changeset 1:88ebde55bef8 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/virAnnot commit 48a3a1fa033745898a131f9dca7132947683c02f
author iuc
date Sat, 18 May 2024 18:14:54 +0000
parents e889010415a1
children 77c3ef9b0ed7
files macros.xml test-data/rps_test.tab virAnnot_blast2tsv.xml
diffstat 3 files changed, 13 insertions(+), 7 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Mon Mar 04 19:55:52 2024 +0000
+++ b/macros.xml	Sat May 18 18:14:54 2024 +0000
@@ -1,4 +1,9 @@
 <macros>
+    <xml name="xrefs">
+        <xrefs>
+            <xref type="bio.tools">virannot</xref>
+        </xrefs>
+    </xml>
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="1.83">biopython</requirement>
--- a/test-data/rps_test.tab	Mon Mar 04 19:55:52 2024 +0000
+++ b/test-data/rps_test.tab	Sat May 18 18:14:54 2024 +0000
@@ -1,6 +1,6 @@
 #query_id	query_length	cdd_id	hit_id	evalue	startQ	endQ	frame	description	superkingdom
 ds2020-267_120	339	pfam01333	gnl|CDD|366578	0.000848733	197	325	-3	pfam01333, Apocytochr_F_C, Apocytochrome F, C-terminal.  This is a sub-family of cytochrome C. See pfam00034.	Eukaryota(19);Bacteria(1)
-ds2020-267_374	242	pfam00124	gnl|CDD|365890	5.09126e-07	21	125	3	pfam00124, Photo_RC, Photosynthetic reaction centre protein.  	Bacteria(9);Eukaryota(6);Viruses(4);unclassified sequences(1)
+ds2020-267_374	242	pfam00124	gnl|CDD|365890	5.09126e-07	21	125	3	pfam00124, Photo_RC, Photosynthetic reaction centre protein.  	Bacteria(10);Eukaryota(5);Viruses(4);unclassified sequences(1)
 ds2020-267_471	230	pfam00201	gnl|CDD|278624	3.12575e-07	46	210	1	pfam00201, UDPGT, UDP-glucoronosyl and UDP-glucosyl transferase.  	Eukaryota(20)
 ds2020-267_710	213	pfam01127	gnl|CDD|366480	0.000723904	46	210	1	pfam01127, Sdh_cyt, Succinate dehydrogenase/Fumarate reductase transmembrane subunit.  This family includes a transmembrane protein from both the Succinate dehydrogenase and Fumarate reductase complexes.	Bacteria(20)
 ds2020-267_692	214	pfam00680	gnl|CDD|366242	4.79875e-05	70	180	1	pfam00680, RdRP_1, RNA dependent RNA polymerase.  	Viruses(20)
@@ -11,7 +11,7 @@
 ds2020-267_773	210	pfam01641	gnl|CDD|376583	5.23903e-34	16	174	1	pfam01641, SelR, SelR domain.  Methionine sulfoxide reduction is an important process, by which cells regulate biological processes and cope with oxidative stress. MsrA, a protein involved in the reduction of methionine sulfoxides in proteins, has been known for four decades and has been extensively characterized with respect to structure and function. However, recent studies revealed that MsrA is only specific for methionine-S-sulfoxides. Because oxidized methionines occur in a mixture of R and S isomers in vivo, it was unclear how stereo-specific MsrA could be responsible for the reduction of all protein methionine sulfoxides. It appears that a second methionine sulfoxide reductase, SelR, evolved that is specific for methionine-R-sulfoxides, the activity that is different but complementary to that of MsrA. Thus, these proteins, working together, could reduce both stereoisomers of methionine sulfoxide. This domain is found both in SelR proteins and fused with the peptide methionine sulfoxide reductase enzymatic domain pfam01625. The domain has two conserved cysteine and histidines. The domain binds both selenium and zinc. The final cysteine is found to be replaced by the rare amino acid selenocysteine in some members of the family. This family has methionine-R-sulfoxide reductase activity.	Bacteria(18);Archaea(1);unclassified sequences(1)
 ds2020-267_287	256	pfam00115	gnl|CDD|376293	2.8946e-26	13	237	1	pfam00115, COX1, Cytochrome C and Quinol oxidase polypeptide I.  	Eukaryota(18);Bacteria(2)
 ds2020-267_139	320	pfam05860	gnl|CDD|368641	1.34887e-13	167	298	2	pfam05860, Haemagg_act, haemagglutination activity domain.  This domain is suggested to be a carbohydrate- dependent haemagglutination activity site. It is found in a range of haemagglutinins and haemolysins.	Bacteria(20)
-ds2020-267_763	211	pfam00557	gnl|CDD|376349	0.000231782	167	298	2	pfam00557, Peptidase_M24, Metallopeptidase family M24.  This family contains metallopeptidases. It also contains non-peptidase homologs such as the N terminal domain of Spt16 which is a histone H3-H4 binding module.	Bacteria(18);Archaea(2)
+ds2020-267_763	211	pfam00557	gnl|CDD|376349	0.000231782	167	298	2	pfam00557, Peptidase_M24, Metallopeptidase family M24.  This family contains metallopeptidases. It also contains non-peptidase homologs such as the N terminal domain of Spt16 which is a histone H3-H4 binding module.	Bacteria(17);Archaea(2);unclassified sequences(1)
 ds2020-267_571	221	pfam00501	gnl|CDD|366135	2.61467e-07	34	201	1	pfam00501, AMP-binding, AMP-binding enzyme.  	Bacteria(17);Eukaryota(2);unclassified sequences(1)
 ds2020-267_565	222	pfam03950	gnl|CDD|377172	9.52435e-10	53	184	-3	pfam03950, tRNA-synt_1c_C, tRNA synthetases class I (E and Q), anti-codon binding domain.  Other tRNA synthetase sub-families are too dissimilar to be included. This family includes only glutamyl and glutaminyl tRNA synthetases. In some organisms, a single glutamyl-tRNA synthetase aminoacylates both tRNA(Glu) and tRNA(Gln).	Bacteria(16);Archaea(3);Eukaryota(1)
 ds2020-267_427	235	pfam03154	gnl|CDD|367360	0.000552392	53	184	-3	pfam03154, Atrophin-1, Atrophin-1 family.  Atrophin-1 is the protein product of the dentatorubral-pallidoluysian atrophy (DRPLA) gene. DRPLA OMIM:125370 is a progressive neurodegenerative disorder. It is caused by the expansion of a CAG repeat in the DRPLA gene on chromosome 12p. This results in an extended polyglutamine region in atrophin-1, that is thought to confer toxicity to the protein, possibly through altering its interactions with other proteins. The expansion of a CAG repeat is also the underlying defect in six other neurodegenerative disorders, including Huntington's disease. One interaction of expanded polyglutamine repeats that is thought to be pathogenic is that with the short glutamine repeat in the transcriptional coactivator CREB binding protein, CBP. This interaction draws CBP away from its usual nuclear location to the expanded polyglutamine repeat protein aggregates that are characteristic of the polyglutamine neurodegenerative disorders. This interferes with CBP-mediated transcription and causes cytotoxicity.	Eukaryota(20)
@@ -22,7 +22,7 @@
 ds2020-267_278	258	pfam00012	gnl|CDD|365808	4.1355e-19	50	232	2	pfam00012, HSP70, Hsp70 protein.  Hsp70 chaperones help to fold many proteins. Hsp70 assisted folding involves repeated cycles of substrate binding and release. Hsp70 activity is ATP dependent. Hsp70 proteins are made up of two regions: the amino terminus is the ATPase domain and the carboxyl terminus is the substrate binding region.	Bacteria(15);Eukaryota(4);Viruses(1)
 ds2020-267_364	243	pfam00216	gnl|CDD|365952	1.5507e-10	134	241	-3	pfam00216, Bac_DNA_binding, Bacterial DNA-binding protein.  	Bacteria(19);unclassified sequences(1)
 ds2020-267_558	222	pfam03737	gnl|CDD|377116	4.93695e-13	57	179	-2	pfam03737, RraA-like, Aldolase/RraA.  Members of this family include regulator of ribonuclease E activity A (RraA) and 4-hydroxy-4-methyl-2-oxoglutarate (HMG)/4-carboxy- 4-hydroxy-2-oxoadipate (CHA) aldolase, also known as RraA-like protein. RraA acts as a trans-acting modulator of RNA turnover, binding essential endonuclease RNase E and inhibiting RNA processing. RraA-like proteins seem to contain aldolase and/or decarboxylase activity either in place of or in addition to the RNase E inhibitor functions.	Bacteria(19);unclassified sequences(1)
-ds2020-267_218	274	pfam01348	gnl|CDD|279664	1.66328e-05	51	257	3	pfam01348, Intron_maturas2, Type II intron maturase.  Group II introns use intron-encoded reverse transcriptase, maturase and DNA endonuclease activities for site-specific insertion into DNA. Although this type of intron is self splicing in vitro they require a maturase protein for splicing in vivo. It has been shown that a specific region of the aI2 intron is needed for the maturase function. This region was found to be conserved in group II introns and called domain X.	Eukaryota(15);Bacteria(5)
+ds2020-267_218	274	pfam01348	gnl|CDD|279664	1.66328e-05	51	257	3	pfam01348, Intron_maturas2, Type II intron maturase.  Group II introns use intron-encoded reverse transcriptase, maturase and DNA endonuclease activities for site-specific insertion into DNA. Although this type of intron is self splicing in vitro they require a maturase protein for splicing in vivo. It has been shown that a specific region of the aI2 intron is needed for the maturase function. This region was found to be conserved in group II introns and called domain X.	Eukaryota(16);Bacteria(4)
 ds2020-267_363	243	pfam00416	gnl|CDD|366086	2.02528e-05	15	134	-2	pfam00416, Ribosomal_S13, Ribosomal protein S13/S18.  This family includes ribosomal protein S13 from prokaryotes and S18 from eukaryotes.	Bacteria(16);Archaea(3);Eukaryota(1)
 ds2020-267_746	211	pfam01490	gnl|CDD|279788	0.000177299	15	134	-2	pfam01490, Aa_trans, Transmembrane amino acid transporter protein.  This transmembrane region is found in many amino acid transporters including UNC-47 and MTR. UNC-47 encodes a vesicular amino butyric acid (GABA) transporter, (VGAT). UNC-47 is predicted to have 10 transmembrane domains. MTR is a N system amino acid transporter system protein involved in methyltryptophan resistance. Other members of this family include proline transporters and amino acid permeases.	Eukaryota(20)
 ds2020-267_145	315	pfam02626	gnl|CDD|376868	3.97676e-05	140	256	-3	pfam02626, CT_A_B, Carboxyltransferase domain, subdomain A and B.  Urea carboxylase (UC) catalyzes a two-step, ATP- and biotin-dependent carboxylation reaction of urea. It is composed of biotin carboxylase (BC), carboxyltransferase (CT), and biotin carboxyl carrier protein (BCCP) domains. The CT domain of UC consists of four subdomains, named A, B, C and D. This domain covers the A and B subdomains of the CT domain. This domain covers the whole length of KipA (kinase A) from Bacillus subtilis. It can also be found in S. cerevisiae urea amidolyase Dur1,2, which is a multifunctional biotin-dependent enzyme with domains for urea carboxylase and allophanate (urea carboxylate) hydrolase activity.	Bacteria(19);unclassified sequences(1)
@@ -34,10 +34,10 @@
 ds2020-267_2	2436	pfam02123	gnl|CDD|280316	2.17343e-21	184	1476	1	pfam02123, RdRP_4, Viral RNA-directed RNA-polymerase.  This family includes RNA-dependent RNA polymerase proteins (RdRPs) from Luteovirus, Totivirus and Rotavirus.	Viruses(19);unclassified sequences(1)
 ds2020-267_595	219	pfam02123	gnl|CDD|280316	5.90575e-11	13	210	1	pfam02123, RdRP_4, Viral RNA-directed RNA-polymerase.  This family includes RNA-dependent RNA polymerase proteins (RdRPs) from Luteovirus, Totivirus and Rotavirus.	Viruses(19);unclassified sequences(1)
 ds2020-267_622	217	pfam01370	gnl|CDD|366597	1.5719e-08	50	172	2	pfam01370, Epimerase, NAD dependent epimerase/dehydratase family.  This family of proteins utilize NAD as a cofactor. The proteins in this family use nucleotide-sugar substrates for a variety of chemical reactions.	Bacteria(17);unclassified sequences(2);Archaea(1)
-ds2020-267_214	276	pfam00070	gnl|CDD|365851	1.70856e-05	135	254	3	pfam00070, Pyr_redox, Pyridine nucleotide-disulphide oxidoreductase.  This family includes both class I and class II oxidoreductases and also NADH oxidases and peroxidases. This domain is actually a small NADH binding domain within a larger FAD binding domain.	Eukaryota(12);Bacteria(5);unclassified sequences(2);Archaea(1)
+ds2020-267_214	276	pfam00070	gnl|CDD|365851	1.70856e-05	135	254	3	pfam00070, Pyr_redox, Pyridine nucleotide-disulphide oxidoreductase.  This family includes both class I and class II oxidoreductases and also NADH oxidases and peroxidases. This domain is actually a small NADH binding domain within a larger FAD binding domain.	Eukaryota(11);Bacteria(6);unclassified sequences(2);Archaea(1)
 ds2020-267_610	218	pfam17759	gnl|CDD|380005	1.47034e-13	25	195	1	pfam17759, tRNA_synthFbeta, Phenylalanyl tRNA synthetase beta chain CLM domain.  This domain corresponds to the catalytic like domain (CLM) in the beta chain of phe tRNA synthetase.	Bacteria(17);Archaea(2);unclassified sequences(1)
 ds2020-267_94	386	pfam01347	gnl|CDD|366585	0.000224462	25	195	1	pfam01347, Vitellogenin_N, Lipoprotein amino terminal region.  This family contains regions from: Vitellogenin, Microsomal triglyceride transfer protein and apolipoprotein B-100. These proteins are all involved in lipid transport. This family contains the LV1n chain from lipovitellin, that contains two structural domains.	Eukaryota(20)
-ds2020-267_323	250	pfam00227	gnl|CDD|365960	5.8155e-09	10	150	-2	pfam00227, Proteasome, Proteasome subunit.  The proteasome is a multisubunit structure that degrades proteins. Protein degradation is an essential component of regulation because proteins can become misfolded, damaged, or unnecessary. Proteasomes and their homologs vary greatly in complexity: from HslV (heat shock locus v), which is encoded by 1 gene in bacteria, to the eukaryotic 20S proteasome, which is encoded by more than 14 genes. Recently evidence of two novel groups of bacterial proteasomes was proposed. The first is Anbu, which is sparsely distributed among cyanobacteria and proteobacteria. The second is call beta-proteobacteria proteasome homolog (BPH).	Eukaryota(8);Bacteria(7);Archaea(5)
+ds2020-267_323	250	pfam00227	gnl|CDD|365960	5.8155e-09	10	150	-2	pfam00227, Proteasome, Proteasome subunit.  The proteasome is a multisubunit structure that degrades proteins. Protein degradation is an essential component of regulation because proteins can become misfolded, damaged, or unnecessary. Proteasomes and their homologs vary greatly in complexity: from HslV (heat shock locus v), which is encoded by 1 gene in bacteria, to the eukaryotic 20S proteasome, which is encoded by more than 14 genes. Recently evidence of two novel groups of bacterial proteasomes was proposed. The first is Anbu, which is sparsely distributed among cyanobacteria and proteobacteria. The second is call beta-proteobacteria proteasome homolog (BPH).	Eukaryota(8);Bacteria(6);Archaea(6)
 ds2020-267_168	298	pfam13546	gnl|CDD|379252	0.000766911	10	150	-2	pfam13546, DDE_5, DDE superfamily endonuclease.  This family of proteins are related to pfam00665 and are probably endonucleases of the DDE superfamily. Transposase proteins are necessary for efficient DNA transposition. This domain is a member of the DDE superfamily, which contain three carboxylate residues that are believed to be responsible for coordinating metal ions needed for catalysis. The catalytic activity of this enzyme involves DNA cleavage at a specific site followed by a strand transfer reaction.	Bacteria(18);unclassified sequences(2)
 ds2020-267_636	217	pfam13812	gnl|CDD|316342	0.000111468	16	123	-2	pfam13812, PPR_3, Pentatricopeptide repeat domain.  This family matches additional variants of the PPR repeat that were not captured by the model for pfam01535. In the case of the Arabidopsis protein UniProtKB:Q66GI4, the repeated helices in this N-terminal region, of protein-only RNase P (PRORP) enzymes, form the pentatricopeptide repeat (PPR) domain which enhances pre-tRNA binding affinity. PROPRP enzymes process precursor tRNAs in human mitochondria and in all tRNA-using compartments of Arabidopsis thaliana.	Eukaryota(20)
 ds2020-267_486	228	pfam17035	gnl|CDD|374956	5.12677e-09	108	203	3	pfam17035, BET, Bromodomain extra-terminal - transcription regulation.  The BET, or bromodomain extra-terminal domain, is found on bromodomain proteins that play key roles in development, cancer progression and virus-host pathogenesis. It interacts with NSD3, JMJD6, CHD4, GLTSCR1, and ATAD5 all of which are shown to impart a pTEFb-independent transcriptional activation function on the bromodomain proteins.	Eukaryota(20)
@@ -82,7 +82,7 @@
 ds2020-267_203	281	pfam03040	gnl|CDD|367312	1.76794e-22	121	231	-3	pfam03040, CemA, CemA family.  Members of this family are probable integral membrane proteins. Their molecular function is unknown. CemA proteins are found in the inner envelope membrane of chloroplasts but not in the thylakoid membrane. A cyanobacterial member of this family has been implicated in CO2 transport, but is probably not a CO2 transporter itself. They are predicted to be haem-binding however this has not been proven experimentally.	Eukaryota(20)
 ds2020-267_33	680	pfam04157	gnl|CDD|367847	4.86455e-13	342	494	-1	pfam04157, EAP30, EAP30/Vps36 family.  This family includes EAP30 as well as the Vps36 protein. Vps36 is involved in Golgi to endosome trafficking. EAP30 is a subunit of the ELL complex. The ELL is an 80-kDa RNA polymerase II transcription factor. ELL interacts with three other proteins to form the complex known as ELL complex. The ELL complex is capable of increasing that catalytic rate of transcription elongation, but is unable to repress initiation of transcription by RNA polymerase II as is the case of ELL. EAP30 is thought to lead to the derepression of ELL's transcriptional inhibitory activity.	Eukaryota(17);Archaea(3)
 ds2020-267_6	1860	pfam02123	gnl|CDD|280316	1.35634e-17	1147	1764	-1	pfam02123, RdRP_4, Viral RNA-directed RNA-polymerase.  This family includes RNA-dependent RNA polymerase proteins (RdRPs) from Luteovirus, Totivirus and Rotavirus.	Viruses(19);unclassified sequences(1)
-ds2020-267_555	222	pfam00124	gnl|CDD|365890	7.71427e-08	48	203	3	pfam00124, Photo_RC, Photosynthetic reaction centre protein.  	Bacteria(9);Eukaryota(6);Viruses(4);unclassified sequences(1)
+ds2020-267_555	222	pfam00124	gnl|CDD|365890	7.71427e-08	48	203	3	pfam00124, Photo_RC, Photosynthetic reaction centre protein.  	Bacteria(10);Eukaryota(5);Viruses(4);unclassified sequences(1)
 ds2020-267_550	223	pfam05694	gnl|CDD|377548	0.00097637	48	203	3	pfam05694, SBP56, 56kDa selenium binding protein (SBP56).  This family consists of several eukaryotic selenium binding proteins as well as three sequences from archaea. The exact function of this protein is unknown although it is thought that SBP56 participates in late stages of intra-Golgi protein transport. The Lotus japonicus homolog of SBP56, LjSBP is thought to have more than one physiological role and can be implicated in controlling the oxidation/reduction status of target proteins, in vesicular Golgi transport.	Bacteria(12);Eukaryota(8)
 ds2020-267_65	462	pfam13406	gnl|CDD|372592	4.82338e-27	145	360	-1	pfam13406, SLT_2, Transglycosylase SLT domain.  This family is related to the SLT domain pfam01464.	Bacteria(19);unclassified sequences(1)
 ds2020-267_729	212	pfam01405	gnl|CDD|279713	5.43744e-05	19	99	-3	pfam01405, PsbT, Photosystem II reaction centre T protein.  The exact function of this protein is unknown. It probably consists of a single transmembrane spanning helix. The Chlamydomonas reinhardtii psbT protein appears to be (i) a novel photosystem II subunit and (ii) required for maintaining optimal photosystem II activity under adverse growth conditions.	Eukaryota(17);Bacteria(3)
@@ -102,4 +102,4 @@
 ds2020-267_274	258	pfam03713	gnl|CDD|367619	9.45376e-09	24	173	-2	pfam03713, DUF305, Domain of unknown function (DUF305).  Domain found in small family of bacterial secreted proteins with no known function. Also found in Paramecium bursaria chlorella virus 1. This domain is short and found in one or two copies. The domain has a conserved HH motif that may be functionally important. This domain belongs to the ferritin superfamily. It contains two sequence similar repeats each of which is composed of two alpha helices.	Bacteria(18);unclassified sequences(2)
 ds2020-267_42	575	pfam00283	gnl|CDD|365999	2.95472e-07	325	411	1	pfam00283, Cytochrom_B559, Cytochrome b559, alpha (gene psbE) and beta (gene psbF)subunits.  	Eukaryota(18);Bacteria(2)
 ds2020-267_283	257	pfam13041	gnl|CDD|372443	3.148e-06	13	114	1	pfam13041, PPR_2, PPR repeat family.  This repeat has no known function. It is about 35 amino acids long and is found in up to 18 copies in some proteins. The family appears to be greatly expanded in plants and fungi. The repeat has been called PPR.	Eukaryota(20)
-ds2020-267_685	214	pfam09334	gnl|CDD|370442	1.80219e-14	16	117	-2	pfam09334, tRNA-synt_1g, tRNA synthetases class I (M).  This family includes methionyl tRNA synthetases.	Bacteria(17);Archaea(2);unclassified sequences(1)
+ds2020-267_685	214	pfam09334	gnl|CDD|370442	1.80219e-14	16	117	-2	pfam09334, tRNA-synt_1g, tRNA synthetases class I (M).  This family includes methionyl tRNA synthetases.	Bacteria(16);Archaea(3);unclassified sequences(1)
--- a/virAnnot_blast2tsv.xml	Mon Mar 04 19:55:52 2024 +0000
+++ b/virAnnot_blast2tsv.xml	Sat May 18 18:14:54 2024 +0000
@@ -3,6 +3,7 @@
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="xrefs"/>
     <expand macro="requirements" />
     <required_files>
         <include path="blast2tsv.py" />