significant update

cli/specdb

@@ -97,10 +97,10 @@ sdb_query.add_argument('--db', type=str, metavar='<path>', required=True,
 	help=''.join((
 		('path to specific specdb database file to use.'),
 		(' use `specdb create` to create a new database file'))))
-sdb_query.add_argument('--out', type=str, metavar='<path>', required=True,
+sdb_query.add_argument('--out', type=str, metavar='<path>', required=False,
 	help='directory to place results of the query')
 sdb_query.add_argument('--indices', type=str, metavar='<str>', nargs='+',
-	required=False, default=False, help=''.join((
+	required=False, default=None, help=''.join((
 		("provide a list of row ids in the summary table to collect\n"),
 		("users can provide a list of ids directly on the command line space "),
 		("separated, or in a .csv file with all ids comma separated "),
@@ -184,10 +184,19 @@ elif sdb.command == 'summary':
 	Summary.summary(db=sdb.db, table=sdb.table)
 
 elif sdb.command == 'query':
+# 	print(sdb.indices)
+# 	print(type(sdb.indices))
+# 	print(sdb.sql)
+
+	if sdb.indices:
+		if len(sdb.indices) == 1:
+			if sdb.indices[0].endswith('.csv.'):
+				sdb.indices = str(sdb.indices[0])
+
 	Query.query(
 		db=sdb.db,
-		sql=sdb.sql[0],
-		indices=sdb.indices[0],
+		sql=str(sdb.sql[0]) if type(sdb.sql) == list else None,
+		indices=sdb.indices,
 		star=sdb.star,
 		output_dir=sdb.out)
 

sample/sample_forms/default.processing.yaml

@@ -0,0 +1,5 @@
+default_processing_scripts: # record a default nmrpipe processing script for every pulse sequence
+  0:
+    pulse_sequence_name: hsqcetgp                 #  name of pulse sequence, from Bruker it is the value of the PULPROG tag
+    nickname: 2D 1H-15N HSQC                      #  user provided nickname, references the pulse_sequence_nicknames table
+    default_processing: /Users/kfraga/RESEARCH/RPISpecDB/sample/sample_forms/default.processing.yaml #  path to text file of a nmrpipe processing script that read a FID for this pulse sequence type

sample/sample_forms/fid.com

@@ -0,0 +1,19 @@
+#!/bin/csh
+
+bruk2pipe -verb -in ./ser \
+  -bad 0.0 -ext -aswap -AMX -decim 1920 -dspfvs 20 -grpdly 67.9841918945312  \
+  -xN              2048  -yN               512  \
+  -xT              1024  -yT               256  \
+  -xMODE            DQD  -yMODE  Echo-AntiEcho  \
+  -xSW        10416.667  -ySW        15151.515  \
+  -xOBS         800.144  -yOBS         201.204  \
+  -xCAR           4.773  -yCAR          44.741  \
+  -xLAB              1H  -yLAB             13C  \
+  -ndim               2  -aq2D         Complex  \
+| nmrPipe -fn MULT -c 3.90625e+00 \
+  -out ./test.fid -ov
+
+#
+# nmrDraw -process -in test.fid -fid test.fid
+
+sleep 5

sample/sample_forms/sample.yaml

@@ -1,53 +1,53 @@
 target:                  # molecular target information, REQUIRED: `target_id`
   0:
     target_id: Db0515                             #  text identifier for target, must be unique, no spaces, len <= 32, Ex: Db0515
-    target_comment: ''                            #  free field comment, anything to note about target, len <= 128, Ex: from UW-Madison
+    target_comment:                               #  free field comment, anything to note about target, len <= 128, Ex: from UW-Madison
     target_sequence: MGPLIEVLA                    #  target's molecular seq., any type of code/alphabet, no spaces, len <= 1024, Ex: MGSHHHHILVAM
     organism_source: synthetic                    #  organism name for target source, can indicate if target is synthetic, len <= 128, Ex: synthetic
-    gene_name: ''                                 #  gene name, len <= 64, Ex: SpikeCoV2
+    gene_name:                                    #  gene name, len <= 64, Ex: SpikeCoV2
     project_id: DBh                               #  `project_id` target is a member of, must be in project table, Ex: SpikeFraga
     target_preparer: GTM                          #  `user_id` that assigned the target, must be in user table, Ex: KJF
-construct:               # molecular construct from a target, REQUIRED: `construct_id`, `construct_sequence`, `target_id`
+construct:               # molecular construct from a target, REQUIRED: `construct_id`,
   0:
     construct_id: Db0515A                         #  text identifier for construct, must be unique, no spaces, len <= 32, Ex: Db0515A
     construct_sequence: MGHHHHHHHSMGPLIEVLA       #  construct sequence, any type of code/alphabet, no spaces, len <= 1024, Ex: MGSHHHINLVAE
     target_id: Db0515                             #  `target id` this construct was made for, must already be in target table, Ex: Db0515
     ext_coefficient_280: 0.0                      #  extinction coefficient at 280 nm, Ex: 108.7
     expected_mw: 0.0                              #  expected molecular weight of construct in Da, Ex: 1211.8
-    construct_comment: ''                         #  free field comment, anything to note about construct, len <= 128, Ex: with primers RE1A/RE1B
-    plasmid_id: ''                                #  plasmid construct DNA sequence is cloned in, len <= 64, Ex: pET218(+)
-    plasmid_id_comment: ''                        #  comments on plasmid, len <= 256, Ex: from Underwood lab
+    construct_comment:                            #  free field comment, anything to note about construct, len <= 128, Ex: with primers RE1A/RE1B
+    plasmid_id:                                   #  plasmid construct DNA sequence is cloned in, len <= 64, Ex: pET218(+)
+    plasmid_id_comment:                           #  comments on plasmid, len <= 256, Ex: from Underwood lab
     construct_preparer: KJF                       #  `user_id` who prepared the construct, must already be in user table, Ex: KJF
-    construct_company: ''                         #  if the construct was produced by a company, indicate where it came from, len <= 128, Ex: Genscript
-expression:              # describe a molecular expression experiment/results, REQUIRED: `expression_id`, `construct_id`
+    construct_company:                            #  if the construct was produced by a company, indicate where it came from, len <= 128, Ex: Genscript
+expression:              # describe a molecular expression experiment/results, REQUIRED: `expression_id`
   0:
     expression_id: Db0515A                        #  text identifier for expression, must be unique, no spaces, len <= 32, Ex: Db0515A.X
-    expression_comment: ''                        #  free field comment, anything of note for expression, len <= 128, Ex: reached 4.5 OD
+    expression_comment:                           #  free field comment, anything of note for expression, len <= 128, Ex: reached 4.5 OD
     construct_id: Db0515A                         #  `construct_id` this expression was for, must already be in construct table, Ex: Db0515A
     expression_media: MJ9                         #  growth media expression was in, len <= 32, Ex: MJ9
-    strain: ''                                    #  cellular strain expression was in, len <= 32, Ex: BL21A (+)
-    expression_organism: ''                       #  organism expression was in, len <- 32, Ex: E. colli
+    strain:                                       #  cellular strain expression was in, len <= 32, Ex: BL21A (+)
+    expression_organism:                          #  organism expression was in, len <- 32, Ex: E. colli
     expression_preparer: TAR                      #  `user_id` of person who did the expression, must already be in user table, Ex: KJF
-purification_batch:      # describe the purification run for an expression product, REQUIRED: `batch_id`, `expression_id`, `sample_sequence`
+purification_batch:      # describe the purification run for an expression product, REQUIRED: `batch_id`
   0:
     batch_id: Db0515A                             #  text identifier for batch, must be unique, no spaces, len <= 32, Ex: Db0515.X.batch
     expression_id: Db0515A                        #  expression run this purification batch is for, must already be in expression table Ex: Db0515.X
     sample_sequence: GPLIEVLA                     #  sequence of molecule after purification (i.e if there was tag cleaving), any type of code/alphabet, no spaces, len <= 1024, Ex: MQNGPILA
-    purif_comment: ''                             #  free text comment about the purification, len <= 128, Ex: HPLC in RM 204
+    purif_comment:                                #  free text comment about the purification, len <= 128, Ex: HPLC in RM 204
     production_method: Ni column                  #  indicate the purification method, len <= 64, Ex: Ni column only
     isotopic_labeling_remark: NC                  #  provide the isotopic labeling, preferred method to indicate labeling in the appropriate column below, len <= 64, Ex: NC5
-    iso_13c_enrichment: ''                        #  13C labeling percentage, must contain `% 13C`, len <= 32, Ex: 100% 13C
-    iso_15n_enrichment: ''                        #  15N labeling percentage, must contain `% 15N`, len <= 32, Ex: 99% 15N
-    iso_2h_enrichment: ''                         #  2H labeling percentage, must contain `% 2H`, len <= 32, Ex: 100% 2H
-    iso_19f_Trp_enrichment: ''                    #  19F-Trp labeling percentage, must contain `% 19F-Trp`, len <= 32, Ex: 11% 19F-Trp
-    iso_19f_Phe_enrichment: ''                    #  19F-Phe labeling percentage, must contain `% 19F-Phe`, len <= 32, Ex: 9.1% 19F-Phe
-    iso_1hd1_Leu_methyl_enrichment: ''            #  1HD1-Leu stereospecific labeling percentage, must contain `% 1HD1-Leu`, len <= 32, Ex: 13.3% 1HD1-Leu
-    iso_1hd2_Leu_methyl_enrichment: ''            #  1HD2-Leu stereospecific labeling percentage, must contain `% 1HD2-Leu`, len <= 32, Ex: 15% 1HD2-Leu
-    iso_1hd_Ile_methyl_enrichment: ''             #  1HD-Ile labeling percentage, must contain `% 1HD-Ile`, len <= 32, Ex: 50% 1HD-Ile
-    iso_1hg1_Val_methyl_enrichment: ''            #  1HG1-Val stererospecific labeling percentage, must contain `% 1HG1-Val`, len <= 32, Ex: 25% 1HG1-Val
-    iso_1hg2_Val_methyl_enrichment: ''            #  1HG2-Val stereospecific labeling percentage, must contain `% 1HG2-Val`, len <= 32, Ex: 27%% 1HG2-Val
-    iso_1hb_Ala_methyl_enrichment: ''             #  1HB-Ala labeling percentage, must contain `% 1HB-Ala`, len <= 32, Ex: 100% 1HB-Ala
-    batch_preparer: ''                            #  `user_id` of person who did the purification, must already be in user table, Ex: KJF
+    iso_13c_enrichment:                           #  13C labeling percentage, must contain `% 13C`, len <= 32, Ex: 100% 13C
+    iso_15n_enrichment:                           #  15N labeling percentage, must contain `% 15N`, len <= 32, Ex: 99% 15N
+    iso_2h_enrichment:                            #  2H labeling percentage, must contain `% 2H`, len <= 32, Ex: 100% 2H
+    iso_19f_Trp_enrichment:                       #  19F-Trp labeling percentage, must contain `% 19F-Trp`, len <= 32, Ex: 11% 19F-Trp
+    iso_19f_Phe_enrichment:                       #  19F-Phe labeling percentage, must contain `% 19F-Phe`, len <= 32, Ex: 9.1% 19F-Phe
+    iso_1hd1_Leu_methyl_enrichment:               #  1HD1-Leu stereospecific labeling percentage, must contain `% 1HD1-Leu`, len <= 32, Ex: 13.3% 1HD1-Leu
+    iso_1hd2_Leu_methyl_enrichment:               #  1HD2-Leu stereospecific labeling percentage, must contain `% 1HD2-Leu`, len <= 32, Ex: 15% 1HD2-Leu
+    iso_1hd_Ile_methyl_enrichment:                #  1HD-Ile labeling percentage, must contain `% 1HD-Ile`, len <= 32, Ex: 50% 1HD-Ile
+    iso_1hg1_Val_methyl_enrichment:               #  1HG1-Val stererospecific labeling percentage, must contain `% 1HG1-Val`, len <= 32, Ex: 25% 1HG1-Val
+    iso_1hg2_Val_methyl_enrichment:               #  1HG2-Val stereospecific labeling percentage, must contain `% 1HG2-Val`, len <= 32, Ex: 27%% 1HG2-Val
+    iso_1hb_Ala_methyl_enrichment:                #  1HB-Ala labeling percentage, must contain `% 1HB-Ala`, len <= 32, Ex: 100% 1HB-Ala
+    batch_preparer:                               #  `user_id` of person who did the purification, must already be in user table, Ex: KJF
 pst:                     # description of a protein sample tube, not only proteins, REQUIRED: `pst_id`, `pst_preparer`, `sample_ph`, `total_volume`, `volume_unit`, `tube_type`
   0:
     pst_id: Db0515A.000                           #  text identifier for the pst, must be unique, no spaces, len <= 32, Ex: Db0515A.001

sample/sample_sessions/example1/specdb.session.yaml

@@ -0,0 +1,16 @@
+session:                 # describe a data collection session, REQUIRED: pst_id (if not none, just use 'NONE')
+  0:
+    session_preparer: TAR                         #  `user_id` of the person who prepared and collected the session, must already be in user table, Ex: KJF
+    spectrometer_id: Hu800                        #  `spectrometer_id` session was collected at, must already be in spectrometer table, Ex: Hu800
+    pst_id: Db0515A.000                           #  `pst_id` the session is for
+time_domain_dataset:     # record information about a time domain dataset, REQUIRED: `subdir_name`
+  0:
+    subdir_name: '1'                              #  path to where fid/ser file is, can be a relative path, len <= 128, Ex: 1/
+    pst_id: Db0515A.000                           #  `pst_id` of sample, must already be in pst table, Ex: Db0515.001
+    pulse_sequence_nickname:                      #  nickname for pulse sequence, controlled vocabulary
+    probe_id:                                     #  `probe_id` for the probe, if blank probe information pulled from fid directory
+  1:
+    subdir_name: '2'                              #  path to where fid/ser file is, can be a relative path, len <= 128, Ex: 1/
+    pst_id: Db0515A.000                           #  `pst_id` of sample, must already be in pst table, Ex: Db0515.001
+    pulse_sequence_nickname:                      #  nickname for pulse sequence, controlled vocabulary
+    probe_id:                                     #  `probe_id` for the probe, if blank probe information pulled from fid directory