methplotlib 0.23.0__py3-none-any.whl → 0.23.1__py3-none-any.whl

methplotlib/annotation.py

@@ -27,17 +27,16 @@ def open_gtf(gtff):
     return gzip.open(gtff, "rt") if gtff.endswith(".gz") else open(gtff)
 
 
-def good_record(line, chromosome):
+def good_record(fields, chromosome):
     """
     Filtering on the gtf lines
     by checking for right chromosome and right feature type
 
+    Takes the first fields of a line, as splitting off the long attributes
+    field for every line of an annotation is a waste.
     The chromosome has to match the entire field, as a prefix match would
     e.g. also accept chr10 up to chr19 and chr1_KI270706v1_random for chr1
     """
-    if line.startswith("#"):
-        return False
-    fields = line.split("\t")
     return len(fields) > 2 and fields[0] == str(chromosome) and fields[2] in ["exon", "gene"]
 
 
@@ -100,10 +99,15 @@ def parse_annotation(gtff, window, simplify=False):
     chromosomes_seen = set()
     records = []
     for line in open_gtf(gtff):
-        if good_record(line, window.chromosome):
+        if line.startswith("#") or not line.strip():
+            continue
+        # only the fields needed to decide, the attributes are split off
+        # further down for the few lines that are of interest
+        fields = line.split("\t", 3)
+        if good_record(fields, window.chromosome):
             records.append(get_features(line, type=type))
-        elif line.strip() and not line.startswith("#"):
-            chromosomes_seen.add(line.split("\t")[0])
+        else:
+            chromosomes_seen.add(fields[0])
     if not records and chromosomes_seen:
         sys.stderr.write(
             f"\nWARNING: no exons or genes of chromosome '{window.chromosome}' "
@@ -121,9 +125,13 @@ def parse_annotation(gtff, window, simplify=False):
     if simplify:
         df.drop_duplicates(subset=["chromosome", "begin", "end", "gene"], inplace=True)
         res = []
-        for g in transcripts_in_window(df, window, feature="gene"):
-            gtable = df.loc[df["gene"] == g]
-            if len(gtable):
+        genes = transcripts_in_window(df, window, feature="gene")
+        # grouping the features of interest once, rather than scanning the
+        # entire frame again for every gene
+        per_gene = dict(list(df[df["gene"].isin(genes)].groupby("gene")))
+        for g in genes:
+            gtable = per_gene.get(g)
+            if gtable is not None and len(gtable):
                 res.append(
                     Transcript(
                         transcript=gtable["gene"].tolist()[0],
@@ -138,8 +146,15 @@ def parse_annotation(gtff, window, simplify=False):
         logging.info(f"Found {len(res)} gene(s) in the region.\n")
     else:
         res = []
-        for t in transcripts_in_window(df, window, feature="transcript"):
-            tr = df.loc[df["transcript"] == t]
+        transcripts = transcripts_in_window(df, window, feature="transcript")
+        # grouping the features of interest once, rather than scanning the
+        # entire frame again for every transcript
+        per_transcript = dict(list(df[df["transcript"].isin(transcripts)].groupby("transcript")))
+        for t in transcripts:
+            tr = per_transcript.get(t)
+            if tr is None or not len(tr):
+                # an annotation without transcript_id, e.g. some gff flavors
+                continue
             res.append(
                 Transcript(
                     transcript=t,

methplotlib/import_methylation.py

@@ -540,9 +540,10 @@ def get_modified_reference_positions(read):
                 # Nake an array with all read positions for which that nucleotide exists in the read
                 # Oddly, get_forward_sequence() returns the sequence as it came from the sequencer
                 # This is the same direction as the Mm/Ml tags are specified in
-                base_index = np.array(
-                    [i for i, letter in enumerate(read.get_forward_sequence()) if letter == base]
-                )
+                # the positions of that nucleotide in the read, found with numpy
+                # as a python loop over every base of a long read is expensive
+                sequence = np.frombuffer(read.get_forward_sequence().encode(), dtype="S1")
+                base_index = np.flatnonzero(sequence == base.encode())
                 # Based on both arrays, find those read coordinates that have a modification
                 modified_bases = base_index[locations]
                 # Convert the array of read coordinates to reference coordinates

methplotlib/plots.py

@@ -189,13 +189,15 @@ def make_per_read_meth_traces_phred(
     table = table.join(df_heights, on="read_name", how="outer")
     traces = []
     hidden = 0
-    for read in table["read_name"].unique():
-        strand = table.loc[table["read_name"] == read, "strand"].values[0]
+    # one row per read, to avoid scanning the entire table for every read
+    per_read = table.drop_duplicates(subset="read_name").set_index("read_name")
+    for read in per_read.index:
+        strand = per_read.at[read, "strand"]
         try:
             traces.append(
                 make_per_read_line_trace(
                     read_range=minmax_table.loc[read],
-                    y_pos=df_heights.loc[read, "height"],
+                    y_pos=df_heights.at[read, "height"],
                     strand=strand,
                 )
             )
@@ -233,17 +235,16 @@ def make_per_read_meth_traces_llr(
         )
     traces = []
     hidden = 0
-    for read in table["read_name"].unique():
-        strand = table.loc[table["read_name"] == read, "strand"].values[0]
-        if phased:
-            phase = table.loc[table["read_name"] == read, "HP"].values[0]
-        else:
-            phase = None
+    # one row per read, to avoid scanning the entire table for every read
+    per_read = table.drop_duplicates(subset="read_name").set_index("read_name")
+    for read in per_read.index:
+        strand = per_read.at[read, "strand"]
+        phase = per_read.at[read, "HP"] if phased else None
         try:
             traces.append(
                 make_per_read_line_trace(
                     read_range=minmax_table.loc[read],
-                    y_pos=df_heights.loc[read, "height"],
+                    y_pos=df_heights.at[read, "height"],
                     strand=strand,
                     phase=phase,
                     size=dotsize,

methplotlib/version.py

@@ -1 +1 @@
-__version__ = "0.23.0"
+__version__ = "0.23.1"

{methplotlib-0.23.0.dist-info → methplotlib-0.23.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: methplotlib
-Version: 0.23.0
+Version: 0.23.1
 Summary: Plot nucleotide modification data from nanopore sequencing
 Home-page: https://github.com/wdecoster/methplotlib
 Author: Wouter De Coster

methplotlib-0.23.1.dist-info/RECORD

@@ -0,0 +1,19 @@
+methplotlib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+methplotlib/annotation.py,sha256=c-b5bUlVTi2Mc0QDBzsKe4V7N0ETw8BEtvY-e0ZtCjQ,7541
+methplotlib/helpers.py,sha256=D69CLM_M8D0wNoV4p-ODr81uatfeCBUUzYdifUmjL88,432
+methplotlib/import_methylation.py,sha256=XyI52b6GYPDlxm_JbUMFqeDkEMUu8Sg51BcT9a2aEm8,22728
+methplotlib/methplotlib.py,sha256=Gk07ODKVfDlA33SlzgIsqRLP0j1DYng24ku87DyYrXY,6264
+methplotlib/plots.py,sha256=MPViIwPrrYn_gx_1VYs3ZECthll3OPrbcyoVAC00cLU,14757
+methplotlib/qc.py,sha256=1EvpxeU7xfwKcQeNflrO4pgsZbc9gbCTcMbShumB_Mo,5590
+methplotlib/utils.py,sha256=ffRDe2ITycIj7_5JV2NBjU6XA4qYYIK3HuWUkqhfJLI,14536
+methplotlib/version.py,sha256=EmtVqV41YmZp6Mj5pkm4iGXDMznVEE4GQEUYGGidq30,23
+methplotlib/differential/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+methplotlib/differential/differential.py,sha256=YSWUAeMaI_yERj6oAdvyWM3vKn2laTtWp6Y8ZuwvLA4,1773
+methplotlib-0.23.1.data/scripts/allele_specific_modification,sha256=PpBdGIiVm8M6OjM0m68OPWnsyDeXJZDnbSNCrH3CaHY,1403
+methplotlib-0.23.1.data/scripts/differential_modification,sha256=SZ0odGaykx_cqIHh5tOKSVUCbXOdHR4PSv4Yv6V04Zw,1461
+methplotlib-0.23.1.dist-info/licenses/LICENSE,sha256=qan9p7Fjhl7WzXuiZoaXCViH5si1PSKBNm9K2f0_51c,1073
+methplotlib-0.23.1.dist-info/METADATA,sha256=-khfgkXsY0_Jr48VBRtkrn1YYX4r4_qYPZhzS-lGQuo,5718
+methplotlib-0.23.1.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+methplotlib-0.23.1.dist-info/entry_points.txt,sha256=Tav-_W5yZc2G8ApYYuFLfVKU2QugXuEN8z_AjPZwORs,61
+methplotlib-0.23.1.dist-info/top_level.txt,sha256=w1XBGUmKUyGeE0_ufRQ6Vi5lMIzDq6TwF587aofDxuQ,12
+methplotlib-0.23.1.dist-info/RECORD,,

methplotlib-0.23.0.dist-info/RECORD

@@ -1,19 +0,0 @@
-methplotlib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-methplotlib/annotation.py,sha256=JjbwXoAmb53lBJJq4W-_B1P3b2-vIrK2QlHUDavq6lk,6671
-methplotlib/helpers.py,sha256=D69CLM_M8D0wNoV4p-ODr81uatfeCBUUzYdifUmjL88,432
-methplotlib/import_methylation.py,sha256=7sf396Cjrkdx-JvvEYcj7IVCCQClch-Sv4YJ9kSfQH4,22561
-methplotlib/methplotlib.py,sha256=Gk07ODKVfDlA33SlzgIsqRLP0j1DYng24ku87DyYrXY,6264
-methplotlib/plots.py,sha256=EZRzc-B4OLjmgFlagzIdhs0S2zyuc_oSv6JqAQs3j3c,14609
-methplotlib/qc.py,sha256=1EvpxeU7xfwKcQeNflrO4pgsZbc9gbCTcMbShumB_Mo,5590
-methplotlib/utils.py,sha256=ffRDe2ITycIj7_5JV2NBjU6XA4qYYIK3HuWUkqhfJLI,14536
-methplotlib/version.py,sha256=6bYcjtcATvc99ZNMjTUfPlrJP3-1WenVEc656roVn_I,23
-methplotlib/differential/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-methplotlib/differential/differential.py,sha256=YSWUAeMaI_yERj6oAdvyWM3vKn2laTtWp6Y8ZuwvLA4,1773
-methplotlib-0.23.0.data/scripts/allele_specific_modification,sha256=PpBdGIiVm8M6OjM0m68OPWnsyDeXJZDnbSNCrH3CaHY,1403
-methplotlib-0.23.0.data/scripts/differential_modification,sha256=SZ0odGaykx_cqIHh5tOKSVUCbXOdHR4PSv4Yv6V04Zw,1461
-methplotlib-0.23.0.dist-info/licenses/LICENSE,sha256=qan9p7Fjhl7WzXuiZoaXCViH5si1PSKBNm9K2f0_51c,1073
-methplotlib-0.23.0.dist-info/METADATA,sha256=ekpREpDBaoqT6fQD0gTEDI3rN2sYfcgGstYss_OiAB8,5718
-methplotlib-0.23.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
-methplotlib-0.23.0.dist-info/entry_points.txt,sha256=Tav-_W5yZc2G8ApYYuFLfVKU2QugXuEN8z_AjPZwORs,61
-methplotlib-0.23.0.dist-info/top_level.txt,sha256=w1XBGUmKUyGeE0_ufRQ6Vi5lMIzDq6TwF587aofDxuQ,12
-methplotlib-0.23.0.dist-info/RECORD,,