CENTER-TBI six-months GOSe-Outcome Imputation

This repository contains the entire source code to reproduce the imputation for the six-months GOSe in CENTER-TBI.

Prerequisites

Data Access

To reproduce the analysis, access to the CENTER-TBI 'Neurobot' database at https://center-tbi.incf.org and a personal access toke to the curl API is required. For information on how to get dat access, see https://www.center-tbi.eu/data.

Software dependencies

The workflow assumes a linux command line. To facilitate reproducibility, a docker container container with all software dependencies (R packages etc.) is provided here. The workflow itself is automated using snakemake 5.2.1.

To fully leverage the container and snakemake workflow, the following software dependencies must be available:

• python 3.5.1 (higher versions might work as well)
• snakemake version 5.2.1 (higher versions will work as well)
• singularity 2.6.0 (higher versions might work as well)

How-To

The download script requires the neurobot user name and the personal API key to be stored in the environment variables NEUROBOT_USR NEUROBOT_API, respectively, i.e.

export NEUROBOT_USR=[my-neurobot-username]
export NEUROBOT_API=[my-neurobot-api-key]

Execute Workflow on Desktop

The workflow can be executed on a potent desktop machine although a cluster execution is recommended (cf. blow).

./singularity manuscript_v1_1
./singularity impute_msm_v1_1

All output is written to output/. Depending on the number of cores and available RAM, the cross-validated model comparison may take several days (3+) to complete.

Execute Workflow on Cluster

Cluster execution requires slightly more configuration and assumes existence of a slurm cluster. Simply modify the cluster.json accordingly and execute

./singularity_slurm manuscript_v1_1
./singularity_slurm impute_msm_v1_1