From ScientificComputing
Jump to: navigation, search

< Examples

AlphaFold2 predicts a protein's 3D folding structure by its amino acid sequence with the accuracy that is competitive with experimental results. This AI-powered structure prediction of AlphaFold2 has been recognized as the scientific breakthrough of the year 2021. The AlphaFold package is now installed in the new software stack on Euler.

Create a job script

A job script is a BASH script containing commands to request computing resources, set up the computing environment, run the application and retrieve the results.

Here is a breakdown of a typical job script for Alphafold2.

Request computing resources

AlphaFold2 can run with CPUs only, or with CPUs and GPUs which help speed up the computation significantly. Here we request 12 CPU cores, in total 120GB of memory, in total 120GB of local scratch space and one GPU.


#SBATCH -n 12                                                    # Number of CPUs
#SBATCH --time=24:00:00                                          # Runtime
#SBATCH --mem-per-cpu=10000                                      # CPU memory per CPU core
#SBATCH --nodes=1                                                # All CPUs in the same host
#SBATCH -G 1                                                     # Number of GPUs
#SBATCH --gres=gpumem:10240                                      # GPU memory
#SBATCH --tmp=120000                                             # Scratch space per CPU core
#SBATCH -A es_cdss                                               # Shareholder group name
#SBATCH -J alphafold                                             # Job name

For LSF :

#BSUB -n 12                                                    # Number of CPUs
#BSUB -W 24:00                                                 # Runtime
#BSUB -R "rusage[mem=10000, scratch=10000]"                    # CPU memory and scratch space per CPU core
#BSUB -R "rusage[ngpus_excl_p=1] select[gpu_mtotal0>=10240]"   # Number of GPUs and GPU memory 
#BSUB -R "span[hosts=1]"                                       # All CPUs in the same host
#BSUB -J alphafold                                             # Job name

Set up a computing environment for AlphaFold

source /cluster/apps/local/
module load gcc/6.3.0 openmpi/4.0.2 alphafold/2.1.1
source /cluster/apps/nss/alphafold/venv_alphafold/bin/activate

Enable Unified Memory (if needed)

If the input protein sequence is too large for a single GPU memory (approximately larger than 1500aa), enable Unified Memory to bridge the system memory to the GPU memory so that you can oversubscribe the GPU memory of a single GPU.


Define paths

# Define paths to databases, fasta file and output directory

For the output directory, there are two options.

  • Use $SCRATCH (max 2.7TB), $HOME (max. 20GB) or group storage (/cluster/project or /cluster/work), e.g.,
  • Use the local /scratch as the output directory. To do so, request the scratch space with BSUB options, e.g., here requesting 120GB scratch space in total. At the end of the computation, don't forget to copy the result from there.
python /path/ ...
cp ${TMPDIR}/output ${SCRATCH}/protein_name

Start Multi-Process Service on GPU (version >= 2.1.2, only for LSF)

From the version 2.1.2, it is possible to enable running relaxation on GPU with the option --use_gpu_relax=1. This option will try to create multiple contexts on the GPU but, for LSF, the default GPU computing mode is exclusive and does not allow creating multiple contexts. This can be circumvented by starting Multi-Process Service with the command

nvidia-cuda-mps-control -d

For SLURM the default computing mode allows the creation of multiple contexts on GPUs, therefore the use of this option will be redundant.

Call Python run script

python /cluster/apps/nss/alphafold/alphafold-2.1.1/ \
--data_dir=$DATA_DIR \
--output_dir=$OUTPUT_DIR \
--max_template_date="2021-12-06" \
--bfd_database_path=$DATA_DIR/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt \
--uniref90_database_path=$DATA_DIR/uniref90/uniref90.fasta \
--uniclust30_database_path=$DATA_DIR/uniclust30/uniclust30_2018_08/uniclust30_2018_08 \
--mgnify_database_path=$DATA_DIR/mgnify/mgy_clusters_2018_12.fa \
--template_mmcif_dir=$DATA_DIR/pdb_mmcif/mmcif_files \
--obsolete_pdbs_path=$DATA_DIR/pdb_mmcif/obsolete.dat \

Then, define the input fasta file, select the model preset (monomer or multimer) and define the path to structure databases accordingly.

  • For a monomeric protein
--fasta_paths=$FASTA_DIR/ubiquitin.fasta \
--model_preset=monomer \
  • For a multimeric protein
--fasta_paths=$FASTA_DIR/IFGSC_6mer.fasta \
--model_preset=multimer \
--pdb_seqres_database_path=$DATA_DIR/pdb_seqres/pdb_seqres.txt \

Enable relaxation on GPU (version >= 2.1.2)
In this version, it is possible to enable running relaxation on GPU with the option --use_gpu_relax. Please see above how to start MPS to use this option.


Disable Multi-Process Service (version >= 2.1.2, only for LSF)

If MPS is enabled before running AlphaFold, disable MPS with the command

echo quit | nvidia-cuda-mps-control

Submit a job

For SLURM, submit a job with the command

$ sbatch < run_alphafold.sbatch

The screen output will be save in the slurm-JobID.out file, e.g slurm-3435300.out. For LSF, submit a job with the command

$ bsub < run_alphafold.bsub

The screen output is saved in the output file named starting with lsf.o followed by the JobID, e.g., lsf.o195525946. Please see this page for how to read the output file.

From our benchmark, it took around 40 minutes to fold Ubiquitin[76aa] and 2.5 hours to fold T1050[779aa].

Setup script

This setup script creates a job script with estimate computing resources depending on the input protein sequence. To download the setup script:

git clone


./ -f [Fasta file] -w [work directory] --max_template_date yyyy-mm-dd -b [LSF/SLURM]


$ ./ -f ../../fastafiles/IFGSC_6mer.fasta -w $SCRATCH
 Reading /cluster/home/jarunanp/alphafold_run/fastafiles/IFGSC_6mer.fasta
 Protein name:            IFGSC_6mer
 Number of sequences:     6
 Protein type:            multimer
 Number of amino acids:
                   sum: 1246
                   max: 242
 Estimate required resources:
   Run time: 24:00
   Number of CPUs: 12
   Total CPU memory: 120000
   Number of GPUs: 1
   Total GPU memory: 20480
   Total scratch space: 120000
 Output an LSF run script for AlphaFold2: /cluster/scratch/jarunanp/run_alphafold.bsub

For SLURM, submit the script with the command

$ sbatch < run_alphafold.sbatch

For LSF, submit the script with the command

$ bsub < run_alphafold.bsub


Similar plots as generated by the Colabfold jupyter notebook can be created by the alphafold-postprocessing python script. It is available on Euler as a module

module load gcc/6.3.0 alphafold-postprocessing -o plots/ work_directory/

The above command will process pkl files generated by alphafold in the folder work_directory/ and put the resulting plots into a folder plots/.

The postprocessing is integrated in the setup script described above.


The AlphaFold databases are available for all cluster users at /cluster/project/alphafold.

If you wish to download databases separately, you can see the instruction here.


The Ubiquitin fastafile is provided with the AlphaFold setup script. It can be used to test AlphaFold2 on Euler. If the working directory is on $SCRATCH, a successful run would complete in ~40 min (depending on the type of resources allocated by the batch system) and generate the following files :

├── features.pkl
├── msas
│   ├── bfd_uniclust_hits.a3m
│   ├── mgnify_hits.sto
│   ├── pdb_hits.hhr
│   └── uniref90_hits.sto
├── ranked_0.pdb 
├── ranked_1.pdb
├── ranked_2.pdb
├── ranked_3.pdb
├── ranked_4.pdb
├── ranking_debug.json
├── relaxed_model_1_pred_0.pdb
├── relaxed_model_2_pred_0.pdb
├── relaxed_model_3_pred_0.pdb
├── relaxed_model_4_pred_0.pdb
├── relaxed_model_5_pred_0.pdb
├── result_model_1_pred_0.pkl
├── result_model_2_pred_0.pkl
├── result_model_3_pred_0.pkl
├── result_model_4_pred_0.pkl
├── result_model_5_pred_0.pkl
├── timings.json
├── unrelaxed_model_1_pred_0.pdb
├── unrelaxed_model_2_pred_0.pdb
├── unrelaxed_model_3_pred_0.pdb
├── unrelaxed_model_4_pred_0.pdb
└── unrelaxed_model_5_pred_0.pdb

Further readings

< Examples