Error unrecognized argument for --uniref30_database_path

Hi,

I'm attempting to run FastFold on a university computer and encountering an issue with the inference.py script. Despite following the instructions and using the same shell command as provided in the repository to run inference.py, I'm receiving an error indicating an unrecognized argument for --uniref30_database_path.

Here's the error message I receive:

Below is the bash script I'm using for submission:


#!/bin/bash
. 
# SOME SBATCH STUFF ....  
.

module load StdEnv/2020 gcc/9.3.0 openmpi/4.0.3 cuda/11.4 cudnn/8.2.0 kalign/2.03 hmmer/3.2.1 openmm/7.7.0 hh-suite/3.3.0 python/3.8

DOWNLOAD_DIR=/datashare/alphafold
INPUT_DIR=$SCRATCH/fastfold/input
OUTPUT_DIR=${SCRATCH}/fastfold/output

virtualenv --no-download ${SLURM_TMPDIR}/ENV
source ${SLURM_TMPDIR}/ENV/bin/activate
pip install --no-index --upgrade pip
pip install --no-index --requirement ~/fastfold-0.2.0-requirements.txt

python ~/FastFold/inference.py ${SCRATCH}/fastfold/input/rcsb_pdb_1BET.fasta ${DOWNLOAD_DIR}/pdb_mmcif/mmcif_files \
   --output_dir=${OUTPUT_DIR} \
   --gpus 1 \
   --uniref90_database_path ${DOWNLOAD_DIR}/uniref90/uniref90.fasta \
   --mgnify_database_path   ${DOWNLOAD_DIR}/mgnify/mgy_clusters_2022_05.fa \
   --pdb70_database_path    ${DOWNLOAD_DIR}/pdb70/pdb70 \
   --uniref30_database_path ${DOWNLOAD_DIR}/uniref30/UniRef30_2021_03 \
   --bfd_database_path      ${DOWNLOAD_DIR}/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt \
   --jackhmmer_binary_path  ${EBROOTHMMER}/bin/jackhmmer \
   --hhblits_binary_path    ${EBROOTHHMINSUITE}/bin/hhblits \
   --hhsearch_binary_path   ${EBROOTHHMINSUITE}/bin/hhsearch \
   --kalign_binary_path     ${EBROOTKALIGN}/bin/kalign \
   --enable_workflow \
   --inplace

hpcaitech / FastFold

Error unrecognized argument for --uniref30_database_path #187