Merge pull request #33 from YeoLab/0711_updates

updates and readme

README.md

@@ -12,14 +12,22 @@ MARINE was developed and tested using Python 3.8.18 and is not guaranteed to wor
 Use the provided .yml file to create a new conda environment that contains all required dependencies, including the proper Python version, for MARINE:
 
 ```
-conda env create  --file=marine_environment.yml
+conda env create  --file=marine_environment2.yaml
+conda activate marine_environment
+```
+
+or if you encounter problems with this approach, try using mamba instead, which can be faster:
+
+```
+mamba create -n marine_environment python=3.8.18 -y
+mamba env update -n marine_environment --file marine_environment2.yaml
 conda activate marine_environment
 ```
 
 Notes:
 * The more cores used, the faster MARINE will run
 * Ensure that your annotation bedfile has the same chromosome nomenclature (e.g., "9" vs "chr9") as your bam
-* The annotation file should be tab-separated and should have a standard bed column ordering, as follows:
+* The annotation bedfile should be tab-separated and should have a standard bed6 column ordering, as follows:
 ```
 1       29554   31109   MIR1302-2HG     lincRNA  +       
 1       34554   36081   FAM138A         lincRNA  -       

marine.py

@@ -16,6 +16,7 @@
 import tracemalloc
 from matplotlib import pyplot as plt
 
+
 sys.path.append(os.path.join(os.path.dirname(os.path.realpath(__file__)), 'src/'))
 
 from read_process import incorporate_replaced_pos_info,incorporate_insertions_and_deletions,\

marine_environment2.yaml

@@ -215,7 +215,7 @@ dependencies:
   - python-json-logger=2.0.7=py38h06a4308_0
   - python-tzdata=2023.3=pyhd3eb1b0_0
   - python_abi=3.8=4_cp38
-  - pytz=2023.3.post1=py38h06a4308_0
+  - pytz
   - pyyaml=6.0.1=py38h5eee18b_0
   - pyzmq=25.1.0=py38h6a678d5_0
   - qt-main=5.15.2=h53bd1ea_10

marine_environment_3_10.yml

@@ -106,7 +106,7 @@ dependencies:
   - pyopenssl             
   - pysam                 
   - pysocks               
-  - python                
+  - python           
   - python-dateutil       
   - python-tzdata         
   - python_abi            

src/annotate.py

@@ -2,6 +2,12 @@
 import pandas as pd
 
 import pybedtools
+import os
+import sys
+
+bin_dir = os.path.dirname(sys.executable)
+pybedtools.set_bedtools_path(bin_dir)
+
 import pandas as pd
 
 
@@ -10,7 +16,7 @@ def make_bedtool_from_final_sites(df):
     return pybedtools.BedTool.from_dataframe(df_bed_cols)
 
 
-def get_strand_specific_conversion(r, reverse_stranded):
+def get_strand_specific_conversion(r, strandedness):
     ref_alt_dict = {
         'A': 'T',
         'T': 'A',
@@ -22,14 +28,9 @@ def get_strand_specific_conversion(r, reverse_stranded):
     alt = r.alt
     mapped_strand = r.strand
 
-    """
-    if reverse_stranded:
-        if mapped_strand == '+':
-            mapped_strand = '-'
-        elif mapped_strand == '-':
-            mapped_strand = '+'
-    """
-
+    if strandedness == 0:
+        return '{}>{}'.format(ref, alt)
+
     if mapped_strand == '+':
         return '{}>{}'.format(
             ref,