From c4b283a3c44f8c562d5289c5ccc31719678dcd8b Mon Sep 17 00:00:00 2001 From: Nadia Mohammed Date: Tue, 22 Mar 2022 11:00:19 +0000 Subject: [PATCH 1/6] rows added to for loop, else statement for unknown and none reported samples as NA --- resources/home/dnanexus/reformat.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/resources/home/dnanexus/reformat.py b/resources/home/dnanexus/reformat.py index 356043c..c3ea437 100644 --- a/resources/home/dnanexus/reformat.py +++ b/resources/home/dnanexus/reformat.py @@ -204,8 +204,11 @@ def matching_sexes(data): # If reported sex is not unknown or none, then see if reported and # predicted sex is a match (false/true boolean) for idx, row in data.iterrows(): - if not (row['original_pedigree_sex'] == "unknown" or row['original_pedigree_sex'] == "none"): + if not (row['original_pedigree_sex'] == "unknown" or row['original_pedigree_sex'] == "none" or row['Predicted_Sex'] == "unknown"): data.at[idx, 'Match_Sexes'] = row['original_pedigree_sex'] == row['Predicted_Sex'] + else: + if (row['original_pedigree_sex'] == "unknown" or row['Predicted_Sex'] == "unknown" or row['original_pedigree_sex'] == "none"): + data.at[idx, 'Match_Sexes'] = "NA" # need to make the false/true boolean to string to make it # lower case for multiqc data.at[idx, 'Match_Sexes'] = str(data.at[idx, 'Match_Sexes']).lower() From d208be987e15847fc20978f851956ef49b46cc82 Mon Sep 17 00:00:00 2001 From: Nadia Mohammed Date: Tue, 22 Mar 2022 13:54:54 +0000 Subject: [PATCH 2/6] removed else statement --- resources/home/dnanexus/reformat.py | 3 --- 1 file changed, 3 deletions(-) diff --git a/resources/home/dnanexus/reformat.py b/resources/home/dnanexus/reformat.py index c3ea437..21614f7 100644 --- a/resources/home/dnanexus/reformat.py +++ b/resources/home/dnanexus/reformat.py @@ -206,9 +206,6 @@ def matching_sexes(data): for idx, row in data.iterrows(): if not (row['original_pedigree_sex'] == "unknown" or row['original_pedigree_sex'] == "none" or row['Predicted_Sex'] == "unknown"): data.at[idx, 'Match_Sexes'] = row['original_pedigree_sex'] == row['Predicted_Sex'] - else: - if (row['original_pedigree_sex'] == "unknown" or row['Predicted_Sex'] == "unknown" or row['original_pedigree_sex'] == "none"): - data.at[idx, 'Match_Sexes'] = "NA" # need to make the false/true boolean to string to make it # lower case for multiqc data.at[idx, 'Match_Sexes'] = str(data.at[idx, 'Match_Sexes']).lower() From 50ce94d9f985731aade46a2e112c5cc76aed096b Mon Sep 17 00:00:00 2001 From: Nadia Mohammed Date: Mon, 28 Mar 2022 10:17:23 +0100 Subject: [PATCH 3/6] formatted if not statement --- resources/home/dnanexus/reformat.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/resources/home/dnanexus/reformat.py b/resources/home/dnanexus/reformat.py index 21614f7..d544b4c 100644 --- a/resources/home/dnanexus/reformat.py +++ b/resources/home/dnanexus/reformat.py @@ -204,7 +204,8 @@ def matching_sexes(data): # If reported sex is not unknown or none, then see if reported and # predicted sex is a match (false/true boolean) for idx, row in data.iterrows(): - if not (row['original_pedigree_sex'] == "unknown" or row['original_pedigree_sex'] == "none" or row['Predicted_Sex'] == "unknown"): + if not (row['original_pedigree_sex'] == "unknown" or row['original_pedigree_sex'] == "none" + or row['Predicted_Sex'] == "unknown"): data.at[idx, 'Match_Sexes'] = row['original_pedigree_sex'] == row['Predicted_Sex'] # need to make the false/true boolean to string to make it # lower case for multiqc From 63f2fd3260e9c69b5fca45902b66222ddd116a88 Mon Sep 17 00:00:00 2001 From: Nadia Mohammed Date: Mon, 28 Mar 2022 11:21:20 +0100 Subject: [PATCH 4/6] updated loop comment and removed white space --- resources/home/dnanexus/reformat.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/resources/home/dnanexus/reformat.py b/resources/home/dnanexus/reformat.py index d544b4c..811886f 100644 --- a/resources/home/dnanexus/reformat.py +++ b/resources/home/dnanexus/reformat.py @@ -195,19 +195,20 @@ def matching_sexes(data): lambda x: mappings.get(str(x)) ) - # Need to create a column called match that has true/false boolean + # Need to create a column called match that has true/false boolean # for every row, stating whether they match between reported and # predicted sex. If reported is unknown/none, then match is NA data["Match_Sexes"] = "NA" - # If reported sex is not unknown or none, then see if reported and + # If reported sex is not unknown or none, then see if reported and # predicted sex is a match (false/true boolean) + # If predicted sex is unknown, matching sex will be reported as NA for idx, row in data.iterrows(): - if not (row['original_pedigree_sex'] == "unknown" or row['original_pedigree_sex'] == "none" + if not (row['original_pedigree_sex'] == "unknown" or row['original_pedigree_sex'] == "none" or row['Predicted_Sex'] == "unknown"): data.at[idx, 'Match_Sexes'] = row['original_pedigree_sex'] == row['Predicted_Sex'] - # need to make the false/true boolean to string to make it + # need to make the false/true boolean to string to make it # lower case for multiqc data.at[idx, 'Match_Sexes'] = str(data.at[idx, 'Match_Sexes']).lower() From 41413999215a5197a752e7f63b20cbd9d7319d16 Mon Sep 17 00:00:00 2001 From: Nadia Mohammed Date: Mon, 28 Mar 2022 11:31:07 +0100 Subject: [PATCH 5/6] comment detail added --- resources/home/dnanexus/reformat.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/resources/home/dnanexus/reformat.py b/resources/home/dnanexus/reformat.py index 811886f..2c2bc1c 100644 --- a/resources/home/dnanexus/reformat.py +++ b/resources/home/dnanexus/reformat.py @@ -197,7 +197,7 @@ def matching_sexes(data): # Need to create a column called match that has true/false boolean # for every row, stating whether they match between reported and - # predicted sex. If reported is unknown/none, then match is NA + # predicted sex. If reported is unknown/none, then matching sex is NA data["Match_Sexes"] = "NA" From c79226e4a1d80f1f2b56ef484805c5b425051079 Mon Sep 17 00:00:00 2001 From: Nadia Mohammed Date: Mon, 28 Mar 2022 17:59:23 +0100 Subject: [PATCH 6/6] changed Uranus version to v1.0.2 --- dxapp.json | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/dxapp.json b/dxapp.json index 9b5c163..6c7fc2a 100644 --- a/dxapp.json +++ b/dxapp.json @@ -1,10 +1,10 @@ { - "name": "eggd_somalier_relate2multiqc_v1.0.1", - "title": "eggd_somalier_relate2multiqc_v1.0.1", + "name": "eggd_somalier_relate2multiqc_v1.0.2", + "title": "eggd_somalier_relate2multiqc_v1.0.2", "summary": "Reformats somalier output somalier.samples.tsv to append predicted sex to file and it is in a suitable format for multiqc", - "dxapi": "1.0.1", + "dxapi": "1.0.2", "properties": { - "githubRelease": "v1.0.1" + "githubRelease": "v1.0.2" }, "inputSpec": [ {