Pylint fixes

Author: AntonPetrov

r2dt.py

@@ -38,7 +38,10 @@ def get_ribotyper_output(fasta_input, output_folder, cm_library, skip_ribovore_f
         output_folder, os.path.basename(output_folder) + ".ribotyper.long.out"
     )
     if not os.path.exists(ribotyper_long_out):
-        cmd = f"ribotyper.pl --skipval -i {cm_library}/modelinfo.txt -f {fasta_input} {output_folder}"
+        cmd = (
+            f"ribotyper.pl --skipval -i {cm_library}/modelinfo.txt "
+            f"-f {fasta_input} {output_folder}"
+        )
         print(cmd)
         os.system(cmd)
     f_out = os.path.join(output_folder, "hits.txt")
@@ -58,20 +61,9 @@ def get_ribotyper_output(fasta_input, output_folder, cm_library, skip_ribovore_f
     return f_out
 
 
-def symlink_cms(source):
-    for cm_file in glob.glob(os.path.join(source, "*.cm")):
-        if "all.cm" not in cm_file:
-            target = os.path.join(
-                os.path.abspath(config.CM_LIBRARY), os.path.basename(cm_file)
-            )
-            if not os.path.exists(target):
-                cmd = f"ln -s {os.path.abspath(cm_file)} {target}"
-                os.system(cmd)
-
-
 @click.group()
 def cli():
-    pass
+    """Required click stub function."""
 
 
 @cli.command()
@@ -418,9 +410,6 @@ def gtrnadb_setup():
 
 
 @gtrnadb_group.command("draw")
-@click.option(
-    "--test", default=False, is_flag=True, help="Process only the first 10 sequences"
-)
 @click.option(
     "--domain",
     default=False,
@@ -442,7 +431,6 @@ def gtrnadb_draw(
     output_folder,
     domain="",
     isotype="",
-    test=None,
     constraint=None,
     exclusion=None,
     fold_type=None,
@@ -459,7 +447,6 @@ def gtrnadb_draw(
             isotype.capitalize(),
             fasta_input,
             output_folder,
-            test,
             constraint,
             exclusion,
             fold_type,
@@ -506,6 +493,7 @@ def rnasep_group():
 def rnasep_draw(
     fasta_input, output_folder, constraint, exclusion, fold_type, skip_ribovore_filters
 ):
+    """Draw 2D diagrams using RNAse P templates."""
     print(shared.get_r2dt_version_header())
     os.system(f"mkdir -p {output_folder}")
     with open(
@@ -553,6 +541,7 @@ def crw_group():
 def rrna_draw(
     fasta_input, output_folder, constraint, exclusion, fold_type, skip_ribovore_filters
 ):
+    """Draw 2D diagrams using CRW templates."""
     print(shared.get_r2dt_version_header())
     os.system(f"mkdir -p {output_folder}")
     with open(
@@ -600,6 +589,7 @@ def ribovision_group():
 def ribovision_draw_lsu(
     fasta_input, output_folder, constraint, exclusion, fold_type, skip_ribovore_filters
 ):
+    """Draw 2D diagrams using LSU templates from RiboVision."""
     print(shared.get_r2dt_version_header())
     os.system(f"mkdir -p {output_folder}")
     with open(
@@ -643,6 +633,7 @@ def ribovision_draw_lsu(
 def ribovision_draw_ssu(
     fasta_input, output_folder, constraint, exclusion, fold_type, skip_ribovore_filters
 ):
+    """Draw 2D diagrams using SSU templates from RiboVision."""
     print(shared.get_r2dt_version_header())
     os.system(f"mkdir -p {output_folder}")
     with open(
@@ -823,6 +814,7 @@ def force_draw(
     exclusion=None,
     fold_type=None,
 ):
+    """Draw 2D diagrams using a specified template."""
     print(shared.get_r2dt_version_header())
     model_type = lm.get_model_type(model_id)
     if not model_type:
@@ -890,9 +882,8 @@ def force_draw(
         )
     elif model_type == "gtrnadb":
         domain, isotype = model_id.split("_")
-        test = False
         gtrnadb.visualise(
-            domain, isotype, fasta_input, output, test, constraint, exclusion, fold_type
+            domain, isotype, fasta_input, output, constraint, exclusion, fold_type
         )
     # organise results into folders
     organise_results(output, output_folder)

svg2json.py

@@ -1,5 +1,19 @@
 #!/usr/bin/env python3
 
+"""
+Copyright [2009-present] EMBL-European Bioinformatics Institute
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+     http://www.apache.org/licenses/LICENSE-2.0
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+"""
+
+
 import json
 from xml.dom import minidom
 
@@ -13,7 +27,6 @@
 def main(pdb_id, filename, output):
     pdb, model, chain = pdb_id.split("_")
     doc = minidom.parse(filename)
-    svg_lines = []
 
     residues = []
     prev = None

utils/crw.py

@@ -19,6 +19,7 @@
 
 
 def setup():
+    """Setup CRW CM library."""
     print("Deleting old CRW library")
     os.system(f"rm -Rf {config.CRW_CM_LIBRARY}")
     print("Extracting precomputed CRW archive")

utils/generate_cm_library.py

@@ -11,15 +11,11 @@
 limitations under the License.
 """
 
-
 import os
-import glob
-
-
-# CRW_FASTA_NO_PSEUDOKNOTS = '/rna/r2dt/data/crw-fasta-no-pseudoknots'
 
 
 def convert_bpseq_to_fasta(bpseq):
+    """Use a Traveler script to convert from BPSEQ to FASTA."""
     fasta = bpseq.replace(".bpseq", ".fasta")
     if not os.path.exists(fasta):
         cmd = f"python /rna/traveler/utils/bpseq2fasta.py -i {bpseq} -o {fasta}"
@@ -28,6 +24,7 @@ def convert_bpseq_to_fasta(bpseq):
 
 
 def break_pseudoknots(fasta):
+    """Remove pseudoknots using RNAStructure."""
     fasta_no_knots = fasta.replace("-with-knots.fasta", ".fasta")
     if not os.path.exists(fasta_no_knots):
         cmd = f"RemovePseudoknots -b {fasta} {fasta_no_knots}"
@@ -36,11 +33,12 @@ def break_pseudoknots(fasta):
 
 
 def convert_fasta_to_stockholm(fasta):
+    """Convert fasta to stockholm."""
     stockholm = fasta.replace(".fasta", ".sto")
     model_id = os.path.basename(stockholm).replace(".sto", "")
     if not os.path.exists(stockholm):
-        with open(fasta, "r") as f_input:
-            with open(stockholm, "w") as f_output:
+        with open(fasta, "r", encoding="utf-8") as f_input:
+            with open(stockholm, "w", encoding="utf-8") as f_output:
                 lines = f_input.readlines()
                 f_output.write("# STOCKHOLM 1.0\n")
                 f_output.write("\n")
@@ -50,27 +48,33 @@ def convert_fasta_to_stockholm(fasta):
     return stockholm
 
 
-def copy_cm_evalues(cm):
+def copy_cm_evalues(cm_filename):
     """
-    Update covariance files genenrated from CRW covariance models
+    Update covariance files generated from CRW covariance models
     by copying E-values from Rfam CMs.
     """
-    if not os.path.exists("RF00177.cm"):
-        cmd = "wget -O RF00177.cm http://rfam.org/family/RF00177/cm"
+    rfam_acc = "RF00177"
+    example_cm_filename = os.path.join("temp", f"{rfam_acc}.cm")
+    if not os.path.exists(example_cm_filename):
+        cmd = f"wget -O {rfam_acc}.cm http://rfam.org/family/{rfam_acc}/cm"
         os.system(cmd)
-    cmd = "perl /rna/jiffy-infernal-hmmer-scripts/cm-copy-evalue-parameters.pl RF00177.cm {cm}".format(
-        cm=cm
+    cmd = (
+        f"perl /rna/jiffy-infernal-hmmer-scripts/cm-copy-evalue-parameters.pl "
+        f"{rfam_acc}.cm {cm_filename}"
     )
     os.system(cmd)
-    os.system(f"rm {cm}.old")
+    os.system(f"rm {cm_filename}.old")
 
 
 def build_cm(stockholm, cm_library):
-    cm = os.path.join(cm_library, os.path.basename(stockholm).replace(".sto", ".cm"))
-    if not os.path.exists(cm):
-        cmd = f"cmbuild {cm} {stockholm}"
+    """Build an Infernal covariance model."""
+    cm_filename = os.path.join(
+        cm_library, os.path.basename(stockholm).replace(".sto", ".cm")
+    )
+    if not os.path.exists(cm_filename):
+        cmd = f"cmbuild {cm_filename} {stockholm}"
         os.system(cmd)
-        copy_cm_evalues(cm)
+        copy_cm_evalues(cm_filename)
     else:
-        print(f"CM already exists {cm}")
-    return cm
+        print(f"CM already exists {cm_filename}")
+    return cm_filename

utils/gtrnadb.py

@@ -92,6 +92,7 @@ def skip_trna(entry):
 
 
 def classify_trna_sequences(fasta_input, output_folder):
+    """Run tRNAScan-SE 2.0 and select the matching model."""
     if not os.path.exists(output_folder):
         os.mkdir(output_folder)
     mito_vert = run_trnascan(fasta_input, output_folder, "M")
@@ -151,8 +152,9 @@ def classify_trna_sequences(fasta_input, output_folder):
 
 
 def visualise(
-    domain, isotype, fasta_input, output_folder, test, constraint, exclusion, fold_type
+    domain, isotype, fasta_input, output_folder, constraint, exclusion, fold_type
 ):
+    """A wrapper for visualising multiple tRNA sequences in a FASTA file."""
     filename = "headers.txt"
     if not os.path.exists(output_folder):
         os.makedirs(output_folder)
@@ -165,9 +167,7 @@ def visualise(
     os.system(cmd)
 
     with open(filename, "r", encoding="utf-8") as f_headers:
-        for i, line in enumerate(f_headers):
-            if test and i > 10:
-                continue
+        for _, line in enumerate(f_headers):
             seq_id = line.split(" ", 1)[0].replace(">", "").strip()
             print(seq_id)
             ribovision.visualise(