classify_WHAM_vcf.py issue
JuanmaMedina opened this issue · comments
Good morning Zev,
After correctly running WHAMG
script, I tried to perform the classification step by using classify_WHAM_vcf.py
. But in this step I found a couple of errors:
-
The first is a slight modification of the source code of the python script, as the
cross_validation
module seems to be deprecated, and it is advised to import the corresponding functions frommodel_selection
instead (see https://stackoverflow.com/questions/30667525/importerror-no-module-named-sklearn-cross-validation for further details). This can be easily fixed by editing line 6 of code with:
from sklearn.model_selection import cross_val_score
-
I have not solved the second problem, which is the main reason I am opening this issue:
Traceback (most recent call last):
File "/home/genomica/bin/wham/utils/classify_WHAM_vcf.py", line 333, in <module>
for r in results:
File "/home/genomica/anaconda3/envs/wham/lib/python2.7/multiprocessing/pool.py", line 673, in next
raise value
KeyError: 'AT'
Could you give me a hint here? Regarding the conda environment where I am running the script:
# Name Version Build Channel
_libgcc_mutex 0.1 main
blas 1.0 mkl
ca-certificates 2019.5.15 0
certifi 2019.6.16 py27_1
intel-openmp 2019.4 243
libedit 3.1.20181209 hc058e9b_0
libffi 3.2.1 hd88cf55_4
libgcc-ng 9.1.0 hdf63c60_0
libgfortran-ng 7.3.0 hdf63c60_0
libstdcxx-ng 9.1.0 hdf63c60_0
mkl 2019.4 243
mkl_fft 1.0.12 py27ha843d7b_0
mkl_random 1.0.2 py27hd81dba3_0
ncurses 6.1 he6710b0_1
numpy 1.16.4 py27h7e9f1db_0
numpy-base 1.16.4 py27hde5b4d6_0
openssl 1.1.1c h7b6447c_1
pip 19.1.1 py27_0
python 2.7.16 h9bab390_0
readline 7.0 h7b6447c_5
scikit-learn 0.20.3 py27hd81dba3_0
scipy 1.2.1 py27h7c811a0_0
setuptools 41.0.1 py27_0
sqlite 3.29.0 h7b6447c_0
tk 8.6.8 hbc83047_0
wheel 0.33.4 py27_0
zlib 1.2.11 h7b6447c_3
Thanks in advance!
Depending on your use case whamG might better choice. WhamG internally classifies structural variant types, and is generally more accurate. However, if you need to classify wham calls, I'll revisit this issue.
Hello Zev,
Thanks for your fast response.
Yes, I indeed used the whamg
script, as recommended in the documentation. I edited the OP in case it was not clear.
I parsed out the resulting .vcf
to extract the SV-annotation information. However, I was trying to use the classify_WHAM_vcf.py
on the resulting raw .vcf
in case it provided me with any extra useful information. This was the reason of my issue opening. If the script actually does not provide with more information, or it is not suitable to run it after performing a whamg
run, maybe we can close this, although I think this error could persist in other users.
Cheers.