Comments (8)
Really sorry this error occurred. It seems that msa_mask
feature of one of your proteins is correct and this error has nothing to do with GPU or CPU. Could you let us know how you created the pickles in the create_individual_features.py```? I wonder if it's also related to
mmseqs2``` mode. Thank you.
Yours
Dingquan
from alphapulldown.
I successfully created the pickles by running the following command
export HHLIB=/home/anaconda3/envs/AlphaPulldown
export HMMER=/home/Analysis/alphafold_analysis/hmmer-3.4
create_individual_features.py --fasta_paths=/home/Analysis/alphafold_analysis/output/alphapulldown/baits.fasta --data_dir=/home/Analysis/alphafold_analysis/alphafold_database --output_dir=/home/Analysis/alphafold_analysis/output/alphapulldown/output --skip_existing=False --use_mmseqs2=True --max_template_date=$(date +"%Y-%m-%d") --seq_index=1
However, it stopped at line 191 like the following. I do not know whether it is completed or not.
from alphapulldown.
In addition, I came across this error while running alpha-analysis.sif to calculate the pi score. Is it because I only have one pull-down group? And it assumes more than one pull-down group for pi score calculation?
from alphapulldown.
In addition, I came across this error while running alpha-analysis.sif to calculate the pi score. Is it because I only have one pull-down group? And it assumes more than one pull-down group for pi score calculation?
Hi @herman-einstein ,
According to your screenshot, it should be caused by mounting a wrong directory. You should in this case mount one level above.
Yours
Dingquan
from alphapulldown.
In addition, I came across this error while running alpha-analysis.sif to calculate the pi score. Is it because I only have one pull-down group? And it assumes more than one pull-down group for pi score calculation?
Hi @herman-einstein ,
According to your screenshot, it should be caused by mounting a wrong directory. You should in this case mount one level above.
Yours Dingquan
Hi, @dingquanyu
Thank you for your quick reply,
I tried mounting the directory one level above. However, there is the same issue.
This is the command I ran:
"singularity exec --no-home --bind /home/Desktop/pulldown/pull2:/mnt /media/data/alpha-analysis_jax_0.4.sif run_get_good_pae.sh --output_dir=/mnt --cutoff=10"
from alphapulldown.
In addition, I came across this error while running alpha-analysis.sif to calculate the pi score. Is it because I only have one pull-down group? And it assumes more than one pull-down group for pi score calculation?
Hi @herman-einstein ,
According to your screenshot, it should be caused by mounting a wrong directory. You should in this case mount one level above.
Yours DingquanHi, @dingquanyu
Thank you for your quick reply,
I tried mounting the directory one level above. However, there is the same issue.
This is the command I ran:
"singularity exec --no-home --bind /home/Desktop/pulldown/pull2:/mnt /media/data/alpha-analysis_jax_0.4.sif run_get_good_pae.sh --output_dir=/mnt --cutoff=10"
Hi @herman-einstein ,
Sorry this still persisted. I suspected that this model quality wasn't good enough to pass the cutoff. Could you change the cutoff to 100 and run again?
Yours
Dingquan
from alphapulldown.
In addition, I came across this error while running alpha-analysis.sif to calculate the pi score. Is it because I only have one pull-down group? And it assumes more than one pull-down group for pi score calculation?
Hi @herman-einstein ,
According to your screenshot, it should be caused by mounting a wrong directory. You should in this case mount one level above.
Yours DingquanHi, @dingquanyu
Thank you for your quick reply,
I tried mounting the directory one level above. However, there is the same issue.
This is the command I ran:
"singularity exec --no-home --bind /home/Desktop/pulldown/pull2:/mnt /media/data/alpha-analysis_jax_0.4.sif run_get_good_pae.sh --output_dir=/mnt --cutoff=10"Hi @herman-einstein ,
Sorry this still persisted. I suspected that this model quality wasn't good enough to pass the cutoff. Could you change the cutoff to 100 and run again?
Yours Dingquan
It works!!!! very much appreciate your help!
May I know what the cutoff means in this calculation?
from alphapulldown.
Hi @herman-einstein ,
Glad it worked for you! cutoff is to check if any residues has a PAE value below the specified cutoff in the PAE plot between 2 or more chains. For the details about what PAE means, please refer to AlphaFold Multimer paper. In short, the lower the value, the more strict the selection.
Yours
Dingquan
from alphapulldown.
Related Issues (20)
- Multiple feature directories HOT 2
- Improve resume predictions HOT 1
- GPU seems not working when run_multimer_jobs.py HOT 5
- Runtime of each prediction HOT 1
- Use DEFINE_list for model_names flag HOT 3
- Clean duplicating functions/ redundant code
- 'ranking_confidence' is not in the result.pkl file after the update HOT 10
- create_indvidual_features.py HOT 3
- Merging individual monomer MSAs for multimer prediction HOT 3
- Problem with MSA for Q6DI86 HOT 2
- rename_colab_search_a3m.py does something unintended HOT 4
- output jupyter notebook is empty HOT 2
- Computing MSA takes long time
- jax error when create_notebook.py is run HOT 4
- create_notebook doesn't work on AlphaPulldown 2.0b? HOT 8
- Remove result pickles HOT 1
- question: correct pipeline for mmseqs alignments in alphapulldown?
- Move Databases download to a common installation step for both snakamake and Python CLI modes? HOT 1
- jax installation version issue HOT 1
- use_mmseqs2=True is no longer possible in 2.0.0b4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from alphapulldown.