A package, and script, to perform imaging transcriptomics on a neuroimaging scan.

Overview

Imaging Transcriptomics

DOI License: GPL v3 Maintainer Generic badge Documentation Status

Imaging-transcriptomics_overwiew

Imaging transcriptomics is a methodology that allows to identify patterns of correlation between gene expression and some property of brain structure or function as measured by neuroimaging (e.g., MRI, fMRI, PET).


The imaging-transcriptomics package allows performing imaging transcriptomics analysis on a neuroimaging scan (e.g., PET, MRI, fMRI...).

The software is implemented in Python3 (v.3.7), its source code is available on GitHub, it can be installed via Pypi and is released under the GPL v3 license.

NOTE Versions from v1.0.0 are or will be maintained. The original script linked by the BioRxiv preprint (v0.0) is still available on GitHub but no changes will be made to that code. If you have downloaded or used that script please update to the newer version by installing this new version.

Installation

NOTE We recommend to install the package in a dedicated environment of your choice (e.g., venv or anaconda). Once you have created your environment and you have activated it, you can follow the below guide to install the package and dependencies. This process will avoid clashes between conflicting packages that could happen during/after the installation.

To install the imaging-transcriptomics Python package, first you will need to install a packages that can't be installed directly from PyPi, but require to be downloaded from GitHub. The package to install is pypyls. To install this package you can follow the installation on the documentation for the package or simply run the command

pip install -e git+https://github.com/netneurolab/pypyls.git/#egg=pyls

to download the package, and its dependencies directly from GitHub by using pip.

Once this package is installed you can install the imaging-transcriptomics package by running

pip install imaging-transcriptomics

Usage

Once installed the software can be used in two ways:

  • as standalone script
  • as part of some python script

WARNING Before running the script make sure the Pyhton environment where you have installed the package is activated.

Standalone script


To run the standalone script from the terminal use the command:

imagingtranscriptomics options

The options available are:

  • -i (--input): Path to the imaging file to analise. The path should be given to the program as an absolute path (e.g., /Users/myusername/Documents/my_scan.nii, since a relative path could raise permission errors and crashes. The script only accepts imaging files in the NIfTI format (.nii, .nii.gz).
  • -v (--variance): Amount of variance that the PLS components must explain. This MUST be in the range 0-100.

    NOTE: if the variance given as input is in the range 0-1 the script will treat this as 30% the same way as if the number was in the range 10-100 (e.g., the script treats the inputs -v 30 and -v 0.3 in the exact same way and the resulting components will explain 30% of the variance).

  • -n (--ncomp): Number of components to be used in the PLS regression. The number MUST be in the range 1-15.
  • --corr: Run the analysis using Spearman correlation instead of PLS.

    NOTE: if you run with the --corr command no other input is required, apart from the input scan (-i).

  • -o (--output) (optional): Path where to save the results. If none is provided the results will be saved in the same directory as the input scan.

WARNING: The -i flag is MANDATORY to run the script, and so is one, and only one, of the -n or -v flags. These last two are mutually exclusive, meaning that ONLY one of the two has to be given as input.

Part of Python script


When used as part of a Python script the library can be imported as:

import imaging_transcriptomics as imt

The core class of the package is the ImagingTranscriptomics class which gives access to the methods used in the standalone script. To use the analysis in your scripts you can initialise the class and then simply call the ImagingTranscriptomics().run() method.

import numpy as np
import imaging_transcriptomics as imt
my_data = np.ones(41)  # MUST be of size 41 
                       # (corresponds to the regions in left hemisphere of the DK atlas)

analysis = imt.ImagingTranscriptomics(my_data, n_components=1)
analysis.run()
# If instead of running PLS you want to analysze the data with correlation you can run the analysis with:
analysis.run(method="corr")

Once completed the results will be part of the analysis object and can be accessed with analysis.gene_results.

The import of the imaging_transcriptomics package will import other helpful functions for input and reporting. For a complete explanation of this please refer to the official documentation of the package.

Documentation

The documentation of the script is available at imaging-transcriptomics.rtfd.io/.

Troubleshooting

For any problems with the software you can open an issue in GitHub or contact the maintainer) of the package.

Citing

If you publish work using imaging-transcriptomics as part of your analysis please cite:

Imaging transcriptomics: Convergent cellular, transcriptomic, and molecular neuroimaging signatures in the healthy adult human brain. Daniel Martins, Alessio Giacomel, Steven CR Williams, Federico Turkheimer, Ottavia Dipasquale, Mattia Veronese, PET templates working group. bioRxiv 2021.06.18.448872; doi: https://doi.org/10.1101/2021.06.18.448872

Imaging-transcriptomics: Second release update (v1.0.2).Alessio Giacomel, & Daniel Martins. (2021). Zenodo. https://doi.org/10.5281/zenodo.5726839

Comments
  • pip installation can not resolve enigmatoolbox dependencies

    pip installation can not resolve enigmatoolbox dependencies

    After pip install -e git+https://github.com/netneurolab/pypyls.git/#egg=pyls and pip install imaging-transcriptomics in a new conda environment with Python=3.8, an error was occurred when import imaging-transcriptomics package that it can't find the module named enigmatoolbox. I figured out that the enigmatoolbox package seems can not be resolve by pip installation automatically, so I have to install the enigmatoolbox package from Github manually, with the code bellow according to the document of enigmatoolbox:

    git clone https://github.com/MICA-MNI/ENIGMA.git
    cd ENIGMA
    python setup.py install
    
    opened by YCHuang0610 4
  • DK atlas regions

    DK atlas regions

    Dear alegiac95,

    thanks for providing the scripts! I have just gone through the paper and description of this GitHub repo and I want to adapt your software to my project. However, I use the typical implementation of the DK from Freesurfer with 34 cortical DK ROIs instead of the 41 ROIs that you have used and, if I'm not mistaken, 41 ROIs are required to implement the script as ist is. Is it possible to change the input to other cortical parcellations as well (i.e., DK-34)?

    Cheers, Melissa

    enhancement 
    opened by Melissa1909 3
  • Script not calling the correct python version

    Script not calling the correct python version

    The script in version v1.0.0 is invoking the #!/usr/bin/env python interpreter, which could generate some issue if you default python is python2 (e.g., in older MacOS versions).

    bug 
    opened by alegiac95 1
  • Version 1.1.0

    Version 1.1.0

    Updated the scripts with:

    • support for both full brain analysis and cortical regions only
    • GSEA analysis (both during the analysis and as a separate script)
    • pdf report of the analysis
    opened by alegiac95 0
  • clean code and fix test

    clean code and fix test

    This commit does an extensive code cleaning following the PEP8 standard. It also fixes a test that was most probably intended for previous unstable versions of the software.

    Still to do:

    • Remove logging
    opened by matteofrigo 0
  • Add mathematical background on PLS

    Add mathematical background on PLS

    A more detailed explanation on PLS model and regression is required in the docs.

    • [ ] Add a general mathematical formulation of PLS
    • [ ] Use of PLS in neuroimaging applications
    • [ ] Description of the SIMPLS algorithm used by pypls

    In addition provide some background on correlation, since it is now added to the methods available in the python package/script

    documentation 
    opened by alegiac95 0
Releases(v.1.1.8)
Easy and comprehensive assessment of predictive power, with support for neuroimaging features

Documentation: https://raamana.github.io/neuropredict/ News As of v0.6, neuropredict now supports regression applications i.e. predicting continuous t

Pradeep Reddy Raamana 93 Nov 29, 2022
Machine learning for NeuroImaging in Python

nilearn Nilearn enables approachable and versatile analyses of brain volumes. It provides statistical and machine-learning tools, with instructive doc

null 919 Dec 25, 2022
Medical-Image-Triage-and-Classification-System-Based-on-COVID-19-CT-and-X-ray-Scan-Dataset

Medical-Image-Triage-and-Classification-System-Based-on-COVID-19-CT-and-X-ray-Sc

null 2 Dec 26, 2021
Useful materials and tutorials for 110-1 NTU DBME5028 (Application of Deep Learning in Medical Imaging)

Useful materials and tutorials for 110-1 NTU DBME5028 (Application of Deep Learning in Medical Imaging)

null 7 Jun 22, 2022
Non-Imaging Transient Reconstruction And TEmporal Search (NITRATES)

Non-Imaging Transient Reconstruction And TEmporal Search (NITRATES) This repo contains the full NITRATES pipeline for maximum likelihood-driven discov

null 13 Nov 8, 2022
MRQy is a quality assurance and checking tool for quantitative assessment of magnetic resonance imaging (MRI) data.

Front-end View Backend View Table of Contents Description Prerequisites Running Basic Information Measurements User Interface Feedback and usage Descr

Center for Computational Imaging and Personalized Diagnostics 58 Dec 2, 2022
Official Keras Implementation for UNet++ in IEEE Transactions on Medical Imaging and DLMIA 2018

UNet++: A Nested U-Net Architecture for Medical Image Segmentation UNet++ is a new general purpose image segmentation architecture for more accurate i

Zongwei Zhou 1.8k Jan 7, 2023
The code release of paper 'Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization' NIPS 2020.

Domain Generalization for Medical Imaging Classification with Linear Dependency Regularization The code release of paper 'Domain Generalization for Me

Yufei Wang 56 Dec 28, 2022
A medical imaging framework for Pytorch

Welcome to MedicalTorch MedicalTorch is an open-source framework for PyTorch, implementing an extensive set of loaders, pre-processors and datasets fo

Christian S. Perone 799 Jan 3, 2023
Code associated with the paper "Deep Optics for Single-shot High-dynamic-range Imaging"

Deep Optics for Single-shot High-dynamic-range Imaging Code associated with the paper "Deep Optics for Single-shot High-dynamic-range Imaging" CVPR, 2

Stanford Computational Imaging Lab 40 Dec 12, 2022
Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

Jian Zhang 20 Oct 24, 2022
[MICCAI'20] AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes

AlignShift NEW: Code for our new MICCAI'21 paper "Asymmetric 3D Context Fusion for Universal Lesion Detection" will also be pushed to this repository

Medical 3D Vision 42 Jan 6, 2023
Neural Nano-Optics for High-quality Thin Lens Imaging

Neural Nano-Optics for High-quality Thin Lens Imaging Project Page | Paper | Data Ethan Tseng, Shane Colburn, James Whitehead, Luocheng Huang, Seung-H

Ethan Tseng 39 Dec 5, 2022
Official implementation of NLOS-OT: Passive Non-Line-of-Sight Imaging Using Optimal Transport (IEEE TIP, accepted)

NLOS-OT Official implementation of NLOS-OT: Passive Non-Line-of-Sight Imaging Using Optimal Transport (IEEE TIP, accepted) Description In this reposit

Ruixu Geng(耿瑞旭) 16 Dec 16, 2022
Official implementation of the method ContIG, for self-supervised learning from medical imaging with genomics

ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics This is the code implementation of the paper "ContIG: Self-s

Digital Health & Machine Learning 22 Dec 13, 2022
Simulation of moving particles under microscopic imaging

Simulation of moving particles under microscopic imaging Install scipy numpy scikit-image tiffile Run python simulation.py Read result https://imagej

Zehao Wang 2 Dec 14, 2021
PyTorch implementation of Deep HDR Imaging via A Non-Local Network (TIP 2020).

NHDRRNet-PyTorch This is the PyTorch implementation of Deep HDR Imaging via A Non-Local Network (TIP 2020). 0. Differences between Original Paper and

Yutong Zhang 1 Mar 1, 2022
Equivariant Imaging: Learning Beyond the Range Space

[Project] Equivariant Imaging: Learning Beyond the Range Space Project about the

Georges Le Bellier 3 Feb 6, 2022
Pytorch implementation of various High Dynamic Range (HDR) Imaging algorithms

Deep High Dynamic Range Imaging Benchmark This repository is the pytorch impleme

Tianhong Dai 5 Nov 16, 2022