Merge pull request #298 from gbouras13/dev

v 1.5.1

HISTORY.md

@@ -1,6 +1,12 @@
 History
 =======
 
+1.5.1 (2023-10-26)
+------------------
+
+* Fixes `dnaapler` version to `>=0.4.0` with new changes to dnaapler
+* Adds `.svg` format output with `pharokka_plotter.py`
+
 1.5.0 (2023-09-20)
 ------------------
 

README.md

@@ -402,6 +402,7 @@ The 673 crAss-like genomes were run with `-m` (defaults to `--mmseqs2_only` in v
 
 Benchmarking was conducted on Enterbacteria Phage Lambda (Genbank accession J02459) Staphylococcus Phage SAOMS1 (Genbank Accession MW460250) and 673 crAss-like phage genomes in one multiFASTA input taken from Yutin, N., Benler, S., Shmakov, S.A. et al. Analysis of metagenome-assembled viral genomes from the human gut reveals diverse putative CrAss-like phages with unique genomic features. Nat Commun 12, 1044 (2021) https://doi.org/10.1038/s41467-021-21350-w.
 
+
 For the crAss-like phage genomes, `pharokka` meta mode `-m` was enabled.
 
 | Phage Lambda            | `pharokka` PHANOTATE | `pharokka` Prodigal | Prokka with PHROGs | 

bin/pharokka.py

@@ -9,21 +9,42 @@
 from custom_db import run_custom_pyhmmer
 from databases import check_db_installation
 from hmm import run_pyhmmer
-from input_commands import (check_dependencies, get_input, instantiate_dirs,
-                            instantiate_split_output,
-                            validate_and_extract_genbank, validate_custom_hmm,
-                            validate_fasta, validate_gene_predictor,
-                            validate_meta, validate_terminase,
-                            validate_threads)
+from input_commands import (
+    check_dependencies,
+    get_input,
+    instantiate_dirs,
+    instantiate_split_output,
+    validate_and_extract_genbank,
+    validate_custom_hmm,
+    validate_fasta,
+    validate_gene_predictor,
+    validate_meta,
+    validate_terminase,
+    validate_threads,
+)
 from loguru import logger
 from post_processing import Pharok, remove_post_processing_files
-from processes import (concat_phanotate_meta, concat_trnascan_meta,
-                       convert_gff_to_gbk, reorient_terminase, run_aragorn,
-                       run_dnaapler, run_mash_dist, run_mash_sketch,
-                       run_minced, run_mmseqs, run_phanotate,
-                       run_phanotate_fasta_meta, run_phanotate_txt_meta,
-                       run_pyrodigal, run_pyrodigal_gv, run_trna_scan,
-                       run_trnascan_meta, split_input_fasta, translate_fastas)
+from processes import (
+    concat_phanotate_meta,
+    concat_trnascan_meta,
+    convert_gff_to_gbk,
+    reorient_terminase,
+    run_aragorn,
+    run_dnaapler,
+    run_mash_dist,
+    run_mash_sketch,
+    run_minced,
+    run_mmseqs,
+    run_phanotate,
+    run_phanotate_fasta_meta,
+    run_phanotate_txt_meta,
+    run_pyrodigal,
+    run_pyrodigal_gv,
+    run_trna_scan,
+    run_trnascan_meta,
+    split_input_fasta,
+    translate_fastas,
+)
 from util import count_contigs, get_version
 
 
@@ -160,14 +181,9 @@ def main():
         )
 
         if dnaapler_success == True:
-            if contig_count == 1:
-                input_fasta = os.path.join(
+            input_fasta = os.path.join(
                     out_dir, "dnaapler/dnaapler_reoriented.fasta"
                 )
-            elif contig_count > 1:  # dnaapler all
-                input_fasta = os.path.join(
-                    out_dir, "dnaapler/dnaapler_all_reoriented.fasta"
-                )
             destination_file = os.path.join(
                 out_dir, f"{prefix}_dnaapler_reoriented.fasta"
             )
@@ -440,7 +456,7 @@ def main():
     pharok.extract_terl()
 
     # run mash
-    if args.skip_mash is False: # skips mash
+    if args.skip_mash is False:  # skips mash
         logger.info("Finding the closest match for each contig in INPHARED using mash.")
         # in process.py
         run_mash_sketch(input_fasta, out_dir, logdir)
@@ -449,7 +465,9 @@ def main():
         pharok.inphared_top_hits()
     else:
         logger.info("You have chosen --skip_mash.")
-        logger.info("Skipping finding the closest match for each contig in INPHARED using mash.")
+        logger.info(
+            "Skipping finding the closest match for each contig in INPHARED using mash."
+        )
 
     # delete tmp files
     remove_post_processing_files(out_dir, gene_predictor, args.meta)

bin/pharokka_plotter.py

@@ -158,8 +158,10 @@ def get_input():
     # check if plot already exists
     if args.outdir == "":
         plot_file = str(args.plot_name) + ".png"
+        svg_plot_file = str(args.plot_name) + ".svg"
     else:
         plot_file = os.path.join(args.outdir, f"{args.plot_name}.png")
+        svg_plot_file = os.path.join(args.outdir, f"{args.plot_name}.svg")
 
     if args.force == True:
         if os.path.isfile(plot_file) == True:
@@ -175,6 +177,20 @@ def get_input():
                 f"Output plot file {plot_file} already exists and force was not specified. Please specify -f or --force to overwrite the output plot file."
             )
 
+    if args.force == True:
+        if os.path.isfile(svg_plot_file) == True:
+            os.remove(svg_plot_file)
+        else:
+            logger.warning(
+                "--force was specified even though the output plot file does not already exist."
+            )
+            logger.warning("Continuing")
+    else:
+        if os.path.isfile(svg_plot_file) == True:
+            logger.error(
+                f"Output plot file {svg_plot_file} already exists and force was not specified. Please specify -f or --force to overwrite the output plot file."
+            )
+
     # flag to see if user provided gff and genbank or output directory
     gff_genbank_flag = True
 
@@ -283,6 +299,7 @@ def get_input():
         args.plot_title,
         args.truncate,
         plot_file,
+        svg_plot_file,
         args.dpi,
         args.label_size,
         args.label_hypotheticals,

bin/pharokka_proteins.py

@@ -6,12 +6,20 @@
 from pathlib import Path
 
 from databases import check_db_installation
-from input_commands import (check_dependencies, instantiate_dirs,
-                            validate_fasta, validate_threads)
+from input_commands import (
+    check_dependencies,
+    instantiate_dirs,
+    validate_fasta,
+    validate_threads,
+)
 from loguru import logger
 from post_processing import remove_directory, remove_file
-from proteins import (Pharok_Prot, get_input_proteins, run_mmseqs_proteins,
-                      run_pyhmmer_proteins)
+from proteins import (
+    Pharok_Prot,
+    get_input_proteins,
+    run_mmseqs_proteins,
+    run_pyhmmer_proteins,
+)
 from util import get_version
 
 
@@ -80,7 +88,7 @@ def main():
 
     # dependencies
     logger.info("Checking dependencies.")
-    check_dependencies(False) # to check pharokka_proteins.py, don't need mash
+    check_dependencies(False)  # to check pharokka_proteins.py, don't need mash
 
     # instantiation/checking fasta and gene_predictor
     validate_fasta(args.infile)

bin/plot.py

@@ -17,6 +17,7 @@ def create_plot(
     plot_title,
     truncate,
     outfile,
+    svg_plot_file,
     dpi,
     label_size,
     label_hypotheticals,
@@ -581,4 +582,8 @@ def create_plot(
 
     dpi = int(dpi)
 
+    # save as png
     fig.savefig(outfile, dpi=dpi)
+
+    # Save the image as an SVG
+    fig.savefig(svg_plot_file, format='svg', dpi=dpi)