Giter Club home page Giter Club logo

prs-net's Introduction

PRS-Net

About

This repository contains the code and resources of the following paper:

PRS-Net: Interpretable polygenic risk scores via geometric learning

Overview of the framework

PRS-Net is an interpretable genomic deep learning-based approach designed to effectively model the nonlinearity of the biological system and deliver precise and interpretable polygenic risk scores.

Data preprocessing

Setup environment

Setup the required environment using environment_data.yml with Anaconda. While in the project directory run:

conda env create -f environment_data.yml

Activate the environment

conda activate PRS-Net_data

Step 1: Arrange GWAS summary statistic data

Ensure the columns in your GWAS summary statistic data are ordered as follows, separated by tabs (\t): CHR, BP, SNP, A1, A2, N, SE, P, OR, INFO, MAF, BETA, where A1 stands for the effect allele of the SNP and A2 stands for the non-effect allele of the SNP.

Step 2: Run preprocessing script

Execute the 1_data_preprocess.sh script with the following command:

./1_data_preprocess.sh your_base_data_path your_target_data_path your_phenotype_data_path your_ld_data_path your_output_path

  • your_base_data_path: the path of the gwas summarty stastistics file derived from Step 1

  • your_target_data_path: the path (without postfix) of the target data in PLINK format (.bim, .fam, .bed)

  • your_phenotype_data_path: the path of the phenotype data separated by blanks (Sample_ID Sample_ID Phenotype_label)

  • your_ld_data_path: the path (without postfix) of the data used for LD calculating in PLINK format

  • your_output_path: the path of the output files

Step 3: Run PRS-Net data generation script

Execute the gwas_data_preprocess.sh script with the following command:

./2_data_generation.sh your_preprocessed_data_path your_phenotype_data_path your_output_path

  • your_preprocessed_data_path: the path of the preprocessed files derived from Step 2

  • your_phenotype_data_path: the path of the phenotype data separated by tabs (ID \t ID \t Label)

  • your_output_path: the path of the output files

Train

Setup environment

Setup the required environment using environment.yml with Anaconda. While in the project directory run:

conda env create -f environment.yml

Activate the environment

conda activate PRS-Net

We upload an example dataset at https://cloud.tsinghua.edu.cn/f/30a1c8df0c024fefa3c1/?dl=1.

Unzip the file and put it in example_dataset/ and excecute the train.py with the following command:

python train.py --data_path ../example_dataset/ --dataset ad_eur

License

PRS-Net is licensed under the Apache License, Version 2.0: http://www.apache.org/licenses/LICENSE-2.0.

prs-net's People

Watchers

avatar

prs-net's Issues

Questions about installing the package

Hi, thanks for your interesting project. When installing the package to reproduce the training result, I meet an error:

      /tmp/pip-build-env-5nfkk1gy/overlay/lib/python3.7/site-packages/setuptools/command/build_py.py:201: _Warning: Package 'pyreadr.libs.lzma.lzma' is absent from the `packages` configuration.
      !!
      
              ********************************************************************************
              ############################
              # Package would be ignored #
              ############################
              Python recognizes 'pyreadr.libs.lzma.lzma' as an importable package[^1],
              but it is absent from setuptools' `packages` configuration.
      
              This leads to an ambiguous overall configuration. If you want to distribute this
              package, please make sure that 'pyreadr.libs.lzma.lzma' is explicitly added
              to the `packages` configuration field.
      
              Alternatively, you can also rely on setuptools' discovery methods
              (for example by using `find_namespace_packages(...)`/`find_namespace:`
              instead of `find_packages(...)`/`find:`).
      
              You can read more about "package discovery" on setuptools documentation page:
      
              - https://setuptools.pypa.io/en/latest/userguide/package_discovery.html
      
              If you don't want 'pyreadr.libs.lzma.lzma' to be distributed and are
              already explicitly excluding 'pyreadr.libs.lzma.lzma' via
              `find_namespace_packages(...)/find_namespace` or `find_packages(...)/find`,
              you can try to use `exclude_package_data`, or `include-package-data=False` in
              combination with a more fine grained `package-data` configuration.
      
              You can read more about "package data files" on setuptools documentation page:
      
              - https://setuptools.pypa.io/en/latest/userguide/datafiles.html
      
      
              [^1]: For Python, any directory (with suitable naming) can be imported,
                    even if it does not contain any `.py` files.
                    On the other hand, currently there is no concept of package data
                    directory, all directories are treated like packages.
              ********************************************************************************
      
      !!
        check.warn(importable)
      /tmp/pip-build-env-5nfkk1gy/overlay/lib/python3.7/site-packages/setuptools/command/build_py.py:201: _Warning: Package 'pyreadr.libs.zlib' is absent from the `packages` configuration.
      !!
      
              ********************************************************************************
              ############################
              # Package would be ignored #
              ############################
              Python recognizes 'pyreadr.libs.zlib' as an importable package[^1],
              but it is absent from setuptools' `packages` configuration.
      
              This leads to an ambiguous overall configuration. If you want to distribute this
              package, please make sure that 'pyreadr.libs.zlib' is explicitly added
              to the `packages` configuration field.
      
              Alternatively, you can also rely on setuptools' discovery methods
              (for example by using `find_namespace_packages(...)`/`find_namespace:`
              instead of `find_packages(...)`/`find:`).
      
              You can read more about "package discovery" on setuptools documentation page:
      
              - https://setuptools.pypa.io/en/latest/userguide/package_discovery.html
      
              If you don't want 'pyreadr.libs.zlib' to be distributed and are
              already explicitly excluding 'pyreadr.libs.zlib' via
              `find_namespace_packages(...)/find_namespace` or `find_packages(...)/find`,
              you can try to use `exclude_package_data`, or `include-package-data=False` in
              combination with a more fine grained `package-data` configuration.
      
              You can read more about "package data files" on setuptools documentation page:
      
              - https://setuptools.pypa.io/en/latest/userguide/datafiles.html
      
      
              [^1]: For Python, any directory (with suitable naming) can be imported,
                    even if it does not contain any `.py` files.
                    On the other hand, currently there is no concept of package data
                    directory, all directories are treated like packages.
              ********************************************************************************
      
      !!
        check.warn(importable)
      error: command '/usr/bin/gcc' failed with exit code 1
      [end of output]
  
  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for pyreadr
ERROR: Could not build wheels for pyreadr, which is required to install pyproject.toml-based projects

It seems that the current conda.yml file is not enough. Would you please provide more information? Thanks.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.