diff --git a/data-exploration/direction-of-effect.ipynb b/data-exploration/direction-of-effect.ipynb index f4705e8..70525d8 100644 --- a/data-exploration/direction-of-effect.ipynb +++ b/data-exploration/direction-of-effect.ipynb @@ -207,7 +207,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 245, "id": "d22115ea-56f6-404d-9839-c91c8ed74a89", "metadata": { "pycharm": { @@ -215,134 +215,6 @@ }, "scrolled": true }, - "outputs": [], - "source": [ - "# Looking at the data - output suppressed for brevity\n", - "var_drug_ann.head()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "12dada29-2a14-4992-acf4-45115aed57d2", - "metadata": { - "pycharm": { - "name": "#%%\n" - }, - "scrolled": true - }, - "outputs": [], - "source": [ - "var_fa_ann.head()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "70537798-e6fb-47f5-8ba2-6859c4b645a2", - "metadata": { - "scrolled": true - }, - "outputs": [], - "source": [ - "var_pheno_ann.head()" - ] - }, - { - "cell_type": "markdown", - "id": "3b84a02e-1791-4a6b-8223-d904442ddf7c", - "metadata": {}, - "source": [ - "The 3 annotations tables provide evidence for the clinical annotations, can be connected by joining with the `clinical_ann_evidence.tsv` file. In general a clinical annotation can have multiple variant annotations as evidence, and a variant annotation can be used as evidence for multiple clinical annotations (in theory, I've not actually observed this).\n", - "\n", - "Each of these tables has a \"Direction of effect\" column, and the type of \"effect\" is different for each - likelihood of side effects, formation of product, metabolism of drug, etc.\n", - "\n", - "**Question for OT**: when we say \"direction of effect\", do we mean any of these \"effects\"? I.e. should we include all three of these tables or focus on one?" - ] - }, - { - "cell_type": "code", - "execution_count": 38, - "id": "d43fd147-43b4-4541-9595-f757da937e60", - "metadata": {}, - "outputs": [], - "source": [ - "clinical_annotations = read_tsv_to_df(os.path.join(data_dir, 'clinical_annotations.tsv'))\n", - "clinical_ann_evidence = read_tsv_to_df(os.path.join(data_dir, 'clinical_ann_evidence.tsv'))\n", - "clinical_ann_alleles = read_tsv_to_df(os.path.join(data_dir, 'clinical_ann_alleles.tsv'))" - ] - }, - { - "cell_type": "code", - "execution_count": 122, - "id": "1a553aac-a9f7-4579-ab7c-05fa6f90ddfe", - "metadata": {}, - "outputs": [], - "source": [ - "main_df = pd.merge(clinical_annotations, clinical_ann_evidence, how='left', on=ID_COL_NAME)\n", - "main_df = main_df[[\n", - " # Main table\n", - " 'Clinical Annotation ID', 'Variant/Haplotypes', 'Gene', 'Level of Evidence', 'Phenotype Category', 'Drug(s)', 'Phenotype(s)',\n", - " # Evidence table\n", - " 'Evidence ID', 'Evidence Type', 'PMID', 'Summary',\n", - "]]" - ] - }, - { - "cell_type": "markdown", - "id": "5945f09b-9516-4d65-ad75-d27a5a1890cf", - "metadata": {}, - "source": [ - "#### Example clinical annotation\n", - "\n", - "[Top of page](#Table-of-contents)\n", - "\n", - "Looking at [981755803](https://www.pharmgkb.org/clinicalAnnotation/981755803), which has all three types of variant annotation evidence as well as label/guideline evidence." - ] - }, - { - "cell_type": "code", - "execution_count": 124, - "id": "f5bb8c9e-baeb-4ef6-9373-7c38a333601c", - "metadata": {}, - "outputs": [], - "source": [ - "df_981755803 = main_df[main_df[ID_COL_NAME] == '981755803']\n", - "\n", - "df_981755803_drug = pd.merge(df_981755803, var_drug_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_drug'))\n", - "df_981755803_pheno = pd.merge(df_981755803, var_pheno_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_pheno'))\n", - "df_981755803_fa = pd.merge(df_981755803, var_fa_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_fa'))" - ] - }, - { - "cell_type": "code", - "execution_count": 229, - "id": "811adf62-6f79-4451-9a3e-2772057e4a01", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Number of evidence 30\n", - "Number of var/drug evidence 24\n", - "Number of var/fa evidence 2\n", - "Number of var/pheno evidence 2\n" - ] - } - ], - "source": [ - "print('Number of evidence', len(df_981755803))\n", - "print('Number of var/drug evidence', len(df_981755803_drug))\n", - "print('Number of var/fa evidence', len(df_981755803_fa))\n", - "print('Number of var/pheno evidence', len(df_981755803_pheno))" - ] - }, - { - "cell_type": "code", - "execution_count": 206, - "id": "c4a15bc6-90fc-4d4b-bd0e-621b8ffd6093", - "metadata": {}, "outputs": [ { "data": { @@ -365,23 +237,12 @@ " \n", " \n", " \n", - " Clinical Annotation ID\n", + " Variant Annotation ID\n", " Variant/Haplotypes\n", " Gene\n", - " Level of Evidence\n", - " Phenotype Category\n", " Drug(s)\n", - " Phenotype(s)\n", - " Evidence ID\n", - " Evidence Type\n", " PMID\n", - " Summary\n", - " Variant Annotation ID\n", - " Variant/Haplotypes_var_drug\n", - " Gene_var_drug\n", - " Drug(s)_var_drug\n", - " PMID_var_drug\n", - " Phenotype Category_var_drug\n", + " Phenotype Category\n", " Significance\n", " Notes\n", " Sentence\n", @@ -399,10 +260,1514 @@ " Comparison Allele(s) or Genotype(s)\n", " Comparison Metabolizer types\n", " \n", - " \n", - " \n", + " \n", + " \n", + " \n", + " 0\n", + " 1451834452\n", + " CYP3A4*1, CYP3A4*17\n", + " CYP3A4\n", + " nifedipine\n", + " 15634941\n", + " Other, Metabolism/PK\n", + " not stated\n", + " in vitro expression of the recombinant CYP3A4*17 allelic protein and the wild-type protein\n", + " CYP3A4 *17 is associated with decreased metabolism of nifedipine as compared to CYP3A4 *1.\n", + " *17\n", + " NaN\n", + " NaN\n", + " Is\n", + " Associated with\n", + " decreased\n", + " metabolism of\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", + " *1\n", + " NaN\n", + " \n", + " \n", + " 1\n", + " 1451159680\n", + " rs5031016\n", + " CYP2A6\n", + " warfarin\n", + " 22248286\n", + " Dosage\n", + " no\n", + " No association was found between this variant and warfarin-maintenance dose. Described as CYP2A6*7 in this study.\n", + " Allele G is not associated with increased dose of warfarin in people with an international normalized ratio (INR) of 2.0-3.0 as compared to allele A.\n", + " G\n", + " NaN\n", + " NaN\n", + " Is\n", + " Not associated with\n", + " increased\n", + " dose of\n", + " NaN\n", + " in people with\n", + " Other:an international normalized ratio (INR) of 2.0-3.0\n", + " NaN\n", + " A\n", + " NaN\n", + " \n", + " \n", + " 2\n", + " 1451306860\n", + " CYP2C9*11\n", + " CYP2C9\n", + " warfarin\n", + " 33350885\n", + " Dosage\n", + " not stated\n", + " \"This case suggests that CYP2C9 *11/*11 carriers require approximately two thirds less warfarin than CYP2C9\" normal function homozygotes.\n", + " CYP2C9 *11/*11 is associated with decreased dose of warfarin.\n", + " *11/*11\n", + " NaN\n", + " NaN\n", + " Is\n", + " Associated with\n", + " decreased\n", + " dose of\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", + " \n", + " \n", + " 3\n", + " 1448997750\n", + " CYP2B6*1, CYP2B6*18\n", + " CYP2B6\n", + " efavirenz\n", + " 16495778\n", + " Metabolism/PK\n", + " yes\n", + " Please note that in the paper the allele was referred to as CYP2B6*16. CYP2B6*16 and *18 alleles have been consolidated by PharmVar in Jan 2020, with *16 now listed as a suballele of *18 (CYP2B6*18.002). This annotation is updated to be on CYP2B6*18, instead of CYP2B6*16.\n", + " CYP2B6 *1/*18 is associated with increased concentrations of efavirenz in people with HIV Infections as compared to CYP2B6 *1/*1.\n", + " *1/*18\n", + " NaN\n", + " NaN\n", + " Is\n", + " Associated with\n", + " increased\n", + " concentrations of\n", + " NaN\n", + " in people with\n", + " Disease:HIV Infections\n", + " NaN\n", + " *1/*1\n", + " NaN\n", + " \n", + " \n", + " 4\n", + " 1448631821\n", + " CYP2C19*1, CYP2C19*2\n", + " CYP2C19\n", + " clomipramine, desmethyl clomipramine\n", + " 28470111\n", + " Metabolism/PK\n", + " no\n", + " in a single individual\n", + " CYP2C19 *1/*2 is associated with increased trough concentration of clomipramine and desmethyl clomipramine.\n", + " *1/*2\n", + " NaN\n", + " NaN\n", + " Is\n", + " Associated with\n", + " increased\n", + " trough concentration of\n", + " and\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", + " \n", + " \n", + "\n", + "" + ], + "text/plain": [ + " Variant Annotation ID Variant/Haplotypes Gene \\\n", + "0 1451834452 CYP3A4*1, CYP3A4*17 CYP3A4 \n", + "1 1451159680 rs5031016 CYP2A6 \n", + "2 1451306860 CYP2C9*11 CYP2C9 \n", + "3 1448997750 CYP2B6*1, CYP2B6*18 CYP2B6 \n", + "4 1448631821 CYP2C19*1, CYP2C19*2 CYP2C19 \n", + "\n", + " Drug(s) PMID Phenotype Category \\\n", + "0 nifedipine 15634941 Other, Metabolism/PK \n", + "1 warfarin 22248286 Dosage \n", + "2 warfarin 33350885 Dosage \n", + "3 efavirenz 16495778 Metabolism/PK \n", + "4 clomipramine, desmethyl clomipramine 28470111 Metabolism/PK \n", + "\n", + " Significance \\\n", + "0 not stated \n", + "1 no \n", + "2 not stated \n", + "3 yes \n", + "4 no \n", + "\n", + " Notes \\\n", + "0 in vitro expression of the recombinant CYP3A4*17 allelic protein and the wild-type protein \n", + "1 No association was found between this variant and warfarin-maintenance dose. Described as CYP2A6*7 in this study. \n", + "2 \"This case suggests that CYP2C9 *11/*11 carriers require approximately two thirds less warfarin than CYP2C9\" normal function homozygotes. \n", + "3 Please note that in the paper the allele was referred to as CYP2B6*16. CYP2B6*16 and *18 alleles have been consolidated by PharmVar in Jan 2020, with *16 now listed as a suballele of *18 (CYP2B6*18.002). This annotation is updated to be on CYP2B6*18, instead of CYP2B6*16. \n", + "4 in a single individual \n", + "\n", + " Sentence \\\n", + "0 CYP3A4 *17 is associated with decreased metabolism of nifedipine as compared to CYP3A4 *1. \n", + "1 Allele G is not associated with increased dose of warfarin in people with an international normalized ratio (INR) of 2.0-3.0 as compared to allele A. \n", + "2 CYP2C9 *11/*11 is associated with decreased dose of warfarin. \n", + "3 CYP2B6 *1/*18 is associated with increased concentrations of efavirenz in people with HIV Infections as compared to CYP2B6 *1/*1. \n", + "4 CYP2C19 *1/*2 is associated with increased trough concentration of clomipramine and desmethyl clomipramine. \n", + "\n", + " Alleles Specialty Population Metabolizer types isPlural \\\n", + "0 *17 NaN NaN Is \n", + "1 G NaN NaN Is \n", + "2 *11/*11 NaN NaN Is \n", + "3 *1/*18 NaN NaN Is \n", + "4 *1/*2 NaN NaN Is \n", + "\n", + " Is/Is Not associated Direction of effect PD/PK terms \\\n", + "0 Associated with decreased metabolism of \n", + "1 Not associated with increased dose of \n", + "2 Associated with decreased dose of \n", + "3 Associated with increased concentrations of \n", + "4 Associated with increased trough concentration of \n", + "\n", + " Multiple drugs And/or Population types \\\n", + "0 NaN NaN \n", + "1 NaN in people with \n", + "2 NaN NaN \n", + "3 NaN in people with \n", + "4 and NaN \n", + "\n", + " Population Phenotypes or diseases \\\n", + "0 NaN \n", + "1 Other:an international normalized ratio (INR) of 2.0-3.0 \n", + "2 NaN \n", + "3 Disease:HIV Infections \n", + "4 NaN \n", + "\n", + " Multiple phenotypes or diseases And/or Comparison Allele(s) or Genotype(s) \\\n", + "0 NaN *1 \n", + "1 NaN A \n", + "2 NaN NaN \n", + "3 NaN *1/*1 \n", + "4 NaN NaN \n", + "\n", + " Comparison Metabolizer types \n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN " + ] + }, + "execution_count": 245, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Looking at the data - output suppressed for brevity\n", + "var_drug_ann.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 246, + "id": "12dada29-2a14-4992-acf4-45115aed57d2", + "metadata": { + "pycharm": { + "name": "#%%\n" + }, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Variant Annotation IDVariant/HaplotypesGeneDrug(s)PMIDPhenotype CategorySignificanceNotesSentenceAllelesSpecialty PopulationAssay typeMetabolizer typesisPluralIs/Is Not associatedDirection of effectFunctional termsGene/gene productWhen treated with/exposed to/when assayed withMultiple drugs And/orCell typeComparison Allele(s) or Genotype(s)Comparison Metabolizer types
01451148445CYP2C19*1, CYP2C19*17CYP2C19normeperidine30902024NaNnot statedIn other in vitro experiments, normeperidine formation was significantly correlated with CYP2C19 activity, as measured by S-mephenytoin 4-hydroxylation.CYP2C19 *17/*17 is associated with increased formation of normeperidine as compared to CYP2C19 *1/*1 + *1/*17.*17/*17NaNin human liver microsomesNaNIsAssociated withincreasedformation ofNaNNaNNaNNaN*1/*1 + *1/*17NaN
11447814273rs9923231VKORC1NaN26847243OthernoNaNAllele T is not associated with transcription of VKORC1 in HepG2 cells as compared to allele C.TNaNluciferase assayNaNIsNot associated withNaNtranscription ofVKORC1NaNNaNin HepG2 cellsCNaN
21447814277rs56314408VKORC1NaN26847243OtheryesIn the European population, this SNPs is in high LD with rs9923231 but not other populations. This SNP disrupts a binding motif for transcription factor TFAP2A/C.Allele C is associated with increased transcription of VKORC1 in HepG2 cells as compared to allele T.CNaNluciferase assayNaNIsAssociated withincreasedtranscription ofVKORC1NaNNaNin HepG2 cellsTNaN
31447990384rs1065852CYP2D6bufuralol2211621Metabolism/PKnot statedIn vitro experiments showed a significant decrease in CYP2D6 activity for the variant construct expressed in COS-1 cells as compared to wild-type.Allele A is associated with decreased activity of CYP2D6 when assayed with bufuralol in COS-1 cells as compared to allele G.ANaNNaNNaNIsAssociated withdecreasedactivity ofCYP2D6when assayed withNaNin COS-1 cellsGNaN
41448281185CYP2B6*1, CYP2B6*6CYP2B6bupropion27439448EfficacyyesThe ratio of hydroxybupropion versus bupropion (AUC_hyd/ AUC_bup) in terms of area under the time-concentration curve (AUC) was used to assay CYP2B6 activity.CYP2B6 *1/*1 is associated with increased activity of CYP2B6 when assayed with bupropion as compared to CYP2B6 *1/*6.*1/*1NaNNaNNaNIsAssociated withincreasedactivity ofCYP2B6when assayed withNaNNaN*1/*6NaN
\n", + "
" + ], + "text/plain": [ + " Variant Annotation ID Variant/Haplotypes Gene Drug(s) \\\n", + "0 1451148445 CYP2C19*1, CYP2C19*17 CYP2C19 normeperidine \n", + "1 1447814273 rs9923231 VKORC1 NaN \n", + "2 1447814277 rs56314408 VKORC1 NaN \n", + "3 1447990384 rs1065852 CYP2D6 bufuralol \n", + "4 1448281185 CYP2B6*1, CYP2B6*6 CYP2B6 bupropion \n", + "\n", + " PMID Phenotype Category Significance \\\n", + "0 30902024 NaN not stated \n", + "1 26847243 Other no \n", + "2 26847243 Other yes \n", + "3 2211621 Metabolism/PK not stated \n", + "4 27439448 Efficacy yes \n", + "\n", + " Notes \\\n", + "0 In other in vitro experiments, normeperidine formation was significantly correlated with CYP2C19 activity, as measured by S-mephenytoin 4-hydroxylation. \n", + "1 NaN \n", + "2 In the European population, this SNPs is in high LD with rs9923231 but not other populations. This SNP disrupts a binding motif for transcription factor TFAP2A/C. \n", + "3 In vitro experiments showed a significant decrease in CYP2D6 activity for the variant construct expressed in COS-1 cells as compared to wild-type. \n", + "4 The ratio of hydroxybupropion versus bupropion (AUC_hyd/ AUC_bup) in terms of area under the time-concentration curve (AUC) was used to assay CYP2B6 activity. \n", + "\n", + " Sentence \\\n", + "0 CYP2C19 *17/*17 is associated with increased formation of normeperidine as compared to CYP2C19 *1/*1 + *1/*17. \n", + "1 Allele T is not associated with transcription of VKORC1 in HepG2 cells as compared to allele C. \n", + "2 Allele C is associated with increased transcription of VKORC1 in HepG2 cells as compared to allele T. \n", + "3 Allele A is associated with decreased activity of CYP2D6 when assayed with bufuralol in COS-1 cells as compared to allele G. \n", + "4 CYP2B6 *1/*1 is associated with increased activity of CYP2B6 when assayed with bupropion as compared to CYP2B6 *1/*6. \n", + "\n", + " Alleles Specialty Population Assay type Metabolizer types \\\n", + "0 *17/*17 NaN in human liver microsomes NaN \n", + "1 T NaN luciferase assay NaN \n", + "2 C NaN luciferase assay NaN \n", + "3 A NaN NaN NaN \n", + "4 *1/*1 NaN NaN NaN \n", + "\n", + " isPlural Is/Is Not associated Direction of effect Functional terms \\\n", + "0 Is Associated with increased formation of \n", + "1 Is Not associated with NaN transcription of \n", + "2 Is Associated with increased transcription of \n", + "3 Is Associated with decreased activity of \n", + "4 Is Associated with increased activity of \n", + "\n", + " Gene/gene product When treated with/exposed to/when assayed with \\\n", + "0 NaN NaN \n", + "1 VKORC1 NaN \n", + "2 VKORC1 NaN \n", + "3 CYP2D6 when assayed with \n", + "4 CYP2B6 when assayed with \n", + "\n", + " Multiple drugs And/or Cell type Comparison Allele(s) or Genotype(s) \\\n", + "0 NaN NaN *1/*1 + *1/*17 \n", + "1 NaN in HepG2 cells C \n", + "2 NaN in HepG2 cells T \n", + "3 NaN in COS-1 cells G \n", + "4 NaN NaN *1/*6 \n", + "\n", + " Comparison Metabolizer types \n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN " + ] + }, + "execution_count": 246, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "var_fa_ann.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 247, + "id": "70537798-e6fb-47f5-8ba2-6859c4b645a2", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Variant Annotation IDVariant/HaplotypesGeneDrug(s)PMIDPhenotype CategorySignificanceNotesSentenceAllelesSpecialty PopulationMetabolizer typesisPluralIs/Is Not associatedDirection of effectSide effect/efficacy/otherPhenotypeMultiple phenotypes And/orWhen treated with/exposed to/when assayed withMultiple drugs And/orPopulation typesPopulation Phenotypes or diseasesMultiple phenotypes or diseases And/orComparison Allele(s) or Genotype(s)Comparison Metabolizer types
01449169911HLA-B*35:08HLA-Blamotrigine29238301ToxicitynoThe allele was not significant when comparing allele frequency in cases of severe cutaneous adverse reactions (SCAR), Stevens-Johnson Syndrome (SJS) and Maculopapular Exanthema (MPE) (1/15) and controls (individuals without AEs who took lamotrigine) (0/50). The allele was significant when comparing between cases (1/15) and the general population (1/986).HLA-B *35:08 is not associated with likelihood of Maculopapular Exanthema, severe cutaneous adverse reactions or Stevens-Johnson Syndrome when treated with lamotrigine in people with Epilepsy.*35:08NaNNaNIsNot associated withNaNlikelihood ofSide Effect:Maculopapular Exanthema, Side Effect:severe cutaneous adverse reactions, Side Effect:Stevens-Johnson Syndromeorwhen treated withNaNin people withDisease:EpilepsyNaNNaNNaN
1982022165rs45607939NAT2sulfamethoxazole / trimethoprim22850190ToxicitynoMinor allele frequencies were compared between cases (with drug-induced hypersensitivity) and controls.Allele T is not associated with increased risk of Hypersensitivity when treated with sulfamethoxazole / trimethoprim in people with Infection.TNaNNaNIsNot associated withincreasedrisk ofDisease:HypersensitivityNaNwhen treated withNaNin people withDisease:InfectionNaNNaNNaN
2982022148rs1799930NAT2sulfamethoxazole / trimethoprim22850190ToxicitynoMinor allele frequencies were compared between cases (with drug-induced hypersensitivity) and controls.Allele A is not associated with increased risk of Hypersensitivity when treated with sulfamethoxazole / trimethoprim in people with Infection.ANaNNaNIsNot associated withincreasedrisk ofDisease:HypersensitivityNaNwhen treated withNaNin people withDisease:InfectionNaNNaNNaN
31451283480rs16969968CHRNA5NaN22071378Otheryesthis was from meta-analysis of 27 studies but the number of total cases and the risk allele not clearly specified. Minor allele frequency was given for A allele. Introduction states that variant is Asp398Asn, where Asn (A allele) has lower nicotine response than Asp (G allele) and may be at greater risk for nicotine addiction.Allele A is associated with increased severity of Tobacco Use Disorder in people with Tobacco Use Disorder.ANaNNaNIsAssociated withincreasedseverity ofOther:Tobacco Use DisorderNaNNaNNaNin people withOther:Tobacco Use DisorderNaNNaNNaN
41444696916rs267606617MT-RNR1streptomycin7689389Toxicitynot statedPedigree analysis with 3 separate families. Within the maternal lines, 15 individuals had the 1555G variant, took aminoglycoside antibiotics, and developed hearing loss. 100% of individuals with the 1555G variant who took aminoglycosides developed hearing loss. Homoplasmic. Please note that no statistical analyses were done.Allele G is associated with Ototoxicity when treated with streptomycin as compared to allele A.GNaNNaNIsAssociated withNaNNaNSide Effect:Ototoxicityandwhen treated withNaNNaNNaNNaNANaN
\n", + "
" + ], + "text/plain": [ + " Variant Annotation ID Variant/Haplotypes Gene \\\n", + "0 1449169911 HLA-B*35:08 HLA-B \n", + "1 982022165 rs45607939 NAT2 \n", + "2 982022148 rs1799930 NAT2 \n", + "3 1451283480 rs16969968 CHRNA5 \n", + "4 1444696916 rs267606617 MT-RNR1 \n", + "\n", + " Drug(s) PMID Phenotype Category Significance \\\n", + "0 lamotrigine 29238301 Toxicity no \n", + "1 sulfamethoxazole / trimethoprim 22850190 Toxicity no \n", + "2 sulfamethoxazole / trimethoprim 22850190 Toxicity no \n", + "3 NaN 22071378 Other yes \n", + "4 streptomycin 7689389 Toxicity not stated \n", + "\n", + " Notes \\\n", + "0 The allele was not significant when comparing allele frequency in cases of severe cutaneous adverse reactions (SCAR), Stevens-Johnson Syndrome (SJS) and Maculopapular Exanthema (MPE) (1/15) and controls (individuals without AEs who took lamotrigine) (0/50). The allele was significant when comparing between cases (1/15) and the general population (1/986). \n", + "1 Minor allele frequencies were compared between cases (with drug-induced hypersensitivity) and controls. \n", + "2 Minor allele frequencies were compared between cases (with drug-induced hypersensitivity) and controls. \n", + "3 this was from meta-analysis of 27 studies but the number of total cases and the risk allele not clearly specified. Minor allele frequency was given for A allele. Introduction states that variant is Asp398Asn, where Asn (A allele) has lower nicotine response than Asp (G allele) and may be at greater risk for nicotine addiction. \n", + "4 Pedigree analysis with 3 separate families. Within the maternal lines, 15 individuals had the 1555G variant, took aminoglycoside antibiotics, and developed hearing loss. 100% of individuals with the 1555G variant who took aminoglycosides developed hearing loss. Homoplasmic. Please note that no statistical analyses were done. \n", + "\n", + " Sentence \\\n", + "0 HLA-B *35:08 is not associated with likelihood of Maculopapular Exanthema, severe cutaneous adverse reactions or Stevens-Johnson Syndrome when treated with lamotrigine in people with Epilepsy. \n", + "1 Allele T is not associated with increased risk of Hypersensitivity when treated with sulfamethoxazole / trimethoprim in people with Infection. \n", + "2 Allele A is not associated with increased risk of Hypersensitivity when treated with sulfamethoxazole / trimethoprim in people with Infection. \n", + "3 Allele A is associated with increased severity of Tobacco Use Disorder in people with Tobacco Use Disorder. \n", + "4 Allele G is associated with Ototoxicity when treated with streptomycin as compared to allele A. \n", + "\n", + " Alleles Specialty Population Metabolizer types isPlural \\\n", + "0 *35:08 NaN NaN Is \n", + "1 T NaN NaN Is \n", + "2 A NaN NaN Is \n", + "3 A NaN NaN Is \n", + "4 G NaN NaN Is \n", + "\n", + " Is/Is Not associated Direction of effect Side effect/efficacy/other \\\n", + "0 Not associated with NaN likelihood of \n", + "1 Not associated with increased risk of \n", + "2 Not associated with increased risk of \n", + "3 Associated with increased severity of \n", + "4 Associated with NaN NaN \n", + "\n", + " Phenotype \\\n", + "0 Side Effect:Maculopapular Exanthema, Side Effect:severe cutaneous adverse reactions, Side Effect:Stevens-Johnson Syndrome \n", + "1 Disease:Hypersensitivity \n", + "2 Disease:Hypersensitivity \n", + "3 Other:Tobacco Use Disorder \n", + "4 Side Effect:Ototoxicity \n", + "\n", + " Multiple phenotypes And/or When treated with/exposed to/when assayed with \\\n", + "0 or when treated with \n", + "1 NaN when treated with \n", + "2 NaN when treated with \n", + "3 NaN NaN \n", + "4 and when treated with \n", + "\n", + " Multiple drugs And/or Population types Population Phenotypes or diseases \\\n", + "0 NaN in people with Disease:Epilepsy \n", + "1 NaN in people with Disease:Infection \n", + "2 NaN in people with Disease:Infection \n", + "3 NaN in people with Other:Tobacco Use Disorder \n", + "4 NaN NaN NaN \n", + "\n", + " Multiple phenotypes or diseases And/or Comparison Allele(s) or Genotype(s) \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN A \n", + "\n", + " Comparison Metabolizer types \n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN " + ] + }, + "execution_count": 247, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "var_pheno_ann.head()" + ] + }, + { + "cell_type": "markdown", + "id": "3b84a02e-1791-4a6b-8223-d904442ddf7c", + "metadata": {}, + "source": [ + "The 3 annotations tables provide evidence for the clinical annotations, can be connected by joining with the `clinical_ann_evidence.tsv` file. In general a clinical annotation can have multiple variant annotations as evidence, and a variant annotation can be used as evidence for multiple clinical annotations (in theory, I've not actually observed this).\n", + "\n", + "Each of these tables has a \"Direction of effect\" column, and the type of \"effect\" is different for each - likelihood of side effects, formation of product, metabolism of drug, etc.\n", + "\n", + "**Question for OT**: when we say \"direction of effect\", do we mean any of these \"effects\"? I.e. should we include all three of these tables or focus on one?" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "id": "d43fd147-43b4-4541-9595-f757da937e60", + "metadata": {}, + "outputs": [], + "source": [ + "clinical_annotations = read_tsv_to_df(os.path.join(data_dir, 'clinical_annotations.tsv'))\n", + "clinical_ann_evidence = read_tsv_to_df(os.path.join(data_dir, 'clinical_ann_evidence.tsv'))\n", + "clinical_ann_alleles = read_tsv_to_df(os.path.join(data_dir, 'clinical_ann_alleles.tsv'))" + ] + }, + { + "cell_type": "code", + "execution_count": 122, + "id": "1a553aac-a9f7-4579-ab7c-05fa6f90ddfe", + "metadata": {}, + "outputs": [], + "source": [ + "main_df = pd.merge(clinical_annotations, clinical_ann_evidence, how='left', on=ID_COL_NAME)\n", + "main_df = main_df[[\n", + " # Main table\n", + " 'Clinical Annotation ID', 'Variant/Haplotypes', 'Gene', 'Level of Evidence', 'Phenotype Category', 'Drug(s)', 'Phenotype(s)',\n", + " # Evidence table\n", + " 'Evidence ID', 'Evidence Type', 'PMID', 'Summary',\n", + "]]" + ] + }, + { + "cell_type": "markdown", + "id": "5945f09b-9516-4d65-ad75-d27a5a1890cf", + "metadata": {}, + "source": [ + "#### Example clinical annotation\n", + "\n", + "[Top of page](#Table-of-contents)\n", + "\n", + "Looking at [981755803](https://www.pharmgkb.org/clinicalAnnotation/981755803), which has all three types of variant annotation evidence as well as label/guideline evidence." + ] + }, + { + "cell_type": "code", + "execution_count": 124, + "id": "f5bb8c9e-baeb-4ef6-9373-7c38a333601c", + "metadata": {}, + "outputs": [], + "source": [ + "df_981755803 = main_df[main_df[ID_COL_NAME] == '981755803']\n", + "\n", + "df_981755803_drug = pd.merge(df_981755803, var_drug_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_drug'))\n", + "df_981755803_pheno = pd.merge(df_981755803, var_pheno_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_pheno'))\n", + "df_981755803_fa = pd.merge(df_981755803, var_fa_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_fa'))" + ] + }, + { + "cell_type": "code", + "execution_count": 229, + "id": "811adf62-6f79-4451-9a3e-2772057e4a01", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Number of evidence 30\n", + "Number of var/drug evidence 24\n", + "Number of var/fa evidence 2\n", + "Number of var/pheno evidence 2\n" + ] + } + ], + "source": [ + "print('Number of evidence', len(df_981755803))\n", + "print('Number of var/drug evidence', len(df_981755803_drug))\n", + "print('Number of var/fa evidence', len(df_981755803_fa))\n", + "print('Number of var/pheno evidence', len(df_981755803_pheno))" + ] + }, + { + "cell_type": "code", + "execution_count": 248, + "id": "c4a15bc6-90fc-4d4b-bd0e-621b8ffd6093", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -410,21 +1775,237 @@ " \n", " \n", " \n", - " \n", + " \n", " \n", - " \n", - " \n", - " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -437,58 +2018,393 @@ " \n", " \n", " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", "
Clinical Annotation IDVariant/HaplotypesGeneLevel of EvidencePhenotype CategoryDrug(s)Phenotype(s)Evidence IDEvidence TypePMIDSummaryVariant Annotation IDVariant/Haplotypes_var_drugGene_var_drugDrug(s)_var_drugPMID_var_drugPhenotype Category_var_drugSignificanceNotesSentenceAllelesSpecialty PopulationMetabolizer typesisPluralIs/Is Not associatedDirection of effectPD/PK termsMultiple drugs And/orPopulation typesPopulation Phenotypes or diseasesMultiple phenotypes or diseases And/orComparison Allele(s) or Genotype(s)Comparison Metabolizer types
0981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis981755665Variant Drug Annotation21083385Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis.981755665rs75527207CFTRivacaftor21083385Efficacynot statedClinical trials were carried out to test efficacy of ivacaftor selecting only patients with the CFTR G551D mutation on at least one allele (genotype AA or AG).Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis.AA + AGNaNNaNAreAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
1981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis981755678Variant Drug Annotation22047557Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis.981755678rs75527207CFTRivacaftor22047557Efficacynot statedA clinical trial that selected patients with the G551D CFTR mutation (rs75527207 genotype AA or AG). Patients without this mutation were excluded. One patient included in the placebo group was homozygous for F508del (rs113993960 genotype del/del).Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis.AA + AGNaNNaNAreAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
2981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis982009991Variant Drug Annotation23590265Allele A is associated with response to ivacaftor in children with Cystic Fibrosis.982009991rs75527207CFTRivacaftor23590265EfficacyyesPatients aged 6-11 at time of screening who had at least one allele with the G551D mutation (allele A at position rs75527207) were recruited for this trial. Ivacaftor is only indicated in CF patients with this mutation. Significant improvements in lung function were seen in the ivacaftor treatment group compared to placebo.Allele A is associated with response to ivacaftor in children with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin children withDisease:Cystic FibrosisNaNNaNNaN
3981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1183629335Variant Drug Annotation24066763Genotype AA is associated with response to ivacaftor in women with Cystic Fibrosis.1183629335rs75527207CFTRivacaftor24066763Efficacynot statedCase report of a female homozygous for the G551D CFTR mutation (genotype AA) in which ivacaftor was efficacious: increased absolute change in percent of predicted FEV1, increased weight and walk distance and decreased sweat chloride levels over a 12 month course with no sign of plateau to date.Genotype AA is associated with response to ivacaftor in women with Cystic Fibrosis.AANaNNaNIsAssociated withNaNresponse toNaNin women withDisease:Cystic FibrosisNaNNaNNaN
4981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1448423752Variant Drug Annotation27773592Genotypes AA + AG is associated with increased response to ivacaftor in people with Cystic Fibrosis as compared to genotype GG.1448423752rs75527207CFTRivacaftor27773592EfficacyyesThe outcome of change in sweat chloride was correlated with change in FEV1 in patients with cystic fibrosis and found to have improved results for both.Genotypes AA + AG is associated with increased response to ivacaftor in people with Cystic Fibrosis as compared to genotype GG.AA + AGPediatricNaNIsAssociated withincreasedresponse toNaNin people withDisease:Cystic FibrosisNaNGGNaN
5981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449191908Variant Drug Annotation25682022Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449191908rs75527207CFTRivacaftor25682022Efficacynot statedStudy was an expanded access program targeted at patients with severe lung disease and was not powered to determine efficacy. Majority of patients reported an improvement in FEV following 24 weeks of treatment.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
6981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192055Variant Drug Annotation28711222Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449192055rs75527207CFTRivacaftor28711222EfficacyyesG551D allele. Statistically significant increases in FEV1, weight and BMI and statistically significant decreases in sweat chloride level, the number of days of antibiotic treatment and in the use of some maintenance treatments.; No differences in bone density, pancreatic insufficiency and cystic fibrosis related diabetes were observed.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
7981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192093Variant Drug Annotation25311995Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449192093rs75527207CFTRivacaftor25311995Efficacynot statedG551 D allele. Increases in FEV1, body weight, CFQ-R scores and time to first pulmonary exacerbation were observed.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
8981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192439Variant Drug Annotation28611235Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449192439rs75527207CFTRivacaftor28611235EfficacyyesG551D allele. FEV1, Alfred wellness score, exercise time, CFQ-R score and sweat chloride levels showed a significant improvement following ivacaftor treatment as compared to placebo while other outcomes (VO2, ventilation, cardiac response nd recovery following exercise) did not.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.ANaNNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
9981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192481Variant Drug Annotation26135562Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449192481rs75527207CFTRivacaftor26135562EfficacyyesG551D allele. Analysis of CFQ-R scores from participants in the STRIVE trial. Scores for eating problems, health perceptions, physical functioning, respiratory symptoms, social functioning, treatment burden and vitality showed significant improvements following ivacaftor treatment.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
10981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192494Variant Drug Annotation25171465Allele A is associated with response to ivacaftor in children with Cystic Fibrosis.1449192494rs75527207CFTRivacaftor25171465Efficacynot statedCase study of a pediatric cystic fibrosis patient. Improvements in sweat chloride, BMI, bronchiectasis and lung function reported following ivacaftor treatment.Allele A is associated with response to ivacaftor in children with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin children withDisease:Cystic FibrosisNaNNaNNaN
11981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192576Variant Drug Annotation25755212Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449192576rs75527207CFTRivacaftor25755212EfficacyyesPost hoc analysis of clinical outcomes of the STRIVE and ENVISION trials. Participants were split into tertiles based on FEV1 score and outcomes in change in baseline FEV1, body weight, CFQ-R score and sweat chloride levels as well as number of days of pulmonary exacerbation were assessed. All outcomes were significantly improved in the upper tertile, all outcomes apart from number of days of pulmonary exacerbation were significantly improved in the middle tertile and absolute change in FEV1, body weight and sweat chloride levels were significantly improved in the lower tertile.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
12981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192615Variant Drug Annotation26568242Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449192615rs75527207CFTRivacaftor26568242EfficacyyesResponse measured by changes in sweat chloride levels, FEV1 and BMI.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
13981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192709Variant Drug Annotation25473543Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449192709rs75527207CFTRivacaftor25473543Efficacynot statedG551D allele. Case report of three patients with the F508del/G551D genotype. Reported improvements in FEV1, body weight, sweat chloride levels and scores in the respiratory domain of the CFQ-R.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.ANaNNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
14981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1449192721Variant Drug Annotation25145599Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1449192721rs75527207CFTRivacaftor25145599EfficacyyesG551D allele. Significant increases in %FVC and %FEV1 compared to baseline were seen at 6 months of ivacaftor treatment, but both measures declined to baseline by 12 months of ivacaftor treatment. Significant improvements in BMI, body weight, sinus disease status and sweat chloride levels were seen at 12 months of ivacaftor treatment.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
15981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1450043422Variant Drug Annotation23628510Allele A is associated with response to ivacaftor in children with Cystic Fibrosis.1450043422rs75527207CFTRivacaftor23628510EfficacyyesNaNAllele A is associated with response to ivacaftor in children with Cystic Fibrosis.APediatricNaNIsAssociated withNaNresponse toNaNin children withDisease:Cystic FibrosisNaNNaNNaN
016981755803rs75527207CFTREfficacyivacaftorCystic Fibrosis9817556651184512440Variant Drug Annotation21083385Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis.98175566525049054Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1184512440rs75527207CFTRivacaftor2108338525049054EfficacyyesPatients with at least one G551D-CFTR allele were recruited and treated with ivacaftor for one year. Mean weight and BMI improved at 6 months from baseline, but only mean weight was increased again at 12 months. Mean percentage FVC, FEV1 and FEF25-75% returned to baseline levels by 12 months of treatment.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.ANaNNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
17981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis981755746Variant Drug Annotation22942289Allele A is associated with increased response to ivacaftor.981755746rs75527207CFTRivacaftor22942289Efficacynot statedClinical trials were carried out to test efficacy of ivacaftor selecting only patients with the CFTR G551D mutation on at least one allele (genotype AA or AG).In vitro studies using proteoliposomes containing CFTR, or CFTR with the G551D mutation (rs75527207 allele A), or CFTR with the F508del mutation (rs113993960 allele del). Ivacaftor in the presence of ATP potentiated channel activity of CFTR-G551D.Allele A is associated with increased response to ivacaftor.ANaNNaNIsAssociated withincreasedresponse toNaNNaNNaNNaNNaNNaN
18981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis981755699Variant Drug Annotation19846789Allele A is associated with increased response to ivacaftor.981755699rs75527207CFTRivacaftor19846789EfficacyyesIn vitro assays that show ivacaftor potentiates CFTR with the G551D mutation (rs75527207 allele A) - see details described in study parameters.Allele A is associated with increased response to ivacaftor.ANaNNaNIsAssociated withincreasedresponse toNaNNaNNaNNaNNaNNaN
19981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis981755787Variant Drug Annotation22293084Allele A is associated with increased response to ivacaftor.981755787rs75527207CFTRivacaftor22293084Efficacyyesas compared to baseline. In vitro assays using transfected Fisher Rat Thyroid cells expressing CFTR. Before treatment, cells were activated by exposure to PKA and ATP before ivacaftor treatment. In vitro assays using transfected Fisher Rat Thyroid cells expressing CFTR. Cells expressing G551D-CFTR (rs75527207 allele A) responded to ivacaftor treatment with a significantly enhanced channel open probability and increased chloride transport. Single channel current amplitude at 80mV was not significantly enhanced.Allele A is associated with increased response to ivacaftor.ANaNNaNIsAssociated withincreasedresponse toNaNNaNNaNNaNNaNNaN
20981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1043737597Variant Drug Annotation23757359Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.1043737597rs75527207CFTRivacaftor23757359EfficacyyesA retrospective study of patients in Germany with severe Cystic Fibrosis (FEV1 <40%predicted) with the G551D mutation who were treated with ivacaftor. On average, FEV1and body weight increased significantly, though response was variable in this patient group and several patients discontinued ivacaftor for different complications.Allele A is associated with response to ivacaftor in people with Cystic Fibrosis.ANaNNaNIsAssociated withNaNresponse toNaNin people withDisease:Cystic FibrosisNaNNaNNaN
21981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis982006840Variant Drug Annotation23313410Allele A is associated with response to ivacaftor in men with Cystic Fibrosis.982006840rs75527207CFTRivacaftor23313410Efficacynot statedA case report of lung function improvements 6 months after treatment with ivacaftor in a male patient with severe lung disease - he had the CFTR G511D (rsrs75527207 allele A)/deltaF508 genotype (rs113993960 del CTT) and so could be given ivacaftor.Allele A is associated with response to ivacaftor in men with Cystic Fibrosis.ANaNNaNIsAssociated withNaNresponse toNaNin men withDisease:Cystic FibrosisNaNNaNNaN
22981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1446903789Variant Drug Annotation24461666Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis.1446903789rs75527207CFTRivacaftor24461666EfficacyyesThe authors wanted to assess the efficacy of ivacaftor in patients with cystic fibrosis who have normal spirometry. The authors assessed lung function improvement in patients using lung clearance index (LCI) as well as forced expiratory volume in 1 second (FEV1), and only included patients with < 90% FEV1 values. The primary outcome was change in LCI from baseline. This was a phase 2, multi-centre, placebo-controlled, 2x2 crossover study. One group, sequence 1, took placebo first, followed by 28 day washout, then took ivacaftor 150 mg 2x daily for 4 weeks. The second group had the sequence of treatment reversed.Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis.AA + AGNaNPediatricNaNAreAssociated withNaNNaN
23981755803rs75527207CFTR1AEfficacyivacaftorCystic Fibrosis1448099051Variant Drug Annotation27158673Genotypes AA + AG are associated with increased response to ivacaftor in people with Cystic Fibrosis as compared to genotype GG.1448099051rs75527207CFTRivacaftor27158673EfficacyyesMeasured in adult patients, with changes in lung volume, sweat chloride, distensibility, wall thickness, expiratory lumen area, and inspiratory lumen area measured before starting ivacaftor and 48 hour after starting ivacaftor.Genotypes AA + AG are associated with increased response to ivacaftor in people with Cystic Fibrosis as compared to genotype GG.AA + AGNaNNaNAreAssociated withincreasedresponse toNaNin people withDisease:Cystic FibrosisNaNGGNaN
\n", "
" ], "text/plain": [ - " Clinical Annotation ID Variant/Haplotypes Gene Level of Evidence \\\n", - "0 981755803 rs75527207 CFTR 1A \n", + " Clinical Annotation ID Variant/Haplotypes Gene Level of Evidence \\\n", + "0 981755803 rs75527207 CFTR 1A \n", + "1 981755803 rs75527207 CFTR 1A \n", + "2 981755803 rs75527207 CFTR 1A \n", + "3 981755803 rs75527207 CFTR 1A \n", + "4 981755803 rs75527207 CFTR 1A \n", + "5 981755803 rs75527207 CFTR 1A \n", + "6 981755803 rs75527207 CFTR 1A \n", + "7 981755803 rs75527207 CFTR 1A \n", + "8 981755803 rs75527207 CFTR 1A \n", + "9 981755803 rs75527207 CFTR 1A \n", + "10 981755803 rs75527207 CFTR 1A \n", + "11 981755803 rs75527207 CFTR 1A \n", + "12 981755803 rs75527207 CFTR 1A \n", + "13 981755803 rs75527207 CFTR 1A \n", + "14 981755803 rs75527207 CFTR 1A \n", + "15 981755803 rs75527207 CFTR 1A \n", + "16 981755803 rs75527207 CFTR 1A \n", + "17 981755803 rs75527207 CFTR 1A \n", + "18 981755803 rs75527207 CFTR 1A \n", + "19 981755803 rs75527207 CFTR 1A \n", + "20 981755803 rs75527207 CFTR 1A \n", + "21 981755803 rs75527207 CFTR 1A \n", + "22 981755803 rs75527207 CFTR 1A \n", + "23 981755803 rs75527207 CFTR 1A \n", "\n", - " Phenotype Category Drug(s) Phenotype(s) Evidence ID \\\n", - "0 Efficacy ivacaftor Cystic Fibrosis 981755665 \n", + " Phenotype Category Drug(s) Phenotype(s) Evidence ID \\\n", + "0 Efficacy ivacaftor Cystic Fibrosis 981755665 \n", + "1 Efficacy ivacaftor Cystic Fibrosis 981755678 \n", + "2 Efficacy ivacaftor Cystic Fibrosis 982009991 \n", + "3 Efficacy ivacaftor Cystic Fibrosis 1183629335 \n", + "4 Efficacy ivacaftor Cystic Fibrosis 1448423752 \n", + "5 Efficacy ivacaftor Cystic Fibrosis 1449191908 \n", + "6 Efficacy ivacaftor Cystic Fibrosis 1449192055 \n", + "7 Efficacy ivacaftor Cystic Fibrosis 1449192093 \n", + "8 Efficacy ivacaftor Cystic Fibrosis 1449192439 \n", + "9 Efficacy ivacaftor Cystic Fibrosis 1449192481 \n", + "10 Efficacy ivacaftor Cystic Fibrosis 1449192494 \n", + "11 Efficacy ivacaftor Cystic Fibrosis 1449192576 \n", + "12 Efficacy ivacaftor Cystic Fibrosis 1449192615 \n", + "13 Efficacy ivacaftor Cystic Fibrosis 1449192709 \n", + "14 Efficacy ivacaftor Cystic Fibrosis 1449192721 \n", + "15 Efficacy ivacaftor Cystic Fibrosis 1450043422 \n", + "16 Efficacy ivacaftor Cystic Fibrosis 1184512440 \n", + "17 Efficacy ivacaftor Cystic Fibrosis 981755746 \n", + "18 Efficacy ivacaftor Cystic Fibrosis 981755699 \n", + "19 Efficacy ivacaftor Cystic Fibrosis 981755787 \n", + "20 Efficacy ivacaftor Cystic Fibrosis 1043737597 \n", + "21 Efficacy ivacaftor Cystic Fibrosis 982006840 \n", + "22 Efficacy ivacaftor Cystic Fibrosis 1446903789 \n", + "23 Efficacy ivacaftor Cystic Fibrosis 1448099051 \n", "\n", - " Evidence Type PMID \\\n", - "0 Variant Drug Annotation 21083385 \n", + " Evidence Type PMID \\\n", + "0 Variant Drug Annotation 21083385 \n", + "1 Variant Drug Annotation 22047557 \n", + "2 Variant Drug Annotation 23590265 \n", + "3 Variant Drug Annotation 24066763 \n", + "4 Variant Drug Annotation 27773592 \n", + "5 Variant Drug Annotation 25682022 \n", + "6 Variant Drug Annotation 28711222 \n", + "7 Variant Drug Annotation 25311995 \n", + "8 Variant Drug Annotation 28611235 \n", + "9 Variant Drug Annotation 26135562 \n", + "10 Variant Drug Annotation 25171465 \n", + "11 Variant Drug Annotation 25755212 \n", + "12 Variant Drug Annotation 26568242 \n", + "13 Variant Drug Annotation 25473543 \n", + "14 Variant Drug Annotation 25145599 \n", + "15 Variant Drug Annotation 23628510 \n", + "16 Variant Drug Annotation 25049054 \n", + "17 Variant Drug Annotation 22942289 \n", + "18 Variant Drug Annotation 19846789 \n", + "19 Variant Drug Annotation 22293084 \n", + "20 Variant Drug Annotation 23757359 \n", + "21 Variant Drug Annotation 23313410 \n", + "22 Variant Drug Annotation 24461666 \n", + "23 Variant Drug Annotation 27158673 \n", "\n", - " Summary \\\n", - "0 Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis. \n", + " Summary \\\n", + "0 Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "1 Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "2 Allele A is associated with response to ivacaftor in children with Cystic Fibrosis. \n", + "3 Genotype AA is associated with response to ivacaftor in women with Cystic Fibrosis. \n", + "4 Genotypes AA + AG is associated with increased response to ivacaftor in people with Cystic Fibrosis as compared to genotype GG. \n", + "5 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "6 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "7 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "8 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "9 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "10 Allele A is associated with response to ivacaftor in children with Cystic Fibrosis. \n", + "11 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "12 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "13 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "14 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "15 Allele A is associated with response to ivacaftor in children with Cystic Fibrosis. \n", + "16 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "17 Allele A is associated with increased response to ivacaftor. \n", + "18 Allele A is associated with increased response to ivacaftor. \n", + "19 Allele A is associated with increased response to ivacaftor. \n", + "20 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "21 Allele A is associated with response to ivacaftor in men with Cystic Fibrosis. \n", + "22 Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "23 Genotypes AA + AG are associated with increased response to ivacaftor in people with Cystic Fibrosis as compared to genotype GG. \n", "\n", - " Variant Annotation ID Variant/Haplotypes_var_drug Gene_var_drug \\\n", - "0 981755665 rs75527207 CFTR \n", + " Variant Annotation ID Variant/Haplotypes_var_drug Gene_var_drug \\\n", + "0 981755665 rs75527207 CFTR \n", + "1 981755678 rs75527207 CFTR \n", + "2 982009991 rs75527207 CFTR \n", + "3 1183629335 rs75527207 CFTR \n", + "4 1448423752 rs75527207 CFTR \n", + "5 1449191908 rs75527207 CFTR \n", + "6 1449192055 rs75527207 CFTR \n", + "7 1449192093 rs75527207 CFTR \n", + "8 1449192439 rs75527207 CFTR \n", + "9 1449192481 rs75527207 CFTR \n", + "10 1449192494 rs75527207 CFTR \n", + "11 1449192576 rs75527207 CFTR \n", + "12 1449192615 rs75527207 CFTR \n", + "13 1449192709 rs75527207 CFTR \n", + "14 1449192721 rs75527207 CFTR \n", + "15 1450043422 rs75527207 CFTR \n", + "16 1184512440 rs75527207 CFTR \n", + "17 981755746 rs75527207 CFTR \n", + "18 981755699 rs75527207 CFTR \n", + "19 981755787 rs75527207 CFTR \n", + "20 1043737597 rs75527207 CFTR \n", + "21 982006840 rs75527207 CFTR \n", + "22 1446903789 rs75527207 CFTR \n", + "23 1448099051 rs75527207 CFTR \n", "\n", - " Drug(s)_var_drug PMID_var_drug Phenotype Category_var_drug Significance \\\n", - "0 ivacaftor 21083385 Efficacy not stated \n", + " Drug(s)_var_drug PMID_var_drug Phenotype Category_var_drug Significance \\\n", + "0 ivacaftor 21083385 Efficacy not stated \n", + "1 ivacaftor 22047557 Efficacy not stated \n", + "2 ivacaftor 23590265 Efficacy yes \n", + "3 ivacaftor 24066763 Efficacy not stated \n", + "4 ivacaftor 27773592 Efficacy yes \n", + "5 ivacaftor 25682022 Efficacy not stated \n", + "6 ivacaftor 28711222 Efficacy yes \n", + "7 ivacaftor 25311995 Efficacy not stated \n", + "8 ivacaftor 28611235 Efficacy yes \n", + "9 ivacaftor 26135562 Efficacy yes \n", + "10 ivacaftor 25171465 Efficacy not stated \n", + "11 ivacaftor 25755212 Efficacy yes \n", + "12 ivacaftor 26568242 Efficacy yes \n", + "13 ivacaftor 25473543 Efficacy not stated \n", + "14 ivacaftor 25145599 Efficacy yes \n", + "15 ivacaftor 23628510 Efficacy yes \n", + "16 ivacaftor 25049054 Efficacy yes \n", + "17 ivacaftor 22942289 Efficacy not stated \n", + "18 ivacaftor 19846789 Efficacy yes \n", + "19 ivacaftor 22293084 Efficacy yes \n", + "20 ivacaftor 23757359 Efficacy yes \n", + "21 ivacaftor 23313410 Efficacy not stated \n", + "22 ivacaftor 24461666 Efficacy yes \n", + "23 ivacaftor 27158673 Efficacy yes \n", "\n", - " Notes \\\n", - "0 Clinical trials were carried out to test efficacy of ivacaftor selecting only patients with the CFTR G551D mutation on at least one allele (genotype AA or AG). \n", + " Notes \\\n", + "0 Clinical trials were carried out to test efficacy of ivacaftor selecting only patients with the CFTR G551D mutation on at least one allele (genotype AA or AG). \n", + "1 A clinical trial that selected patients with the G551D CFTR mutation (rs75527207 genotype AA or AG). Patients without this mutation were excluded. One patient included in the placebo group was homozygous for F508del (rs113993960 genotype del/del). \n", + "2 Patients aged 6-11 at time of screening who had at least one allele with the G551D mutation (allele A at position rs75527207) were recruited for this trial. Ivacaftor is only indicated in CF patients with this mutation. Significant improvements in lung function were seen in the ivacaftor treatment group compared to placebo. \n", + "3 Case report of a female homozygous for the G551D CFTR mutation (genotype AA) in which ivacaftor was efficacious: increased absolute change in percent of predicted FEV1, increased weight and walk distance and decreased sweat chloride levels over a 12 month course with no sign of plateau to date. \n", + "4 The outcome of change in sweat chloride was correlated with change in FEV1 in patients with cystic fibrosis and found to have improved results for both. \n", + "5 Study was an expanded access program targeted at patients with severe lung disease and was not powered to determine efficacy. Majority of patients reported an improvement in FEV following 24 weeks of treatment. \n", + "6 G551D allele. Statistically significant increases in FEV1, weight and BMI and statistically significant decreases in sweat chloride level, the number of days of antibiotic treatment and in the use of some maintenance treatments.; No differences in bone density, pancreatic insufficiency and cystic fibrosis related diabetes were observed. \n", + "7 G551 D allele. Increases in FEV1, body weight, CFQ-R scores and time to first pulmonary exacerbation were observed. \n", + "8 G551D allele. FEV1, Alfred wellness score, exercise time, CFQ-R score and sweat chloride levels showed a significant improvement following ivacaftor treatment as compared to placebo while other outcomes (VO2, ventilation, cardiac response nd recovery following exercise) did not. \n", + "9 G551D allele. Analysis of CFQ-R scores from participants in the STRIVE trial. Scores for eating problems, health perceptions, physical functioning, respiratory symptoms, social functioning, treatment burden and vitality showed significant improvements following ivacaftor treatment. \n", + "10 Case study of a pediatric cystic fibrosis patient. Improvements in sweat chloride, BMI, bronchiectasis and lung function reported following ivacaftor treatment. \n", + "11 Post hoc analysis of clinical outcomes of the STRIVE and ENVISION trials. Participants were split into tertiles based on FEV1 score and outcomes in change in baseline FEV1, body weight, CFQ-R score and sweat chloride levels as well as number of days of pulmonary exacerbation were assessed. All outcomes were significantly improved in the upper tertile, all outcomes apart from number of days of pulmonary exacerbation were significantly improved in the middle tertile and absolute change in FEV1, body weight and sweat chloride levels were significantly improved in the lower tertile. \n", + "12 Response measured by changes in sweat chloride levels, FEV1 and BMI. \n", + "13 G551D allele. Case report of three patients with the F508del/G551D genotype. Reported improvements in FEV1, body weight, sweat chloride levels and scores in the respiratory domain of the CFQ-R. \n", + "14 G551D allele. Significant increases in %FVC and %FEV1 compared to baseline were seen at 6 months of ivacaftor treatment, but both measures declined to baseline by 12 months of ivacaftor treatment. Significant improvements in BMI, body weight, sinus disease status and sweat chloride levels were seen at 12 months of ivacaftor treatment. \n", + "15 NaN \n", + "16 Patients with at least one G551D-CFTR allele were recruited and treated with ivacaftor for one year. Mean weight and BMI improved at 6 months from baseline, but only mean weight was increased again at 12 months. Mean percentage FVC, FEV1 and FEF25-75% returned to baseline levels by 12 months of treatment. \n", + "17 In vitro studies using proteoliposomes containing CFTR, or CFTR with the G551D mutation (rs75527207 allele A), or CFTR with the F508del mutation (rs113993960 allele del). Ivacaftor in the presence of ATP potentiated channel activity of CFTR-G551D. \n", + "18 In vitro assays that show ivacaftor potentiates CFTR with the G551D mutation (rs75527207 allele A) - see details described in study parameters. \n", + "19 as compared to baseline. In vitro assays using transfected Fisher Rat Thyroid cells expressing CFTR. Before treatment, cells were activated by exposure to PKA and ATP before ivacaftor treatment. In vitro assays using transfected Fisher Rat Thyroid cells expressing CFTR. Cells expressing G551D-CFTR (rs75527207 allele A) responded to ivacaftor treatment with a significantly enhanced channel open probability and increased chloride transport. Single channel current amplitude at 80mV was not significantly enhanced. \n", + "20 A retrospective study of patients in Germany with severe Cystic Fibrosis (FEV1 <40%predicted) with the G551D mutation who were treated with ivacaftor. On average, FEV1and body weight increased significantly, though response was variable in this patient group and several patients discontinued ivacaftor for different complications. \n", + "21 A case report of lung function improvements 6 months after treatment with ivacaftor in a male patient with severe lung disease - he had the CFTR G511D (rsrs75527207 allele A)/deltaF508 genotype (rs113993960 del CTT) and so could be given ivacaftor. \n", + "22 The authors wanted to assess the efficacy of ivacaftor in patients with cystic fibrosis who have normal spirometry. The authors assessed lung function improvement in patients using lung clearance index (LCI) as well as forced expiratory volume in 1 second (FEV1), and only included patients with < 90% FEV1 values. The primary outcome was change in LCI from baseline. This was a phase 2, multi-centre, placebo-controlled, 2x2 crossover study. One group, sequence 1, took placebo first, followed by 28 day washout, then took ivacaftor 150 mg 2x daily for 4 weeks. The second group had the sequence of treatment reversed. \n", + "23 Measured in adult patients, with changes in lung volume, sweat chloride, distensibility, wall thickness, expiratory lumen area, and inspiratory lumen area measured before starting ivacaftor and 48 hour after starting ivacaftor. \n", "\n", - " Sentence \\\n", - "0 Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis. \n", + " Sentence \\\n", + "0 Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "1 Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "2 Allele A is associated with response to ivacaftor in children with Cystic Fibrosis. \n", + "3 Genotype AA is associated with response to ivacaftor in women with Cystic Fibrosis. \n", + "4 Genotypes AA + AG is associated with increased response to ivacaftor in people with Cystic Fibrosis as compared to genotype GG. \n", + "5 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "6 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "7 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "8 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "9 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "10 Allele A is associated with response to ivacaftor in children with Cystic Fibrosis. \n", + "11 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "12 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "13 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "14 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "15 Allele A is associated with response to ivacaftor in children with Cystic Fibrosis. \n", + "16 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "17 Allele A is associated with increased response to ivacaftor. \n", + "18 Allele A is associated with increased response to ivacaftor. \n", + "19 Allele A is associated with increased response to ivacaftor. \n", + "20 Allele A is associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "21 Allele A is associated with response to ivacaftor in men with Cystic Fibrosis. \n", + "22 Genotypes AA + AG are associated with response to ivacaftor in people with Cystic Fibrosis. \n", + "23 Genotypes AA + AG are associated with increased response to ivacaftor in people with Cystic Fibrosis as compared to genotype GG. \n", "\n", - " Alleles Specialty Population Metabolizer types isPlural \\\n", - "0 AA + AG NaN NaN Are \n", + " Alleles Specialty Population Metabolizer types isPlural \\\n", + "0 AA + AG NaN NaN Are \n", + "1 AA + AG NaN NaN Are \n", + "2 A Pediatric NaN Is \n", + "3 AA NaN NaN Is \n", + "4 AA + AG Pediatric NaN Is \n", + "5 A Pediatric NaN Is \n", + "6 A Pediatric NaN Is \n", + "7 A Pediatric NaN Is \n", + "8 A NaN NaN Is \n", + "9 A Pediatric NaN Is \n", + "10 A Pediatric NaN Is \n", + "11 A Pediatric NaN Is \n", + "12 A Pediatric NaN Is \n", + "13 A NaN NaN Is \n", + "14 A Pediatric NaN Is \n", + "15 A Pediatric NaN Is \n", + "16 A NaN NaN Is \n", + "17 A NaN NaN Is \n", + "18 A NaN NaN Is \n", + "19 A NaN NaN Is \n", + "20 A NaN NaN Is \n", + "21 A NaN NaN Is \n", + "22 AA + AG Pediatric NaN Are \n", + "23 AA + AG NaN NaN Are \n", "\n", - " Is/Is Not associated Direction of effect PD/PK terms Multiple drugs And/or \\\n", - "0 Associated with NaN response to NaN \n", + " Is/Is Not associated Direction of effect PD/PK terms \\\n", + "0 Associated with NaN response to \n", + "1 Associated with NaN response to \n", + "2 Associated with NaN response to \n", + "3 Associated with NaN response to \n", + "4 Associated with increased response to \n", + "5 Associated with NaN response to \n", + "6 Associated with NaN response to \n", + "7 Associated with NaN response to \n", + "8 Associated with NaN response to \n", + "9 Associated with NaN response to \n", + "10 Associated with NaN response to \n", + "11 Associated with NaN response to \n", + "12 Associated with NaN response to \n", + "13 Associated with NaN response to \n", + "14 Associated with NaN response to \n", + "15 Associated with NaN response to \n", + "16 Associated with NaN response to \n", + "17 Associated with increased response to \n", + "18 Associated with increased response to \n", + "19 Associated with increased response to \n", + "20 Associated with NaN response to \n", + "21 Associated with NaN response to \n", + "22 Associated with NaN response to \n", + "23 Associated with increased response to \n", "\n", - " Population types Population Phenotypes or diseases \\\n", - "0 in people with Disease:Cystic Fibrosis \n", + " Multiple drugs And/or Population types Population Phenotypes or diseases \\\n", + "0 NaN in people with Disease:Cystic Fibrosis \n", + "1 NaN in people with Disease:Cystic Fibrosis \n", + "2 NaN in children with Disease:Cystic Fibrosis \n", + "3 NaN in women with Disease:Cystic Fibrosis \n", + "4 NaN in people with Disease:Cystic Fibrosis \n", + "5 NaN in people with Disease:Cystic Fibrosis \n", + "6 NaN in people with Disease:Cystic Fibrosis \n", + "7 NaN in people with Disease:Cystic Fibrosis \n", + "8 NaN in people with Disease:Cystic Fibrosis \n", + "9 NaN in people with Disease:Cystic Fibrosis \n", + "10 NaN in children with Disease:Cystic Fibrosis \n", + "11 NaN in people with Disease:Cystic Fibrosis \n", + "12 NaN in people with Disease:Cystic Fibrosis \n", + "13 NaN in people with Disease:Cystic Fibrosis \n", + "14 NaN in people with Disease:Cystic Fibrosis \n", + "15 NaN in children with Disease:Cystic Fibrosis \n", + "16 NaN in people with Disease:Cystic Fibrosis \n", + "17 NaN NaN NaN \n", + "18 NaN NaN NaN \n", + "19 NaN NaN NaN \n", + "20 NaN in people with Disease:Cystic Fibrosis \n", + "21 NaN in men with Disease:Cystic Fibrosis \n", + "22 NaN in people with Disease:Cystic Fibrosis \n", + "23 NaN in people with Disease:Cystic Fibrosis \n", "\n", - " Multiple phenotypes or diseases And/or Comparison Allele(s) or Genotype(s) \\\n", - "0 NaN NaN \n", + " Multiple phenotypes or diseases And/or Comparison Allele(s) or Genotype(s) \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN GG \n", + "5 NaN NaN \n", + "6 NaN NaN \n", + "7 NaN NaN \n", + "8 NaN NaN \n", + "9 NaN NaN \n", + "10 NaN NaN \n", + "11 NaN NaN \n", + "12 NaN NaN \n", + "13 NaN NaN \n", + "14 NaN NaN \n", + "15 NaN NaN \n", + "16 NaN NaN \n", + "17 NaN NaN \n", + "18 NaN NaN \n", + "19 NaN NaN \n", + "20 NaN NaN \n", + "21 NaN NaN \n", + "22 NaN NaN \n", + "23 NaN GG \n", "\n", - " Comparison Metabolizer types \n", - "0 NaN " + " Comparison Metabolizer types \n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "5 NaN \n", + "6 NaN \n", + "7 NaN \n", + "8 NaN \n", + "9 NaN \n", + "10 NaN \n", + "11 NaN \n", + "12 NaN \n", + "13 NaN \n", + "14 NaN \n", + "15 NaN \n", + "16 NaN \n", + "17 NaN \n", + "18 NaN \n", + "19 NaN \n", + "20 NaN \n", + "21 NaN \n", + "22 NaN \n", + "23 NaN " ] }, - "execution_count": 206, + "execution_count": 248, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df_981755803_drug.head(1)" + "df_981755803_drug" ] }, { @@ -2178,10 +4094,64 @@ "* Using the additional phenotype annotations (side effect etc.) to disambiguate or supplement the phenotype information we use from the clinical annotation" ] }, + { + "cell_type": "markdown", + "id": "72471a5a-8c7f-4d4c-ae6f-92fa86c13d34", + "metadata": {}, + "source": [ + "## Post-meeting\n", + "\n", + "* Get a few representative (?!) examples of annotations\n", + "* Join with all variant evidence _and_ all clinical_alleles\n", + "* Dump to CSV" + ] + }, + { + "cell_type": "code", + "execution_count": 285, + "id": "442da098-f2a2-4436-89a0-e7a4760aad7d", + "metadata": {}, + "outputs": [], + "source": [ + "# Build a clean table showing everything\n", + "complete_df = pd.merge(clinical_annotations, clinical_ann_evidence, how='left', on=ID_COL_NAME)\n", + "complete_df = pd.merge(complete_df, clinical_ann_alleles, how='left', on=ID_COL_NAME)" + ] + }, + { + "cell_type": "code", + "execution_count": 286, + "id": "dc9116ed-cf4d-4c01-9a2d-f6189a77ee0e", + "metadata": {}, + "outputs": [], + "source": [ + "def get_annotation_tables_for_ids(ca_ids):\n", + " df = complete_df[complete_df[ID_COL_NAME].isin({str(id) for id in ca_ids})]\n", + " df_drug = pd.merge(df, var_drug_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_drug'))\n", + " df_pheno = pd.merge(df, var_pheno_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_pheno'))\n", + " df_fa = pd.merge(df, var_fa_ann, left_on='Evidence ID', right_on='Variant Annotation ID', how='inner', suffixes=(None, '_var_fa'))\n", + " return df_drug, df_pheno, df_fa" + ] + }, + { + "cell_type": "code", + "execution_count": 276, + "id": "86bab485-ccf8-426b-9565-01fe35058871", + "metadata": {}, + "outputs": [], + "source": [ + "example_ca_ids = [981755803, 1139506787, 1183888969, 1184514050, 981419266]\n", + "\n", + "d, p, f = get_annotation_tables_for_ids(example_ca_ids)\n", + "d.to_csv(f'{data_dir}/example_drug.csv', index=False)\n", + "p.to_csv(f'{data_dir}/example_pheno.csv', index=False)\n", + "f.to_csv(f'{data_dir}/example_func.csv', index=False)" + ] + }, { "cell_type": "code", "execution_count": null, - "id": "c60bfd67-58b3-4264-b847-5847f6a14fce", + "id": "b4cee848-abf7-422d-9d64-c3c4f66f5242", "metadata": {}, "outputs": [], "source": []