Author: ketan
Date: 2013-09-10 10:19:56 -0500 (Tue, 10 Sep 2013)
New Revision: 7049
Added:
SwiftApps/gocat/psql.txt
SwiftApps/gocat/taglocate.README
Modified:
SwiftApps/gocat/catalog.swift
SwiftApps/gocat/test.sh
Log:
add readme, psql
Modified: SwiftApps/gocat/catalog.swift
===================================================================
--- SwiftApps/gocat/catalog.swift 2013-09-09 20:16:06 UTC (rev 7048)
+++ SwiftApps/gocat/catalog.swift 2013-09-10 15:19:56 UTC (rev 7049)
@@ -8,8 +8,8 @@
get_tags catalog_id dataset_id tag_args stdout=@tags stderr=@err;
}
-app (file datasets, file err) tag_cmd (string catalogid){
- tag_dataset catalogid stdout=@datasets stderr=@err;
+app (file out, file err) tag_cmd (string tagargs){
+ tag_dataset tagargs stdout=@out stderr=@err;
}
app (file tags) locate_cmd (string tag_args){
@@ -25,3 +25,8 @@
tracef("f[%i]: mapped to: %s\n", i, @f);
}
+file tagout<"tagout.txt">;
+file tagerr<"tagerr.txt">;
+
+(tagout, tagerr)=tag_cmd("/home/maheshwari/gocat owner=maheshwari group=swift create-date=2013.0910.10:45:12:211");
+
Added: SwiftApps/gocat/psql.txt
===================================================================
--- SwiftApps/gocat/psql.txt (rev 0)
+++ SwiftApps/gocat/psql.txt 2013-09-10 15:19:56 UTC (rev 7049)
@@ -0,0 +1,2 @@
+psql -U provdb -h swift.rcc.uchicago.edu provdb -c "\d+ annot_dataset_text"
+psql -U provdb -h swift.rcc.uchicago.edu provdb -c "select dataset_id from annot_dataset_text"
Added: SwiftApps/gocat/taglocate.README
===================================================================
--- SwiftApps/gocat/taglocate.README (rev 0)
+++ SwiftApps/gocat/taglocate.README 2013-09-10 15:19:56 UTC (rev 7049)
@@ -0,0 +1,701 @@
+
+*** Metadata/Provenance prototype
+
+A prototype/testbed database is now running (on swift.rcc.uchicago.edu) for metadata and provenance.
+
+====
+
+To access the metadata database:
+
+module load postresql # Using 9.2 but earlier versions will likelik work for metadata
+PATH=/home/wilde/swift/provenancedb:/home/wilde/swift/provwork:/home/wilde/pgsql/bin:$PATH
+
+
+# create a file "$HOME/.pgpass" set to mode 600, with these 2 lines:
+
+swift.rcc.uchicago.edu:5432:provdb:provdb:sesame
+db:5432:provdb:provdb:sesame
+
+
+====
+
+Below are some example queries.
+
+I suspect you can try this shortly if you have time and interest.
+
+- Mike
+
+
+At the moment you add metadata like so:
+
+tag /d1/d2/f3 owner=asinitskiy group=cmts-chem create-date=2013.0415.12:20:29.456 type=trajectory-namd \
+ state=pubished note="trajectory for case 1" molecule=1ubq domain=loop7 bead=px
+...
+tag /d1/d2/f0 owner=jdama group=cmts-chem create-date=2013.0412.12:20:29.456 type=trajectory-namd \
+ state=pubished note="trajectory for case 1" molecule=4ubq domain=loop1 bead=px
+
+...and query like this:
+
+mid$ ./locate-test01.sh
+
+ Query ==> owner=wilde
+
+
+ dataset_id | name | value
+------------+-------------+--------------------------------------------------
+
+ /d1/d2/f1 | owner | wilde
+ | group | cmts-cyber
+ | create-date | 2013.0123.23:07:29.123
+ | type | pdb
+ | state | unverified
+ | note | Initial structure prediction from loop model. mw
+
+ /d1/d2/f7 | owner | wilde
+ | group | cmts-chem
+ | create-date | 2013.0419.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop3
+ | bead | px
+
+ /d1/d2/f8 | owner | wilde
+ | group | cmts-chem
+ | create-date | 2013.0410.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop3
+ | bead | px
+
+(24 rows)
+
+
+
+ Query ==> (owner=asinitskiy) or (owner=msaunders)
+
+
+ dataset_id | name | value
+------------+-------------+------------------------
+
+ /d1/d2/f2 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0414.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop7
+ | bead | px
+
+ /d1/d2/f3 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0415.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop7
+ | bead | px
+
+ /d1/d2/f4 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0416.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop7
+ | bead | dt
+
+ /d1/d2/f6 | owner | msaunders
+ | group | cmts-chem
+ | create-date | 2013.0418.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop7
+ | bead | an
+
+(36 rows)
+
+
+
+ Query ==> (owner=asinitskiy) and (molecule=2ubq)
+
+
+ dataset_id | name | value
+------------+-------------+------------------------
+
+ /d1/d2/f4 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0416.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop7
+ | bead | dt
+
+(9 rows)
+
+
+mid$
+
+mid$ locate '*'
+
+ dataset_id | name | value
+------------+-------------+--------------------------------------------------
+
+ /d1/d2/f1 | owner | wilde
+ | group | cmts-cyber
+ | create-date | 2013.0123.23:07:29.123
+ | type | pdb
+ | state | unverified
+ | note | Initial structure prediction from loop model. mw
+
+ /d1/d2/f2 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0414.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop7
+ | bead | px
+
+ /d1/d2/f3 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0415.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop7
+ | bead | px
+
+ /d1/d2/f4 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0416.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop7
+ | bead | dt
+
+ /d1/d2/f5 | owner | jgrime
+ | group | cmts-chem
+ | create-date | 2013.0417.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop7
+ | bead | xy
+
+ /d1/d2/f6 | owner | msaunders
+ | group | cmts-chem
+ | create-date | 2013.0418.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop7
+ | bead | an
+
+ /d1/d2/f7 | owner | wilde
+ | group | cmts-chem
+ | create-date | 2013.0419.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop3
+ | bead | px
+
+ /d1/d2/f8 | owner | wilde
+ | group | cmts-chem
+ | create-date | 2013.0410.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop3
+ | bead | px
+
+ /d1/d2/f9 | owner | fvazquez
+ | group | cmts-chem
+ | create-date | 2013.0411.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 3ubq
+ | domain | loop2
+ | bead | px
+
+ /d1/d2/f0 | owner | jdama
+ | group | cmts-chem
+ | create-date | 2013.0412.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 4ubq
+ | domain | loop1
+ | bead | px
+
+(87 rows)
+
+###
+
+The commands have no provision yet for changing data or adding data thats already there. Just try queries (locate) for now.
+
+I almost have ready a script that will take a csv version of your dataset spreadsheet (firsttab) and add records.
+
+====
+
+Hi Anton,
+
+The first worksheet (only) is in the database now, with a few adjustments:
+
+- I used the folder name as the dataset key
+
+- I omitted the replica location field for now: need to adjust a few things to add the same tag twice on an object
+
+- I used all lower case tag names; I need to work on upper-loca case issues. For now, case of both keys and values must, I think, match, unless you use "like" instead of = in the locate query.
+
+- I broke up the dataset location into a servername, "collection name", and folder name.
+
+- The machine name field got goofed up as you will see in the database; dont use it till I fix it.
+
+- I omitted commas and hence quotes from the comment fields.
+
+Check the field names: I might have made a few other changes.
+
+you should be able to see all the data by using the query:
+
+ locate '*' # must use ' ' around the * !
+
+I also paste the data below but it might get chopped up by email.
+
+- Mike
+
+====
+
+expect that you will get some errors from your queries, in part because my parser is still quite crude and not robust.
+
+Use parens () as in the examples. Send me any errors that you encounter, including the input query, the echoed SQL, and the error message.
+
+- Mike
+
+ps I think I will try to soon make the "tag" command contain all the needed query and update interfaces:
+
+tag add
+tag update
+tag remove
+tag find
+tag ...etc
+
+===
+
+
+mid$ locate '*'
+
+select * from annot_dataset_text where dataset_id in ((select distinct dataset_id from annot_dataset_text));
+
+ dataset_id | name | value
+--------------------------------------------------------------+--------------------------+----------------------------------------------------------------------------------------------------------------
+
+ /d1/d2/f1 | owner | wilde
+ | group | cmts-cyber
+ | create-date | 2013.0123.23:07:29.123
+ | type | pdb
+ | state | unverified
+ | note | Initial structure prediction from loop model. mw
+
+ /d1/d2/f2 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0414.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop7
+ | bead | px
+
+ /d1/d2/f3 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0415.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop7
+ | bead | px
+
+ /d1/d2/f4 | owner | asinitskiy
+ | group | cmts-chem
+ | create-date | 2013.0416.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop7
+ | bead | dt
+
+ /d1/d2/f5 | owner | jgrime
+ | group | cmts-chem
+ | create-date | 2013.0417.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop7
+ | bead | xy
+
+ /d1/d2/f6 | owner | msaunders
+ | group | cmts-chem
+ | create-date | 2013.0418.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop7
+ | bead | an
+
+ /d1/d2/f7 | owner | wilde
+ | group | cmts-chem
+ | create-date | 2013.0419.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 1ubq
+ | domain | loop3
+ | bead | px
+
+ /d1/d2/f8 | owner | wilde
+ | group | cmts-chem
+ | create-date | 2013.0410.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 2ubq
+ | domain | loop3
+ | bead | px
+
+ /d1/d2/f9 | owner | fvazquez
+ | group | cmts-chem
+ | create-date | 2013.0411.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 3ubq
+ | domain | loop2
+ | bead | px
+
+ /d1/d2/f0 | owner | jdama
+ | group | cmts-chem
+ | create-date | 2013.0412.12:20:29.456
+ | type | trajectory-namd
+ | state | pubished
+ | note | trajectory for case 1
+ | molecule | 4ubq
+ | domain | loop1
+ | bead | px
+
+ /sinitskiy/home/Ribosome.tar.gz | title | ribosome
+ | author | sinitskiy
+ | datestart | 3/21/11
+ | dateend | 3/22/11
+ | machinemakena |
+ | software | bash
+ | script |
+ | softwareversion | included
+ | in |
+ | the |
+ | folder |
+ | sizemb | 42984
+ | server | makena
+ | collection | /project/votharchive
+ | standardformatsubfolders | no
+ | pdbcode | n/a
+ | straightforwardmd | no
+ | cgsimulations | no
+ | forcefield | n/a
+ | monomersnumber | n/a
+ | replicasnumber | 1
+ | totallengthns | 100
+ | papers | SSV12
+ | comment | brute force MD trajectory of E. Coli ribosome from K. Sanbonmatsu converted to xyz format with only CA/P atoms
+
+ /sinitskiy/junction_actin.tar.gz | title | Arp2/3
+ | junction |
+ | author | sinitskiy
+ | datestart | 5/9/11
+ | dateend | 7/7/11
+ | machinemakena |
+ | software | edcg-space
+ | softwareversion | n/a
+ | sizemb | 1299
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /sinitskiy/junction_actin.tar.gz
+ | standardformatsubfolders | no
+ | pdbcode | n/a
+ | straightforwardmd | no
+ | cgsimulations | no
+ | forcefield | n/a
+ | monomersnumber | n/a
+ | replicasnumber | 1
+ | totallengthns | 100
+ | papers | SSV12
+ | comment | number of CG sites in different parts of Arp2/3 junction
+
+ /sinitskiy/ribosome.tar.gz | title | ribosome
+ | author | sinitskiy
+ | datestart | 3/22/11
+ | dateend | 8/5/11
+ | machinemakena |
+ | software | edcg-space
+ | softwareversion | n/a
+ | sizemb | 6966
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /sinitskiy/ribosome.tar.gz
+ | standardformatsubfolders | no
+ | pdbcode | n/a
+ | straightforwardmd | no
+ | cgsimulations | no
+ | forcefield | n/a
+ | monomersnumber | n/a
+ | replicasnumber | 1
+ | totallengthns | 100
+ | papers | SSV12
+ | comment | number of CG sites in different parts of E. Coli ribosome
+
+ /sinitskiy/actin.tar.gz | title | G-actin
+ | author | sinitskiy
+ | datestart | 7/11/11
+ | dateend | 8/25/11
+ | machinemakena |
+ | software | edcg-space
+ | softwareversion | n/a
+ | sizemb | 274
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /sinitskiy/actin.tar.gz
+ | standardformatsubfolders | no
+ | pdbcode | n/a
+ | straightforwardmd | no
+ | cgsimulations | no
+ | forcefield | n/a
+ | monomersnumber | 1
+ | replicasnumber | 6
+ | totallengthns | 42
+ | papers | SSV12
+ | comment | number of CG sites in G-actin - chi2 vs N_CG
+
+ /sinitskiy/ubiquitin_allatom.tar.gz | title | ubiquitin
+ | author | sinitskiy
+ | datestart | 7/31/11
+ | dateend | 8/15/11
+ | machinemakena |
+ | software | edcg-space
+ | softwareversion | n/a
+ | sizemb | 207
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /sinitskiy/ubiquitin_allatom.tar.gz
+ | standardformatsubfolders | no
+ | pdbcode | 1UBQ
+ | straightforwardmd | no
+ | cgsimulations | no
+ | forcefield | n/a
+ | monomersnumber | 1
+ | replicasnumber | 3
+ | totallengthns | 100
+ | papers | SSV12
+ | comment | Number of CG sites in ubiquitin - chi2 vs N_CG
+
+ /sinitskiy/lysozyme.tar.gz | title | lysozyme
+ | author | sinitskiy
+ | datestart | 7/9/11
+ | dateend | 7/10/11
+ | machinemakena |
+ | software | edcg-space
+ | softwareversion | n/a
+ | sizemb | 6166
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /sinitskiy/lysozyme.tar.gz
+ | standardformatsubfolders | no
+ | pdbcode | 3LZT
+ | straightforwardmd | no
+ | cgsimulations | no
+ | forcefield | n/a
+ | monomersnumber | 1
+ | replicasnumber | 3
+ | totallengthns | 100
+ | papers | SSV12
+ | comment | Nnumber of CG sites in lysozyme - chi2 vs N_CG; also includes some preparatory data for SV_CP13
+
+ /sinitskiy/pyruvatekinase.tar.gz | title | pyruvate
+ | kinase |
+ | author | sinitskiy
+ | datestart | 7/10/11
+ | dateend | 8/23/11
+ | machinemakena |
+ | software | edcg-space
+ | softwareversion | n/a
+ | sizemb | 280
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /sinitskiy/pyruvatekinase.tar.gz
+ | standardformatsubfolders | no
+ | pdbcode | 1PKL
+ | straightforwardmd | no
+ | cgsimulations | no
+ | forcefield | n/a
+ | monomersnumber | 1
+ | replicasnumber | 3
+ | totallengthns | 100
+ | papers | SSV12
+ | comment | Number of CG sites in pyruvate kinase - chi2 vs N_CG
+
+ /sinitskiy/lysozyme_namd/kraken5 | title | lysozyme
+ | author | sinitskiy
+ | datestart | 2/17/12
+ | dateend | 3/12/12
+ | machinekraken |
+ | software | NAMD
+ | softwareversion | 2.8
+ | sizemb | 446605
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /sinitskiy/lysozyme_namd/kraken5
+ | standardformatsubfolders | no
+ | pdbcode | 3LZT
+ | straightforwardmd | yes
+ | cgsimulations | no
+ | forcefield | par_all27_prot_lipid.inp
+ | monomersnumber | 1
+ | replicasnumber | 1
+ | totallengthns | 64
+ | papers | SV_CP13
+ | comment |
+
+ /sinitskiy/lysozyme_namd/kraken6 | title | lysozyme
+ | author | sinitskiy
+ | datestart | 2/18/12
+ | dateend | 3/12/12
+ | machinekraken |
+ | software | NAMD
+ | softwareversion | 2.8
+ | sizemb | 446910
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /sinitskiy/lysozyme_namd/kraken6
+ | standardformatsubfolders | no
+ | pdbcode | 3LZT
+ | straightforwardmd | yes
+ | cgsimulations | no
+ | forcefield | par_all27_prot_lipid.inp
+ | monomersnumber | 1
+ | replicasnumber | 1
+ | totallengthns | 64
+ | papers | SV_CP13
+ | comment |
+
+ /jlbaker/from_pads/research/data/3i5g_am_system/prod/ | title | actomyosin
+ | author | jlbaker
+ | datestart | 6/18/12
+ | dateend | 6/25/12
+ | machinebeagle |
+ | software | NAMD
+ | softwareversion | 2.8
+ | sizemb | 284108
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /jlbaker/from_pads/research/data/3i5g_am_system/prod/
+ | standardformatsubfolders | no
+ | pdbcode | n/a
+ | straightforwardmd | yes
+ | cgsimulations | no
+ | forcefield | par_CMAP.inpf
+ | monomersnumber | n/a
+ | replicasnumber | 1
+ | totallengthns | 24
+ | papers | BV13
+ | comment | 3i5g actomyosin
+
+ /jlbaker/from_pads/research/data/3i5g_am_system/prod_beagle/ | title | actomyosin
+ | author | jlbaker
+ | datestart | 6/15/12
+ | dateend | 7/11/12
+ | machinebeagle |
+ | software | NAMD
+ | softwareversion | 2.8
+ | sizemb | 410151
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /jlbaker/from_pads/research/data/3i5g_am_system/prod_beagle/
+ | standardformatsubfolders | no
+ | pdbcode | n/a
+ | straightforwardmd | yes
+ | cgsimulations | no
+ | forcefield | par_CMAP.inpf
+ | monomersnumber | n/a
+ | replicasnumber | 1
+ | totallengthns | 80
+ | papers | BV14
+ | comment | 3i5g actomyosin
+
+ /jlbaker/from_pads/research/data/3i5g_myosinS1_model/prod/ | title | actomyosin
+ | author | jlbaker
+ | datestart | 6/18/12
+ | dateend | 7/11/12
+ | machinegrotthuss |
+ | software | NAMD
+ | softwareversion | 2.9
+ | sizemb | 249601
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /jlbaker/from_pads/research/data/3i5g_myosinS1_model/prod/
+ | standardformatsubfolders | no
+ | pdbcode | n/a
+ | straightforwardmd | yes
+ | cgsimulations | no
+ | forcefield | par_CMAP.inpf
+ | monomersnumber | n/a
+ | replicasnumber | 1
+ | totallengthns | 70
+ | papers | BV14
+ | comment | 3i5g actomyosin
+
+ /jlbaker/from_pads/research/data/3i5f_myosinS1_model/prod/ | title | actomyosin
+ | author | jlbaker
+ | datestart | 6/18/12
+ | dateend | 7/11/12
+ | machinegrotthuss |
+ | software | NAMD
+ | softwareversion | 2.9
+ | sizemb | 277334
+ | server | makena
+ | collection | /project/votharchive
+ | folder | /jlbaker/from_pads/research/data/3i5f_myosinS1_model/prod/
+ | standardformatsubfolders | no
+ | pdbcode | n/a
+ | straightforwardmd | yes
+ | cgsimulations | no
+ | forcefield | par_CMAP.inpf
+ | monomersnumber | n/a
+ | replicasnumber | 1
+ | totallengthns | 80
+ | papers | BV14
+ | comment | 3i5g actomyosin
+
+
Modified: SwiftApps/gocat/test.sh
===================================================================
--- SwiftApps/gocat/test.sh 2013-09-09 20:16:06 UTC (rev 7048)
+++ SwiftApps/gocat/test.sh 2013-09-10 15:19:56 UTC (rev 7049)
@@ -1 +1,2 @@
swift -tc.file apps -sites.file sites.local.xml catalog.swift -ds='run like 3'
+swift -tc.file apps -sites.file sites.local.xml catalog.swift -ds='owner=wilde'