attempt to fix input/output specification

elvers/rules/khmer/khmer.rule

@@ -10,15 +10,15 @@ prog_params = config[prog]['program_params']
 output_dir = elvers_params['outputs']['outdir']
 # set default input dir, extensions
 input_dir = config['elvers_directories']['outdirs']['preprocess']
-ext = '.trim.fq.gz'
+ext = ['.trim.fq.gz']
 # get input we're using in this case
 input_name = prog_params.get('inputs', ['trimmed'])[0]
 # update input_dir, ext
 input_dir = elvers_params['input_options'][input_name].get('indir', input_dir )
-ext = elvers_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)
+ext = elvers_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)[0]
 diginorm = prog_params.get('diginorm', True)
 
-def get_trimmed(w):
+def get_reads(w):
     readsD = {}
     if not is_single_end(**w):
         readsD['r1'] = expand(join(input_dir, '{sample}_{unit}_1{ext}'),**w, ext=ext)
@@ -35,7 +35,7 @@ if diginorm:
         """
         kmer trim and diginorm with khmer
         """
-        input: unpack(get_trimmed)
+        input: unpack(get_reads)
         output: 
             paired=join(output_dir,'{sample}_{unit}.paired.khmer.fq.gz'),
             single=join(output_dir,'{sample}_{unit}.single.khmer.fq.gz'),
@@ -62,7 +62,7 @@ if diginorm:
         """
         kmer trim and diginorm with khmer
         """
-        input: get_trimmed
+        input: get_reads
         output: join(output_dir, '{sample}_{unit}.se.khmer.fq.gz'),
         message:
             """--- khmer trimming of low-abundance kmers and digital normalization ---"""
@@ -86,7 +86,7 @@ else:
         """
         kmer trim with khmer, no diginorm
         """
-        input: unpack(get_trimmed)
+        input: unpack(get_reads)
         output: 
             paired=join(output_dir,'{sample}_{unit}.paired.khmer.fq.gz'),
             single=join(output_dir,'{sample}_{unit}.single.khmer.fq.gz'),
@@ -109,7 +109,7 @@ else:
         """
         khmer trim se, no diginorm
         """
-        input: get_trimmed
+        input: get_reads
         output: join(output_dir, '{sample}_{unit}.se.khmer.fq.gz'),
         message:
             """--- khmer trimming of low-abundance kmers ---"""

elvers/rules/khmer/params.yml

@@ -8,7 +8,7 @@ khmer:
     output_options:
       kmer_raw:
         input: raw
-        outdir: preprocess
+        outdir: preprocess/khmer
         extensions:
           read:
             common_ext: 
@@ -22,7 +22,7 @@ khmer:
               - '.se.khmer.fq.gz'
       kmer_trimmed:
         input: trimmed
-        outdir: preprocess
+        outdir: preprocess/khmer
         extensions:
           read:
             common_ext: 

elvers/rules/paladin/paladin.rule

@@ -1,17 +1,25 @@
 import os
 from os.path import join
 
+prog = 'paladin'
+
 logs_dir  = config['elvers_directories']['logs']
 assembly_dir  = config['elvers_directories']['outdirs']['assemble']
 
-ep_params = config['paladin']['elvers_params']
-prog_params = config['paladin']['program_params']
+elvers_params = config[prog]['elvers_params']
+prog_params = config[prog]['program_params']
 index_params = prog_params['index_params']
 alignment_params = prog_params['alignment_params']
 
-# get outdir
-paladin_dir = ep_params['outputs']['outdir']
-assembly_extension = ep_params['outputs']['paladin_mapped']['extensions']['reference_extensions'][0]
+# set output dir
+output_dir = elvers_params['outputs']['outdir']
+# set default input dir, extensions
+#input_dir = config['elvers_directories']['outdirs']['preprocess']
+#ext = '.trim.fq.gz'
+# get input we're using in this case
+# update input_dir, ext
+#assembly_extension = elvers_params['outputs']['paladin_mapped']['extensions']['reference_extensions'][0]
+inputs = prog_params.get('inputs')
 
 # handle "associated_samples"
 associated_samples = {}
@@ -22,19 +30,16 @@ if 'assembly_info' in config.keys():
     assemb_info = config['assembly_info']
     refs.update(assemb_info)
 
-for ref_ext, ref_info in refs.items(): #in #config['get_reference']['program_params']['reference_list'].items():#config['reference_info'].items():
-#for ref_ext, ref_info in config['reference_info'].items():
+for ref_ext, ref_info in refs.items(): 
     if ref_info.get('associated_samples'):
         sample_list = ref_info['associated_samples']
         if not ref_ext.startswith('_'):
             ref_ext = '_' + ref_ext
         refname = basename + ref_ext
         associated_samples[refname] = sample_list
 
-
 def get_paladin_input(w):
     readsD = {}
-    inputs = prog_params['inputs']
     # grab list of only the associated samples
     if w.assembly in associated_samples.keys():
         # this assembly has some associated samples
@@ -53,23 +58,26 @@ def get_paladin_input(w):
         elif 'raw' in inputs:
             ext = '_1.fq.gz'
             input_dir = config['elvers_directories']['outdirs']['input_data']
+        #input_dir = elvers_params['input_options'][input_name].get('indir', input_dir )
+        #ext = elvers_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)
         if w.sample in sample_list:
             readsD['r'] = join(input_dir, f'{w.sample}_{w.unit}{ext}')
         return readsD
     # if single end:
-    elif 'trimmed' in inputs: 
-        input_dir = config['elvers_directories']['outdirs']['preprocess']
-        ext = '.trim.fq.gz'
-    elif 'raw' in inputs:
-        ext = '_1.fq.gz'
-        input_dir = config['elvers_directories']['outdirs']['input_data']
+    else:
+        if 'trimmed' in inputs: 
+            input_dir = config['elvers_directories']['outdirs']['preprocess']
+            ext = '_se.trim.fq.gz'
+        elif 'raw' in inputs:
+            ext = '_1.fq.gz'
+            input_dir = config['elvers_directories']['outdirs']['input_data']
     if w.sample in sample_list:
         readsD['r'] = join(input_dir, f'{w.sample}_{w.unit}{ext}')
     return readsD
 
 rule paladin_index:
     input: join(assembly_dir, "{assembly}.fasta")
-    output: join(paladin_dir, "{assembly}.fasta.bwt"),
+    output: join(output_dir, "{assembly}.fasta.bwt"),
     params: 
         reference_type= index_params.get('reference_type', '3'),
         gff = index_params.get('gff_file', '')
@@ -81,9 +89,9 @@ rule paladin_index:
 rule paladin_align:
     input:  
         unpack(get_paladin_input),
-        index = join(paladin_dir, "{assembly}.fasta.bwt"), 
+        index = join(output_dir, "{assembly}.fasta.bwt"), 
     output: 
-        join(paladin_dir,"{sample}_{unit}_x_{assembly}.paladin.bam"),
+        join(output_dir,"{sample}_{unit}_x_{assembly}.paladin.bam"),
     threads: 20
     params:
         f = alignment_params.get('f','125'),
@@ -94,8 +102,8 @@ rule paladin_align:
     script: 'paladin-align.py'
 
 rule samtools_sort_paladin:
-    input: join(paladin_dir,"{sample}_{unit}_x_{assembly}.paladin.bam")
-    output: join(paladin_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam") 
+    input: join(output_dir,"{sample}_{unit}_x_{assembly}.paladin.bam")
+    output: join(output_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam") 
     conda: "environment.yml"
     log: join(logs_dir, 'paladin',"{sample}_{unit}_x_{assembly}.paladin.sort.bam.log")
     benchmark: join(logs_dir, 'paladin',"{sample}_{unit}_x_{assembly}.paladin.sort.bam.benchmark")
@@ -105,8 +113,8 @@ rule samtools_sort_paladin:
     """
 
 rule samtools_flagstat_paladin:
-    input: join(paladin_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam") 
-    output: join(paladin_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam.flagstat")
+    input: join(output_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam") 
+    output: join(output_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam.flagstat")
     log: join(logs_dir, 'paladin',"{sample}_{unit}_x_{assembly}.paladin.sort.bam.flagstat.log")
     benchmark: join(logs_dir, 'paladin',"{sample}_{unit}_x_{assembly}.paladin.sort.bam.flagstat.benchmark")
     conda: "environment.yml"
@@ -115,8 +123,8 @@ rule samtools_flagstat_paladin:
     """
 
 rule samtools_index_paladin:
-    input: join(paladin_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam") 
-    output: join(paladin_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam.bai")
+    input: join(output_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam") 
+    output: join(output_dir,"{sample}_{unit}_x_{assembly}.paladin.sort.bam.bai")
     conda: "environment.yml"
     log: join(logs_dir, 'paladin',"{sample}_{unit}_x_{assembly}.paladin.sort.bam.index.log")
     benchmark: join(logs_dir, 'paladin',"{sample}_{unit}_x_{assembly}.paladin.sort.bam.index.benchmark")

elvers/rules/paladin/params.yml

@@ -33,7 +33,7 @@ paladin:
   program_params:
     inputs:
       - pear_merged
-      - fasta
+      - plass_fasta
     index_params:
       reference_type: '3'
     alignment_params:

elvers/rules/paladin/test/test.yml

@@ -3,4 +3,4 @@
 paladin:
   inputs:
     - raw
-    - fasta
+    - plass_fasta

elvers/rules/pear/pear.rule

@@ -10,12 +10,12 @@ prog_params = config[prog]['program_params']
 output_dir = elvers_params['outputs']['outdir']
 # set default input dir, extensions
 input_dir = config['elvers_directories']['outdirs']['preprocess']
-ext = '.trim.fq.gz'
+ext = ['.trim.fq.gz']
 # get input we're using in this case
 input_name = prog_params.get('inputs', ['trimmed'])[0]
 # update input_dir, ext
 input_dir = elvers_params['input_options'][input_name].get('indir', input_dir )
-ext = elvers_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)
+ext = elvers_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)[0]
 
 def get_pairs(w):
     readsD = {}

elvers/rules/rcorrector/rcorrector.rule

@@ -11,13 +11,13 @@ ep_params = config['rcorrector']['elvers_params']
 rcorr_dir     = ep_params['outputs']['outdir']
 # set default input dir, extensions
 input_dir = config['elvers_directories']['outdirs']['preprocess']
-ext = '.trim.fq.gz'
+ext = ['.trim.fq.gz']
 
 # get input we're using in this case
 input_name = rcorr_params.get('inputs', ['trimmed'])[0]
 # update input_dir, ext
 input_dir = ep_params['input_options'][input_name].get('indir', input_dir )
-ext = ep_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)
+ext = ep_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)[0]
 
 # use if you don't want to collapse technical replicates ("units" column)
 def get_sample_no_combine(w):

elvers/rules/sourmash/params.yml

@@ -2,6 +2,7 @@ sourmash:
   elvers_params:
     input_options:
       read:
+        - kmer_trimmed
         - trimmed
         - raw
       base:

elvers/rules/sourmash/sourmash.rule

@@ -1,17 +1,27 @@
 from os.path import join
 
-logs_dir  = config['elvers_directories']['logs']
-assembly_dir= config['elvers_directories']['outdirs']['assemble']
-preprocess_dir= config['elvers_directories']['outdirs']['preprocess']
+prog = "sourmash"
 
-sourmash_params = config['sourmash']['program_params']
-sourmash_dir = config['sourmash']['elvers_params']['outputs']['outdir']
+logs_dir  = config['elvers_directories']['logs']
+elvers_params = config[prog]['elvers_params']
+prog_params = config[prog]['program_params']
 
+# set output dir
+output_dir = elvers_params['outputs']['outdir']
+# set default input dir, extensions
+input_dir = config['elvers_directories']['outdirs']['preprocess']
+ext = ['.trim.fq.gz']
+# get input we're using in this case
+input_name = prog_params.get('inputs', ['kmer_trimmed'])[0]
+# update input_dir, ext
+reads_dir = elvers_params['input_options'][input_name].get('indir', input_dir)
+assembly_dir= config['elvers_directories']['outdirs']['assemble']
+ext = elvers_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)[0]
 
 def get_reads(wildcards):
     if not is_single_end(**wildcards):
-        return expand(join(preprocess_dir, '{sample}_{unit}.paired.khmer.fq.gz'), **wildcards)
-    return expand(join(preprocess_dir, '{sample}_{unit}.se.khmer.fq.gz'), **wildcards)
+        return expand(join(reads_dir, '{sample}_{unit}.paired.khmer.fq.gz'), **wildcards)
+    return expand(join(reads_dir, '{sample}_{unit}.se.khmer.fq.gz'), **wildcards)
 
 
 rule sourmash_compute_assembly:
@@ -21,14 +31,14 @@ rule sourmash_compute_assembly:
     input:
         join(assembly_dir, "{assembly}.fasta")
     output:
-        join(sourmash_dir, "{assembly}.fasta.sig")
+        join(output_dir, "{assembly}.fasta.sig")
     message:
         """--- Computing a MinHash signature of the transcriptome with Sourmash ---"""
     threads: 2
     params:
-        k_size = sourmash_params.get('k_size', 31),
-        scaled  = sourmash_params.get('scaled', 1000),
-        extra = sourmash_params.get('extra', '')
+        k_size = prog_params.get('k_size', 31),
+        scaled  = prog_params.get('scaled', 1000),
+        extra = prog_params.get('extra', '')
     log: join(logs_dir, 'sourmash', '{assembly}.log')
     benchmark: join(logs_dir, 'sourmash', '{assembly}.benchmark')
     conda: 
@@ -41,14 +51,14 @@ rule sourmash_compute_pe_interleaved:
     Computing a MinHash signature of the kmer-trimmed with Sourmash
     """
     input: get_reads 
-    output: join(sourmash_dir, "{sample}_{unit}.paired.khmer.fq.sig")
+    output: join(output_dir, "{sample}_{unit}.paired.khmer.fq.sig")
     message:
         """--- Computing a MinHash signature of the kmer-trimmed reads with Sourmash ---"""
     threads: 6
     params:
-        k_size = sourmash_params.get('k_size', 31),
-        scaled  = sourmash_params.get('scaled', 1000),
-        extra = sourmash_params.get('extra', '')
+        k_size = prog_params.get('k_size', 31),
+        scaled  = prog_params.get('scaled', 1000),
+        extra = prog_params.get('extra', '')
     log: join(logs_dir, 'sourmash', '{sample}_{unit}.log')
     benchmark: join(logs_dir, 'sourmash', '{sample}_{unit}_pe.benchmark')
     conda: 
@@ -61,14 +71,14 @@ rule sourmash_compute_se:
     Computing a MinHash signature of the kmer-trimmed reads with Sourmash
     """
     input: get_reads 
-    output: join(sourmash_dir, "{sample}_{unit}.se.khmer.fq.sig")
+    output: join(output_dir, "{sample}_{unit}.se.khmer.fq.sig")
     message:
         """--- Computing a MinHash signature of the kmer-trimmed reads with Sourmash ---"""
     threads: 6
     params:
-        k_size = sourmash_params.get('k_size', 31),
-        scaled  = sourmash_params.get('scaled', 1000),
-        extra = sourmash_params.get('extra', '')
+        k_size = prog_params.get('k_size', 31),
+        scaled  = prog_params.get('scaled', 1000),
+        extra = prog_params.get('extra', '')
     log: join(logs_dir, 'sourmash', '{sample}_{unit}.log')
     benchmark: join(logs_dir, 'sourmash', '{sample}_{unit}_se.benchmark')
     conda: 

elvers/rules/trimmomatic/trimmomatic.rule

@@ -11,12 +11,12 @@ prog_params = config[prog]['program_params']
 output_dir = os.path.dirname(elvers_params['outputs']['output_files'][0])
 # set default input dir, extensions
 input_dir = config['elvers_directories']['outdirs']['input_data']
-ext = '.fq.gz'
+ext = ['.fq.gz']
 # get input we're using in this case
-input_name = prog_params.get('input', 'raw').lower()
+input_name = prog_params.get('inputs', ['raw'])[0]
 # update input_dir, ext
 input_dir = elvers_params['input_options'][input_name].get('indir', input_dir)
-ext = elvers_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)
+ext = elvers_params['input_options'][input_name]['extensions']['read'].get('common_ext', ext)[0]
 
 # find adapters --> use utils/find_input_file for this?
 base_dir = config['elvers_directories']['base_dir']

elvers/rules/trinity/test/test.yml

@@ -2,6 +2,6 @@
 # Additional parameters required for testing the trinity rule
 
 trinity:
-  input_kmer_trimmed: False
-  input_trimmed: False
+  inputs:
+    - raw
   max_memory: 4G