revise README for mappings for 01182017 update

Author: ningyifan

.gitignore

@@ -2,4 +2,9 @@
 .DS_Store
 *.lock
 *.log
-linkedSPLs/LinkedSPLs-activeMoiety/activeMoietySub-in-rdf.xml
+linkedSPLs/LinkedSPLs-activeMoiety/activeMoietySub-in-rdf.xml
+LinkedSPLs-clinicalDrug/clinicalDrugSub-in-rdf.xml
+LinkedSPLs-update/data/
+LinkedSPLs-update/load-dailymed-spls/problematic-spls/
+LinkedSPLs-update/mappings/FDA-pharmacogenetic-info-mapping/cached-table-downloads/
+LinkedSPLs-update/mappings/PT-UNII-ChEBI-mapping/ChEBIJavaClient/bin/

linkedSPLs/LinkedSPLs-update/mappings/DrOn-to-RxNorm/README

@@ -26,7 +26,7 @@ SELECT * WHERE {   ?dron obo:DRON_00010000 ?rxcui. }' > dron-rxcui-drug.txt
 
 (1) run python script to clean the data
 
-$ python cleanData.py > cleaned_dron-to-chebi-and-rxnorm-07232014.txt
+$ python cleanData.py > cleaned_dron-to-chebi-and-rxnorm-<DATE>.txt
 
 outputs: <dron_id>|<chebi_id>|<rxcui>
 
@@ -63,7 +63,7 @@ CREATE TABLE `DrOn_ChEBI_RXCUI_INGREDIENT` (
 
 $ mysql -u root -p --local-infile linkedSPLs
 
-LOAD DATA LOCAL INFILE './cleaned_dron-to-chebi-and-rxnorm-07232014.txt' INTO TABLE `DrOn_ChEBI_RXCUI_DRUG`  FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n' (dron_id, ChEBI, rxcui);
+LOAD DATA LOCAL INFILE './cleaned_dron-to-chebi-and-rxnorm-<DATE>.txt' INTO TABLE `DrOn_ChEBI_RXCUI_DRUG`  FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n' (dron_id, ChEBI, rxcui);
 
 
 (4) get dron and drugbank mapping by query Mysql schema

linkedSPLs/LinkedSPLs-update/mappings/FDA-pharmacogenetic-info-mapping/README

@@ -1,14 +1,4 @@
-TODO (4/04/2014)
-
-- drop  FDAPharmgxTable and then recreate and reload the table per the instructions in ../README
-
-- drop FDAPharmgxTableToOntologyMap and then recreate and reload the table per the instructions in ../README
-
-- revise the D2R mapping file to reflect changes to table's schema: 1) biomarker in FDAPharmgxTable is now a foreign key to HGNCGeneSymbol in FDAPharmgxTableToOntologyMap; 2) FDAString in FDAPharmgxTableToOntologyMap is now FDAReferencedSubgroup, 3) there are new therapeuticApplication instances that need to be mapped to NCIT
-
------
-
-Workflow (as of 04/04/2014):
+Workflow (as of 01/18/2017):
 
 1) Data from the FDA's pharmacogenomic biomarker table
  <http://www.fda.gov/Drugs/ScienceResearch/ResearchAreas/Pharmacogenetics/ucm083378.htm>

linkedSPLs/LinkedSPLs-update/mappings/PT-UNII-ChEBI-mapping/README

@@ -6,17 +6,18 @@ How to update mappings of ChEBI and FDA preferred term - Table: FDA_UNII_to_ChEB
 mappings/PT-UNII-ChEBI-mapping/ChEBIJavaClient
 
 Input: FDA prefered term
-Output: Mappings of UNII to ChEBI, save to UNIIToChEBI.txt (7601 by 06/10/2016)
-
+Output: Mappings of UNII to ChEBI, save to UNIIToChEBI.txt
 
+(7953 by 01/18/2017)
+(7601 by 06/10/2016)
 
 --------------------------------------------------------------------------------
 Deprecated below - Overview 
 --------------------------------------------------------------------------------
 
 This folder has a mapping between FDA UNIIs and ChEBI PURLs created using the
 Python script and the NCBO Bioportal's SPARQL endpoint. The UNII entities 
-and identifiers came from the FDA on 06/27/2014.
+and identifiers came from the FDA on 01/18/2017.
 
 The script 'getChebiMappingsFromJSON.py' was ran to identify all
 entities in ChEBI as recorded in Bioportal with an uppercase label
@@ -32,40 +33,40 @@ Tip: backup mysql tables before truncate its
 
 UPDATE FDAPreferredSubstanceToUNII
 
-(1)download UNIIS 27Jun2014 Names.txt from repository swat-4-med-safety
+(1)download UNIIS_<DATE>_Names.txt from repository swat-4-med-safety
 
 (2)slice data by linux shell command: 
-cat ../Data_Source/FDA/UNIIS\ 27Jun2014\ Names.txt | cut -f 1,3 | sort > /PATH/TO/FDAPreferredSubstanceToUNII_10202014.txt
-output column 1 as preferred terms and synonymns, and column 3 as UNII to FDAPreferredSubstanceToUNII_10202014.txt
+cat ../Data_Source/FDA/UNIIS_<DATE>_Names.txt | cut -f 1,3 | sort > /PATH/TO/FDAPreferredSubstanceToUNII_<DATE>.txt
+output column 1 as preferred terms and synonymns, and column 3 as UNII to FDAPreferredSubstanceToUNII_<DATE>.txt
 
-(3)import data in FDAPreferredSubstanceToUNII_10202014.txt to mysql table FDAPreferredSubstanceToUNII
+(3)import data in FDAPreferredSubstanceToUNII_<DATE>.txt to mysql table FDAPreferredSubstanceToUNII
 
 command in shell:
 mysql -u root -p --local-infile linkedSPLs
-LOAD DATA LOCAL INFILE "/PATH/TO/FDAPreferredSubstanceToUNII_10202014.txt" INTO TABLE FDAPreferredSubstanceToUNII(PreferredSubstance, UNII);
+LOAD DATA LOCAL INFILE "/PATH/TO/FDAPreferredSubstanceToUNII_<DATE>.txt" INTO TABLE FDAPreferredSubstanceToUNII(PreferredSubstance, UNII);
 
 UPDATE FDA_UNII_to_ChEBI
 
 (1) run script 'getChebiMappingsFromJSON.py' to get mappings of of preferred term and ChEBI by command:
 
-$ python getChebiMappingsFromJSON.py > UNIIToChEBI-10302014.txt
+$ python getChebiMappingsFromJSON.py > UNIIToChEBI-<DATE>.txt
 
-(3)import data in UNIIToChEBI-10302014.txt to RDB table FDA_UNII_to_ChEBI
+(3)import data in UNIIToChEBI-<DATE>.txt to RDB table FDA_UNII_to_ChEBI
 
 $ mysql -u root -p --local-infile linkedSPLs
 
-LOAD DATA LOCAL INFILE "/PATH/TO/UNIIToChEBI-10302014.txt/FDA_UNII_to_ChEBI_10202014.txt" INTO TABLE FDA_UNII_to_ChEBI(PreferredSubstance, ChEBI);
+LOAD DATA LOCAL INFILE "/PATH/TO/UNIIToChEBI-<DATE>.txt/FDA_UNII_to_ChEBI_<DATE>.txt" INTO TABLE FDA_UNII_to_ChEBI(PreferredSubstance, ChEBI);
 
 --------------------------------------------------------------------------------
 --How to merge original UNIIs data with UNIIs type including column SY, SN, CD
 --------------------------------------------------------------------------------
 
 run the python script to merge:
 
-$ python mergeUNIIsNamesWithRecords.py > mergedUNIIs-07282014.txt
+$ python mergeUNIIsNamesWithRecords.py > mergedUNIIs-<DATE>.txt
 
-inputs: ../Data_Source/FDA/UNIIs 27Jun2014 Records.txt
-	../Data_Source/FDA/UNIIS 25Jan2014 Names.txt
+inputs: ../Data_Source/FDA/UNIIs_<DATE>_Records.txt
+	../Data_Source/FDA/UNIIS_<DATE>_Names.txt
 
 outputs: tsv file have columns: 
 

linkedSPLs/LinkedSPLs-update/mappings/pharmacologic_class_indexing/README

@@ -1,4 +1,8 @@
-This data, totally 9479, is up to date with all current SPLs as of March 20 2014.
+
+For all current SPLs
+9479 by March 20 2014,
+9607 by June 10 2016,
+9887 by Jan 18 2017
 
 (1) To update, get the most current SPL class mappings from Dailymed, unzip
 the file into the /pharmacologic_class_indexing_spl_files/ folder.