#!/bin/bash

# Manually specify values used in the config
main_task="preprocess"
data_task_type="cluster"
timestamp=$(date "+%Y-%m-%d_%H-%M-%S")

run_dir="/vast/projects/pranam/lab/sophie/DPACMAN/logs/${main_task}/${data_task_type}/runs/${timestamp}"
mkdir -p "$run_dir"

nohup python -u -m scripts.preprocess \
    hydra.run.dir="${run_dir}" \
    data_task=${data_task_type}/remap \
    data_task.cluster_dna_full="false" \
    data_task.cluster_dna_peaks="false" \
    data_task.cluster_protein="true" \
    > "${run_dir}/run.log" 2>&1 &

echo $! > "${run_dir}/pid.txt"