diff --git a/plans/map_microorganisms.plan b/plans/map_microorganisms.plan index c4d294564f78b782289d1560ea24a0de6f93208f..83f575c019fe01f17ccaad1415f4cc644f319a5a 100644 --- a/plans/map_microorganisms.plan +++ b/plans/map_microorganisms.plan @@ -14,7 +14,7 @@ </param> <param name="taxa+id_full"> - <alias module="taxa.dict" param="taxaDict"/> + <alias module="taxa" param="taxaDict"/> </param> diff --git a/process_CIRM_corpus.snakefile b/process_CIRM_corpus.snakefile index 902e3b404d8c10804856ad80cd63332a564f9c60..34f4400c777c5551b5ab92136ee442fb1d784e10 100644 --- a/process_CIRM_corpus.snakefile +++ b/process_CIRM_corpus.snakefile @@ -18,7 +18,7 @@ get taxa and habitats (CIRM BIA) ''' rule get_cirm_bia_taxa_habitats: input: - file='corpora/cirm/BIA_2021/florilege_20_07_2021.xlsx' + file='corpora/cirm/BIA_2022/Omnicrobe_03-2022.xlsx' params: taxa_index='2', strain_index='1', @@ -26,7 +26,7 @@ rule get_cirm_bia_taxa_habitats: output: taxa='corpora/cirm/bia/bia_taxa.txt', habitats='corpora/cirm/bia/bia_habitats.txt', - tsv='corpora/cirm/BIA_2021/florilege_export_final_17_02_21.tsv' + tsv='corpora/cirm/BIA_final/florilege_export_final.tsv' conda: 'softwares/envs/python3_pandas_env.yaml' shell: """ python3.7 softwares/scripts/preprocess-cirm.py --input {input.file} --taxa-index {params.taxa_index} --habitat-index {params.habitat_index} --strain-index {params.strain_index} --taxa-outfile {output.taxa} --habitat-outfile {output.habitats} --tsv-outfile {output.tsv} @@ -44,7 +44,7 @@ rule get_cirm_yeast_taxa_habitats: output: taxa='corpora/cirm/levures/yeast_taxa.txt', habitats='corpora/cirm/levures/yeast_habitats.txt', - tsv='corpora/cirm/Levures_2021/Florilege_21012021.tsv' + tsv='corpora/cirm/Levures_final/florilege_export_final.tsv' conda: 'softwares/envs/python3_pandas_env.yaml' shell: """ python3.7 softwares/scripts/preprocess-cirm-yeast.py --input {input.file} --taxa-index {params.taxa_index} --habitat-index {params.habitat_index} --taxa-outfile {output.taxa} --habitat-outfile {output.habitats} --tsv-outfile {output.tsv} @@ -55,15 +55,15 @@ get taxa and habitats (CIRM CFBP) ''' rule get_cirm_cfbp_taxa_habitats: input: - file='corpora/cirm/CFBP_2021/20210617_PPortier.xlsx' + file='corpora/cirm/CFBP_2022/ExportBaseCIRM-CFBP_Omnicrobe_8mars2022.xlsx' params: - taxa_index='3', - strain_index='1', - habitat_index='6,10,13,14' + taxa_index='17', + strain_index='0', + habitat_index='27,3,31,29,26' output: taxa='corpora/cirm/cfbp/cfbp_taxa.txt', habitats='corpora/cirm/cfbp/cfbp_habitats.txt', - tsv='corpora/cirm/CFBP_2021/20210617_PPortier.tsv' + tsv='corpora/cirm/CFBP_final/florilege_export_final.tsv' conda: 'softwares/envs/python3_pandas_env.yaml' shell: """ python3.7 softwares/scripts/preprocess-cirm-cfbp.py --input {input.file} --taxa-index {params.taxa_index} --strain-index {params.strain_index} --habitat-index {params.habitat_index} --taxa-outfile {output.taxa} --habitat-outfile {output.habitats} --tsv-outfile {output.tsv} @@ -217,7 +217,7 @@ format results ''' rule format_cirm_results: input: - file='corpora/cirm/BIA_2021/florilege_export_final_17_02_21.tsv', + file='corpora/cirm/BIA_final/florilege_export_final.tsv', taxa='corpora/cirm/bia/mapped_bia_taxa.txt', habitats='corpora/cirm/bia/mapped_bia_habitats.txt' output: @@ -234,7 +234,7 @@ format results (CIRM Levures) ''' rule format_cirm_yeast_results: input: - file='corpora/cirm/Levures_2021/Florilege_21012021.tsv', + file='corpora/cirm/Levures_final/florilege_export_final.tsv', taxa='corpora/cirm/levures/mapped_yeast_taxa.txt', habitats='corpora/cirm/levures/mapped_yeast_habitats.txt' output: @@ -250,7 +250,7 @@ format results (CIRM CFBP) ''' rule format_cirm_cfbp_results: input: - file='corpora/cirm/CFBP_2021/20210617_PPortier.tsv', + file='corpora/cirm/CFBP_final/florilege_export_final.tsv', taxa='corpora/cirm/cfbp/mapped_cfbp_taxa.txt', habitats='corpora/cirm/cfbp/mapped_cfbp_habitats.txt' output: