search

RosettaCommons / RFDesign

Protein hallucination and inpainting with RoseTTAFold
Other
234 stars 67 forks source link

Unnecessary residue change when loop inpainting. #10

Open YaoYinYing opened 2 years ago

YaoYinYing commented 2 years ago

Hi!

I tried to rebuild a loop of my protein of interest using the following:

python /repo/RFDesign/inpainting/inpaint.py --pdb ../my.pdb --contigs A1-338,2-3,A343-585 --out RF_inpaint/338-343_pilot --num_designs 10

python /repo/RFDesign/inpainting/inpaint.py --pdb ../my.pdb --contigs A1-336,3-5,A344-585 --out RF_inpaint/336-344_pilot --num_designs 10

and the multiple sequence alignment shows one extra residue mutation in the fixed region of 5 decoys. Is that a bug? Does this extra mutation make sense?

I saw these mutations far away from my target loop in structure.

jueseph commented 2 years ago

I don't quite remember if we've seen this. If you send me example inputs and outputs I might be able to look into it further.

Also, just a tip -- inpainting is deterministic: a given set of inputs always gives the same outputs. So if you have a length range of 3-5, you don't need to generate 10 designs. There are only 3 possible unique outputs -- one for length 3, 4, and 5 of the masked region.

On Thu, Jul 28, 2022 at 5:17 PM Yinying Yao @.***> wrote:

Hi!

I tried to rebuild a loop of my protein of interest using the following:

python /repo/RFDesign/inpainting/inpaint.py --pdb ../my.pdb --contigs A1-338,2-3,A343-585 --out RF_inpaint/338-343_pilot --num_designs 10

python /repo/RFDesign/inpainting/inpaint.py --pdb ../my.pdb --contigs A1-336,3-5,A344-585 --out RF_inpaint/336-344_pilot --num_designs 10

and the multiple sequence alignment shows one extra residue mutation in the fixed region of 5 decoys. Is that a bug? Does this extra mutation make sense?

I saw these mutations far away from my target loop in structure.

— Reply to this email directly, view it on GitHub https://github.com/RosettaCommons/RFDesign/issues/10, or unsubscribe https://github.com/notifications/unsubscribe-auth/AABCU566VHVX6U7HW4DP54TVWMPKXANCNFSM547BCY2Q . You are receiving this because you are subscribed to this thread.Message ID: @.***>

YaoYinYing commented 2 years ago

I don't quite remember if we've seen this. If you send me example inputs and outputs I might be able to look into it further.

Thanks for your quick reply! Here are the input and output in this run. RF_inpaint.zip

There are only 3 possible unique outputs -- one for length 3, 4, and 5 of the masked region

Yes i was taking trials to see if RF design could give me more choices