts="filenamemangle=s/.+\/biojava-legacy-(\d\S*)\.tar\.gz/biojava-legacy-$1\.tar\.gz/, \
+ repack, repacksuffix=+dfsg, compression=xz, dversionmangle=auto" \
https://github.com/biojava/biojava-legacy/tags .*/biojava-legacy-(\d\S*)\.tar\.gz
View it on GitLab: https://salsa.debian.org/med-team/biojava-live/-/compare/7220fa8d880077d24388e3beb8012daccda37c9f...257884d23818586ce192904c6ac9fa4e0112248e
--
View it on GitLab: https://salsa.debian.org/med-team/biojava-live/-/compare/7220fa8d880077d24388e3beb8012daccda37c9f...257884d23818586ce192904c6ac9fa4e0112248e
You're receiving this email because of your account on salsa.debian.org.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://alioth-lists.debian.net/pipermail/debian-med-commit/attachments/20220408/34a31124/attachment-0001.htm>
More information about the debian-med-commit
mailing list