BARACUS is a BIDS-compliant application that predicts brain age, based on combining data from cortical thickness, cortical surface area, and subcortical information

Web site

• Home page

• Module Name: baracus (see the modules page for more information)
• Executable Name: baracus

Allocate an interactive session and run the program.
Sample session (user input in bold):

[user@biowulf]$ sinteractive
salloc.exe: Pending job allocation 46116226
salloc.exe: job 46116226 queued and waiting for resources
salloc.exe: job 46116226 has been allocated resources
salloc.exe: Granted job allocation 46116226
salloc.exe: Waiting for resource configuration
salloc.exe: Nodes cn3144 are ready for job

[user@cn3144 ~]$ module load baracus

[user@cn3144 ~]$ baracus -h
usage: run_brain_age_bids.py [-h]
                             [--participant_label PARTICIPANT_LABEL [PARTICIPANT_LABEL ...]]
                             [--freesurfer_dir FREESURFER_DIR]
                             [--models {Liem2016__OCI_norm,Liem2016__full_2samp_training} [{Liem2016__OCI_norm,Liem2016__full_2samp_training} ...]]
                             [--skip_missing] --license_key LICENSE_KEY
                             [--n_cpus N_CPUS] [-v]
                             bids_dir out_dir {participant,group}

BARACUS: Brain-Age Regression Analysis and Computation Utility Software. BIDS
mode. You specify a BIDS-formatted freesurfer folder as input. All data is
extracted automatiacally from that folder.

positional arguments:
  bids_dir              The directory with the input dataset formatted
                        according to the BIDS standard.
  out_dir               Results are put into {out_dir}/baracus.
  {participant,group}   Level of the analysis that will be performed.
                        "participant": predicts single subject brain age,
                        "group": collects single subject predictions.

optional arguments:
  -h, --help            show this help message and exit
  --participant_label PARTICIPANT_LABEL [PARTICIPANT_LABEL ...]
                        The label of the participant that should be analyzed.
                        The label corresponds to sub- from
                        the BIDS spec (so it does not include "sub-"). If this
                        parameter is not provided all subjects should be
                        analyzed. Multiple participants can be specified with
                        a space separated list.
  --freesurfer_dir FREESURFER_DIR
                        Folder with FreeSurfer subjects formatted according to
                        BIDS standard. If subject's recon-all folder cannot be
                        found, recon-all will be run. If not specified
                        freesurfer data will be saved to {out_dir}/freesurfer
  --models {Liem2016__OCI_norm,Liem2016__full_2samp_training} [{Liem2016__OCI_norm,Liem2016__full_2samp_training} ...]
  --skip_missing        Flag to skip not segmented subjects
  --license_key LICENSE_KEY
                        FreeSurfer license key - letters and numbers after "*"
                        in the email you received after registration. To
                        register (for free) visit
                        https://surfer.nmr.mgh.harvard.edu/registration.html
  --n_cpus N_CPUS       Number of CPUs/cores available to use.
  -v, --version         show program's version number and exit

[user@cn3144 ~]$ exit
salloc.exe: Relinquishing job allocation 46116226
[user@biowulf ~]$

Create a batch input file (e.g. baracus.sh). For example:

#!/bin/bash
# sbatch --gres=lscratch:100 --mem=3g --cpus-per-task=48 --time=10:00:00 baracus.sh

set -e

function fail {
    echo "FAIL: $@" >&2
    exit 1  # signal failure
}

module load baracus
cp /data/$USER/BARACUS_TEST/ds001.tar.gz /lscratch/$SLURM_JOB_ID/.
cd /lscratch/$SLURM_JOB_ID
tar -xzvf ds001.tar.gz
baracus --participant_label 01 \
        --license_key /usr/local/apps/freesurfer/license.txt \
        --n_cpus $SLURM_CPUS_PER_TASK \
        /lscratch/$SLURM_JOB_ID/ds001 \
        /lscratch/$SLURM_JOB_ID \
        participant
cp -R /lscratch/$SLURM_JOB_ID/baracus /data/$USER/BARACUS_TEST/.
cp -R /lscratch/$SLURM_JOB_ID/freesurfer /data/$USER/BARACUS_TEST/.

Submit this job using the Slurm sbatch command.

sbatch [--gres=lscratch:#] [--cpus-per-task=#] [--mem=#] baracus.sh

Create a swarmfile (e.g. baracus.swarm). For example:

# swarm -f baracus.swarm --gres=lscratch:100 -g 4 -t 48 --time 10:00:00 --module baracus
cp /data/$USER/BARACUS_TEST/ds001.tar.gz /lscratch/$SLURM_JOB_ID/.; \
cd /lscratch/$SLURM_JOB_ID; \
tar -xzvf ds001.tar.gz; \
baracus --participant_label 01 \
        --license_key /usr/local/apps/freesurfer/license.txt \
        --n_cpus $SLURM_CPUS_PER_TASK \
        /lscratch/$SLURM_JOB_ID/ds001 \
        /lscratch/$SLURM_JOB_ID \
        participant; \
mv /lscratch/$SLURM_JOB_ID/baracus /data/$USER/BARACUS_TEST/baracus_01; \
mv /lscratch/$SLURM_JOB_ID/freesurfer /data/$USER/BARACUS_TEST/freesurfer_01
cp /data/$USER/BARACUS_TEST/ds001.tar.gz /lscratch/$SLURM_JOB_ID/.; \
cd /lscratch/$SLURM_JOB_ID; \
tar -xzvf ds001.tar.gz; \
baracus --participant_label 02 \
        --license_key /usr/local/apps/freesurfer/license.txt \
        --n_cpus $SLURM_CPUS_PER_TASK \
        /lscratch/$SLURM_JOB_ID/ds001 \
        /lscratch/$SLURM_JOB_ID \
        participant; \
mv /lscratch/$SLURM_JOB_ID/baracus /data/$USER/BARACUS_TEST/baracus_02; \
mv /lscratch/$SLURM_JOB_ID/freesurfer /data/$USER/BARACUS_TEST/freesurfer_02

Submit this job using the swarm command.

swarm -f baracus.swarm [--gres=lscratch:#] [-g #] [-t #] --module baracus