From f36ae76e53b8255a9b78be9cbfb2207e8075c81f Mon Sep 17 00:00:00 2001
From: Katherine Eaton <ktmeaton@gmail.com>
Date: Tue, 27 Apr 2021 12:47:31 -0400
Subject: [PATCH] fix typo in eager_tsv script

---
 results/config/snakemake.yaml | 6 +++---
 workflow/Snakefile            | 5 +++--
 workflow/rules/alignment.smk  | 4 ++--
 workflow/scripts/eager_tsv.py | 4 ++++
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/results/config/snakemake.yaml b/results/config/snakemake.yaml
index 77c64a938..131042bd4 100644
--- a/results/config/snakemake.yaml
+++ b/results/config/snakemake.yaml
@@ -14,7 +14,7 @@ sqlite_select_command_asm : SELECT
                               (BioSampleComment LIKE '%KEEP%Assembly%Modern%'
                               AND length(AssemblyFTPGenbank) > 0
                               AND length(BioSampleCollectionDate) > 0)
-                              OR (BioSampleComment LIKE '%KEEP%Assembly%Modern%Outgroup%')
+
 
 sqlite_select_command_sra : SELECT
                               BioSampleAccession,
@@ -100,7 +100,7 @@ iqtree_runs : 1
 iqtree_other : "--ufboot 1000"
 
 # Outgroup Option #1: Reference
-#iqtree_outgroup : "Reference"
+iqtree_outgroup : "Reference"
 
 # Outgroup Option #2: Basal modern clade
 #iqtree_outgroup : "GCA_000323485.1_ASM32348v1_genomic,GCA_000323845.1_ASM32384v1_genomic"
@@ -109,4 +109,4 @@ iqtree_other : "--ufboot 1000"
 #iqtree_outgroup : "SAMEA3541826"
 
 # Outgroup Option #4: Outgroup
-iqtree_outgroup : "GCA_900637475.1_51108_B01_genomic,GCA_000834295.1_ASM83429v1_genomic"
+#iqtree_outgroup : "GCA_900637475.1_51108_B01_genomic,GCA_000834295.1_ASM83429v1_genomic"
diff --git a/workflow/Snakefile b/workflow/Snakefile
index 448f0ed33..4cba2e8ad 100644
--- a/workflow/Snakefile
+++ b/workflow/Snakefile
@@ -114,9 +114,10 @@ rule all:
         # Multiqc
         #multiqc_all_input,
         # Phylo
-        iqtree_all_input,
+        #iqtree_all_input,
         # Post-Phylo
-        #lsd_all_input,
+        lsd_all_input,
+        snippy_multi_filter_prune_all_input,
         # Plot
         plot_missing_data_all_input,
         plot_snp_matrix_all_input,
diff --git a/workflow/rules/alignment.smk b/workflow/rules/alignment.smk
index 114169a3c..575d61473 100644
--- a/workflow/rules/alignment.smk
+++ b/workflow/rules/alignment.smk
@@ -21,7 +21,7 @@ rule eager:
         final_bam = results_dir + "/eager/{reads_origin}/{sample}/final_bams/{sample}.bam",
         eager_tsv = results_dir + "/eager/{reads_origin}/{sample}/metadata_{sample}.tsv",
         log_html  = results_dir + "/eager/{reads_origin}/{sample}/{sample}.html",
-        #log_txt  = results_dir + "/eager/{reads_origin}/{sample}/{sample}.log",
+        log_txt  = results_dir + "/eager/{reads_origin}/{sample}/{sample}.log",
     wildcard_constraints:
         reads_origin = "(sra|local)",
     resources:
@@ -58,7 +58,7 @@ rule eager:
             --max_memory {resources.mem_mb}.MB \
             --max_time {resources.time_min}m \
 			{config[eager_other]} \
-            -resume;
+            -resume > {output.log_txt};
         {scripts_dir}/eager_cleanup.sh {results_dir} {wildcards.reads_origin} {wildcards.sample};
         """
 
diff --git a/workflow/scripts/eager_tsv.py b/workflow/scripts/eager_tsv.py
index 06125a331..bfa25e178 100755
--- a/workflow/scripts/eager_tsv.py
+++ b/workflow/scripts/eager_tsv.py
@@ -86,6 +86,10 @@
         sample_file_dict[sample_name] = {}
     # Iterate through the single or paired fastq files
     for library_file in sample_files:
+        # Catch random log files
+        library_ext = os.path.splitext(library_file)[1]
+        if library_ext != ".fastq" and library_ext != ".gz":
+            continue
         library_id = library_file.split("_")[0]
         if library_id not in sample_file_dict[sample_name]:
             sample_file_dict[sample_name][library_id] = []