diff --git a/workflow/rules/annotation.smk b/workflow/rules/annotation.smk
index e72e5ecd703b13006b01a43c8c79839a40916b34..246cf89ea18123cfadae4716f4ab7f1d7a04431b 100644
--- a/workflow/rules/annotation.smk
+++ b/workflow/rules/annotation.smk
@@ -9,11 +9,11 @@ rule annotation_prodigal:
output:
os.path.join(RESULTS_DIR, "annotation/prodigal/{rtype}/{tool}/proteins.faa")
log:
- out="logs/annotation_prodigal_{rtype}.{tool}.out.log",
- err="logs/annotation_prodigal_{rtype}.{tool}.err.log"
+ out="logs/prodigal.{rtype}.{tool}.out.log",
+ err="logs/prodigal.{rtype}.{tool}.err.log"
wildcard_constraints:
- rtype="|".join(config["assemblers"].keys()),
- tool="|".join(["|".join(a) for a in config["assemblers"].values()])
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
threads: 1
conda:
os.path.join(ENV_DIR, "prodigal.yaml")
@@ -34,11 +34,11 @@ rule annotation_diamond_daa:
# NOTE: use uncompressed DAA format; other formats can be derived using `diamond view`
os.path.join(RESULTS_DIR, "annotation/diamond/{rtype}/{tool}/proteins.daa")
log:
- out="logs/annotation_diamond_{rtype}.{tool}.out.log",
- err="logs/annotation_diamond_{rtype}.{tool}.err.log"
+ out="logs/diamond_daa.{rtype}.{tool}.out.log",
+ err="logs/diamond_daa.{rtype}.{tool}.err.log"
wildcard_constraints:
- rtype="|".join(config["assemblers"].keys()),
- tool="|".join(["|".join(a) for a in config["assemblers"].values()])
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
threads:
config["diamond"]["threads"]
params:
@@ -58,11 +58,11 @@ rule annotation_diamond_tsv:
output:
os.path.join(RESULTS_DIR, "annotation/diamond/{rtype}/{tool}/proteins.tsv")
log:
- out="logs/annotation_diamond_tsv_{rtype}.{tool}.out.log",
- err="logs/annotation_diamond_tsv_{rtype}.{tool}.err.log"
+ out="logs/diamond_tsv.{rtype}.{tool}.out.log",
+ err="logs/diamond_tsv.{rtype}.{tool}.err.log"
wildcard_constraints:
- rtype="|".join(config["assemblers"].keys()),
- tool="|".join(["|".join(a) for a in config["assemblers"].values()])
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
params:
# NOTE: For the used conda version, need to specify the entire column layout (outfmt) explicitly
outfmt="6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qlen slen",
@@ -85,8 +85,8 @@ rule annotation_rgi_input:
output:
temp(os.path.join(RESULTS_DIR, "annotation/rgi/{rtype}/{tool}/input.faa"))
wildcard_constraints:
- rtype="|".join(config["assemblers"].keys()),
- tool="|".join(["|".join(a) for a in config["assemblers"].values()])
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
message:
"RGI: create input FAA: {input}"
shell:
@@ -99,8 +99,8 @@ rule annotation_rgi_db:
archive=temp(os.path.join(DB_DIR, "rgi/card-data.tar.bz2")),
json=os.path.join(DB_DIR, "rgi/card.json")
log:
- out="logs/annotation_rgi_db.out.log",
- err="logs/annotation_rgi_db.err.log"
+ out="logs/rgi_db.out.log",
+ err="logs/rgi_db.err.log"
params:
db_url=config["rgi"]["db_url"]
message:
@@ -119,11 +119,11 @@ rule annotation_rgi:
output:
os.path.join(RESULTS_DIR, "annotation/rgi/{rtype}/{tool}/rgi.txt")
log:
- out="logs/annotation_rgi_{rtype}.{tool}.out.log",
- err="logs/annotation_rgi_{rtype}.{tool}.err.log"
+ out="logs/rgi.{rtype}.{tool}.out.log",
+ err="logs/rgi.{rtype}.{tool}.err.log"
wildcard_constraints:
- rtype="|".join(config["assemblers"].keys()),
- tool="|".join(["|".join(a) for a in config["assemblers"].values()])
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
threads:
config["rgi"]["threads"]
params:
@@ -154,8 +154,11 @@ rule casc:
output:
os.path.join(RESULTS_DIR, "annotation/casc/{rtype}/{tool}/ASSEMBLY.results.txt")
log:
- out="logs/annotation_casc_{rtype}.{tool}.out.log",
- err="logs/annotation_casc_{rtype}.{tool}.err.log"
+ out="logs/casc.{rtype}.{tool}.out.log",
+ err="logs/casc.{rtype}.{tool}.err.log"
+ wildcard_constraints:
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
threads:
config["casc"]["threads"]
conda:
@@ -174,8 +177,11 @@ rule minced:
txt=os.path.join(RESULTS_DIR, "annotation/minced/{rtype}/{tool}/ASSEMBLY.results.txt"),
gff=os.path.join(RESULTS_DIR, "annotation/minced/{rtype}/{tool}/ASSEMBLY.results.gff")
log:
- out="logs/annotation_minced_{rtype}.{tool}.out.log",
- err="logs/annotation_minced_{rtype}.{tool}.err.log"
+ out="logs/minced.{rtype}.{tool}.out.log",
+ err="logs/minced.{rtype}.{tool}.err.log"
+ wildcard_constraints:
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
conda: "../envs/analysis.yaml"
shell:
"(date && "
@@ -184,7 +190,7 @@ rule minced:
"date) 2> {log.err} > {log.out}"
##################################################
-# PlasFlow
+# Plasmids
rule annotation_plasflow_input:
input:
@@ -192,8 +198,8 @@ rule annotation_plasflow_input:
output:
temp(os.path.join(RESULTS_DIR, "annotation/plasflow/{rtype}/{tool}/input.fasta"))
wildcard_constraints:
- rtype="|".join(config["assemblers"].keys()),
- tool="|".join(["|".join(a) for a in config["assemblers"].values()])
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
threads: 1
params:
script=os.path.join(SRC_DIR, "filter_fasta_by_length.pl"),
@@ -210,11 +216,11 @@ rule annotation_plasflow:
tmp=os.path.join(RESULTS_DIR, "annotation/plasflow/{rtype}/{tool}/plasflow.tsv.tmp"),
tsv=os.path.join(RESULTS_DIR, "annotation/plasflow/{rtype}/{tool}/plasflow.tsv")
log:
- out="logs/annotation_plasflow_{rtype}.{tool}.out.log",
- err="logs/annotation_plasflow_{rtype}.{tool}.err.log"
+ out="logs/plasflow.{rtype}.{tool}.out.log",
+ err="logs/plasflow.{rtype}.{tool}.err.log"
wildcard_constraints:
- rtype="|".join(config["assemblers"].keys()),
- tool="|".join(["|".join(a) for a in config["assemblers"].values()])
+ rtype="|".join(READ_TYPES),
+ tool="|".join(ASSEMBLERS)
threads: 1
params:
threshold=config["plasflow"]["threshold"]