Mercurial > repos > dchristiany > data_manager_proteore
changeset 15:83f57ba70416 draft
planemo upload commit 8040003119a3d54866ec6ee9b9f659f2af554817-dirty
| author | dchristiany |
|---|---|
| date | Tue, 15 Jan 2019 04:29:28 -0500 |
| parents | f8ed6fc5f3ae |
| children | 454c2e2984ea |
| files | data_manager/resource_building.py data_manager/resource_building.xml data_manager_conf.xml tool-data/proteore_biogrid_dictionaries.loc.sample tool-data/proteore_bioplex_dictionaries.loc.sample tool-data/proteore_id_mapping.loc.sample tool-data/proteore_id_mapping_dictionaries.loc.sample tool_data_table_conf.xml.sample |
| diffstat | 8 files changed, 284 insertions(+), 56 deletions(-) [+] |
line wrap: on
line diff
--- a/data_manager/resource_building.py Fri Jan 04 06:11:49 2019 -0500 +++ b/data_manager/resource_building.py Tue Jan 15 04:29:28 2019 -0500 @@ -2,7 +2,7 @@ The purpose of this script is to create source files from different databases to be used in other proteore tools """ -import os, sys, argparse, requests, time, csv, re +import os, sys, argparse, requests, time, csv, re, json, zipfile, shutil from io import BytesIO from zipfile import ZipFile from galaxy.util.json import from_json_string, to_json_string @@ -117,7 +117,7 @@ ####################################################################################################### # 3. ID mapping file ####################################################################################################### -import ftplib, gzip, pickle +import ftplib, gzip csv.field_size_limit(sys.maxsize) # to handle big files def id_mapping_sources (data_manager_dict, species, target_directory) : @@ -127,15 +127,12 @@ files=["idmapping_selected.tab.gz","idmapping.dat.gz"] #header - if human : - ids_list = ["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","neXtProt","BioGrid","STRING","KEGG"] - else : - ids_list = ["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","BioGrid","STRING","KEGG"] - tab = [ids_list] + if human : tab = [["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","neXtProt","BioGrid","STRING","KEGG"]] + else : tab = [["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","BioGrid","STRING","KEGG"]] #print("header ok") - #selected.tab and keep only ids of interest + #get selected.tab and keep only ids of interest selected_tab_file=species_dict[species]+"_"+files[0] tab_path = download_from_uniprot_ftp(selected_tab_file,target_directory) with gzip.open(tab_path,"rt") as select : @@ -151,6 +148,7 @@ -NextProt,BioGrid,STRING,KEGG """ + #there's more id type for human if human : ids = ['neXtProt','BioGrid','STRING','KEGG' ] #ids to get from dat_file else : ids = ['BioGrid','STRING','KEGG' ] unidict = {} @@ -212,38 +210,19 @@ if nextprotID == '' and uniprotID in next_dict : line[13]=next_dict[uniprotID] - #create empty dictionary and dictionary index - ids_dictionary, ids_dictionary_index = create_ids_dictionary(ids_list) - - #fill dictionary and sub dictionaries with ids - for line in tab[1:] : - for index, ids in enumerate(line) : - other_id_type_index = [accession_id for accession_id in ids_dictionary_index.keys() if accession_id!=index] - for id in ids.replace(" ","").split(";") : #if there's more than one id, one key per id (example : GO) - if id not in ids_dictionary[ids_dictionary_index[index]] : #if the key is not created yet - ids_dictionary[ids_dictionary_index[index]][id]={} - for other_id_type in other_id_type_index : - if ids_dictionary_index[other_id_type] not in ids_dictionary[ids_dictionary_index[index]][id] : - ids_dictionary[ids_dictionary_index[index]][id][ids_dictionary_index[other_id_type]] = set(line[other_id_type].replace(" ","").split(";")) - else : - ids_dictionary[ids_dictionary_index[index]][id][ids_dictionary_index[other_id_type]] |= set(line[other_id_type].replace(" ","").split(";")) - if len(ids_dictionary[ids_dictionary_index[index]][id][ids_dictionary_index[other_id_type]]) > 1 and '' in ids_dictionary[ids_dictionary_index[index]][id][ids_dictionary_index[other_id_type]] : - ids_dictionary[ids_dictionary_index[index]][id][ids_dictionary_index[other_id_type]].remove('') - - ##writing output files - output_file = species+"_id_mapping_"+ time.strftime("%d-%m-%Y") + ".pickle" + output_file = species+"_id_mapping_"+ time.strftime("%d-%m-%Y") + ".tsv" path = os.path.join(target_directory,output_file) - #save ids_dictionary - with open(output_dict, 'wb') as handle: - pickle.dump(ids_dictionary, handle, protocol=pickle.HIGHEST_PROTOCOL) + with open(path,"w") as out : + w = csv.writer(out,delimiter='\t') + w.writerows(tab) name_dict={"human" : "Homo sapiens", "mouse" : "Mus musculus", "rat" : "Rattus norvegicus"} name = name_dict[species]+" "+time.strftime("%d/%m/%Y") id = species+"_id_mapping_"+ time.strftime("%d-%m-%Y") data_table_entry = dict(id=id, name = name, value = species, path = path) - _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_id_mapping_dictionaries") + _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_id_mapping") def download_from_uniprot_ftp(file,target_directory) : ftp_dir = "pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/" @@ -289,17 +268,112 @@ else : return (next_id) -#create empty dictionary with index for tab -def create_ids_dictionary (ids_list) : - ids_dictionary = {} - for id_type in ids_list : - ids_dictionary[id_type]={} - ids_dictionary_index = {} + +####################################################################################################### +# 4. Build protein interaction maps files +####################################################################################################### + +def PPI_ref_files(data_manager_dict, species, interactome, target_directory): + + species_dict={'human':'Homo sapiens',"mouse":"Mus musculus","rat":"Rattus norvegicus"} + + ##BioGRID + if interactome=="biogrid": + + tab2_link="https://downloads.thebiogrid.org/Download/BioGRID/Release-Archive/BIOGRID-3.5.167/BIOGRID-ORGANISM-3.5.167.tab2.zip" + + #dowload zip file + r = requests.get(tab2_link) + with open("BioGRID.zip", "wb") as code: + code.write(r.content) + + #unzip files + with zipfile.ZipFile("BioGRID.zip", 'r') as zip_ref: + if not os.path.exists("tmp_BioGRID"): os.makedirs("tmp_BioGRID") + zip_ref.extractall("tmp_BioGRID") + + #import file of interest and build dictionary + file_path="tmp_BioGRID/BIOGRID-ORGANISM-"+species_dict[species].replace(" ","_")+"-3.5.167.tab2.txt" + with open(file_path,"r") as handle : + tab_file = csv.reader(handle,delimiter="\t") + dico_network = {} + GeneID_index=1 + network_cols=[1,2,7,8,11,12,18,20] + for line in tab_file : + dico_network[line[GeneID_index]]=[line[i] for i in network_cols] + + #delete tmp_BioGRID directory + os.remove("BioGRID.zip") + shutil.rmtree("tmp_BioGRID", ignore_errors=True) + + #download NCBI2Reactome.txt file and build dictionary + download = requests.get('https://www.reactome.org/download/current/NCBI2Reactome.txt') + decoded_content = download.content.decode('utf-8') + tab_file = csv.reader(decoded_content.splitlines(), delimiter='\t') + dico_nodes = {} + GeneID_index=0 + pathway_description_index=3 + species_index=5 + for line in tab_file : + if line[species_index]==species_dict[species]: + if line[GeneID_index] in dico_nodes : + dico_nodes[line[GeneID_index]].append(line[pathway_description_index]) + else : + dico_nodes[line[GeneID_index]] = [line[pathway_description_index]] - for i,id in enumerate(ids_list) : - ids_dictionary_index[i]=id - - return(ids_dictionary,ids_dictionary_index) + dico={} + dico['network']=dico_network + dico['nodes']=dico_nodes + + ##Bioplex + elif interactome=="bioplex": + + download = requests.get("http://bioplex.hms.harvard.edu/data/BioPlex_interactionList_v4a.tsv") + decoded_content = download.content.decode('utf-8') + bioplex = csv.reader(decoded_content.splitlines(), delimiter='\t') + dico_network = {} + dico_network["GeneID"]={} + network_geneid_cols=[0,1,4,5,8] + dico_network["UniProt-AC"]={} + network_uniprot_cols=[2,3,4,5,8] + dico_GeneID_to_UniProt = {} + dico_nodes = {} + for line in bioplex : + dico_network["GeneID"][line[0]]=[line[i] for i in network_geneid_cols] + dico_network["UniProt-AC"][line[2]]=[line[i] for i in network_uniprot_cols] + dico_GeneID_to_UniProt[line[0]]=line[2] + + download = requests.get("https://reactome.org/download/current/UniProt2Reactome.txt") + decoded_content = download.content.decode('utf-8') + tab_file = csv.reader(decoded_content.splitlines(), delimiter='\t') + dico_nodes = {} + uniProt_index=0 + pathway_description_index=3 + species_index=5 + for line in tab_file : + if line[species_index]==species_dict[species]: + if line[uniProt_index] in dico_nodes : + dico_nodes[line[uniProt_index]].append(line[pathway_description_index]) + else : + dico_nodes[line[uniProt_index]] = [line[pathway_description_index]] + + dico={} + dico['network']=dico_network + dico['nodes']=dico_nodes + dico['convert']=dico_GeneID_to_UniProt + + #writing output + output_file = species+'_'+interactome+'_dict_'+ time.strftime("%d-%m-%Y") + ".json" + path = os.path.join(target_directory,output_file) + name = species+" ("+species_dict[species]+") "+time.strftime("%d/%m/%Y") + id = interactome+"_"+species+ time.strftime("%d-%m-%Y") + + with open(path, 'w') as handle: + json.dump(dico, handle, sort_keys=True) + + data_table_entry = dict(id=id, name = name, value = species, path = path) + _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_"+interactome+"_dictionaries") + ####################################################################################################### # Main function @@ -309,6 +383,8 @@ parser.add_argument("--hpa", metavar = ("HPA_OPTION")) parser.add_argument("--peptideatlas", metavar=("SAMPLE_CATEGORY_ID")) parser.add_argument("--id_mapping", metavar = ("ID_MAPPING_SPECIES")) + parser.add_argument("--interactome", metavar = ("PPI")) + parser.add_argument("--species") parser.add_argument("-o", "--output") args = parser.parse_args() @@ -350,6 +426,16 @@ id_mapping = id_mapping .split(",") for species in id_mapping : id_mapping_sources(data_manager_dict, species, target_directory) + + ## Download PPI ref files from biogrid/bioplex/humap + try: + interactome=args.interactome + species=args.species + except NameError: + interactome=None + species=None + if interactome is not None and species is not None: + PPI_ref_files(data_manager_dict, species, interactome, target_directory) #save info to json file filename = args.output
--- a/data_manager/resource_building.xml Fri Jan 04 06:11:49 2019 -0500 +++ b/data_manager/resource_building.xml Tue Jan 15 04:29:28 2019 -0500 @@ -1,4 +1,4 @@ -<tool id="data_manager_proteore" name="Get source files for proteore tools" version="2019.01.04" tool_type="manage_data"> +<tool id="data_manager_proteore" name="Get source files for proteore tools" version="2019.01.15" tool_type="manage_data"> <description> to create or update reference files for proteore tools </description> @@ -13,9 +13,12 @@ #if $database.database == "human_protein_atlas" --hpa "$database.tissues" #else if $database.database == "peptide_atlas" - --peptideatlas "$database.tissues" + --peptideatlas="$database.tissues" #else if $database.database == "id_mapping" --id_mapping="$database.species" + #else if $database.database == "PPI" + --species="$database.species" + --interactome="$database.interactome" #end if --output "$output" @@ -27,6 +30,7 @@ <option value="human_protein_atlas">Human Protein Atlas</option> <option value="peptide_atlas">Peptide Atlas</option> <option value="id_mapping">ID mapping</option> + <option value="PPI">Build protein interaction maps</option> </param> <when value="human_protein_atlas"> <param name="tissues" type="select" multiple="false" label="Please select tissue"> @@ -53,6 +57,18 @@ <option value="rat">Rat (Rattus norvegicus)</option> </param> </when> + <when value="PPI"> + <param name="interactome" type="select" multiple="false" label="Please select interactome"> + <option value="biogrid">BioGRID</option> + <option value="bioplex">Bioplex</option> + <option value="humap">Hu.map</option> + </param> + <param name="species" type="select" multiple="false" label="Please select the species"> + <option value="human">Human (Homo sapiens)</option> + <option value="mouse">Mouse (Mus musculus)</option> + <option value="rat">Rat (Rattus norvegicus)</option> + </param> + </when> </conditional> </inputs> @@ -68,7 +84,87 @@ <help><![CDATA[ -TODO +**Description** + +This tool is a data manager designed to update resources files of ProteoRe tools. For now, only resources files for tools listed below are handled: + +* "Get MS/MS observations in tissue/fluid [Peptide Atlas]" +* "Get expression profiles by (normal or tumor) tissue/cell type [Human Protein Atlas]" +* "ID converter" + +----- + +**Input** + +There's no input needed, once you selected the tool and file you want to update, it will be generated automatically. + +----- + +**Parameters** + +* database: the database to update (for now one per tool) + +Once a database is selected, there's a second dropdown menu to select the specific file you want to update. + +* for 'Human Protein Atlas': 'Normal tissue', 'Pathology' and 'Full Atlas' + +* for 'Peptide Atlas': 'Human liver', 'Human brain', 'Human heart', 'Human kidney', 'Human blood plasma', 'Human urine' and 'Human cerebrospinal fluid' + +* for 'ID mapping': 'Human (Homo sapiens)', 'Mouse (Mus musculus)' and 'Rat (Rattus norvegicus)' + +* for 'Build protein interaction maps': "BioGRID", "Bioplex" and "Human (Homo sapiens)", "Mouse (Mus musculus)", "Rat (Rattus norvegicus)" + +----- + +**Output** + +The output is the reference file selected for update in input. + +For example, if you select database="Human Protein Atlas" and Please select tissue="Normal tissue": + +the output is a new reference file for "Get expression profiles by (normal or tumor) tissue/cell type [Human Protein Atlas]" +dated from the day and listed in the dropdown menu "Normal tissue HPA version". + +.. class:: warningmark + +A reference file created with this data manager will appears in the concerned ProteoRE tool. It can not be removed with the data manager. + +----- + +**Data sources** + +For 'Human Protein Atlas': + +* `Normal Tissue <https://www.proteinatlas.org/download/normal_tissue.tsv.zip>`_. +* `Pathology <https://www.proteinatlas.org/download/pathology.tsv.zip>`_. +* `Full Atlas <https://www.proteinatlas.org/download/proteinatlas.tsv.zip>`_. + +For 'Peptide Atlas': + +* `Human liver <"https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetPeptides?atlas_build_id=472&display_options=ShowMappings&organism_id=2&sample_category_id=1&QUERY_NAME=AT_GetPeptides&output_mode=tsv&apply_action=QUERY">`_. +* `Human brain <"https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetPeptides?atlas_build_id=472&display_options=ShowMappings&organism_id=2&sample_category_id=2&QUERY_NAME=AT_GetPeptides&output_mode=tsv&apply_action=QUERY">`_. +* `Human heart <"https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetPeptides?atlas_build_id=472&display_options=ShowMappings&organism_id=2&sample_category_id=3&QUERY_NAME=AT_GetPeptides&output_mode=tsv&apply_action=QUERY">`_. +* `Human kidney <"https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetPeptides?atlas_build_id=472&display_options=ShowMappings&organism_id=2&sample_category_id=4&QUERY_NAME=AT_GetPeptides&output_mode=tsv&apply_action=QUERY">`_. +* `Human plasma <"https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetPeptides?atlas_build_id=472&display_options=ShowMappings&organism_id=2&sample_category_id=5&QUERY_NAME=AT_GetPeptides&output_mode=tsv&apply_action=QUERY">`_. +* `Human urine <"https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetPeptides?atlas_build_id=472&display_options=ShowMappings&organism_id=2&sample_category_id=6&QUERY_NAME=AT_GetPeptides&output_mode=tsv&apply_action=QUERY">`_. +* `Human CSF <"https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetPeptides?atlas_build_id=472&display_options=ShowMappings&organism_id=2&sample_category_id=7&QUERY_NAME=AT_GetPeptides&output_mode=tsv&apply_action=QUERY">`_. + +For ID mapping: + +* `HUMAN_9606_idmapping_selected.tab <ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/HUMAN_9606_idmapping_selected.tab.gz>`_. +* `HUMAN_9606_idmapping.dat <ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/HUMAN_9606_idmapping.dat.gz>`_. +* `nextprot_ac_list_all.txt <ftp://ftp.nextprot.org/pub/current_release/ac_lists/nextprot_ac_list_all.txt>`_. +* `MOUSE_10090_idmapping_selected.tab <ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/MOUSE_10090_idmapping_selected.tab.gz>`_. +* `MOUSE_10090_idmapping.dat <ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/MOUSE_10090_idmapping.dat.gz>`_. +* `RAT_10116_idmapping_selected.tab <ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/RAT_10116_idmapping_selected.tab.gz>`_. +* `RAT_10116_idmapping.dat <ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/RAT_10116_idmapping.dat.gz>`_. + +For Build protein interaction maps: + +* `BIOGRID_oragism <https://downloads.thebiogrid.org/Download/BioGRID/Release-Archive/BIOGRID-3.5.167/BIOGRID-ORGANISM-3.5.167.tab2.zip>`_. +* `NCBI2Reactome.txt <https://www.reactome.org/download/current/NCBI2Reactome.txt>`_. +* `Bioplex_interactionList_v4a.tsv <http://bioplex.hms.harvard.edu/data/BioPlex_interactionList_v4a.tsv>`_. +* `UniProt2Reactome.txt <https://reactome.org/download/current/UniProt2Reactome.txt>`_. ----- @@ -76,7 +172,7 @@ **Authors** -Lisa Peru, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR +David Christiany, Lisa Peru, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform
--- a/data_manager_conf.xml Fri Jan 04 06:11:49 2019 -0500 +++ b/data_manager_conf.xml Tue Jan 15 04:29:28 2019 -0500 @@ -30,7 +30,22 @@ </column> </output> </data_table> - <data_table name="proteore_id_mapping_dictionaries"> + <data_table name="proteore_id_mapping"> + <output> + <column name="id" /> + <column name="name" /> + <column name="value" /> + <column name="path" output_ref="output" > + <move type="file"> + <!--source>${path}</source--> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">id_mapping/</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/id_mapping/${id}.tsv</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + </output> + </data_table> + <data_table name="proteore_biogrid_dictionaries"> <output> <column name="id" /> <column name="name" /> @@ -38,9 +53,24 @@ <column name="path" output_ref="output" > <move type="file"> <!--source>${path}</source--> - <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">id_mapping_dictionaries/</target> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">PPI_dictionaries/</target> </move> - <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/id_mapping_dictionaries/${id}.pickle</value_translation> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/PPI_dictionaries/${id}.json</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + </output> + </data_table> + <data_table name="proteore_bioplex_dictionaries"> + <output> + <column name="id" /> + <column name="name" /> + <column name="value" /> + <column name="path" output_ref="output" > + <move type="file"> + <!--source>${path}</source--> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">PPI_dictionaries/</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/PPI_dictionaries/${id}.json</value_translation> <value_translation type="function">abspath</value_translation> </column> </output>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/proteore_biogrid_dictionaries.loc.sample Tue Jan 15 04:29:28 2019 -0500 @@ -0,0 +1,4 @@ +#id name value path +#biogrid_human_08-01-2019 Human (Homo sapiens) human PPI_dictionaries/human_biogrid_dict.json +#biogrid_mouse_08-01-2019 Mouse (Mus musculus) mouse PPI_dictionaries/mouse_biogrid_dict.json +#biogrid_rat_08-01-2019 Rat (Rattus norvegicus) rat PPI_dictionaries/rat_biogrid_dict.json
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/proteore_bioplex_dictionaries.loc.sample Tue Jan 15 04:29:28 2019 -0500 @@ -0,0 +1,4 @@ +#id name value path +#bioplex_human_08-01-2019 Human (Homo sapiens) human PPI_dictionaries/human_bioplex_dict.json +#bioplex_mouse_08-01-2019 Mouse (Mus musculus) mouse PPI_dictionaries/mouse_bioplex_dict.json +#bioplex_rat_08-01-2019 Rat (Rattus norvegicus) rat PPI_dictionaries/rat_bioplex_dict.json
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/proteore_id_mapping.loc.sample Tue Jan 15 04:29:28 2019 -0500 @@ -0,0 +1,5 @@ +#This file lists the locations of reference file for id_converter tool +#<id> <name> <value> <path> +#human_id_mapping_01-01-2018 Human (homo sapiens) human_id_mapping tool-data/human_id_mapping_file.tsv +#mouse_id_mapping_01-01-2018 Mouse (Mus musculus) mouse_id_mapping tool-data/mouse_id_mapping.tsv +#rat_id_mapping_01-01-2018 Rat (Rattus norvegicus) rat_id_mapping tool-data/rat_id_mapping.tsv
--- a/tool-data/proteore_id_mapping_dictionaries.loc.sample Fri Jan 04 06:11:49 2019 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,5 +0,0 @@ -#This file lists the locations of reference file for id_converter tool -#<id> <name> <value> <path> -#human_id_mapping_01-01-2018 Human (homo sapiens) human_id_mapping tool-data/human_id_mapping_file.tsv -#mouse_id_mapping_01-01-2018 Mouse (Mus musculus) mouse_id_mapping tool-data/mouse_id_mapping.tsv -#rat_id_mapping_01-01-2018 Rat (Rattus norvegicus) rat_id_mapping tool-data/rat_id_mapping.tsv
--- a/tool_data_table_conf.xml.sample Fri Jan 04 06:11:49 2019 -0500 +++ b/tool_data_table_conf.xml.sample Tue Jan 15 04:29:28 2019 -0500 @@ -8,8 +8,16 @@ <columns>id, name, value, path</columns> <file path="tool-data/proteore_protein_atlas.loc" /> </table> - <table name="proteore_id_mapping_dictionaries" comment_char="#"> + <table name="proteore_id_mapping" comment_char="#"> + <columns>id, name, value, path</columns> + <file path="tool-data/proteore_id_mapping.loc" /> + </table> + <table name="proteore_biogrid_dictionaries" comment_char="#"> <columns>id, name, value, path</columns> - <file path="tool-data/proteore_id_mapping_dictionaries.loc" /> + <file path="tool-data/proteore_biogrid_dictionaries.loc" /> + </table> + <table name="proteore_bioplex_dictionaries" comment_char="#"> + <columns>id, name, value, path</columns> + <file path="tool-data/proteore_bioplex_dictionaries.loc" /> </table> </tables>