Merck / Merck/deepbgc

running "deepbgc info" issue

Open
#91 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
161
Forks
29
PR merge metrics
No merged PRs in 30d

Description

Dear developers,
Currently I followed the standard commendline(pip) provided in readme to install deepbgc-0.1.30-py3-none-any.whl (64 kB). However, when I check the installation (using deepbgc info) and found out that:

INFO 09/06 12:22:52 Available data files: ['releases', 'Pfam-A.31.0.hmm', 'Pfam-A.31.0.hmm.h3i', 'Pfam-A.31.0.hmm.h3m', 'Pfam-A.31.0.hmm.h3f', 'Pfam-A.31.0.hmm.h3p', 'Pfam-A.31.0.clans.tsv']
INFO 09/06 12:22:52 ================================================================================
INFO 09/06 12:22:52 Available detectors: ['deepbgc', 'clusterfinder_retrained', 'clusterfinder_original', 'clusterfinder_geneborder']
INFO 09/06 12:22:52 --------------------------------------------------------------------------------
INFO 09/06 12:22:52 Model: deepbgc
INFO 09/06 12:22:52 Loading model from: /public/home/zhaoxinghong/.local/share/deepbgc/data/0.1.0/detector/deepbgc.pkl
Using TensorFlow backend.
WARNING 09/06 12:22:59 Model not supported: ("Error unpickling model from path '/public/home/zhaoxinghong/.local/share/deepbgc/data/0.1.0/detector/deepbgc.pkl'", TypeError('Descriptors cannot not be created directly.\nIf this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.\nIf you cannot immediately regenerate your protos, some other possible workarounds are:\n 1. Downgrade the protobuf package to 3.20.x or lower.\n 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).\n\nMore information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates'))
INFO 09/06 12:22:59 --------------------------------------------------------------------------------
INFO 09/06 12:22:59 Model: clusterfinder_retrained
INFO 09/06 12:22:59 Loading model from: /public/home/zhaoxinghong/.local/share/deepbgc/data/0.1.0/detector/clusterfinder_retrained.pkl
WARNING 09/06 12:23:00 Model not supported: ('Package "hmmlearn" needs to be installed to run ClusterFinder HMM. ', 'Install extra dependencies using: \n pip install "deepbgc[hmm]"')
INFO 09/06 12:23:00 --------------------------------------------------------------------------------
INFO 09/06 12:23:00 Model: clusterfinder_original
INFO 09/06 12:23:00 Loading model from: /public/home/zhaoxinghong/.local/share/deepbgc/data/0.1.0/detector/clusterfinder_original.pkl
WARNING 09/06 12:23:00 Model not supported: ('Package "hmmlearn" needs to be installed to run ClusterFinder HMM. ', 'Install extra dependencies using: \n pip install "deepbgc[hmm]"')
INFO 09/06 12:23:00 --------------------------------------------------------------------------------
INFO 09/06 12:23:00 Model: clusterfinder_geneborder
INFO 09/06 12:23:00 Loading model from: /public/home/zhaoxinghong/.local/share/deepbgc/data/0.1.0/detector/clusterfinder_geneborder.pkl
WARNING 09/06 12:23:00 Model not supported: ('Package "hmmlearn" needs to be installed to run ClusterFinder HMM. ', 'Install extra dependencies using: \n pip install "deepbgc[hmm]"')
INFO 09/06 12:23:00 ================================================================================
INFO 09/06 12:23:00 Available classifiers: ['product_class', 'product_activity']
INFO 09/06 12:23:00 --------------------------------------------------------------------------------
INFO 09/06 12:23:00 Model: product_class
INFO 09/06 12:23:00 Loading model from: /public/home/zhaoxinghong/.local/share/deepbgc/data/0.1.0/classifier/product_class.pkl
/public/home/zhaoxinghong/miniconda3/envs/deepbgc/lib/python3.7/site-packages/sklearn/base.py:306: UserWarning: Trying to unpickle estimator DecisionTreeClassifier from version 0.18.2 when using version 0.21.3. This might lead to breaking code or invalid results. Use at your own risk.
UserWarning)
/public/home/zhaoxinghong/miniconda3/envs/deepbgc/lib/python3.7/site-packages/sklearn/base.py:306: UserWarning: Trying to unpickle estimator RandomForestClassifier from version 0.18.2 when using version 0.21.3. This might lead to breaking code or invalid results. Use at your own risk.
UserWarning)
INFO 09/06 12:23:02 Type: RandomForestClassifier
INFO 09/06 12:23:02 Version: 0.1.0
INFO 09/06 12:23:02 Timestamp: 1551781410.019103 (2019-03-05T18:23:30.019103)
INFO 09/06 12:23:02 --------------------------------------------------------------------------------
INFO 09/06 12:23:02 Model: product_activity
INFO 09/06 12:23:02 Loading model from: /public/home/zhaoxinghong/.local/share/deepbgc/data/0.1.0/classifier/product_activity.pkl
INFO 09/06 12:23:02 Type: RandomForestClassifier
INFO 09/06 12:23:02 Version: 0.1.0
INFO 09/06 12:23:02 Timestamp: 1551781433.886473 (2019-03-05T18:23:53.886473)
INFO 09/06 12:23:02 ================================================================================
WARNING 09/06 12:23:02 Some warnings detected, check the output above

I've tried using protobuf==3.19.0 to solve the first WARNING but which caused more problem and for the last two WARNING, scikit-learn=0.18.2 doesn't seem support python=3.7.

How can I solve above problems?

Thank you for the assistance.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the README installation instructions and reproduce the reported deepbgc info output using the published wheel. Inspect the model-loading paths shown for the detector and classifier files, then verify that the documented installation completes without the reported protobuf, hmmlearn, and scikit-learn warnings.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, scikit-learn, tensorflow
Domain
devtools, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.