fMRIprep Pipeline To Machine Learning

Overview

fMRIprep Pipeline To Machine Learning(Demo)

所有配置均在config.py文件下定义

前置环境(lilab)

  • 各个节点均安装docker,并有fmripre的镜像
  • 可以使用conda中的base环境(相应的第三份包之后更新)

1. fmriprep script on single machine(docker)

config.py中的fMRI_Prep_Job类中配置相应变量,注意在修改cmd时,不能修改{}中的关键字。在执行此步骤时,将自动在bids同级目录下建立processed文件夹,用来存放后处理数据。其中处理后的fmriprep数据存放在processed/frmriprepprceossed/fressurfer中。

class fMRI_Prep_Job:
    # input data path
    bids_data_path  = "/share/data2/dataset/ds002748/depression"
    # 一个容器中处理多少个被试 
    step = 8
    # fmriprep opm thread
    thread = 9
    # max work contianers
    max_work_nums = 10

    # 在bids同级目录下创建processed文件夹
    bids_output_path = os.path.join("/".join(bids_data_path.split('/')[:-1]),'processed')
    if not os.path.exists(bids_output_path):
        os.mkdir(bids_output_path)
    # fmri work path 
    fmri_work="/share/fmri_work"
    # freesurfer_license
    freesurfer_license = "/share/user_data/public/fanq_ocd/license.txt"
    # contianer id fmriprep
    contianer_id = "d7235efbbd3c"
    # fmriprep cmd 
    cmd ="docker run -it --rm -v {bids_data_path}:/data -v {freesurfer_license}:/opt/freesurfer/license.txt -v {bids_output_path}:/out -v {fmri_work}:/work {contianer_id} /data /out --skip_bids_validation --ignore slicetiming fieldmaps  -w /work --omp-nthreads {thread} --fs-no-reconall --resource-monitor participant --participant-label {subject_ids}"

2. fmriprep post preocess

这一步的操作主要依赖于fmribrant,主要作用是回归掉白质信号、脑脊液信号、全脑信号、头动信息、并进行滤波(可选),将其处理后的文件放存在prcoessed/post-precoss/ fliter/clean_imgs 中, 可选表示是否进行滤波。该配置中不建议修改dataset_path,store_path

class PostProcess:
    """
    fmriprep 后处理数据
    """
    # 类型的名字
    task_type = "rest"

    dataset_path = os.path.join(fMRI_Prep_Job.bids_output_path,'fmriprep')

    store_path = os.path.join(fMRI_Prep_Job.bids_output_path,'post-process')

    t_r = 2.5

    low_pass = 0.08

    high_pass = 0.01

    n_process = 40

    if t_r != None:
        store_path = os.path.join(store_path,'filter','clean_imgs')
    else:
        store_path = os.path.join(store_path,'unfilter','clean_imgs')

    os.makedirs(store_path,exist_ok=True)

3.获取ROI级别的时间序列

atlas由271个roi组成,分别是Schaefer_200(皮上),Tianye_54(皮下),Buckner_17(小脑)。由于在fmribrant中实现提取时间序列的功能,简单封装一下。

class RoiTs:
    """
    ROI 级别时间序列
    处理271个全脑roi
    """
    n_process = 40

    # 如果在第二步fmri post process已经滤波之后,不建议再次使用滤波操作
    t_r = None
    
    low_pass = None

    high_pass = None
    
    flag_gs = False #  回归全脑均值为 True 否则为False
    # 以下内容不建议修改

    if flag_gs:
        file_name = "*with_gs.nii.gz"
        ts_file = "GS"
    else:
        file_name = "*without_gs.nii.gz"
        ts_file = "NO_GS"
    
    reg_path = os.path.join(PostProcess.store_path,"*",PostProcess.task_type,file_name)
    
    subject_id_index = -3

    save_path = os.path.join("/".join(PostProcess.store_path.split('/')[:-1]),'timeseries',ts_file)

    os.makedirs(save_path,exist_ok=True)

4. Machine Learning(Baseline)

这一步是可选的,一般先用来看看FC做性别分类、年龄回归的效果如何。只保留粗略结果,详细结果可以使用baseline这个包。

class ML:
    # 选择的subject id 默认是全部
    sub_ids = [i.split('.')[0] for i in os.listdir(RoiTs.save_path)]
    # 量表位置
    csv = pd.read_csv('/share/data2/dataset/ds002748/depression/participants.tsv',sep='\t')
    #取交集
    csv = pd.DataFrame({"participant_id":sub_ids}).merge(csv)
    # 分类的任务
    classifies = ["gender"]
    # 回归的任务
    regressions = ["age"]
    # 分类模型
    classify_models = [SVC(),SVC(C=100),SVC(kernel='linear'),SVC(kernel='linear',C=100)]
    # 回归模型
    regress_models = [SVR(),SVR(C=100),SVR(kernel='linear'),SVR(kernel='linear',C=100)]
    kfold = 3
    # 多少个roi
    rois = 200

5. run

修改script/run.py

from fmriprep_job import run_fmri_prep
from fmriprep_pprocess import  run as pp_run
from roi2ts import run as roi_ts_run
from fast_fc_ml import run as ml_run


if __name__ =='__main__':
    run_fmri_prep() # fmriprep
    pp_run() # fmriprep post process
    roi_ts_run() # get roi time series
    ml_run() # machine learning

然后执行

python run.py

6. To Do

  • 质量控制
Owner
Alien
A student
Alien
PyPOTS - A Python Toolbox for Data Mining on Partially-Observed Time Series

A python toolbox/library for data mining on partially-observed time series, supporting tasks of forecasting/imputation/classification/clustering on incomplete multivariate time series with missing va

Wenjie Du 179 Dec 31, 2022
Ml based project which uses regression technique to predict the price.

Price-Predictor Ml based project which uses regression technique to predict the price. I have used various regression models and finds the model with

Garvit Verma 1 Jul 09, 2022
Reproducibility and Replicability of Web Measurement Studies

Reproducibility and Replicability of Web Measurement Studies This repository holds additional material to the paper "Reproducibility and Replicability

6 Dec 31, 2022
This project used bitcoin, S&P500, and gold to construct an investment portfolio that aimed to minimize risk by minimizing variance.

minvar_invest_portfolio This project used bitcoin, S&P500, and gold to construct an investment portfolio that aimed to minimize risk by minimizing var

1 Jan 06, 2022
The easy way to combine mlflow, hydra and optuna into one machine learning pipeline.

mlflow_hydra_optuna_the_easy_way The easy way to combine mlflow, hydra and optuna into one machine learning pipeline. Objective TODO Usage 1. build do

shibuiwilliam 9 Sep 09, 2022
ml4ir: Machine Learning for Information Retrieval

ml4ir: Machine Learning for Information Retrieval | changelog Quickstart → ml4ir Read the Docs | ml4ir pypi | python ReadMe ml4ir is an open source li

Salesforce 77 Jan 06, 2023
It is a forest of random projection trees

rpforest rpforest is a Python library for approximate nearest neighbours search: finding points in a high-dimensional space that are close to a given

Lyst 211 Dec 29, 2022
An AutoML survey focusing on practical systems.

This project is a community effort in constructing and maintaining an up-to-date beginner-friendly introduction to AutoML, focusing on practical systems. AutoML is a big field, and continues to grow

AutoGOAL 16 Aug 14, 2022
Educational python for Neural Networks, written in pure Python/NumPy.

Educational python for Neural Networks, written in pure Python/NumPy.

127 Oct 27, 2022
Time series forecasting with PyTorch

Our article on Towards Data Science introduces the package and provides background information. Pytorch Forecasting aims to ease state-of-the-art time

Jan Beitner 2.5k Jan 02, 2023
UpliftML: A Python Package for Scalable Uplift Modeling

UpliftML is a Python package for scalable unconstrained and constrained uplift modeling from experimental data. To accommodate working with big data, the package uses PySpark and H2O models as base l

Booking.com 254 Dec 31, 2022
Built on python (Mathematical straight fit line coordinates error predictor machine learning foundational model)

Sum-Square_Error-Business-Analytical-Tool- Built on python (Mathematical straight fit line coordinates error predictor machine learning foundational m

om Podey 1 Dec 03, 2021
MICOM is a Python package for metabolic modeling of microbial communities

Welcome MICOM is a Python package for metabolic modeling of microbial communities currently developed in the Gibbons Lab at the Institute for Systems

57 Dec 21, 2022
30 Days Of Machine Learning Using Pytorch

Objective of the repository is to learn and build machine learning models using Pytorch. 30DaysofML Using Pytorch

Mayur 119 Nov 24, 2022
ZenML 🙏: MLOps framework to create reproducible ML pipelines for production machine learning.

ZenML is an extensible, open-source MLOps framework to create production-ready machine learning pipelines. It has a simple, flexible syntax, is cloud and tool agnostic, and has interfaces/abstraction

ZenML 2.6k Jan 08, 2023
2D fluid simulation implementation of Jos Stam paper on real-time fuild dynamics, including some suggested extensions.

Fluid Simulation Usage Download this repo and store it in your computer. Open a terminal and go to the root directory of this folder. Make sure you ha

Mariana Ávalos Arce 5 Dec 02, 2022
Python based GBDT implementation

Py-boost: a research tool for exploring GBDTs Modern gradient boosting toolkits are very complex and are written in low-level programming languages. A

Sberbank AI Lab 20 Sep 21, 2022
A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning

imbalanced-learn imbalanced-learn is a python package offering a number of re-sampling techniques commonly used in datasets showing strong between-cla

6.2k Jan 01, 2023
Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

Hivemind: decentralized deep learning in PyTorch Hivemind is a PyTorch library to train large neural networks across the Internet. Its intended usage

1.3k Jan 08, 2023