Refactored code for logging, optimization and checking if valid gene …

…symbol

data_collection/data/A1BG.txt

@@ -0,0 +1,110 @@
+### LOVD-version 3000-290 ### Full data download ### To import, do not remove or alter this header ###
+## Filter: (gene_public = A1BG)
+# charset = UTF-8
+
+## Genes ## Do not remove or alter this header ##
+## Count = 1
+"{{id}}"	"{{name}}"	"{{chromosome}}"	"{{chrom_band}}"	"{{imprinting}}"	"{{refseq_genomic}}"	"{{refseq_UD}}"	"{{reference}}"	"{{url_homepage}}"	"{{url_external}}"	"{{allow_download}}"	"{{id_hgnc}}"	"{{id_entrez}}"	"{{id_omim}}"	"{{show_hgmd}}"	"{{show_genecards}}"	"{{show_genetests}}"	"{{show_orphanet}}"	"{{note_index}}"	"{{note_listing}}"	"{{refseq}}"	"{{refseq_url}}"	"{{disclaimer}}"	"{{disclaimer_text}}"	"{{header}}"	"{{header_align}}"	"{{footer}}"	"{{footer_align}}"	"{{created_by}}"	"{{created_date}}"	"{{edited_by}}"	"{{edited_date}}"	"{{updated_by}}"	"{{updated_date}}"
+"A1BG"	"alpha-1-B glycoprotein"	"19"	"q13.43"	"unknown"	"NC_000019.9"	"UD_132611092394"	""	"http://www.LOVD.nl/A1BG"	""	"1"	"5"	"1"	"138670"	"1"	"1"	"1"	"1"	"Establishment of this gene variant database (LSDB) was supported by the <a href=\'http://www.LUMC.nl\' target=\'_blank\'>Leiden University Medical Center (LUMC)</a>, Leiden, Nederland."	""	"g"	"http://databases.lovd.nl/shared/refseq/A1BG_codingDNA.html"	"1"	""	""	"-1"	""	"-1"	"00000"	"2012-09-13 00:00:00"	"00006"	"2015-12-13 09:24:24"	"00006"	"2022-01-23 11:30:18"
+
+
+## Transcripts ## Do not remove or alter this header ##
+## Count = 1
+"{{id}}"	"{{geneid}}"	"{{name}}"	"{{id_mutalyzer}}"	"{{id_ncbi}}"	"{{id_ensembl}}"	"{{id_protein_ncbi}}"	"{{id_protein_ensembl}}"	"{{id_protein_uniprot}}"	"{{remarks}}"	"{{position_c_mrna_start}}"	"{{position_c_mrna_end}}"	"{{position_c_cds_end}}"	"{{position_g_mrna_start}}"	"{{position_g_mrna_end}}"	"{{created_by}}"	"{{created_date}}"	"{{edited_by}}"	"{{edited_date}}"
+"00001331"	"A1BG"	"alpha-1-B glycoprotein"	"001"	"NM_130786.3"	""	"NP_570602.2"	""	""	""	"-62"	"1704"	"1488"	"58858172"	"58864865"	"00000"	"2012-09-13 13:27:02"	""	""
+
+
+## Diseases ## Do not remove or alter this header ##
+## Count = 2
+"{{id}}"	"{{symbol}}"	"{{name}}"	"{{inheritance}}"	"{{id_omim}}"	"{{tissues}}"	"{{features}}"	"{{remarks}}"	"{{created_by}}"	"{{created_date}}"	"{{edited_by}}"	"{{edited_date}}"
+"01157"	"CHTE"	"Hypothyroidism, central, testicular enlargement (CHTE)"	"XLR"	"300888"	""	""	""	"00006"	"2014-09-25 23:29:40"	"00006"	"2021-12-10 21:51:32"
+"04254"	"CLP"	"cleft lip, cleft palate (CLP)"	""	""	""	""	""	"00006"	"2015-05-08 09:59:28"	"00006"	"2015-05-08 10:00:15"
+
+
+## Genes_To_Diseases ## Do not remove or alter this header ##
+## Count = 0
+
+
+## Individuals ## Do not remove or alter this header ##
+## Count = 3
+"{{id}}"	"{{fatherid}}"	"{{motherid}}"	"{{panelid}}"	"{{panel_size}}"	"{{license}}"	"{{owned_by}}"	"{{Individual/Reference}}"	"{{Individual/Remarks}}"	"{{Individual/Gender}}"	"{{Individual/Consanguinity}}"	"{{Individual/Origin/Geographic}}"	"{{Individual/Age_of_death}}"	"{{Individual/VIP}}"	"{{Individual/Data_av}}"	"{{Individual/Treatment}}"	"{{Individual/Origin/Population}}"	"{{Individual/Individual_ID}}"
+"00000208"	""	""	""	"1"	""	"00037"	"{PMID:Sun 2011:23143598}, {DOI:Sun 2011:10.1038/ng.2453}"	""	"M"	"no"	"Netherlands"	""	"0"	""	""	""	""
+"00000209"	""	""	""	"1"	""	"00037"	"{PMID:Sun 2011:23143598}, {DOI:Sun 2011:10.1038/ng.2453}"	""	"M"	"no"	"Netherlands"	""	"0"	""	""	""	""
+"00231413"	""	""	""	"3"	""	"03278"	"{PMID:Cox 2019:31215115}"	"3-generation family, 3 affected (2F, M)"	"F;M"	""	"Colombia"	""	"0"	""	""	""	"Fam22"
+
+
+## Individuals_To_Diseases ## Do not remove or alter this header ##
+## Count = 3
+"{{individualid}}"	"{{diseaseid}}"
+"00000208"	"01157"
+"00000209"	"01157"
+"00231413"	"04254"
+
+
+## Phenotypes ## Do not remove or alter this header ##
+## Note: Only showing Phenotype columns active for Diseases 01157, 04254
+## Count = 3
+"{{id}}"	"{{diseaseid}}"	"{{individualid}}"	"{{owned_by}}"	"{{Phenotype/Inheritance}}"	"{{Phenotype/Age}}"	"{{Phenotype/Additional}}"	"{{Phenotype/Age/Onset}}"	"{{Phenotype/Age/Diagnosis}}"	"{{Phenotype/Onset}}"	"{{Phenotype/Protein}}"	"{{Phenotype/Enzyme/CPK}}"	"{{Phenotype/Heart/Myocardium}}"	"{{Phenotype/Lung}}"	"{{Phenotype/Diagnosis/Definite}}"	"{{Phenotype/Diagnosis/Initial}}"
+"0000038983"	"01157"	"00000208"	"00006"	"Familial, X-linked recessive"	""	"central hypothyroidism (FT4 0.50-0.99of lower limit normal), no prolactin deficiency, age sonographic determination testicular volume 17.64y, testicular volume right/left 21/20 (7.3–16ml)"	""	"3w"	""	""	""	""	""	""	""
+"0000038984"	"01157"	"00000209"	"00006"	"Familial, X-linked recessive"	""	"central hypothyroidism (FT4 0.50-0.99of lower limit normal), prolactin deficiency, age sonographic determination testicular volume 21.36y, testicular volume right/left 30/26 (8.5–18.3ml)"	""	"07y04m"	""	""	""	""	""	""	""
+"0000173805"	"04254"	"00231413"	"03278"	"Familial, autosomal dominant"	""	""	""	""	""	""	""	""	""	""	""
+
+
+## Screenings ## Do not remove or alter this header ##
+## Count = 3
+"{{id}}"	"{{individualid}}"	"{{variants_found}}"	"{{owned_by}}"	"{{created_by}}"	"{{created_date}}"	"{{edited_by}}"	"{{edited_date}}"	"{{Screening/Technique}}"	"{{Screening/Template}}"	"{{Screening/Tissue}}"	"{{Screening/Remarks}}"
+"0000000209"	"00000208"	"1"	"00037"	"00001"	"2012-09-13 12:02:03"	""	""	"SEQ-NG-I"	"DNA"	""	""
+"0000000210"	"00000209"	"1"	"00037"	"00001"	"2012-09-13 12:09:36"	""	""	"SEQ-NG-I"	"DNA"	""	""
+"0000232512"	"00231413"	"1"	"03278"	"03278"	"2019-05-02 18:06:52"	""	""	"SEQ-NG-I"	"DNA"	""	""
+
+
+## Screenings_To_Genes ## Do not remove or alter this header ##
+## Count = 1
+"{{screeningid}}"	"{{geneid}}"
+"0000232512"	"FST"
+
+
+## Variants_On_Genome ## Do not remove or alter this header ##
+## Please note that not necessarily all variants found in the given individuals are shown. This output is restricted to variants in the selected gene.
+## Count = 11
+"{{id}}"	"{{allele}}"	"{{effectid}}"	"{{chromosome}}"	"{{position_g_start}}"	"{{position_g_end}}"	"{{type}}"	"{{average_frequency}}"	"{{owned_by}}"	"{{VariantOnGenome/DBID}}"	"{{VariantOnGenome/DNA}}"	"{{VariantOnGenome/Frequency}}"	"{{VariantOnGenome/Reference}}"	"{{VariantOnGenome/Restriction_site}}"	"{{VariantOnGenome/Published_as}}"	"{{VariantOnGenome/Remarks}}"	"{{VariantOnGenome/Genetic_origin}}"	"{{VariantOnGenome/Segregation}}"	"{{VariantOnGenome/dbSNP}}"	"{{VariantOnGenome/VIP}}"	"{{VariantOnGenome/Methylation}}"	"{{VariantOnGenome/ISCN}}"	"{{VariantOnGenome/DNA/hg38}}"	"{{VariantOnGenome/ClinVar}}"	"{{VariantOnGenome/ClinicalClassification}}"	"{{VariantOnGenome/ClinicalClassification/Method}}"
+"0000002698"	"3"	"50"	"19"	"58858614"	"58858614"	"del"	"0"	"00037"	"A1BG_000004"	"g.58858614del"	""	""	""	""	""	"Germline"	""	""	""	""	""	"g.58347248del"	""	"VUS"	""
+"0000010704"	"3"	"50"	"19"	"58858614"	"58858614"	"del"	"0"	"00037"	"A1BG_000004"	"g.58858614del"	""	""	""	""	""	"Germline"	""	""	""	""	""	"g.58347248del"	""	"VUS"	""
+"0000013878"	"3"	"50"	"19"	"58858676"	"58858676"	"subst"	"0.922338"	"00037"	"A1BG_000003"	"g.58858676A>G"	""	""	""	""	""	"Germline"	""	""	""	""	""	"g.58347310A>G"	""	"VUS"	""
+"0000193885"	"3"	"50"	"19"	"58858719"	"58858719"	"subst"	"0"	"00006"	"A1BG_000005"	"g.58858719C>T"	""	""	""	""	""	"Germline"	""	""	"0"	""	""	"g.58347353C>T"	""	"VUS"	""
+"0000193887"	"3"	"50"	"19"	"58858719"	"58858719"	"subst"	"0"	"00006"	"A1BG_000005"	"g.58858719C>T"	""	""	""	""	""	"Germline"	""	""	"0"	""	""	"g.58347353C>T"	""	"VUS"	""
+"0000193889"	"3"	"50"	"19"	"58858719"	"58858719"	"subst"	"0"	"00006"	"A1BG_000005"	"g.58858719C>T"	""	""	""	""	""	"Germline"	""	""	"0"	""	""	"g.58347353C>T"	""	"VUS"	""
+"0000193891"	"3"	"50"	"19"	"58858719"	"58858719"	"subst"	"0"	"00006"	"A1BG_000005"	"g.58858719C>T"	""	""	""	""	""	"Germline"	""	""	"0"	""	""	"g.58347353C>T"	""	"VUS"	""
+"0000193895"	"3"	"50"	"19"	"58858719"	"58858719"	"subst"	"0"	"00006"	"A1BG_000005"	"g.58858719C>T"	""	""	""	""	""	"Germline"	""	""	"0"	""	""	"g.58347353C>T"	""	"VUS"	""
+"0000193897"	"3"	"50"	"19"	"58858719"	"58858719"	"subst"	"0"	"00006"	"A1BG_000005"	"g.58858719C>T"	""	""	""	""	""	"Germline"	""	""	"0"	""	""	"g.58347353C>T"	""	"VUS"	""
+"0000480548"	"0"	"70"	"19"	"58858937"	"58858937"	"subst"	"0"	"03278"	"A1BG_000007"	"g.58858937A>G"	""	"{PMID:Cox 2019:31215115}"	""	""	""	"Germline"	""	""	"0"	""	""	"g.58347571A>G"	""	"VUS"	""
+"0000568608"	"0"	"30"	"19"	"58868716"	"58868716"	"subst"	"0.00112904"	"01804"	"ZNF497_000004"	"g.58868716G>C"	""	""	""	"ZNF497(NM_001207009.1):c.286C>G (p.(Arg96Gly))"	"VKGL data sharing initiative Nederland"	"CLASSIFICATION record"	""	""	""	""	""	"g.58357350G>C"	""	"likely benign"	""
+
+
+## Variants_On_Transcripts ## Do not remove or alter this header ##
+## Please note that not necessarily all variants found in the given individuals are shown. This output is restricted to variants in the selected gene.
+## Note: Only showing Variants_On_Transcript columns active for Genes A1BG
+## Count = 11
+"{{id}}"	"{{transcriptid}}"	"{{effectid}}"	"{{position_c_start}}"	"{{position_c_start_intron}}"	"{{position_c_end}}"	"{{position_c_end_intron}}"	"{{VariantOnTranscript/DNA}}"	"{{VariantOnTranscript/RNA}}"	"{{VariantOnTranscript/Protein}}"	"{{VariantOnTranscript/Exon}}"
+"0000002698"	"00001331"	"50"	"1480"	"105"	"1480"	"105"	"c.1480+105del"	"r.(=)"	"p.(=)"	""
+"0000010704"	"00001331"	"50"	"1480"	"105"	"1480"	"105"	"c.1480+105del"	"r.(=)"	"p.(=)"	""
+"0000013878"	"00001331"	"50"	"1480"	"43"	"1480"	"43"	"c.1480+43T>C"	"r.(=)"	"p.(=)"	""
+"0000193885"	"00001331"	"50"	"1480"	"0"	"1480"	"0"	"c.1480G>A"	"r.1490g>a"	"p.(Glu494Lys)"	""
+"0000193887"	"00001331"	"50"	"1480"	"0"	"1480"	"0"	"c.1480G>A"	"r.(?)"	"p.(Glu494Lys)"	""
+"0000193889"	"00001331"	"50"	"1480"	"0"	"1480"	"0"	"c.1480G>A"	"r.1490g>a"	"p.(Glu494Lys)"	""
+"0000193891"	"00001331"	"50"	"1480"	"0"	"1480"	"0"	"c.1480G>A"	"r.(?)"	"p.(Glu494Lys)"	""
+"0000193895"	"00001331"	"50"	"1480"	"0"	"1480"	"0"	"c.1480G>A"	"r.1490g>a"	"p.(Glu494Lys)"	""
+"0000193897"	"00001331"	"50"	"1480"	"0"	"1480"	"0"	"c.1480G>A"	"r.(?)"	"p.(Glu494Lys)"	""
+"0000480548"	"00001331"	"70"	"1262"	"0"	"1262"	"0"	"c.1262T>C"	"r.(?)"	"p.(Leu421Pro)"	""
+"0000568608"	"00001331"	"30"	"-3913"	"0"	"-3913"	"0"	"c.-3913C>G"	"r.(?)"	"p.(=)"	""
+
+
+## Screenings_To_Variants ## Do not remove or alter this header ##
+## Count = 4
+"{{screeningid}}"	"{{variantid}}"
+"0000000209"	"0000002698"
+"0000000210"	"0000010704"
+"0000000210"	"0000013878"
+"0000232512"	"0000480548"
+
+