Merge branch 'main' of github.com:legumeinfo/datastore-metadata into …

…linkouts

Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/CHECKSUM.CIAT22838.gnm1.ann1.ZM3R.md5

@@ -1,31 +1,27 @@
-9d23627006c67a6edc4b7d54baa4840d  ./aesev.CIAT22838.gnm1.ann1.ZM3R.iprscan.gff3.gz
-5362c8ec30aee45ebd22b07f15100b01  ./aesev.CIAT22838.gnm1.ann1.ZM3R.cds.bed.gz
-54ebe0af9f182e724acd81f120b030c4  ./aesev.CIAT22838.gnm1.ann1.ZM3R.cds.fna.gz.fai
-35cf2cc10e22ea8d4ddb0e6664a5f79b  ./aesev.CIAT22838.gnm1.ann1.ZM3R.mrna_primary.fna.gz.fai
-d9e6007bae48ceec68b274e8210e8750  ./aesev.CIAT22838.gnm1.ann1.ZM3R.cds_primary.fna.gz.fai
-38004d790cc7c700ffb9934b27d2666e  ./README.CIAT22838.gnm1.ann1.ZM3R.yml
-61d7375369302e9b7a334dea5276bf9d  ./aesev.CIAT22838.gnm1.ann1.ZM3R.legfed_v1_0.M65K.pathway.tsv.gz
-5990008661421555f6236f08958034cd  ./aesev.CIAT22838.gnm1.ann1.ZM3R.mrna.fna.gz.fai
-fb1378b44dc6015a39d92d89594dd6fc  ./aesev.CIAT22838.gnm1.ann1.ZM3R.protein.faa.gz.gzi
-6d9a0b82512695bbd3fe6b69b251db8a  ./aesev.CIAT22838.gnm1.ann1.ZM3R.protein_primary.faa.gz.fai
-42110e57fa2e04d2b7860dcfdabc5ee2  ./aesev.CIAT22838.gnm1.ann1.ZM3R.mrna_primary.fna.gz
-4fef0664e395867d84b291ebd3d98aac  ./aesev.CIAT22838.gnm1.ann1.ZM3R.mrna.fna.gz
-42db440be4db0dc9a80e51cba39916f7  ./aesev.CIAT22838.gnm1.ann1.ZM3R.legfed_v1_0.M65K.gfa.tsv.gz
-f0e365a0556703d30515a1bcd0da6128  ./CHANGES.CIAT22838.gnm1.ann1.ZM3R.txt
-affdeedec0b3ff6dd874a0ff895d25cb  ./aesev.CIAT22838.gnm1.ann1.ZM3R.gene_models_main.gff3.gz
-5d4e730b02c9542fd838b3b19531e514  ./aesev.CIAT22838.gnm1.ann1.ZM3R.cds.bed.gz.tbi
-4fda34f042f25689d6d0c2c08f403b85  ./aesev.CIAT22838.gnm1.ann1.ZM3R.gene_models_main.gff3.gz.tbi
-893b7a74fdd06027751b1d45601eb325  ./aesev.CIAT22838.gnm1.ann1.ZM3R.mrna.fna.gz.gzi
-96f785722cb0fa3ec2979dee984cd650  ./aesev.CIAT22838.gnm1.ann1.ZM3R.protein.faa.gz.fai
-bc3ab15bbd800bf83f2cf2a3ebab49ab  ./aesev.CIAT22838.gnm1.ann1.ZM3R.protein_primary.faa.gz.gzi
-87183e40f65b17daeb7b7fe901e5b9ba  ./aesev.CIAT22838.gnm1.ann1.ZM3R.cds.fna.gz
-929232954197543c335b7634ba1abc7b  ./aesev.CIAT22838.gnm1.ann1.ZM3R.cds_primary.fna.gz.gzi
-75a32e17fede12550dfab085913cdca3  ./aesev.CIAT22838.gnm1.ann1.ZM3R.protein_primary.faa.gz
-2e5c7432db0329adf413523cf35ed1c9  ./aesev.CIAT22838.gnm1.ann1.ZM3R.cds.fna.gz.gzi
-3321286b5bfd027ad0d29cf845092149  ./BUSCO/aesev.CIAT22838.gnm1.ann1.ZM3R.busco.fabales_odb10.short_summary.json
-882c873f45b8c097868643016918f676  ./BUSCO/aesev.CIAT22838.gnm1.ann1.ZM3R.busco.fabales_odb10.full_table.tsv.gz
-1941c3d9ae729e9ae3312c4710973f92  ./BUSCO/aesev.CIAT22838.gnm1.ann1.ZM3R.busco.fabales_odb10.short_summary.txt
-b68b5cf7342047f8364b9772ce5808f0  ./aesev.CIAT22838.gnm1.ann1.ZM3R.mrna_primary.fna.gz.gzi
-097cd3ea0134f656e4681ad2d563abf3  ./aesev.CIAT22838.gnm1.ann1.ZM3R.cds_primary.fna.gz
-cd039d1453d6b0c8fd03db2e7ca9b98b  ./aesev.CIAT22838.gnm1.ann1.ZM3R.protein.faa.gz
-e9b603f2ea59d26ca6ba60715cc9118d  ./aesev.CIAT22838.gnm1.ann1.ZM3R.iprscan.gff3.gz.tbi
+097cd3ea0134f656e4681ad2d563abf3 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.cds_primary.fna.gz
+d9e6007bae48ceec68b274e8210e8750 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.cds_primary.fna.gz.fai
+929232954197543c335b7634ba1abc7b Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.cds_primary.fna.gz.gzi
+87183e40f65b17daeb7b7fe901e5b9ba Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.cds.fna.gz
+54ebe0af9f182e724acd81f120b030c4 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.cds.fna.gz.fai
+2e5c7432db0329adf413523cf35ed1c9 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.cds.fna.gz.gzi
+8e4af7485c6c101b865a6560d2465b89 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.gene_models_main.bed.gz
+06a7f61a0d8ddfae616e785d917ce7ba Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.gene_models_main.bed.gz.tbi
+affdeedec0b3ff6dd874a0ff895d25cb Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.gene_models_main.gff3.gz
+4fda34f042f25689d6d0c2c08f403b85 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.gene_models_main.gff3.gz.tbi
+9d23627006c67a6edc4b7d54baa4840d Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.iprscan.gff3.gz
+e9b603f2ea59d26ca6ba60715cc9118d Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.iprscan.gff3.gz.tbi
+42db440be4db0dc9a80e51cba39916f7 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.legfed_v1_0.M65K.gfa.tsv.gz
+42110e57fa2e04d2b7860dcfdabc5ee2 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.mrna_primary.fna.gz
+35cf2cc10e22ea8d4ddb0e6664a5f79b Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.mrna_primary.fna.gz.fai
+b68b5cf7342047f8364b9772ce5808f0 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.mrna_primary.fna.gz.gzi
+4fef0664e395867d84b291ebd3d98aac Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.mrna.fna.gz
+5990008661421555f6236f08958034cd Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.mrna.fna.gz.fai
+893b7a74fdd06027751b1d45601eb325 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.mrna.fna.gz.gzi
+75a32e17fede12550dfab085913cdca3 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.protein_primary.faa.gz
+6d9a0b82512695bbd3fe6b69b251db8a Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.protein_primary.faa.gz.fai
+bc3ab15bbd800bf83f2cf2a3ebab49ab Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.protein_primary.faa.gz.gzi
+cd039d1453d6b0c8fd03db2e7ca9b98b Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.protein.faa.gz
+96f785722cb0fa3ec2979dee984cd650 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.protein.faa.gz.fai
+fb1378b44dc6015a39d92d89594dd6fc Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/aesev.CIAT22838.gnm1.ann1.ZM3R.protein.faa.gz.gzi
+f0e365a0556703d30515a1bcd0da6128 Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/CHANGES.CIAT22838.gnm1.ann1.ZM3R.txt
+38004d790cc7c700ffb9934b27d2666e Aeschynomene/evenia/annotations/CIAT22838.gnm1.ann1.ZM3R/README.CIAT22838.gnm1.ann1.ZM3R.yml

Arachis/GENUS/pangenes/Arachis.pan2.5P1K/CHECKSUM.Arachis.pan2.5P1K.md5

@@ -0,0 +1,8 @@
+c078dcf98a85c3f04d71300d5830e167 Arachis.pan2.5P1K.clust.tsv.gz
+ed4a26b1c5d762aea6ce352e7b95f0de Arachis.pan2.5P1K.complement.fna.gz
+fbb04a017e6d09b40c3092ac90b43740 Arachis.pan2.5P1K.counts.tsv.gz
+d13f12b4febde6a8f801855c5b543356 Arachis.pan2.5P1K.hsh.tsv.gz
+303ecd6b1810bb52ad4793e038de2177 Arachis.pan2.5P1K.inclusive_cds.fna.gz
+6969661a8655bd1e7d1c9ae76f913903 Arachis.pan2.5P1K.inclusive_protein.faa.gz
+f574d2f48719760685fcd6cbb877f2c3 Arachis.pan2.5P1K.pctl40_named_cds.fna.gz
+5e569f186612f2681f477fff34859231 Arachis.pan2.5P1K.pctl40_named_protein.faa.gz

Arachis/GENUS/pangenes/Arachis.pan1.4LN9/README.Arachis.pan1.4LN9.yml → Arachis/GENUS/pangenes/Arachis.pan2.5P1K/README.Arachis.pan2.5P1K.yml

@@ -1,19 +1,18 @@
 ---
-identifier: Arachis.pan1.4LN9
+identifier: Arachis.pan2.5P1K
 
 provenance: "The files in this directory are a product of the staff of the LegumeInfo, PeanutBase, and SoyBase project teams. The method is described here: https://github.com/legumeinfo/pandagma"
 
 source: "https://data.legumeinfo.org"
 
-synopsis: "Pangene set for Arachis species, based on A. hypogaea, A. duranensis, and A. ipaensis. This pangene set includes five annotation sets from A. hypogaea and one each from A. duranensis and A. ipaensis."
+synopsis: "Pangene set for Arachis species, based on A. hypogaea, A. duranensis, and A. ipaensis. This pangene set includes four annotation sets from A. hypogaea and one each from A. duranensis and A. ipaensis."
 
 scientific_name: Arachis
 
 taxid: 3826
 
 annotations_main:
   - arahy.BaileyII.gnm1.ann1
-  - arahy.Tifrunner.gnm1.ann1
   - arahy.Tifrunner.gnm1.ann2
   - arahy.Tifrunner.gnm2.ann1
   - arahy.Tifrunner.gnm2.ann2
@@ -22,30 +21,16 @@ annotations_extra:
   - aradu.V14167.gnm1.ann1
   - araip.K30076.gnm1.ann1
 
-description: "Pan-gene set for Arachis species, spanning 3 species and 6 annotation sets, calculated using the pandagma pipeline, version 2023-04-03"
+description: "Pan-gene set for Arachis species, spanning 3 species and 6 annotation sets, calculated using the pandagma pipeline, version 2023-09-15"
 
-bioproject: 
+original_file_creation_date: "2023-09-15"
 
-sraproject: 
+local_file_creation_date: "2023-09-15"
 
-dataset_doi: 
-
-genbank_accession: 
-
-original_file_creation_date: "2023-04-03"
-
-local_file_creation_date: "2023-04-03"
-
-dataset_release_date: "2023-04-03"
-
-publication_doi: 
-
-publication_title: 
+dataset_release_date: "2023-09-15"
 
 contributors: The International Peanut Genome Initiative and authors of all constituent genomes and annotations
 
-citation: 
-
 data_curators: Steven Cannon, Andrew Farmer
 
 public_access_level: public

Arachis/cardenasii/about_this_collection/description_Arachis_cardenasii.yml

@@ -5,7 +5,10 @@ species: cardenasii
 abbrev: araca
 commonName: Mani silvestre (wild peanut)
 description: "Arachis cardenasii Krapov. & W.C. Greg. is a wild peanut relative native to Bolivia. It has been used by peanut breeders and geneticists in interspecific hybrids with cultivated peanut (A. hypogaea) as a source of pest and disease resistance. A. cardenasii is a diploid  species in the 'A-genome' group of Arachis, similar to A. duranensis, which contributed one of the two subgenomes to tetraploid cultivated peanut."
-
+resources:
+  - name: Dowload at DS
+    URL: "https://data.legumeinfo.org/Arachis/cardenasii/"
+    description: "DataStore dir for Arachis cardenasii."
 strains:
   - identifier: K10017
     accession: PI 262141

Arachis/duranensis/about_this_collection/description_Arachis_duranensis.yml

@@ -5,10 +5,23 @@ species: duranensis
 abbrev: aradu
 commonName: diploid wild peanut - A-genome
 description: "Arachis duranensis, a wild herb native to Argentina, Bolivia, and Paraguay, is thought to be one of the diploid ancestors of cultivated peanut. Its genome has been sequenced as part of the Peanut Genomics Initiative, to help in the accurate assembly of the more important cultivated peanut, A. hypogaea. Cultivated peanut derived all of its genetic material from two wild ancestors, A. duranensis and A. ipaensis whose genomes merged several thousand years ago, in a rare genetic event. The wild species, therefore, have half as much genetic material as cultivated peanut. These two simpler genomes have first been sequenced toward achieving its ultimate goal: the complete genomic sequence for cultivated peanut. The cultivated peanut is an allotetraploid (2n=4x=40) that carries both the A and B genomes and A. duranensis (2n=2x=20) has likely contributed the A genome, the smaller set of chromosomes in the karyotype. These two ancestral diploids separated from each other about 3 million years ago. The genome merger, allopolyploidy event, ocurred relatively very recently, five to ten thousand years ago, followed by domestication in South America from where it appeared in most part of the world by 1600. Arachis duranensis is described further in Bertioli et al., 2016 (doi:10.1038/ng.3517)"
-
+resources:
+  - name: Dowload at DS
+    URL: "https://data.legumeinfo.org/Arachis/duranensis/"
+    description: "DataStore dir for Arachis duranensis."
 strains:
   - identifier: V14167
     accession: V14167
     name: V14167
     origin: Argentina, via USDA National Plant Germplasm Repository
     description: "Arachis duranensis strain V14167 originates in a region east of the Andes, in the vicinity of northern Argentina and southern Bolivia. This accession is thought to be one of the diploid ancestors of cultivated peanut. Its genome has been sequenced as part of the Peanut Genomics Initiative, to help in the accurate assembly of the more important cultivated peanut, A. hypogaea. This accession is described in Bertioli et al., 2016 (doi:10.1038/ng.3517)"
+    resources:
+      - name: Peanutbase Genome Browser (GBrowse)
+        URL: "https://legacy.peanutbase.org/gb2/gbrowse/Aradu1.0"
+        description: "GBrowse for V14167 assembly 1.0"
+      - name: Peanutbase Genome Browser (JBrowse)
+        URL: "https://legacy.peanutbase.org/genomes/jbrowse?data=Aradu1.0"
+        description: "JBrowse for V14167 assembly 1.0"
+      - name: "Genome assembly at NCBI"
+        URL: "http://www.ncbi.nlm.nih.gov/assembly/GCA_000817695.1/"
+        description: "Genome assembly at NCBI, V14167"