Difference between revisions of "AlphaFold"

From UFRC
Jump to navigation Jump to search
 
(3 intermediate revisions by 2 users not shown)
Line 18: Line 18:
 
{{App_Description|app={{#var:app}}|url={{#var:url}}|name={{#var:app}}}}|}}
 
{{App_Description|app={{#var:app}}|url={{#var:url}}|name={{#var:app}}}}|}}
  
This package provides an implementation of the inference pipeline of AlphaFold v2.0. This is a completely new model that was entered in CASP14 and published in Nature. For simplicity, we refer to this model as AlphaFold throughout the rest of this document.
+
This package provides an implementation of the inference pipeline of AlphaFold v2.3. This is a completely new model that was entered in CASP14 and published in Nature. For simplicity, we refer to this model as AlphaFold throughout the rest of this document.
  
 
<!--Modules-->
 
<!--Modules-->
 
==Environment Modules==
 
==Environment Modules==
 
Run <code>module spider {{#var:app}}</code> to find out what environment modules are available for this application.
 
Run <code>module spider {{#var:app}}</code> to find out what environment modules are available for this application.
==System Variables==
 
* HPC_{{uc:{{#var:app}}}}_DIR - installation directory
 
* HPC_{{uc:{{#var:app}}}}_BIN - executable directory
 
  
 
<!--Configuration-->
 
<!--Configuration-->
Line 36: Line 33:
 
Note that Alphafold has large memory requirements and some of its stages use 4 or 8 CPUs in addition to a GPU. An example job script for a run with the test data included with the software is shown below.
 
Note that Alphafold has large memory requirements and some of its stages use 4 or 8 CPUs in addition to a GPU. An example job script for a run with the test data included with the software is shown below.
 
<div class="mw-collapsible mw-collapsed" style="width:70%; padding: 5px; border: 1px solid gray;">
 
<div class="mw-collapsible mw-collapsed" style="width:70%; padding: 5px; border: 1px solid gray;">
''Expand this section to view sample for version 2.1.2.''
+
''Expand this section to view sample script for version 2.1.2.''
 
<div class="mw-collapsible-content" style="padding: 5px;">
 
<div class="mw-collapsible-content" style="padding: 5px;">
 
<pre>
 
<pre>
Line 68: Line 65:
 
</div>
 
</div>
 
<div class="mw-collapsible mw-collapsed" style="width:70%; padding: 5px; border: 1px solid gray;">
 
<div class="mw-collapsible mw-collapsed" style="width:70%; padding: 5px; border: 1px solid gray;">
''Expand this section to view sample script for version 2.0.0.''
+
''Expand this section to view sample script for version 2.3.1.''
 
<div class="mw-collapsible-content" style="padding: 5px;">
 
<div class="mw-collapsible-content" style="padding: 5px;">
 
<pre>
 
<pre>
Line 83: Line 80:
 
module load alphafold
 
module load alphafold
  
run_alphafold.sh -d $HPC_ALPHAFOLD_REF \
+
alphafold_full_db.sh --fasta_paths=${HPC_ALPHAFOLD_REF}/test.fasta --output_dir=~/scratch --max_template_date=2020-05-14 --use_gpu_relax=1
                -o test/ -m model_1 \
 
                -f /apps/alphafold/2.0.0/alphafold/example/query.fasta \
 
                -t 2020-05-14
 
 
date
 
date
 
</pre>
 
</pre>
Line 99: Line 93:
 
{{#if: {{#var: policy}}|==Usage Example==
 
{{#if: {{#var: policy}}|==Usage Example==
  
To simplify the usage use the 'run_alphafold.sh' script. Simple run example:
+
To simplify the usage use the 'alphafold_full_db.sh' script. Simple run example:
  
  run_alphafold.sh -o test/ -m model_1 -f query.fasta -t 2020-05-14
+
  alphafold_full_db.sh --fasta_paths=${HPC_ALPHAFOLD_REF}/test.fasta --output_dir=~/scratch --max_template_date=2020-05-14 --use_gpu_relax=1
  
By default run_alphafold.sh will use the 2.2 TB of pre-downloaded reference data in $HPC_ALPHAFOLD_REF.
+
From version 2.3, the AlphaFold documentation recommends running as Docker container.  However, Docker is not compatible with the HPC.  AlphaFold has been installed as an apptainer container and
 +
the alphafold_full_db.sh wrapper script has been created to mimic the behavior of docker/run_docker.py as referenced in the AlphaFold documentation.  alphafold_full_db,sh will specify the database location options  required by alphafold. 
 +
 
 +
To specify these options manually, use run_alphafold.sh instead.   
 +
 
 +
If using the --model_preset=multimer option, use the alphafold_multimer_db.sh launch script instead.  Example:
 +
 
 +
alphafold_multimer_db.sh  --model_preset=multimer --fasta_paths=${HPC_ALPHAFOLD_REF}/test.fasta --output_dir=~/scratch --max_template_date=2020-05-14 --use_gpu_relax=1
  
To access all options use the run_alphafold.py script.
 
 
|}}
 
|}}
 
<!--Performance-->
 
<!--Performance-->
Line 119: Line 119:
 
{{#if: {{#var: citation}}|==Citation==
 
{{#if: {{#var: citation}}|==Citation==
 
If you publish research that uses {{#var:app}} you have to cite it as follows:
 
If you publish research that uses {{#var:app}} you have to cite it as follows:
 
+
<div class="mw-collapsible mw-collapsed" style="width:70%; padding: 5px; border: 1px solid gray;">
 +
''Expand this section to view citation instructions.''
 +
<div class="mw-collapsible-content" style="padding: 5px;">
 
  @Article{AlphaFold2021,
 
  @Article{AlphaFold2021,
 
   author  = Jumper, John and Evans, Richard and Pritzel, Alexander and Green, Tim and Figurnov, Michael and Ronneberger, Olaf  
 
   author  = Jumper, John and Evans, Richard and Pritzel, Alexander and Green, Tim and Figurnov, Michael and Ronneberger, Olaf  
Line 134: Line 136:
  
 
  https://www.nature.com/articles/s41586-021-03819-2
 
  https://www.nature.com/articles/s41586-021-03819-2
 
+
</div>
 
+
</div>
  
 
<!--Installation-->
 
<!--Installation-->

Latest revision as of 15:38, 2 February 2024

Description

alphafold website  

This package provides an implementation of the inference pipeline of AlphaFold v2.3. This is a completely new model that was entered in CASP14 and published in Nature. For simplicity, we refer to this model as AlphaFold throughout the rest of this document.

Environment Modules

Run module spider alphafold to find out what environment modules are available for this application.


Additional Information

Note that Alphafold has large memory requirements and some of its stages use 4 or 8 CPUs in addition to a GPU. An example job script for a run with the test data included with the software is shown below.

Expand this section to view sample script for version 2.1.2.

#!/bin/bash
#SBATCH --partition=gpu
#SBATCH --constraint=ai
#SBATCH --nodes=1
#SBATCH --ntasks=8
#SBATCH --gpus=1
#SBATCH --mem=48gb
#SBATCH --time=12:00:00
date;hostname;pwd

run_alphafold.py \
    --data_dir "${HPC_ALPHAFOLD_REF}" \
    --output_dir $(pwd) \
    --fasta_paths query.fasta \
    --uniref90_database_path=${HPC_ALPHAFOLD_REF}/uniref90/uniref90.fasta \
    --mgnify_database_path=${HPC_ALPHAFOLD_REF}/mgnify/mgy_clusters_2018_12.fa \
    --template_mmcif_dir=${HPC_ALPHAFOLD_REF}/pdb_mmcif/mmcif_files \
    --max_template_date=2020-05-14 \
    --obsolete_pdbs_path=${HPC_ALPHAFOLD_REF}/pdb_mmcif/obsolete.dat \
    --use_gpu_relax=1 \
    --bfd_database_path=${HPC_ALPHAFOLD_REF}/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt \
    --uniclust30_database_path=${HPC_ALPHAFOLD_REF}/uniclust30/uniclust30_2018_08/uniclust30_2018_08 \
    --pdb70_database_path=${HPC_ALPHAFOLD_REF}/pdb70/pdb70

date

Expand this section to view sample script for version 2.3.1.

#!/bin/bash
#SBATCH --partition=gpu
#SBATCH --constraint=a100
#SBATCH --nodes=1
#SBATCH --ntasks=8
#SBATCH --gpus=1
#SBATCH --mem=300gb
#SBATCH --time=96:00:00
date;hostname;pwd

module load alphafold

alphafold_full_db.sh  --fasta_paths=${HPC_ALPHAFOLD_REF}/test.fasta --output_dir=~/scratch --max_template_date=2020-05-14 --use_gpu_relax=1
date

Usage Example

To simplify the usage use the 'alphafold_full_db.sh' script. Simple run example:

alphafold_full_db.sh  --fasta_paths=${HPC_ALPHAFOLD_REF}/test.fasta --output_dir=~/scratch --max_template_date=2020-05-14 --use_gpu_relax=1

From version 2.3, the AlphaFold documentation recommends running as Docker container. However, Docker is not compatible with the HPC. AlphaFold has been installed as an apptainer container and the alphafold_full_db.sh wrapper script has been created to mimic the behavior of docker/run_docker.py as referenced in the AlphaFold documentation. alphafold_full_db,sh will specify the database location options required by alphafold.

To specify these options manually, use run_alphafold.sh instead.

If using the --model_preset=multimer option, use the alphafold_multimer_db.sh launch script instead. Example:

alphafold_multimer_db.sh  --model_preset=multimer --fasta_paths=${HPC_ALPHAFOLD_REF}/test.fasta --output_dir=~/scratch --max_template_date=2020-05-14 --use_gpu_relax=1


Citation

If you publish research that uses alphafold you have to cite it as follows:

Expand this section to view citation instructions.

@Article{AlphaFold2021,
 author  = Jumper, John and Evans, Richard and Pritzel, Alexander and Green, Tim and Figurnov, Michael and Ronneberger, Olaf 
and Tunyasuvunakool, Kathryn and Bates, Russ and {\v{Z{\'\i}dek, Augustin and Potapenko, Anna and Bridgland, Alex and Meyer, 
Clemens and Kohl, Simon A A and Ballard, Andrew J and Cowie, Andrew and Romera-Paredes, Bernardino and Nikolov, Stanislav and 
Jain, Rishub and Adler, Jonas and Back, Trevor and Petersen, Stig and Reiman, David and Clancy, Ellen and Zielinski, Michal and 
Steinegger, Martin and Pacholska, Michalina and Berghammer, Tamas and Bodenstein, Sebastian and Silver, David and Vinyals, Oriol 
and Senior, Andrew W and Kavukcuoglu, Koray and Kohli, Pushmeet and Hassabis, Demis},
  journal = {Nature},
  title   = {Highly accurate protein structure prediction with {AlphaFold}},
  year    = {2021},
  doi     = {10.1038/s41586-021-03819-2},
  note    = {(Accelerated article preview)}, 
https://www.nature.com/articles/s41586-021-03819-2