Updated requirements docs and readme

Updated imports and added print statement

README.md

@@ -73,14 +73,20 @@ python gene_annotation2bed.py -ann annotation.tsv -o output_suffix -ref hg38 -f
 
 ## Requirements
 
+To generate IGV reports:
+HTSlib is required for generating IGV report with the bed file to check the accuracy.
+This uses tabix and bgzip. Version: 1.19.1.
+
+General requirements see requirements.txt for more info on versions.
+
 - pysam
-- pandas
-- igv-reports (v)
 - numpy
-- re
+- pandas
+- igv-reports (v1.12.0)
+- re (std lib)
 
 install using `requirements.txt`. `pip install requirements.txt`
-
+Alternatively you can use conda and the yml provided.
 ---
 
 ## How does this app work?

environment.yml

@@ -0,0 +1,54 @@
+name: myenvtest
+channels:
+  - bioconda
+  - r
+  - conda-forge
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - bzip2=1.0.8=hd590300_5
+  - ca-certificates=2024.2.2=hbcca054_0
+  - ld_impl_linux-64=2.40=h41732ed_0
+  - libexpat=2.5.0=hcb278e6_1
+  - libffi=3.4.2=h7f98852_5
+  - libgcc-ng=13.2.0=h807b86a_5
+  - libgomp=13.2.0=h807b86a_5
+  - libnsl=2.0.1=hd590300_0
+  - libsqlite=3.45.1=h2797004_0
+  - libuuid=2.38.1=h0b41bf4_0
+  - libxcrypt=4.4.36=hd590300_1
+  - libzlib=1.2.13=hd590300_5
+  - ncurses=6.4=h59595ed_2
+  - openssl=3.2.1=hd590300_0
+  - pip=24.0=pyhd8ed1ab_0
+  - python=3.12.2=hab00c5b_0_cpython
+  - readline=8.2=h8228510_1
+  - setuptools=69.1.1=pyhd8ed1ab_0
+  - tk=8.6.13=noxft_h4845f30_101
+  - wheel=0.42.0=pyhd8ed1ab_0
+  - xz=5.2.6=h166bdaf_0
+  - pip:
+    - argcomplete==3.2.2
+    - certifi==2024.2.2
+    - charset-normalizer==3.3.2
+    - coverage==7.4.3
+    - idna==3.6
+    - igv-reports==1.12.0
+    - iniconfig==2.0.0
+    - intervaltree==3.1.0
+    - numpy==1.26.4
+    - packaging==23.2
+    - pandas==2.2.1
+    - pluggy==1.4.0
+    - pysam==0.22.0
+    - pytest==8.0.2
+    - pytest-cov==4.1.0
+    - python-dateutil==2.9.0
+    - pytz==2024.1
+    - requests==2.31.0
+    - six==1.16.0
+    - sortedcontainers==2.4.0
+    - tzdata==2024.1
+    - urllib3==2.2.1
+prefix: /home/rswilson1/anaconda3/envs/myenvtest

gene_annotation2bed.py

@@ -29,13 +29,13 @@
 -gff ./tests/test_data/GCF_000001405.40_GRCh38.p14_genomic.gff -ann data/mixed_dataset.tsv -build hg38 -f 5 -o "test_GRCh38"
 """
 
-import argparse
-
-import argcomplete
 import numpy as np
 import pandas as pd
 import re
 
+import argparse
+import argcomplete
+
 from utils import gff2pandas as gffpd
 from scripts import igv_report as igv
 
@@ -246,7 +246,7 @@ def convert_coordinates(coordinates_df: pd.DataFrame) -> pd.DataFrame:
     ----------
     coordinates_df : pd.DataFrame (0-based)
         coordinate format provided by the annotation file.
-        ID                  annotation
+        Coordinates                  annotation
         chr1:11874-14409    promoter_of_interest
 
     Returns
@@ -256,7 +256,7 @@ def convert_coordinates(coordinates_df: pd.DataFrame) -> pd.DataFrame:
             end, annotation, gene.
 
         +------------------+----------------------+
-        |        ID        |      annotation      |
+        |   Coordinates    |      annotation      |
         +------------------+----------------------+
         | chr1:11874-14409 | promoter_of_interest |
         +------------------+----------------------+
@@ -472,7 +472,8 @@ def merge_dataframes(hgnc_df: pd.DataFrame, transcript_df: pd.DataFrame,
     if lost_ids:
         print(
             f"IDs removed during merge: {lost_ids}.\n",
-            "These won't be present in the final bed file."
+            "These won't be present in the final bed file.",
+            "This may be due to no refseq transcript present for this HGNC ID."
         )
 
     return final_merged_df, coordinates_df

requirements.txt

@@ -1,6 +1,24 @@
-argcomplete==3.1.1
-numpy==1.24.4
-pandas==2.0.3
-pysam==0.21.0
-pytest==7.4.2
+argcomplete==3.2.2
+certifi==2024.2.2
+charset-normalizer==3.3.2
+coverage==7.4.3
+idna==3.6
+igv-reports==1.12.0
+iniconfig==2.0.0
+intervaltree==3.1.0
+numpy==1.26.4
+packaging==23.2
+pandas==2.2.1
+pluggy==1.4.0
+pysam==0.22.0
+pytest==8.0.2
 pytest-cov==4.1.0
+python-dateutil==2.9.0
+pytz==2024.1
+requests==2.31.0
+setuptools==69.1.1
+six==1.16.0
+sortedcontainers==2.4.0
+tzdata==2024.1
+urllib3==2.2.1
+wheel==0.42.0