debug MD tag missing

docs/version_history.rst

@@ -3,6 +3,9 @@ Version History
 
 v0.2.x release series
 ---------------------
+0.2.10 (2020.09.08):
+	- debug ValueError when MD tag of read is missing (`issue #5<https://github.com/parklab/bamsnap/issues/5>`_)
+
 0.2.9 (2020.09.03):
 	- add ``insert_size_del_threshold`` for deletion, ``insert_size_ins_threshold`` for insertsion
 	- add ``read_color_deletion`` for deletion, ``read_color_insersion`` for insertion

pack.sh

@@ -2,5 +2,5 @@ pip uninstall -y bamsnap
 rm -rf build
 rm -rf ./dist/*
 python3 setup.py sdist bdist_wheel
-pip install ./dist/bamsnap-0.2.9-py3-none-any.whl
+pip install ./dist/bamsnap-0.2.10-py3-none-any.whl
 # twine upload dist/*

setup.py

@@ -20,7 +20,7 @@
 }
 
 setup(name='bamsnap',
-      version='0.2.9',
+      version='0.2.10',
       url='https://github.com/danielmsk/bamsnap',
       license='MIT',
       author='Daniel Minseok Kwon',

src/bamsnap.egg-info/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.1
 Name: bamsnap
-Version: 0.2.9
+Version: 0.2.10
 Summary: A converter from .bam to .png for specific genomic region.
 Home-page: https://github.com/danielmsk/bamsnap
 Author: Daniel Minseok Kwon
 Author-email: [email protected]
 License: MIT
 Download-URL: https://github.com/danielmsk/bamsnap/archive/0.1.tar.gz
-Description: # <img src="https://bampdx.com/wp-content/uploads/2015/12/BAMPDX-logo.png" height=28px width=45px>&nbsp;BAMsnap
+Description: # BamSnap
         <!--[![Build Status](https://travis-ci.org/bamsnap/bamsnap.svg?branch=develop)](https://travis-ci.org/bamsnap/bamsnap) 
         [![Code Health](https://landscape.io/github/bamsnap/bamsnap/develop/landscape.svg?style=flat)](https://landscape.io/github/bamsnap/bamsnap/develop) 
         [![Coverage Status](https://img.shields.io/codecov/c/github/bamsnap/bamsnap/develop.svg)](https://codecov.io/github/bamsnap/bamsnap?branch=develop)-->
@@ -36,6 +36,8 @@ Description: # <img src="https://bampdx.com/wp-content/uploads/2015/12/BAMPDX-lo
         ```bash
         pip install bamsnap
         ```
+        * [pypi site for bamsnap](https://pypi.org/project/bamsnap/)
+
         ### Install with github
 
         ```
@@ -54,6 +56,10 @@ Description: # <img src="https://bampdx.com/wp-content/uploads/2015/12/BAMPDX-lo
         For more details, see BamSnap [**Documentation**](http://bamsnap.readthedocs.io/en/latest).
 
 
+        ## Example Use Case
+
+        * [**1000 Genome Data**](http://100.26.138.46:8000/): 1000 genomic loci in 2504 individuals
+        * [**BamSnap Plot Gallery**](https://bamsnap.readthedocs.io/en/latest/gallery.html)
 
 
 

src/bamsnap/data/conf.json

@@ -1,7 +1,7 @@
 {
     "TITLE":"BAMSNAP",
-    "VERSION":"0.2.9",
-    "VERSION_DATE":"2020-09-03",
+    "VERSION":"0.2.10",
+    "VERSION_DATE":"2020-09-07",
     "PROG":"bamsnap",
     "options":[
         {"param":"bam", "default":[], "nargs":"*", "action": null, "choices":null, "type":null, "help":"bam file(s)"},

src/bamsnap/drawread.py

@@ -21,7 +21,7 @@ class DrawRead():
     y1 = 0
     opt = {}
 
-    def __init__(self, a):  # a:alignment
+    def __init__(self, a, refseq=""):  # a:alignment
         self.a = a
         self.mapq = a.mapq
         self.id = a.query_name
@@ -35,7 +35,11 @@ def __init__(self, a):  # a:alignment
         self.readseq_with_softclipped = a.query_sequence
 
         self.base_qual = a.query_qualities
-        self.refseq = a.get_reference_sequence()
+        self.refseq = refseq
+        # try:
+        #     self.refseq = a.get_reference_sequence()
+        # except ValueError:
+        #     self.refseq = {}
         self.g_spos = a.positions[0] + 1
         self.g_epos = a.positions[-1] + 1
         self.has_del = False
@@ -77,8 +81,6 @@ def set_SV(self):
                 pass
 
 
-
-
     def set_read_variant(self):
         gpos = self.g_spos
         self.g_spos_with_softclipped = self.g_spos
@@ -121,7 +123,7 @@ def set_read_variant(self):
             else:
                 for gp in range(prev_gpos, gpos):
                     base = self.readseq_with_softclipped[bidx]
-                    refbase = self.refseq[ridx].upper()
+                    refbase = self.refseq[gp].upper()
                     if base != refbase:
                         btype = 'S'
                         self.mismatch_list.append(gp)

src/bamsnap/drawreadset.py

@@ -266,15 +266,24 @@ def add_covmap(self, group, read):
             self.covmap[group][gpos] = (cov + 1, base_composition)
 
     def update_ref_seq_with_read(self, a):
-        read_ref_seq = a.get_reference_sequence()
         read_ref_pos = a.get_reference_positions()
+        try:
+            read_ref_seq = a.get_reference_sequence()
+        except ValueError: # when MD tag is missing.
+            read_ref_seq = {}
+
         for pidx in range(len(read_ref_pos)):
             gpos = read_ref_pos[pidx] + 1
-            base = read_ref_seq[pidx]
+
+            try:
+                base = read_ref_seq[pidx]
+            except KeyError: # when MD tag is missing
+                base = "N"
             try:
                 self.refseq[gpos]
             except KeyError:
                 self.refseq[gpos] = base.upper()
+
 
     def calculate_readmap(self, is_strand_group=False):
         group_list = ['all']
@@ -289,8 +298,7 @@ def calculate_readmap(self, is_strand_group=False):
                 rid = self.get_rid(a)
                 self.update_ref_seq_with_read(a)
                 if not self.is_exist_read(rid):
-                    r = DrawRead(a)
-                    r.refseq = self.refseq
+                    r = DrawRead(a, self.refseq)
                     r.id = rid
                     r.read_gap_h = self.read_gap_h
                     r.read_gap_w = self.read_gap_w