Release 0.1.1 Minor updates / bug fixes + Adding containers

CHANGELOG.md

@@ -5,6 +5,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.1.1] - 2024-04-24
+
+### Changed
+
+- Fixed bugs in the E-Step benchmarking script.
+- Re-wrote the logic for finding BLAS libraries in the `setup.py` script. :crossed_fingers:
+
+### Added
+
+- `Dockerfile`s for both `cli` and `jupyter` modes.
+
 ## [0.1.0] - 2024-04-05
 
 A large scale restructuring of the code base to improve efficiency and usability.

benchmarks/benchmark_e_step.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python3
+
 """
 Benchmark the speed of the E-Step in VIPRS
 ----------------------------
@@ -214,9 +216,9 @@ def exec_func():
     # ------------------------------------------------------------------------
 
     # Create a grid:
-    grid = HyperparameterGrid()
+    grid = HyperparameterGrid(n_snps=gdl.n_snps)
     # Generate a grid for pi using 5 equidistant grid points:
-    grid.generate_pi_grid(steps=args.grid_size, n_snps=gdl.n_snps)
+    grid.generate_pi_grid(steps=args.grid_size)
     # Generate a grid for sigma epsilon using 5 equidistant grid points:
     grid.generate_sigma_epsilon_grid(steps=args.grid_size)
 

bin/viprs_evaluate

@@ -103,7 +103,7 @@ if args.covariates_file is not None:
 # Make sure that samples remain after reading both:
 assert sample_table.n > 0, "No samples found after merging the covariates and phenotype files."
 
-prs_df = pd.read_csv(args.prs_file, sep='\t')
+prs_df = pd.read_csv(args.prs_file, sep=r'\s+')
 
 # Merge the PRS data with the phenotype data:
 prs_df = prs_df.merge(sample_table.get_individual_table(), on=['FID', 'IID'])

bin/viprs_fit

@@ -30,6 +30,7 @@ Usage:
 
 import os.path as osp
 
+
 def check_args(args):
     """
     Check the validity, consistency, and completeness of the commandline arguments.

bin/viprs_score

@@ -25,6 +25,7 @@ from magenpy.utils.system_utils import makedir, get_filenames
 from magenpy.GWADataLoader import GWADataLoader
 from viprs.model.BayesPRSModel import BayesPRSModel
 
+
 print(fr"""
         **********************************************
                     _____

containers/cli.Dockerfile

@@ -0,0 +1,43 @@
+# Usage:
+# ** Step 1 ** Build the docker image:
+# docker build -f cli.Dockerfile -t viprs-cli .
+# ** Step 2** Run the docker container in interactive shell mode:
+# docker run -it viprs-cli /bin/bash
+# ** Step 3** Test viprs fit:
+# viprs_fit -h
+
+FROM python:3.11-slim-buster
+
+LABEL authors="Shadi Zabad"
+LABEL version="0.1"
+LABEL description="Docker image containing all requirements to run the commandline scripts in the VIPRS package"
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    unzip \
+    wget \
+    pkg-config \
+    g++ gcc \
+    libopenblas-dev \
+    libomp-dev
+
+# Download and setup plink2:
+RUN mkdir -p /software && \
+    wget https://s3.amazonaws.com/plink2-assets/alpha5/plink2_linux_avx2_20240105.zip -O /software/plink2.zip && \
+    unzip /software/plink2.zip -d /software && \
+    rm /software/plink2.zip
+
+# Download and setup plink1.9:
+RUN mkdir -p /software && \
+    wget https://s3.amazonaws.com/plink1-assets/plink_linux_x86_64_20231211.zip -O /software/plink.zip && \
+    unzip /software/plink.zip -d /software && \
+    rm /software/plink.zip
+
+# Add plink1.9 and plink2 to PATH:
+RUN echo 'export PATH=$PATH:/software' >> ~/.bashrc
+
+# Install viprs package from PyPI
+RUN pip install --upgrade pip viprs
+
+# Test the installation
+RUN viprs_fit -h

containers/jupyter.Dockerfile

@@ -0,0 +1,53 @@
+# Usage:
+# ** Step 1 ** Build the docker image:
+# docker build -f ../vemPRS/containers/jupyter.Dockerfile -t viprs-jupyter .
+# ** Step 2 ** Run the docker container (pass the appropriate port):
+# docker run -p 8888:8888 viprs-jupyter
+# ** Step 3 ** Open the link in your browser:
+# http://localhost:8888
+
+
+FROM python:3.11-slim-buster
+
+LABEL authors="Shadi Zabad"
+LABEL version="0.1"
+LABEL description="Docker image containing all requirements to run the VIPRS package in a Jupyter Notebook"
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    unzip \
+    wget \
+    pkg-config \
+    g++ gcc \
+    libopenblas-dev \
+    libomp-dev
+
+# Download and setup plink2:
+RUN mkdir -p /software && \
+    wget https://s3.amazonaws.com/plink2-assets/alpha5/plink2_linux_avx2_20240105.zip -O /software/plink2.zip && \
+    unzip /software/plink2.zip -d /software && \
+    rm /software/plink2.zip
+
+# Download and setup plink1.9:
+RUN mkdir -p /software && \
+    wget https://s3.amazonaws.com/plink1-assets/plink_linux_x86_64_20231211.zip -O /software/plink.zip && \
+    unzip /software/plink.zip -d /software && \
+    rm /software/plink.zip
+
+# Add plink1.9 and plink2 to PATH:
+RUN echo 'export PATH=$PATH:/software' >> ~/.bashrc
+
+# Install viprs package from PyPI
+RUN pip install --upgrade pip viprs jupyterlab
+
+# Expose the port Jupyter Lab will be served on
+EXPOSE 8888
+
+# Set the working directory
+WORKDIR /viprs_dir
+
+# Copy the current directory contents into the container at /app
+COPY . /viprs_dir
+
+# Run Jupyter Lab
+CMD ["jupyter", "lab", "--ip=0.0.0.0", "--allow-root", "--NotebookApp.token=''"]

docs/getting_started.md

@@ -30,7 +30,7 @@ summary statistics from `fastGWA`:
 ```python linenums="1"
 # Load genotype and GWAS summary statistics data (chromosome 22):
 gdl = mgp.GWADataLoader(bed_files=mgp.tgp_eur_data_path(),  # Path of the genotype data
-                        sumstats_files=mgp.ukb_height_fastGWA_path(),  # Path of the summary statistics
+                        sumstats_files=mgp.ukb_height_sumstats_path(),  # Path of the summary statistics
                         sumstats_format="fastGWA")  # Specify the format of the summary statistics
 ```
 

docs/installation.md

@@ -26,7 +26,7 @@ a new environment with the required dependencies as follows:
 
 ```bash
 python_version=3.11  # Change python version here if needed
-conda create --name "viprs_env" -c anaconda -c conda-forge python=$python_version compilers openblas -y
+conda create --name "viprs_env" -c anaconda -c conda-forge python=$python_version compilers pkg-config openblas -y
 conda activate viprs_env
 ```
 
@@ -68,3 +68,21 @@ source viprs_env/bin/activate
 python -m pip install --upgrade pip
 python -m pip install viprs>=0.1
 ```
+
+### Using `Docker` containers
+
+If you are using `Docker` containers, you can build a container with the `viprs` package 
+and all its dependencies by downloading the relevant `Dockerfile` from the 
+[repository](https://github.com/shz9/viprs/tree/master/containers) and building it 
+as follows:
+
+```bash
+# Build the docker image:
+docker build -f cli.Dockerfile -t viprs-cli .
+# Run the container in interactive mode:
+docker run -it viprs-cli /bin/bash
+# Test that the package installed successfully:
+viprs_fit -h
+```
+
+We plan to publish pre-built `Docker` images on `DockerHub` in the future.

pyproject.toml

@@ -7,6 +7,7 @@ requires = [
     "extension-helpers",
     "scipy",
     "oldest-supported-numpy",
+    "pkgconfig"
 ]
 build-backend = "setuptools.build_meta"