urmi-21 / plncpro

Prediction of lncRNAs using machine learning (Singh et. al NAR 2017)

Hi there 👋

🔭 I’m a Bioinformatics Scientist at Illumina.

plncpro's Issues

build model error

hi,i installed the PLncPRO and successfully ran the tests: bash tests/local_test.sh. i am trying to build the model for maize. but i get an error like this?

plncpro build -p ~/reference/maize/mRNA.fa -n ~/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa -o maize_plncpro_model -m maize.plncpro.model -d uniprotdb -t 50 -v -r

                              _____  _                  _____    _____     ____
                             |  __ \| |                |  __ \  |  __ \   / __ \
                             | |__) | |  _ __     ___  | |__) | | |__) | | |  | |
                             |  ___/| | |  _ \   / __| |  ___/  |  _  /  | |  | |
                             | |    | | | | | | | (__  | |      | | \ \  | |__| |
                             |_|    |_| |_| |_|  \___| |_|      |_|  \_\  \____/

/mnt/data/home/zqq/reference/uniprot_sprot_database/maize_plncpro_model
/mnt/data/home/zqq/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa
/mnt/data/home/zqq/reference/maize
Reading Negative File...
Extracting Features...
Extracting Framefinder Features...
Running BLASTX...This might take some time depending on your input.
blastx -query /mnt/data/home/zqq/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa -db uniprotdb -outfmt '6 qseqid sseqid pident evalue qcovs qcovhsp score bitscore qframe sframe' -out /mnt/data/home/zqq/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa_blastres -qcov_hsp_perc 30 -num_threads 50

Parsing Blast Results...
python /mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/plncpro/bin/blastparse_mt3.py /mnt/data/home/zqq/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa_blastres
Merging all Features...
python /mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/plncpro/bin/mergefeatures.py /mnt/data/home/zqq/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa_features false /mnt/data/home/zqq/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa_ffout_framefinderfeatures false /mnt/data/home/zqq/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa_blastres_blastfeatures /mnt/data/home/zqq/reference/maize/lncRNA_plncdb_ConfidenceLevelHigh.fa_all_features
Reading Positive File...
Extracting Features...
Extracting Framefinder Features...
Running BLASTX...This might take some time depending on your input.
blastx -query /mnt/data/home/zqq/reference/maize/mRNA.fa -db uniprotdb -outfmt '6 qseqid sseqid pident evalue qcovs qcovhsp score bitscore qframe sframe' -out /mnt/data/home/zqq/reference/maize/mRNA.fa_blastres -qcov_hsp_perc 30 -num_threads 50

Parsing Blast Results...
Merging all Features...
Merging Pos and Neg features...
Building Model...
Traceback (most recent call last):
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/plncpro/bin/rf/buildmodel.py", line 75, in
main()
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/plncpro/bin/rf/buildmodel.py", line 45, in main
rf.fit(train, target)
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/sklearn/base.py", line 1151, in wrapper
return fit_method(estimator, *args, **kwargs)
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/sklearn/ensemble/_forest.py", line 348, in fit
X, y = self._validate_data(
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/sklearn/base.py", line 621, in _validate_data
X, y = check_X_y(X, y, **check_params)
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/sklearn/utils/validation.py", line 1147, in check_X_y
X = check_array(
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/sklearn/utils/validation.py", line 959, in check_array
_assert_all_finite(
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/sklearn/utils/validation.py", line 124, in _assert_all_finite
_assert_all_finite_element_wise(
File "/mnt/data/home/zqq/miniconda3/envs/plncpro/lib/python3.10/site-packages/sklearn/utils/validation.py", line 173, in _assert_all_finite_element_wise
raise ValueError(msg_err)
ValueError: Input X contains NaN.
RandomForestClassifier does not accept missing values encoded as NaN natively. For supervised learning, you might want to consider sklearn.ensemble.HistGradientBoostingClassifier and Regressor which accept missing values encoded as NaNs natively. Alternatively, it is possible to preprocess the data, for instance by using an imputer transformer in a pipeline or drop samples with missing values. See https://scikit-learn.org/stable/modules/impute.html You can find a list of all estimators that handle NaN values at the following page: https://scikit-learn.org/stable/modules/impute.html#estimators-that-handle-nan-values
Removing temp files...
mv: cannot stat '/mnt/data/home/zqq/reference/maize/maize.plncpro.model': No such file or directory
All outputs saved to: /mnt/data/home/zqq/reference/uniprot_sprot_database/maize_plncpro_model
END

what need i do?
Also, can I choose diomand when building the model?In the Readme I only see diomand for plncpro predict.

how to create blastdb

i am trying to build the model and predict , but i don't know the steps , i have the protein data and mRNA, how to create blastdb?