Run black

jcvi/apps/align.py

@@ -632,19 +632,17 @@ def blast_main(args, dbtype=None):
             logging.fatal("`%s` not found on PATH. Have you installed BLAST?", bin)
             sys.exit(1)
 
-    db_suffix = '.nin' if dbtype == "nucl" else ".pin"
+    db_suffix = ".nin" if dbtype == "nucl" else ".pin"
 
-    run_formatdb(
-        infile=subject,
-        outfile=subject + db_suffix,
-        dbtype=dbtype)
+    run_formatdb(infile=subject, outfile=subject + db_suffix, dbtype=dbtype)
 
     blastfile = get_outfile(subject, query, suffix="last", outdir=opts.outdir)
     # Make several attempts to run LASTAL
     try:
         sh(
-            cmd + f" -num_threads {cpus} -query {query} -db {subject} -out {blastfile}" +
-            " -outfmt 6 -max_target_seqs 1000 -evalue 1e-5",
+            cmd
+            + f" -num_threads {cpus} -query {query} -db {subject} -out {blastfile}"
+            + " -outfmt 6 -max_target_seqs 1000 -evalue 1e-5",
             check=False,
             redirect_error=STDOUT,
         )
@@ -693,14 +691,16 @@ def diamond_blastp_main(args, dbtype="prot"):
 
     run_diamond_makedb(
         infile=subject,
-        outfile=subject + '.dmnd',)
+        outfile=subject + ".dmnd",
+    )
 
     blastfile = get_outfile(subject, query, suffix="last", outdir=opts.outdir)
     # Make several attempts to run LASTAL
     try:
         sh(
-            cmd + f" --threads {cpus} --query {query} --db {subject} --out {blastfile}" +
-            " --ultra-sensitive --max-target-seqs 1000 --evalue 1e-5 --outfmt 6",
+            cmd
+            + f" --threads {cpus} --query {query} --db {subject} --out {blastfile}"
+            + " --ultra-sensitive --max-target-seqs 1000 --evalue 1e-5 --outfmt 6",
             check=False,
             redirect_error=STDOUT,
         )

jcvi/apps/fetch.py

@@ -2,6 +2,7 @@
 Wrapper for fetching data from various online repositories \
 (Entrez, Ensembl, Phytozome, and SRA)
 """
+
 import logging
 import os.path as op
 import re

jcvi/apps/grid.py

@@ -1,6 +1,7 @@
 """
 Codes to submit multiple jobs to JCVI grid engine
 """
+
 import os.path as op
 import sys
 import re

jcvi/assembly/goldenpath.py

@@ -292,7 +292,6 @@ def otype(self):
 
 
 class CertificateLine(object):
-
     """
     North  chr1  2  0  AC229737.8  telomere     58443
     South  chr1  2  1  AC229737.8  AC202463.29  58443  37835  58443  + Non-terminal

jcvi/assembly/preprocess.py

@@ -32,9 +32,9 @@ def __init__(self, filename, human=False):
             # Sample_RF37-1/RF37-1_GATCAG_L008_R2_fastqc =>
             # RF37-1_GATCAG_L008_R2
             self["Filename"] = op.basename(op.split(filename)[0]).rsplit("_", 1)[0]
-            self["Total Sequences"] = self["Sequence length"] = self[
-                "Total Bases"
-            ] = "na"
+            self["Total Sequences"] = self["Sequence length"] = self["Total Bases"] = (
+                "na"
+            )
             return
 
         fp = open(filename)

jcvi/compara/catalog.py

@@ -672,7 +672,7 @@ def ortholog(args):
         "--ignore_zero_anchor",
         default=False,
         action="store_true",
-        help="Ignore this pair of ortholog identification instead of throwing an error when performing many pairs of cataloging."
+        help="Ignore this pair of ortholog identification instead of throwing an error when performing many pairs of cataloging.",
     )
 
     p.add_option(
@@ -708,13 +708,9 @@ def ortholog(args):
     last = pprefix + ".last"
     if need_update((afasta, bfasta), last, warn=True):
         if align_soft == "blast":
-            blast_main(
-                [bfasta, afasta, cpus_flag], dbtype
-            )
+            blast_main([bfasta, afasta, cpus_flag], dbtype)
         elif dbtype == "prot" and align_soft == "diamond_blastp":
-            diamond_blastp_main(
-                [bfasta, afasta, cpus_flag], dbtype
-            )
+            diamond_blastp_main([bfasta, afasta, cpus_flag], dbtype)
         else:
             last_main([bfasta, afasta, cpus_flag], dbtype)
 

jcvi/formats/agp.py

@@ -314,7 +314,7 @@ def order(self):
         Returns a dict with component_id => (i, agpline)
         """
         d = {}
-        for (i, x) in enumerate(self):
+        for i, x in enumerate(self):
             if x.is_gap:
                 continue
             xid = x.component_id
@@ -1293,9 +1293,9 @@ def stats(args):
     for label, lengths in zip(("Gaps", "Components"), (gap_lengths, component_lengths)):
 
         if not lengths:
-            table[(label, "Min")] = table[(label, "Max")] = table[
-                (label, "Sum")
-            ] = "n.a."
+            table[(label, "Min")] = table[(label, "Max")] = table[(label, "Sum")] = (
+                "n.a."
+            )
             continue
 
         table[(label, "Min")] = "{0} ({1})".format(*min(lengths))

jcvi/formats/bed.py

@@ -1,6 +1,7 @@
 """
 Classes to handle the .bed files
 """
+
 import logging
 import math
 import numpy as np
@@ -151,7 +152,11 @@ def __init__(self, filename=None, key=None, sorted=True, juncs=False, include=No
             return
 
         for line in must_open(filename):
-            if line[0] == "#" or (juncs and line.startswith("track name")) or line.strip()=="":
+            if (
+                line[0] == "#"
+                or (juncs and line.startswith("track name"))
+                or line.strip() == ""
+            ):
                 continue
             b = BedLine(line)
             if include and b.accn not in include:

jcvi/formats/coords.py

@@ -170,7 +170,6 @@ def overlap(self, max_hang=100):
 
 
 class Coords(LineFile):
-
     """
     when parsing the .coords file, first skip first 5 lines
     [S1] [E1] | [S2] [E2] | [LEN 1] [LEN 2] | [% IDY] | [TAGS]

jcvi/formats/fasta.py

@@ -1,6 +1,7 @@
 """
 Wrapper for biopython Fasta, add option to parse sequence headers
 """
+
 import re
 import sys
 import os

jcvi/formats/genbank.py

@@ -141,7 +141,7 @@ def __init__(self, filenames=None, accessions=None, idfile=None):
                 next(iter(SeqIO.to_dict(SeqIO.parse(f, "gb")).items()))
                 for f in filenames
             )
-            for (k, v) in d.items():
+            for k, v in d.items():
                 self[k.split(".")[0]] = v
 
         elif idfile is not None:
@@ -150,7 +150,7 @@ def __init__(self, filenames=None, accessions=None, idfile=None):
                 next(iter(SeqIO.to_dict(SeqIO.parse(f, "gb")).items()))
                 for f in glob(gbdir + "/*.gb")
             )
-            for (k, v) in d.items():
+            for k, v in d.items():
                 self[k.split(".")[0]] = v
 
         else:

jcvi/formats/pdf.py

@@ -77,7 +77,7 @@ def cat(args):
     merger = PdfFileMerger()
     in_fs = {}
     try:
-        for (filename, page_range) in filename_page_ranges:
+        for filename, page_range in filename_page_ranges:
             if verbose:
                 print(filename, page_range, file=sys.stderr)
             if filename not in in_fs:

jcvi/graphics/blastplot.py

@@ -126,7 +126,7 @@ def blastplot(
 
     # plot the chromosome breaks
     logging.debug("xbreaks={0} ybreaks={1}".format(len(qsizes), len(ssizes)))
-    for (seqid, beg, end) in qsizes.get_breaks():
+    for seqid, beg, end in qsizes.get_breaks():
         ignore = abs(end - beg) < ignore_size_x
         if ignore:
             continue
@@ -135,7 +135,7 @@ def blastplot(
         xchr_labels.append((seqid, (beg + end) / 2, ignore))
         ax.plot([end, end], ylim, "-", lw=1, color="grey")
 
-    for (seqid, beg, end) in ssizes.get_breaks():
+    for seqid, beg, end in ssizes.get_breaks():
         ignore = abs(end - beg) < ignore_size_y
         if ignore:
             continue

jcvi/graphics/histogram.py

@@ -103,7 +103,7 @@ def loghistogram(data, base=2, title="Counts", summary=False):
 
     x, y = [], []
     for size, number in sorted(bins.items()):
-        lb, ub = base ** size, base ** (size + 1)
+        lb, ub = base**size, base ** (size + 1)
         x.append((lb, ub))
         y.append(number)
 

jcvi/projects/str.py

@@ -356,7 +356,7 @@ def mendelian2(args):
             m = mendelian_check(tp1, tp2, tpp, is_xlinked=is_xlinked)
             counts[m] += 1
             if is_xlinked:
-                for (p, p_sex) in ((tp1, p1_sex), (tp2, p2_sex), (tpp, proband_sex)):
+                for p, p_sex in ((tp1, p1_sex), (tp2, p2_sex), (tpp, proband_sex)):
                     if p[1].startswith("-"):
                         p[1] = "n.a."
             cells = [shorten(p1), p1_sex] + tp1[1:]
@@ -591,7 +591,7 @@ def depth(args):
     data = pd.read_csv(tsvfile, sep="\t", low_memory=False)
 
     ids, treds = read_treds()
-    for (dp, ax, title) in zip(
+    for dp, ax, title in zip(
         ("FDP", "PDP", "RDP", "PEDP"),
         (ax1, ax2, ax3, ax4),
         ("Spanning reads", "Partial reads", "Repeat-only reads", "Paired-end reads"),

jcvi/projects/sugarcane.py

@@ -697,7 +697,7 @@ def divergence(args):
     }
     # Get median for each genome pair
     medians = {}
-    for (g1, g2) in product(SPECIES_CONFIG.keys(), repeat=2):
+    for g1, g2 in product(SPECIES_CONFIG.keys(), repeat=2):
         g1, g2 = sorted((g1, g2))
         d = data_by_genomes[(g1, g2)]
         medians[(g1, g2)] = np.median(d)

jcvi/utils/cbook.py

@@ -2,6 +2,7 @@
 Useful recipes from various internet sources (thanks)
 mostly decorator patterns
 """
+
 import os.path as op
 import re
 import sys

jcvi/utils/db.py

@@ -16,7 +16,7 @@
 
 # set up valid database connection params
 valid_dbconn = AutoVivification()
-for (dbconn, port, module, host) in zip(
+for dbconn, port, module, host in zip(
     ("Sybase", "MySQL", "PostgreSQL", "Oracle"),
     (2025, 3306, 5432, 1521),
     ("Sybase", "MySQLdb", "psycopg2", "cx_Oracle"),