methplotlib 0.20.0__tar.gz → 0.21.2__tar.gz

methplotlib-0.21.2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2018 Wouter De Coster
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

methplotlib-0.21.2/PKG-INFO

@@ -0,0 +1,93 @@
+Metadata-Version: 2.1
+Name: methplotlib
+Version: 0.21.2
+Summary: Plot methylation data obtained from nanopolish
+Home-page: https://github.com/wdecoster/methplotlib
+Author: Wouter De Coster
+Author-email: decosterwouter@gmail.com
+License: MIT
+Keywords: nanopore
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Requires-Python: >=3
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+[![Anaconda-Server Badge](https://anaconda.org/bioconda/methplotlib/badges/version.svg)](https://anaconda.org/bioconda/methplotlib)
+[![Anaconda-Server Badge](https://anaconda.org/bioconda/methplotlib/badges/license.svg)](https://anaconda.org/bioconda/methplotlib)
+
+# METHPLOTLIB
+
+This script generates a browser view on a window using data from  
+i) [nanopolish](https://github.com/jts/nanopolish), either as methylation calls or methylation frequencies (as processed by calculate_methylation_frequency.py). The methylation calls can additionally be phased using scripts/annotate_calls_by_phase.and scripts/split_calls_by_phase.py  
+ii) [nanocompore](https://github.com/tleonardi/nanocompore)  
+iii) in ont-cram format with MM/ML tags according to the SAM specifications  
+iv) in bedgraph format  
+
+## INSTALLATION
+
+Creating a new conda environment:  
+`conda create -n methplotlib methplotlib`
+
+Or using pip:  
+`pip install methplotlib`
+
+
+
+## USAGE
+```
+methplotlib [-h] [-v] -m METHYLATION [METHYLATION ...] -n NAMES
+                   [NAMES ...] -w WINDOW [-g GTF] [-b BED] [-f FASTA]
+                   [--simplify] [--split] [--static STATIC] [--smooth SMOOTH]
+                   [--dotsize DOTSIZE] [--example] [-o OUTFILE] [-q QCFILE]
+
+plotting nanopolish methylation calls or frequency
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -v, --version         Print version and exit.
+  -m, --methylation METHYLATION [METHYLATION ...]
+                        data in nanopolish, nanocompore, ont-cram or bedgraph
+                        format
+  -n, --names NAMES [NAMES ...]
+                        names of datasets in --methylation
+  -w, --window WINDOW   window (region) to which the visualisation has to be restricted
+  -g, --gtf GTF         add annotation based on a gtf file
+  -b, --bed BED         add annotation based on a bed file
+  -f, --fasta FASTA     required when --window is an entire chromosome, contig or transcript
+  --simplify            simplify annotation track to show genes rather than transcripts
+  --split               split, rather than overlay the methylation tracks
+  --static              Make a static image of the browser window (filename)
+  --binary              Make the nanopolish plot ignorning log likelihood nuances
+  --smooth              Rolling window size for averaging frequency values (int)
+  --dotsize             Control the size of dots in the per read plots (int)
+  --example             Show example command and exit.
+  -o, --outfile OUTFILE File to write results to. Default:
+                        methylation_browser_{chr}_{start}_{end}.html. Use
+                        {region} as a shorthand for {chr}_{start}_{end} in the
+                        filename. Missing paths will be created.
+  -q, --qcfile QCFILE   File to write the qc report to. Default: The path in
+                        outfile prefixed with qc_, default is qc_report_methyl
+                        ation_browser_{chr}_{start}_{end}.html. Use {region}
+                        as a shorthand for {chr}_{start}_{end} in the
+                        filename. Missing paths will be created.
+
+```
+
+## Snakemake workflow
+For streamlining nanopolish a Snakefile is included (using snakemake). The workflow uses a config file, of which an example is in this repository.
+
+## Example data
+The `examples` folder contains calls and frequencies for the human ACTB gene from PromethION sequencing of NA19240. An example command is available.
+
+## Companion scripts
+The `scripts` folder contains scripts for phasing modification calls in haplotypes based on [WhatsHap](https://whatshap.readthedocs.io/en/latest/) phasing, allele specific modification testing for phased data and differential modification testing across subjects.
+
+## TO DO - CONTRIBUTIONS WELCOME
+- Outlier detection (in windows) across samples

{methplotlib-0.20.0 → methplotlib-0.21.2}/README.md

@@ -1,5 +1,3 @@
-[![Build Status](https://travis-ci.com/wdecoster/methplotlib.svg?branch=master)](https://travis-ci.com/wdecoster/methplotlib)
-[![Anaconda-Server Badge](https://anaconda.org/bioconda/methplotlib/badges/installer/conda.svg)](https://conda.anaconda.org/bioconda)
 [![Anaconda-Server Badge](https://anaconda.org/bioconda/methplotlib/badges/version.svg)](https://anaconda.org/bioconda/methplotlib)
 [![Anaconda-Server Badge](https://anaconda.org/bioconda/methplotlib/badges/license.svg)](https://anaconda.org/bioconda/methplotlib)
 
@@ -8,12 +6,19 @@
 This script generates a browser view on a window using data from  
 i) [nanopolish](https://github.com/jts/nanopolish), either as methylation calls or methylation frequencies (as processed by calculate_methylation_frequency.py). The methylation calls can additionally be phased using scripts/annotate_calls_by_phase.and scripts/split_calls_by_phase.py  
 ii) [nanocompore](https://github.com/tleonardi/nanocompore)  
-iii) in ont-cram format with MM/MP tags according to the SAM specifications and converted using e.g. [this script](https://github.com/kpalin/gcf52ref/blob/f5_to_usam/scripts/extract_methylation_fast5_to_sam.py)  
+iii) in ont-cram format with MM/ML tags according to the SAM specifications  
 iv) in bedgraph format  
 
 ## INSTALLATION
+
+Creating a new conda environment:  
+`conda create -n methplotlib methplotlib`
+
+Or using pip:  
 `pip install methplotlib`
 
+
+
 ## USAGE
 ```
 methplotlib [-h] [-v] -m METHYLATION [METHYLATION ...] -n NAMES

{methplotlib-0.20.0 → methplotlib-0.21.2}/README.rst

@@ -1,5 +1,4 @@
-|Build Status| |Anaconda-Server Badge| |Anaconda-Server Badge|
-|Anaconda-Server Badge|
+|Anaconda-Server Badge| |image1|
 
 METHPLOTLIB
 ===========
@@ -11,15 +10,18 @@ METHPLOTLIB
   additionally be phased using scripts/annotate_calls_by_phase.and
   scripts/split_calls_by_phase.py
 | ii) `nanocompore <https://github.com/tleonardi/nanocompore>`__
-| iii) in ont-cram format with MM/MP tags according to the SAM
-  specifications and converted using e.g. `this
-  script <https://github.com/kpalin/gcf52ref/blob/f5_to_usam/scripts/extract_methylation_fast5_to_sam.py>`__
+| iii) in ont-cram format with MM/ML tags according to the SAM
+  specifications
 | iv) in bedgraph format
 
 INSTALLATION
 ------------
 
-``pip install methplotlib``
+| Creating a new conda environment:
+| ``conda create -n methplotlib methplotlib``
+
+| Or using pip:
+| ``pip install methplotlib``
 
 USAGE
 -----
@@ -90,11 +92,7 @@ TO DO - CONTRIBUTIONS WELCOME
 
 -  Outlier detection (in windows) across samples
 
-.. |Build Status| image:: https://travis-ci.com/wdecoster/methplotlib.svg?branch=master
-   :target: https://travis-ci.com/wdecoster/methplotlib
-.. |Anaconda-Server Badge| image:: https://anaconda.org/bioconda/methplotlib/badges/installer/conda.svg
-   :target: https://conda.anaconda.org/bioconda
 .. |Anaconda-Server Badge| image:: https://anaconda.org/bioconda/methplotlib/badges/version.svg
    :target: https://anaconda.org/bioconda/methplotlib
-.. |Anaconda-Server Badge| image:: https://anaconda.org/bioconda/methplotlib/badges/license.svg
+.. |image1| image:: https://anaconda.org/bioconda/methplotlib/badges/license.svg
    :target: https://anaconda.org/bioconda/methplotlib

{methplotlib-0.20.0 → methplotlib-0.21.2}/methplotlib/annotation.py

@@ -24,16 +24,15 @@ def open_gtf(gtff):
     Open the gtf, using gzip if it's compressed
     based on extension
     """
-    return gzip.open(gtff, 'rt') if gtff.endswith('.gz') else open(gtff)
+    return gzip.open(gtff, "rt") if gtff.endswith(".gz") else open(gtff)
 
 
 def good_record(line, chromosome):
-    '''
+    """
     Filtering on the gtf lines
     by checking for right chromosome and right feature type
-    '''
-    if line.startswith(chromosome) \
-            and line.split('\t')[2] in ['exon', 'gene']:
+    """
+    if line.startswith(str(chromosome)) and line.split("\t")[2] in ["exon", "gene"]:
         return True
     else:
         return False
@@ -43,7 +42,7 @@ def get_features(gtfline, type="gtf"):
     """
     Extract the desirable features from a gtf record
     """
-    chromosome, _, _, begin, end, _, strand, _, attributes = gtfline.split('\t')
+    chromosome, _, _, begin, end, _, strand, _, attributes = gtfline.split("\t")
     gene, transcript = parse_attributes(attributes.rstrip(), type=type)
     return [chromosome, int(begin), int(end), strand, gene, transcript]
 
@@ -53,25 +52,28 @@ def parse_attributes(attributes, type="gtf"):
     Parse the attributes string of gtf record
     Return the values corresponding to gene_name and transcript_id
     """
-    attribute_delimiter = {'gtf': '; ', 'gff': ';'}
-    kv_delimiter = {'gtf': ' ', 'gff': '='}
-    info = {i.split(kv_delimiter[type])[0]: i.split(kv_delimiter[type])[1].replace('"', '')
-            for i in attributes.split(attribute_delimiter[type])
-            if i.startswith(('gene_name', 'transcript_id', 'locus_tag'))}
+    attribute_delimiter = {"gtf": "; ", "gff": ";"}
+    kv_delimiter = {"gtf": " ", "gff": "="}
+    info = {
+        i.split(kv_delimiter[type])[0]: i.split(kv_delimiter[type])[1].replace('"', "")
+        for i in attributes.split(attribute_delimiter[type])
+        if i.startswith(("gene_name", "transcript_id", "locus_tag"))
+    }
     if "gene_name" in info.keys():
         return info.get("gene_name"), info.get("transcript_id")
     else:
         return info.get("locus_tag"), info.get("locus_tag")
 
 
-def transcripts_in_window(df, window, feature='transcript'):
+def transcripts_in_window(df, window, feature="transcript"):
     """
     Return the transcript names for which
     either the end or the begin of an exon is within the window
     """
-    return df.loc[df['begin'].between(window.begin, window.end)
-                  | df['end'].between(window.begin, window.end), feature] \
-        .unique()
+    return df.loc[
+        df["begin"].between(window.begin, window.end) | df["end"].between(window.begin, window.end),
+        feature,
+    ].unique()
 
 
 def assign_colors_to_genes(transcripts):
@@ -88,23 +90,30 @@ def parse_annotation(gtff, window, simplify=False):
     """
     type = annot_file_sniffer(gtff)
     logging.info(f"Parsing {type} file...")
-    df = pd.DataFrame(data=[get_features(line, type=type)
-                            for line in open_gtf(gtff) if good_record(line, window.chromosome)],
-                      columns=['chromosome', 'begin', 'end', 'strand', 'gene', 'transcript'])
+    df = pd.DataFrame(
+        data=[
+            get_features(line, type=type)
+            for line in open_gtf(gtff)
+            if good_record(line, window.chromosome)
+        ],
+        columns=["chromosome", "begin", "end", "strand", "gene", "transcript"],
+    )
     logging.info("Loaded GTF file, processing...")
     if simplify:
-        df.drop_duplicates(subset=['chromosome', 'begin', 'end', 'gene'], inplace=True)
+        df.drop_duplicates(subset=["chromosome", "begin", "end", "gene"], inplace=True)
         res = []
-        for g in transcripts_in_window(df, window, feature='gene'):
+        for g in transcripts_in_window(df, window, feature="gene"):
             gtable = df.loc[df["gene"] == g]
             if len(gtable):
                 res.append(
-                    Transcript(transcript=gtable["gene"].tolist()[0],
-                               gene=gtable["gene"].tolist()[0],
-                               exon_tuples=gtable.loc[:, ["begin", "end"]].sort_values("begin")
-                               .itertuples(index=False,
-                                           name=None),
-                               strand=gtable["strand"].tolist()[0])
+                    Transcript(
+                        transcript=gtable["gene"].tolist()[0],
+                        gene=gtable["gene"].tolist()[0],
+                        exon_tuples=gtable.loc[:, ["begin", "end"]]
+                        .sort_values("begin")
+                        .itertuples(index=False, name=None),
+                        strand=gtable["strand"].tolist()[0],
+                    )
                 )
         sys.stderr.write(f"Found {len(res)} gene(s) in the region.\n")
         logging.info(f"Found {len(res)} gene(s) in the region.\n")
@@ -113,12 +122,14 @@ def parse_annotation(gtff, window, simplify=False):
         for t in transcripts_in_window(df, window, feature="transcript"):
             tr = df.loc[df["transcript"] == t]
             res.append(
-                Transcript(transcript=t,
-                           gene=tr["gene"].tolist()[0],
-                           exon_tuples=tr.loc[:, ["begin", "end"]].sort_values("begin")
-                                                                  .itertuples(index=False,
-                                                                              name=None),
-                           strand=tr["strand"].tolist()[0])
+                Transcript(
+                    transcript=t,
+                    gene=tr["gene"].tolist()[0],
+                    exon_tuples=tr.loc[:, ["begin", "end"]]
+                    .sort_values("begin")
+                    .itertuples(index=False, name=None),
+                    strand=tr["strand"].tolist()[0],
+                )
             )
         sys.stderr.write(f"Found {len(res)} transcript(s) in the region.\n")
         logging.info(f"Found {len(res)} transcript(s) in the region.\n")
@@ -132,20 +143,22 @@ def annot_file_sniffer(annot_file):
 
     Right not just lazily focus on the extension
     """
-    if annot_file.endswith(('.gtf', '.gtf.gz')):
-        return 'gtf'
-    elif annot_file.endswith(('.gff', '.gff.gz')):
-        return 'gff'
+    if annot_file.endswith((".gtf", ".gtf.gz")):
+        return "gtf"
+    elif annot_file.endswith((".gff", ".gff.gz")):
+        return "gff"
     else:
-        sys.exit("ERROR: unrecognized extension of the annotation file.\n"
-                 "Supported are gtf, gtf.gz, gff and gff.gz")
+        sys.exit(
+            "ERROR: unrecognized extension of the annotation file.\n"
+            "Supported are gtf, gtf.gz, gff and gff.gz"
+        )
 
 
 def parse_bed(bed, window):
     logging.info("Parsing BED file")
-    gr = pr.read_bed(bed)[window.chromosome, window.begin:window.end]
+    gr = pr.read_bed(bed)[window.chromosome, window.begin : window.end]
     df = gr.unstrand().df
-    df = df.drop(columns=["Chromosome", "Score", "Strand"], errors='ignore')
+    df = df.drop(columns=["Chromosome", "Score", "Strand"], errors="ignore")
     if "Name" not in df.columns:
         df["Name"] = "noname"
     return df.itertuples(index=False, name=None)