Fix envs

Changes to environments.
- Add fuzzy matching to problematic environments (dastool, semibin)
- Added full channel set to environments (some only had bioconda)

Bug fix for edge case in `Filter-Complete-Contigs.py`: Dataset consisting of only bins with 100% completeness raises an error in plotting the histogram due to improper bin sizes. Bug fix adds conditional statement to handle this case.

HiFi-MAG-Pipeline/envs/checkm2.yml

@@ -4,128 +4,4 @@ channels:
   - conda-forge
   - defaults
 dependencies:
-  - _libgcc_mutex=0.1
-  - _openmp_mutex=4.5
-  - abseil-cpp=20200923.3
-  - absl-py=1.3.0
-  - aiohttp=3.8.3
-  - aiosignal=1.3.1
-  - astor=0.8.1
-  - astunparse=1.6.3
-  - async-timeout=4.0.2
-  - attrs=22.1.0
-  - blinker=1.5
-  - boost-cpp=1.70.0
-  - brotlipy=0.7.0
-  - bzip2=1.0.8
-  - c-ares=1.18.1
-  - ca-certificates=2022.9.24
-  - cachetools=4.2.4
-  - certifi=2022.9.24
-  - cffi=1.15.1
-  - charset-normalizer=2.1.1
-  - checkm2=1.0.1
-  - click=8.1.3
-  - colorama=0.4.6
-  - cryptography=38.0.3
-  - diamond=2.0.4
-  - frozenlist=1.3.3
-  - gast=0.3.3
-  - giflib=5.2.1
-  - google-auth=1.35.0
-  - google-auth-oauthlib=0.4.6
-  - google-pasta=0.2.0
-  - grpc-cpp=1.36.4
-  - grpcio=1.36.1
-  - h5py=2.10.0
-  - hdf5=1.10.6
-  - icu=67.1
-  - idna=3.4
-  - importlib-metadata=5.0.0
-  - joblib=1.2.0
-  - jpeg
-  - keras-preprocessing=1.1.2
-  - keyutils=1.6.1
-  - krb5=1.19.3
-  - ld_impl_linux-64=2.39
-  - libblas=3.9.0
-  - libcblas=3.9.0
-  - libcurl=7.86.0
-  - libedit=3.1.20191231
-  - libev=4.33
-  - libffi=3.4.2
-  - libgcc-ng=12.2.0
-  - libgfortran-ng=12.2.0
-  - libgfortran5=12.2.0
-  - libgomp=12.2.0
-  - liblapack=3.9.0
-  - libnghttp2=1.47.0
-  - libnsl=2.0.0
-  - libopenblas=0.3.21
-  - libpng=1.6.38
-  - libprotobuf=3.15.8
-  - libsqlite=3.40.0
-  - libssh2=1.10.0
-  - libstdcxx-ng=12.2.0
-  - libuuid=2.32.1
-  - libzlib=1.2.13
-  - lightgbm=3.2.1
-  - lz4-c=1.9.3
-  - markdown=3.4.1
-  - markupsafe=2.1.1
-  - multidict=6.0.2
-  - ncurses=6.3
-  - numpy=1.19.2
-  - oauthlib=3.2.2
-  - openssl=1.1.1s
-  - opt_einsum=3.3.0
-  - packaging=21.3
-  - pandas=1.4.0
-  - pip=22.3.1
-  - prodigal=2.6.3
-  - protobuf=3.15.8
-  - pyasn1=0.4.8
-  - pyasn1-modules=0.2.7
-  - pycparser=2.21
-  - pyjwt=2.6.0
-  - pyopenssl=22.1.0
-  - pyparsing=3.0.9
-  - pysocks=1.7.1
-  - python=3.8.13
-  - python-dateutil=2.8.2
-  - python-flatbuffers=1.12
-  - python_abi=3.8
-  - pytz=2022.6
-  - pyu2f=0.1.5
-  - re2=2021.04.01
-  - readline=8.1.2
-  - requests=2.28.1
-  - requests-oauthlib=1.3.1
-  - rsa=4.9
-  - scikit-learn=0.23.2
-  - scipy=1.8.0
-  - setuptools=65.5.1
-  - six=1.16.0
-  - snappy=1.1.9
-  - sqlite=3.40.0
-  - tensorboard=2.4.1
-  - tensorboard-plugin-wit=1.8.1
-  - tensorflow=2.4.0
-  - tensorflow-base=2.4.0
-  - tensorflow-estimator=2.4.0
-  - termcolor=2.1.0
-  - threadpoolctl=3.1.0
-  - tk=8.6.12
-  - tqdm=4.64.1
-  - typing-extensions=4.4.0
-  - typing_extensions=4.4.0
-  - urllib3=1.26.11
-  - werkzeug=2.2.2
-  - wheel=0.38.4
-  - wrapt=1.14.1
-  - xz=5.2.6
-  - yarl=1.8.1
-  - zipp=3.10.0
-  - zlib=1.2.13
-  - zstd=1.4.9
-
+  - checkm2 == 1.0.1

HiFi-MAG-Pipeline/envs/dastool.yml

@@ -1,7 +1,8 @@
 name: dastool_env
 channels:
-- bioconda
-- conda-forge
+  - bioconda
+  - conda-forge
+  - defaults
 dependencies:
-- das_tool == 1.1.3
+  - das_tool = 1.1
 

HiFi-MAG-Pipeline/envs/gtdbtk.yml

@@ -1,8 +1,8 @@
 name: gtdbtk_env
 channels:
-- bioconda
-- conda-forge
-- defaults
+  - bioconda
+  - conda-forge
+  - defaults
 dependencies:
-- gtdbtk == 2.1.1
-- python == 3.7
+  - gtdbtk == 2.1.1
+  - python == 3.7

HiFi-MAG-Pipeline/envs/metabat.yml

@@ -1,7 +1,7 @@
 name: metabat_env
 channels:
-- bioconda
-- conda-forge
-- defaults
+  - bioconda
+  - conda-forge
+  - defaults
 dependencies:
-- metabat2 == 2.15
+  - metabat2 == 2.15

HiFi-MAG-Pipeline/envs/python.yml

@@ -1,12 +1,12 @@
 name: python_env
 channels:
-- bioconda
-- conda-forge
-- defaults
+  - bioconda
+  - conda-forge
+  - defaults
 dependencies:
-- python == 3.7
-- numpy
-- pandas
-- seaborn
-- matplotlib
-- biopython == 1.77
+  - python == 3.7
+  - numpy
+  - pandas
+  - seaborn
+  - matplotlib
+  - biopython == 1.77

HiFi-MAG-Pipeline/envs/samtools.yml

@@ -1,8 +1,8 @@
 name: samtools_env
 channels:
-- bioconda
-- conda-forge
-- defaults
+  - bioconda
+  - conda-forge
+  - defaults
 dependencies:
-- samtools == 1.10
-- minimap2 == 2.17
+  - samtools == 1.10
+  - minimap2 == 2.17

HiFi-MAG-Pipeline/envs/semibin.yml

@@ -1,6 +1,8 @@
 name: semibin_env
 channels:
   - bioconda
+  - conda-forge
+  - defaults
 dependencies:
-  - semibin == 1.5.0
+  - semibin = 1.5
 #  - semibin=1.5.0=pyh7cba7a3_0

HiFi-MAG-Pipeline/scripts/Filter-Complete-Contigs.py

@@ -80,7 +80,7 @@ def histo_completeness(df, plot_histo, min_completeness):
     """
     print("histo_completeness: Making histogram.")
     fig, ax = plt.subplots(figsize=(10, 8))
-    if df.shape[0] <= 1:
+    if df.shape[0] <= 1 or df.shape[0]*100 == df['Completeness'].sum():
         sns.histplot(data=df, x='Completeness')
     else:
         sns.histplot(data=df, x='Completeness', binwidth=1)