RosettaCommons / RosettaCommons/RFdiffusion

binder design

Open
#317 8 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.1k
Forks
644
PR merge metrics
No merged PRs in 30d

Description

1.0 binder

1.1 about rosetta ddG

In the binding molecules, rosetta ddG<-40 is used as the screening condition. I want to know how this part is calculated. I can't find the relevant script. Is the output of protein mpnn used as the mutation and the initial Gly skeleton used as the comparison?

1.2 about pae_interaction

In my design work, I only used about 10 skeletons and got many sequences with pae_interaction<10, which confused me

1.2.1 for example out.sc

SCORE: binder_aligned_rmsd pae_binder pae_interaction pae_target plddt_binder plddt_target plddt_total target_aligned_rmsd time description
SCORE: 0.592 3.476 8.182 9.139 85.556 74.229 78.750 1.542 83.551 design_ppi_0_dldesign_0_af2pred
SCORE: 0.930 5.717 13.545 9.519 70.353 68.488 69.232 1.716 7.883 design_ppi_0_dldesign_1_af2pred
SCORE: 0.885 2.977 7.414 8.460 87.404 76.294 80.728 1.496 7.833 design_ppi_0_dldesign_2_af2pred
SCORE: 2.054 7.001 13.005 9.961 66.544 65.600 65.977 2.215 7.828 design_ppi_0_dldesign_3_af2pred
SCORE: 0.780 3.225 7.507 8.800 87.345 76.268 80.564 1.516 82.688 design_ppi_1_dldesign_0_af2pred
SCORE: 1.126 3.107 6.819 7.912 88.812 79.364 83.028 1.721 7.771 design_ppi_1_dldesign_1_af2pred
SCORE: 0.687 3.506 7.869 9.009 85.927 76.209 79.978 1.124 7.590 design_ppi_1_dldesign_2_af2pred
SCORE: 0.715 3.452 7.688 9.015 87.045 76.115 80.354 1.181 7.384 design_ppi_1_dldesign_3_af2pred
SCORE: 0.753 2.880 12.781 10.139 82.801 66.895 72.926 2.832 83.061 design_ppi_2_dldesign_0_af2pred
SCORE: 4.713 6.647 17.966 10.022 67.370 64.381 65.514 7.578 7.448 design_ppi_2_dldesign_1_af2pred
SCORE: 0.585 2.578 8.057 9.152 87.885 74.091 79.321 1.455 7.893 design_ppi_2_dldesign_2_af2pred
SCORE: 5.456 8.717 21.638 9.816 66.661 65.740 66.089 10.151 7.169 design_ppi_2_dldesign_3_af2pred
SCORE: 1.223 3.388 8.150 9.291 88.463 74.946 80.523 2.229 83.386 design_ppi_3_dldesign_0_af2pred
SCORE: 1.084 3.811 8.760 9.382 86.099 73.772 78.858 2.097 8.280 design_ppi_3_dldesign_1_af2pred
SCORE: 1.239 3.116 7.614 8.654 88.546 76.457 81.444 2.109 8.154 design_ppi_3_dldesign_2_af2pred
SCORE: 1.114 4.012 8.458 9.047 85.521 74.985 79.332 1.853 8.049 design_ppi_3_dldesign_3_af2pred
SCORE: 30.849 13.027 17.585 9.168 74.318 72.932 73.446 45.073 75.428 design_ppi_4_dldesign_0_af2pred
SCORE: 32.573 9.324 14.422 8.683 87.638 76.735 80.771 47.214 7.665 design_ppi_4_dldesign_1_af2pred
SCORE: 1.036 3.308 8.186 9.418 86.905 74.156 78.876 1.598 6.808 design_ppi_4_dldesign_2_af2pred
SCORE: 1.055 3.597 8.303 9.421 85.697 73.982 78.319 1.433 7.470 design_ppi_4_dldesign_3_af2pred
SCORE: 7.624 10.777 24.481 9.155 52.892 63.817 59.142 12.690 84.331 design_ppi_5_dldesign_0_af2pred
SCORE: 9.163 11.825 26.501 8.199 51.977 69.317 61.897 19.410 8.484 design_ppi_5_dldesign_1_af2pred
SCORE: 7.530 11.392 24.215 9.933 53.076 61.796 58.064 13.101 8.735 design_ppi_5_dldesign_2_af2pred
SCORE: 2.680 7.861 13.244 9.600 68.653 68.895 68.791 3.466 9.189 design_ppi_5_dldesign_3_af2pred
SCORE: 1.138 4.400 9.203 9.374 81.033 72.488 75.802 1.893 7.801 design_ppi_6_dldesign_0_af2pred
SCORE: 1.178 4.334 9.951 9.740 80.572 70.593 74.463 1.821 7.961 design_ppi_6_dldesign_1_af2pred
SCORE: 1.221 4.154 9.192 9.283 82.260 72.068 76.021 1.859 7.870 design_ppi_6_dldesign_2_af2pred
SCORE: 9.541 13.511 20.715 10.050 63.012 65.187 64.343 14.675 8.523 design_ppi_6_dldesign_3_af2pred
...
SCORE: 1.000 4.023 8.681 9.366 83.065 72.978 77.085 1.877 7.684 design_ppi_9_dldesign_3_af2pred
...

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No script or test is named; start by locating the workflow that produces the reported out.sc scores and the calculations for rosetta ddG and pae_interaction. Document which inputs are compared and how each metric is calculated, using the listed ProteinMPNN, Gly skeleton, and AF2 outputs as context; done means the issue's questions are answered with reproducible references.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
28/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.