What dose 'S' key mean in score_only result

[yipukangda]

Hi,

I want to predict the effect of a single point mutation in fasta file, after run MPNN with score_only mode both with raw fasta and mutated fasta, then got processed_pdb.npz file, there are three array in it, score, global_score, S. What dose 'S', which is the same dimension as protein length ,mean() and which score should I use to compare with to check if mutation if better than raw sequence.

Thanks

here is the code I used

python ~/github_repos/ProteinMPNN/protein_mpnn_run.py \
        --use_soluble_mode \
        --path_to_fasta $path_to_fasta \
        --pdb_path $path_to_PDB \
        --pdb_path_chains "$chains_to_design" \
        --out_folder $output_dir \
        --num_seq_per_target 5 \
        --sampling_temp "0.1" \
        --score_only 1 \
        --seed 13 \
        --batch_size 1