conda conflicts

[wensm77]

Hi, nice work! We encountered a problem using your project.

1. I'm having a lot of conflicts using conda env create -f environment.yaml.
2. Do I have to download uniref100 to run tests on my own data?

[tyang816]

1. Can you please provide more information about the conflicts?
2. Yes, if you want to use the amino acid retrieval mode, you should download the uniref100 and search the MSA, but the foldseek retrieval mode only needs .pdb file.

[wensm77]

Hi!
Now i solve conda problem maybe.
But i got another problem:
This script took me a long time and I didn't get any results

# step 1: search homology sequences
# your protein name, eg. fluorescent_protein
protein_dir=<your_protein_dir_name>
# your protein path, eg. data/fluorescent_protein/aa_seq/GFP.fasta
query_protein_name=<your_protein_name>
protein_path=data/$protein_dir/aa_seq/$query_protein_name.fasta
# your unipror dataset path
database=<your_path>/uniref100.fasta
evcouplings \
    -P output/$protein_dir/$query_protein_name \
    -p $query_protein_name \
    -s $protein_path \
    -d $database \
    -b "0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9" \
    -n 5 src/single_config_monomer.txt

Does this script just take a long time to run?

[tyang816]

Yes, it will take a long time to run, maybe a few hours, sometimes half a day if the query protein is very long (exceeds 3000 residues).

This is an example of the MSA result, do you get these files?

[wensm77]

I just get these and script is running:

[tyang816]

Great! Wait until it is done, and run select mas script. We are happy to hear from you if there is any good news in wet-lab experiments.

[wensm77]

For the output of the model, the higher the better? The part greater than 0 is a beneficial mutation.

[tyang816]

The higher the better, and it does not necessarily have to be greater than 0. Just choose according to the ranking.