marakeby/pnet_prostate_paper

P-NET, Biologically informed deep neural network for prostate cancer classification and discovery

pnet_prostate_paper's Issues

Environment fails at installing decorator: not compatible with Python 2.7

During installation I found a conflict with the decorator package version that is installed. Namely, the default version conda installs gets into conflict because it gets in conflict with python 2.7 , a default requirement.

I think this could be solved by downgrading decorator to a 2.6+ compatible version, I found that decorator 4.3.2 is valid based on the current decorator release list.

pip install decorator==4.3.2

Could you update this dependency into the environment.yml file? It could probably ease the installation process.

Thanks for dev and sharing of this repository.

environment.yml ERROR

File configuration error
"""
dependencies:
...
h5py=2.9.0l.c
...
"""
should be modify.
I try to change it:
"""
dependencies:
...
h5py
...
"""
the code is working.
However, I am not sure whether it will affect the subsequent analysis.
We look forward to your reply or solution !!

Thank you for your time

A request to latest code.

I found that your code has been updated recently. python2 and python3 versions, tensorflow1.x and tensorflow2.x are both used in your code.I cannot run your code. Can you give me the latest code that can be run directly? Thank you very much for your kind consideration.

how to incorporate new loss function (your own) in PNET architecture

Any suggestion or comments with reference to PNET architecture will be helpful.

No such file or directory pathways_short_names.xlsx'

I tried to regenerate figure3 in the paper,but there is no 'pathways_short_names.xlsx' file under '~/_database/pathways' directory.
Could you please supply this file?
I am looking forward to your reply!!!
Thank you for your time.

Does PNET support training with multiple classes?

Dear @marakeby,

Thanks for developing and releasing PNET. I am trying to do exploratory analyses in some multimodal data using this framework. Labels are more than two, so I wonder whether a multiclass flag is already available by default in one of the reported architectures tested in the paper. I think small changes in the nn.py and/or model_params_ dictionary could allow this, yet I have been testing without much success (e.g. 'prediction_outputto None, and a alternativeloss` key).

Do you think there are already defaults for trying this? Thanks for any comments on this.

"ResolvePackageNotFound: - h5py=2.9.0l.c" Error

Hi,
I tried to create a p-net environment with "conda env create --name pnet_env --file=environment.yml", but failed. The messages are:

Collecting package metadata (repodata.json): done
Solving environment: failed

ResolvePackageNotFound: 
  - h5py=2.9.0l.c

So, how to solve this problem? Thanks.

Error: No packages found in current win-32 channels matching: imageio

I am trying on windows conda env create --name pnet_env --file=environment.yml and getting this error

Using Anaconda Cloud api site https://api.anaconda.org
Fetching package metadata: ....
Error: No packages found in current win-32 channels matching: imageio

when I am using same versions as mentioned in yml file, it is giving error of package version not found error.
conda env create --name pnet_env --file=environment.yml
Using Anaconda Cloud api site https://api.anaconda.org
Using Anaconda Cloud api site https://api.anaconda.org
Fetching package metadata: ..........
Error: No packages found in current win-32 channels matching: pip 18.1*

data

Dear @marakeby,

How do you get the data（P1000_final_analysis_set_cross_important_only.csv） ？And how to do data preprocessing？
Thanks

Prerequisites must be py2.7?

My conda base is python=3.9.
I create env in this base.
However, I am not sure whether it will affect the subsequent analysis.
We look forward to your reply !!
Thank you for your time

where I can find the file "P1000_final_analysis_set_cross__no_silent_no_introns_not_from_the_paper.csv"

I got an issue, where I can find the file "P1000_final_analysis_set_cross__no_silent_no_introns_not_from_the_paper.csv"? It's mentioned in "data_reader.py", please let me know if you get it, thank you!

environment problem

Problem 1, the lifelines in environment.yml need to install the dependency package Bottleneck, pip will install Bottleneck1.3.4 by default, but there are problems causing Bottleneck1.3.4 will always fail to install, so need to install Bottleneck1.3.2 in advance.

Problem 2, h5py in environment.yml did not find version 2.9.01.c, so install 2.9.0

Extended figures

Where is the code for extended figures 6 and 8?
Thanks

No such file : pathways_short_names.xlsx

I tried to regenerate figure3 in the paper,but there is no 'pathways_short_names.xlsx' file under '~/_database/pathways' directory.
Could you please supply this file?
I am looking forward to your reply!!!
Thank you for your time.

Environment Error

Hi, Can someone please tell me how to rectify the environment error. I am encountering this error for a few days now and the code does not run. My base python version in 3.9. I am also attaching screenshots for the same. Any leads/help would be appreciated.

Thanks