miga-base 1.4.2.6 → 1.4.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1376e139435207427900d1cad220f19cdc4cdae9eb5ab8cb4ac21382bce87503
-  data.tar.gz: c179d1a88b2787ed1532aed4bf2e827600956009e08138de2a45cc2eb30a9561
+  metadata.gz: 674190908d65b39a2a860c3f78c8f3449171ef5ce95005e6b36b008181db5530
+  data.tar.gz: 3f6c844d8a17d4c74bbe7d3a4df8cbae41d10d0263f42c34a0cd555de9164a70
 SHA512:
-  metadata.gz: 4b573b0d05f7fe381efd82f5f024be08755cc92db5ea62572f43bec5b3cb3a0835f89e9fb28dda7285fa841118e96b802ccdcbe7c28ccb1f28ede49e6eeeca37
-  data.tar.gz: a80b497a279317593dafce2e115ca3c9ed3c32dc7d3e2eea95110c7c85c8607872247aeb6a381bfefd46495303b6f49f69e95e2dc857cbaef6eafff9febc2af2
+  metadata.gz: 445197498099f28214ba6a0876dd1dc51df8c568789b4e70678ef0b894f200001cde3e30ed3a6d5c2ea7856c7212e3ba5aa03e18b965294b70a71eec2bff958d
+  data.tar.gz: d665948deb9123884f9cc3774e51d36ac888eeb5c1fa877bd999ac1be643677c40371a70c075d91f38b043e08a49ec3d13eb3151d026ea1798d021c1e3bd5fa4

data/lib/miga/cli/action/preproc_wf.rb

@@ -10,7 +10,7 @@ class MiGA::Cli::Action::PreprocWf < MiGA::Cli::Action
 
   def parse_cli
     default_opts_for_wf
-    cli.defaults = { mytaxa: false }
+    cli.defaults = { mytaxa: false, assembly: true }
     cli.parse do |opt|
       opt.on(
         '-i', '--input-type STRING',
@@ -18,9 +18,13 @@ class MiGA::Cli::Action::PreprocWf < MiGA::Cli::Action
         *MiGA::Cli::Action::Add.INPUT_TYPES.map { |k, v| "~ #{k}: #{v[0]}" }
       ) { |v| cli[:input_type] = v.downcase.to_sym }
       opt.on(
-        '-m', '--mytaxa_scan',
-        'Perform MyTaxa scan analysis'
+        '-m', '--mytaxa',
+        'Perform MyTaxa/MyTaxa scan analyses'
       ) { |v| cli[:mytaxa] = v }
+      opt.on(
+        '--no-assembly',
+        'Do not assemble the datasets or perform downstream analyses'
+      ) { |v| cli[:assembly] = v }
       opts_for_wf(
         opt, 'Input files as defined by --input-type',
         multi: true, cleanup: false, ncbi: false, project_type: true
@@ -36,14 +40,26 @@ class MiGA::Cli::Action::PreprocWf < MiGA::Cli::Action
     ]
     p_metadata = Hash[norun.map { |i| ["run_#{i}", false] }]
     d_metadata = { run_distances: false }
+    cli[:mytaxa] = false unless cli[:assembly]
     unless cli[:mytaxa]
       d_metadata[:run_mytaxa_scan] = false
       d_metadata[:run_mytaxa] = false
     end
+    unless cli[:assembly]
+      %w[assembly cds essential_genes ssu].each do |i|
+        d_metadata[:"run_#{i}"] = false
+      end
+    end
     p = create_project(cli[:input_type], p_metadata, d_metadata)
 
     # Run
     run_daemon
-    summarize
+    summaries = []
+    if cli[:input_type].to_s =~ /^raw_reads_/
+      summaries += %w[raw_reads trimmed_reads]
+    end
+    summaries += %w[trimmed_fasta] if cli[:input_type].to_s =~ /^trimmed_reads_/
+    summaries += %w[cds assembly essential_genes ssu] if cli[:assembly]
+    summarize(summaries)
   end
 end

data/lib/miga/result/stats.rb

@@ -24,16 +24,18 @@ module MiGA::Result::Stats
 
   private
 
-  def compute_stats_raw_reads
+  def compute_stats_raw_reads(format = :fastq)
     stats = {}
     seq_opts = { gc: true, x: true, skew: true }
     if self[:files][:pair1].nil?
-      s = MiGA::MiGA.seqs_length(file_path(:single), :fastq, seq_opts)
+      return {} if file_path(:single).nil?
+      s = MiGA::MiGA.seqs_length(file_path(:single), format, seq_opts)
       stats = seqs_length_as_stats_hash(s)
     else
       stats = { read_pairs: nil }
       { pair1: :forward, pair2: :reverse }.each do |pair, direction|
-        s = MiGA::MiGA.seqs_length(file_path(pair), :fastq, seq_opts)
+        return {} if file_path(pair).nil?
+        s = MiGA::MiGA.seqs_length(file_path(pair), format, seq_opts)
         seqs_length_as_stats_hash(s).each do |k, v|
           stats[k == :reads ? :read_pairs : :"#{direction}_#{k}"] ||= v
         end
@@ -47,11 +49,15 @@ module MiGA::Result::Stats
   end
 
   def compute_stats_trimmed_fasta
-    f = self[:files][:coupled].nil? ? file_path(:single) : file_path(:coupled)
-    return {} if f.nil?
-
-    s = MiGA::MiGA.seqs_length(f, :fasta, gc: true, x: true, skew: true)
-    seqs_length_as_stats_hash(s)
+    if self[:files][:coupled].nil?
+      # Single- and separate paired-end reads
+      compute_stats_raw_reads(:fasta)
+    else
+      # Interleaved paired-end reads
+      f = file_path(:coupled)
+      s = MiGA::MiGA.seqs_length(f, :fasta, gc: true, x: true, skew: true)
+      seqs_length_as_stats_hash(s)
+    end
   end
 
   def compute_stats_assembly

data/lib/miga/version.rb

@@ -12,7 +12,7 @@ module MiGA
   # - String indicating release status:
   #   - rc* release candidate, not released as gem
   #   - [0-9]+ stable release, released as gem
-  VERSION = [1.4, 2, 6].freeze
+  VERSION = [1.4, 3, 0].freeze
 
   ##
   # Nickname for the current major.minor version.
@@ -20,7 +20,7 @@ module MiGA
 
   ##
   # Date of the current gem relese.
-  VERSION_DATE = Date.new(2026, 5, 26)
+  VERSION_DATE = Date.new(2026, 7, 22)
 
   ##
   # References of MiGA

data/scripts/assembly.bash

@@ -52,12 +52,15 @@ CMD="spades.py -o $DATASET -t $CORES"
 TYPE_OPT=""
 case "$(miga ls -P "$PROJECT" -D "$DATASET" -m type | cut -f 2)" in
   "metagenome")
+    # MetaSPADES doesn't support single-end metagenomes, so these datasets
+    # are instead treated as SAGs, which at least doesn't assume uniform
+    # coverage
     TYPE_OPT="--meta" ;;
   "plasmid")
     TYPE_OPT="--plasmid" ;;
   "scgenome")
     TYPE_OPT="--sc" ;;
-  "genome")
+  "popgenome"|"genome")
     TYPE_OPT="--isolate" ;;
   "virome")
     TYPE_OPT="--metaviral" ;;
@@ -69,7 +72,7 @@ if [[ -s "$F1" ]] ; then
     CMD="$CMD -1 $F1 -2 $F2"
   else
     CMD="$CMD -s $F1"
-    [[ "$TYPE_OPT" == "--meta" ]] && TYPE_OPT=""
+    [[ "$TYPE_OPT" == "--meta" ]] && TYPE_OPT="--sc"
   fi
 else
   F1="$TF/${DATASET}.CoupledReads.fa.gz"
@@ -78,7 +81,7 @@ else
     CMD="$CMD --12 $F1"
   elif [[ -s "$F2" ]] ; then
     CMD="$CMD -s $F2"
-    [[ "$TYPE_OPT" == "--meta" ]] && TYPE_OPT=""
+    [[ "$TYPE_OPT" == "--meta" ]] && TYPE_OPT="--sc"
   else
     echo "No input files found to assemble" >&2
     exit 1

data/scripts/trimmed_reads.bash

@@ -51,8 +51,11 @@ else
   mv "$b/unpaired.post_trim_QC_${b}.1.html" \
      "../03.read_quality/${b}.post.1.html"
 fi
-mv "$b/Subsample_Adapter_Detection.stats.txt" \
-  "../03.read_quality/$b.adapters.txt"
+
+if [[ -e "$b/Subsample_Adapter_Detection.stats.txt" ]] ; then
+  mv "$b/Subsample_Adapter_Detection.stats.txt" \
+    "../03.read_quality/$b.adapters.txt"
+fi
 
 # Cleanup
 rm -r "$b"

data/test/result_stats_test.rb

@@ -68,7 +68,7 @@ class ResultStatsTest < Test::Unit::TestCase
     assert_equal({}, r.stats)
   end
 
-  def test_trimmed_fasta
+  def test_trimmed_fasta_interleaved
     dir = 'data/04.trimmed_fasta'
     fa = file_path(dir, '.CoupledReads.fa')
     File.open(fa, 'w') { |fh| fh.puts '>1', 'ACTAC' }
@@ -80,6 +80,20 @@ class ResultStatsTest < Test::Unit::TestCase
     assert_equal([40.0, '%'], r[:stats][:g_c_content])
   end
 
+  def test_trimmed_fasta_separate
+    dir = 'data/04.trimmed_fasta'
+    [1, 2].each do |i|
+      fa = file_path(dir, ".#{i}.fasta")
+      File.open(fa, 'w') { |fh| fh.puts '>1', 'ACTAC' }
+    end
+    touch_done(dir)
+    r = dataset.add_result(:trimmed_fasta)
+    assert_equal({}, r[:stats])
+    r.compute_stats
+    assert_equal(1, r[:stats][:read_pairs])
+    assert_equal([40.0, '%'], r[:stats][:forward_g_c_content])
+  end
+
   def test_assembly
     # Prepare result
     dir = 'data/05.assembly'

data/utils/multitrim/multitrim.py

@@ -502,7 +502,13 @@ def adapter_identification_pe(artificial_artifacts, seqtk_binary, faqcs_binary,
 	ps = subprocess.Popen(faqcs_subset_command)
 	ps.wait()
 
-	os.remove(output + "/" + pdf_name)
+	if os.path.exists(output + "/" + pdf_name):
+		os.remove(output + "/" + pdf_name)
+
+	# If no report can be found, assume no adapters
+	if not os.path.exists(output + "/" + prefix + "Subsample_Adapter_Detection.stats.txt"):
+		print("Nothing detected!")
+		return []
 
 	#Adapter detection from output of FaQCs
 	detection_report = open(output + "/" + prefix + "Subsample_Adapter_Detection.stats.txt")
@@ -527,7 +533,7 @@ def adapter_identification_pe(artificial_artifacts, seqtk_binary, faqcs_binary,
 
 	#Cleans up after itself.
 	for item in seqtk_samples:
-		os.remove(item)
+		if os.path.exists(item): os.remove(item)
 
 	print("Detection done!")
 
@@ -563,7 +569,13 @@ def adapter_identification_se(artificial_artifacts, seqtk_binary, faqcs_binary,
 	ps = subprocess.Popen(faqcs_subset_command)
 	ps.wait()
 
-	os.remove(output + "/" + pdf_name)
+	if os.path.exists(output + "/" + pdf_name):
+		os.remove(output + "/" + pdf_name)
+
+	# If no report can be found, assume no adapters
+	if not os.path.exists(output + "/" + prefix + "Subsample_Adapter_Detection.stats.txt"):
+		print("Nothing detected!")
+		return []
 
 	#Adapter detection from output of FaQCs
 	detection_report = open(output + "/" + prefix + "Subsample_Adapter_Detection.stats.txt")
@@ -629,7 +641,7 @@ def parse_adapters(full_list, detected_adapters, output, prefix = ""):
 
 	subset.close()
 
-	return(output+"/"+ prefix + "detected_adapters.fasta")
+	return(output + "/" + prefix + "detected_adapters.fasta")
 
 #paired end version of the full trim; trims using detected adapters with FaQCs -q 27, then fastp --cut_right window 3 qual 20
 def full_trim_pe(forward_in, reverse_in, forward_out, reverse_out, directory, adapters, threads, faqcs, fastp, score, minlen, window, window_qual, prefix, compressor, compress_level, phred_fmt = "33", advanced = False, skip_fastp = False, skip_faqcs = False):
@@ -640,7 +652,7 @@ def full_trim_pe(forward_in, reverse_in, forward_out, reverse_out, directory, ad
 	Additionally, supports using only one of the two tools. Commands will be built even if the tool is to be skipped, but the call will never be issued.
 	'''
 
-	faqcs_command = [faqcs, "-t", str(threads), "-1", forward_in, "-2", reverse_in, "--artifactFile", adapters, "-q", str(score), "--min_L", str(minlen), "--prefix", "reads", "--trim_only", "-d", directory, "--ascii", phred_fmt]
+	faqcs_command = [faqcs, "-t", str(threads), "-1", forward_in, "-2", reverse_in, "--artifactFile", adapters, "-q", str(score), "--min_L", str(minlen), "--prefix", "reads", "--trim_only", "-d", directory]
 	fastp_command = [fastp, "--thread", str(threads), "--adapter_fasta", adapters, "-l", str(minlen), "--json", directory + "/" + prefix + "post_trim_fastp.json", "--html", directory + "/" + prefix + "post_trim_fastp.html"]
 
 	#Args can be added to fastp command with no consequences if fastp is skipped; command simply won't issue so they will be silent
@@ -653,9 +665,9 @@ def full_trim_pe(forward_in, reverse_in, forward_out, reverse_out, directory, ad
 	else:
 		#FaQCs goes first; this is how I coerce FaQCs reads to look afterwards
 		fastp_command.append("-i")
-		fastp_command.append(directory+"/reads.1.trimmed.fastq")
+		fastp_command.append(directory + "/reads.1.trimmed.fastq")
 		fastp_command.append("-I")
-		fastp_command.append(directory+"/reads.2.trimmed.fastq")
+		fastp_command.append(directory + "/reads.2.trimmed.fastq")
 
 	#Outputs are the same regardless of inputs
 	fastp_command.append("-o")
@@ -670,7 +682,9 @@ def full_trim_pe(forward_in, reverse_in, forward_out, reverse_out, directory, ad
 		fastp_command.append("--cut_right_mean_quality")
 		fastp_command.append(str(window_qual))
 
-	if phred_fmt != "33":
+	if phred_fmt != "33" and skip_faqcs:
+		# Only if skip_faqcs because FaQCs outputs ASCII 33 regardless
+		# of input format
 		fastp_command.append("--phred64")
 
 	if advanced:
@@ -685,15 +699,21 @@ def full_trim_pe(forward_in, reverse_in, forward_out, reverse_out, directory, ad
 		printable_time = timer.strftime(time_format)
 		print("Trimming with FaQCs. Started at:", printable_time)
 		subprocess.run(faqcs_command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
-		os.remove(directory + "/" + "reads.stats.txt")
+
+		if os.path.exists(directory + "/" + "reads.stats.txt"):
+			os.remove(directory + "/" + "reads.stats.txt")
 
 	if not skip_fastp:
 		timer = datetime.now()
 		printable_time = timer.strftime(time_format)
 		print("Trimming with Fastp. Started at:", printable_time)
 		subprocess.run(fastp_command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
-		os.remove(directory + "/" + prefix + "post_trim_fastp.json")
-		os.remove(directory + "/" + prefix + "post_trim_fastp.html")
+
+		if os.path.exists(directory + "/" + prefix + "post_trim_fastp.json"):
+			os.remove(directory + "/" + prefix + "post_trim_fastp.json")
+
+		if os.path.exists(directory + "/" + prefix + "post_trim_fastp.html"):
+			os.remove(directory + "/" + prefix + "post_trim_fastp.html")
 
 
 
@@ -703,7 +723,9 @@ def full_trim_pe(forward_in, reverse_in, forward_out, reverse_out, directory, ad
 		#rename FaQCs files to correct names; compress
 
 		#remove this one in any event. We don't want any unpaireds with paired end
-		os.remove(directory+"/reads.unpaired.trimmed.fastq")
+		if os.path.exists(directory + "/reads.unpaired.trimmed.fastq"):
+			os.remove(directory + "/reads.unpaired.trimmed.fastq")
+
 		shutil.move(directory+"/reads.1.trimmed.fastq", forward_out)
 		shutil.move(directory+"/reads.2.trimmed.fastq", reverse_out)
 		#compress_commands = [[directory+"/reads.1.trimmed.fastq", forward_out], [directory+"/reads.2.trimmed.fastq", reverse_out]]
@@ -714,10 +736,15 @@ def full_trim_pe(forward_in, reverse_in, forward_out, reverse_out, directory, ad
 
 	elif not skip_faqcs:
 		#remove FaQCs files if fastp has results or skip if FaQCs not done.
-		os.remove(directory+"/reads.1.trimmed.fastq")
-		os.remove(directory+"/reads.2.trimmed.fastq")
+		if os.path.exists(directory + "/reads.1.trimmed.fastq"):
+			os.remove(directory + "/reads.1.trimmed.fastq")
+
+		if os.path.exists(directory + "/reads.2.trimmed.fastq"):
+			os.remove(directory + "/reads.2.trimmed.fastq")
+
 		#remove this one in any event. We don't want any unpaireds with paired end - the call has to be duplicated, unfortunately.
-		os.remove(directory+"/reads.unpaired.trimmed.fastq")
+		if os.path.exists(directory + "/reads.unpaired.trimmed.fastq"):
+			os.remove(directory + "/reads.unpaired.trimmed.fastq")
 
 	compress_results([forward_out, reverse_out], threads, compressor, compress_level)
 
@@ -731,7 +758,7 @@ def full_trim_se(reads_in, reads_out, directory, adapters, threads, faqcs, fastp
 	The primary purpose is to issue a FaQCs call on the untrimmed reads, then a subsequent fastp call on the outputs from the FaQCs call.
 	Additionally, supports using only one of the two tools. Commands will be built even if the tool is to be skipped, but the call will never be issued.
 	'''
-	faqcs_command = [faqcs, "-t", str(threads), "-u", reads_in, "--artifactFile", adapters, "-q", str(score), "--min_L", str(minlen), "--prefix", "reads", "--trim_only", "-d", directory, "--ascii", phred_fmt]
+	faqcs_command = [faqcs, "-t", str(threads), "-u", reads_in, "--artifactFile", adapters, "-q", str(score), "--min_L", str(minlen), "--prefix", "reads", "--trim_only", "-d", directory]
 	fastp_command = [fastp, "--thread", str(threads), "--adapter_fasta", adapters, "-l", str(minlen), "--json", directory + "/" + prefix + "post_trim_fastp.json", "--html", directory + "/" + prefix + "post_trim_fastp.html"]
 
 	#Args can be added to fastp command with no consequences if fastp is skipped; command simply won't issue so they will be silent
@@ -742,7 +769,7 @@ def full_trim_se(reads_in, reads_out, directory, adapters, threads, faqcs, fastp
 	else:
 		#FaQCs goes first; this is how I coerce FaQCs reads to look afterwards
 		fastp_command.append("-i")
-		fastp_command.append(directory+"/reads.unpaired.trimmed.fastq")
+		fastp_command.append(directory + "/reads.unpaired.trimmed.fastq")
 
 	#Outputs are the same regardless of inputs
 	fastp_command.append("-o")
@@ -755,7 +782,9 @@ def full_trim_se(reads_in, reads_out, directory, adapters, threads, faqcs, fastp
 		fastp_command.append("--cut_right_mean_quality")
 		fastp_command.append(str(window_qual))
 
-	if phred_fmt != "33":
+	if phred_fmt != "33" and skip_faqcs:
+		# Only if skip_faqcs because FaQCs outputs ASCII 33 regardless
+		# of input format
 		fastp_command.append("--phred64")
 
 	if advanced:
@@ -770,24 +799,30 @@ def full_trim_se(reads_in, reads_out, directory, adapters, threads, faqcs, fastp
 		printable_time = timer.strftime(time_format)
 		print("Trimming with FaQCs. Started at:", printable_time)
 		subprocess.run(faqcs_command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
-		os.remove(directory + "/" + "reads.stats.txt")
+
+		if os.path.exists(directory + "/" + "reads.stats.txt"):
+			os.remove(directory + "/" + "reads.stats.txt")
 
 	if not skip_fastp:
 		timer = datetime.now()
 		printable_time = timer.strftime(time_format)
 		print("Trimming with Fastp. Started at:", printable_time)
 		subprocess.run(fastp_command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
-		os.remove(directory + "/" + prefix + "post_trim_fastp.json")
-		os.remove(directory + "/" + prefix + "post_trim_fastp.html")
+
+		if os.path.exists(directory + "/" + prefix + "post_trim_fastp.json"):
+			os.remove(directory + "/" + prefix + "post_trim_fastp.json")
+
+		if os.path.exists(directory + "/" + prefix + "post_trim_fastp.html"):
+			os.remove(directory + "/" + prefix + "post_trim_fastp.html")
 
 
 	if skip_fastp:
 		#compress the result
 		#remove this one in any event. We don't want any unpaireds with paired end
-		shutil.move(directory+"/reads.unpaired.trimmed.fastq", reads_out)
-	elif not skip_faqcs:
+		shutil.move(directory + "/reads.unpaired.trimmed.fastq", reads_out)
+	elif not skip_faqcs and os.path.exists(directory + "/reads.unpaired.trimmed.fastq"):
 		#remove FaQCs files if fastp has results or skip if FaQCs not run.
-		os.remove(directory+"/reads.unpaired.trimmed.fastq")
+		os.remove(directory + "/reads.unpaired.trimmed.fastq")
 
 	compress_results([reads_out], threads, compressor, compress_level)
 
@@ -959,7 +994,7 @@ def pretty_print_file_size(name, start, end, start_time, end_time):
 
 	runtime = '%02d:%02d:%02d' % (hours, minutes, seconds)
 
-	print(name, "compressed! Compression took:", runtime, "and the file was compressed to",  str(round((end/start)*100, 2)), "percent of original size from", humansize(start), "to", humansize(end))
+	print(name, "compressed! Compression took:", runtime)
 
 	return None
 
@@ -1254,8 +1289,7 @@ def main():
 		adapters_detected = adapter_identification_pe(complete_adapter_file_name, stk, fq, f, r, threads, final_output, minpres, prefix, phred)
 		cleaned_adapters = parse_adapters(adapter_set, adapters_detected, final_output, prefix)
 
-		if needs_cleanup:
-			print("Removing automatically generated adapters...")
+		if needs_cleanup and os.path.exists(complete_adapter_file_name):
 			os.remove(complete_adapter_file_name)
 
 		full_trim_pe(f, r, post_trim_f, post_trim_r, final_output, cleaned_adapters, threads, fq, fp, score, minlen, mid, mid_q, prefix, compressor, compression_level, phred, advanced, skip_fp, skip_fq)
@@ -1274,8 +1308,7 @@ def main():
 		adapters_detected = adapter_identification_se(complete_adapter_file_name, stk, fq, u, threads, final_output, minpres, prefix, phred)
 		cleaned_adapters = parse_adapters(adapter_set, adapters_detected, final_output, prefix)
 
-		if needs_cleanup:
-			print("Removing automatically generated adapters...")
+		if needs_cleanup and os.path.exists(complete_adapter_file_name):
 			os.remove(complete_adapter_file_name)
 
 		full_trim_se(u, post_trim, final_output, cleaned_adapters, threads, fq, fp, score, minlen, mid, mid_q, prefix, compressor, compression_level, phred, advanced, skip_fp, skip_fq)
@@ -1561,4 +1594,4 @@ def create_seq_to_fam():
 
 
 
-	os.remove(name)
+	if os.path.exists(name): os.remove(name)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 1.4.2.6
+  version: 1.4.3.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2026-05-26 00:00:00.000000000 Z
+date: 2026-07-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons