Skip to content

Added residue replacement to handle protein chemical modifications and NCAAs - #128

Open
gfzhou wants to merge 2 commits into
baker-laboratory:mainfrom
gfzhou:main
Open

Added residue replacement to handle protein chemical modifications and NCAAs#128
gfzhou wants to merge 2 commits into
baker-laboratory:mainfrom
gfzhou:main

Conversation

@gfzhou

@gfzhou gfzhou commented Jun 12, 2024

Copy link
Copy Markdown

No description provided.

@r-krishna r-krishna left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

needs some clarification in the README

Comment thread README.md
residue_index_to_replace: 57
input: examples/residue_replacement/SEP_ideal_trim.sdf
input_type: "sdf"
N_index_atom: 1

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is this 0 indexed or 1 indexed?

Comment thread rf2aa/data/covale.py
C_index_atom = int(residue_replacement[chain].C_index_atom)
residues_to_atomize.append(AtomizedResidue(
chain,
0,

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why is this always 0?

Comment thread README.md

<a id="residue_replacement"></a>
### Predicting Proteins with Chemical Modifications or Non-Canonical Amino Acids
To predict proteins with chemically modified residues or non-canonical amino acids, you can use residue replacement. This involves replacing the chemically modified residue or NCAA with a small molecule file that defines the structure of the modified residue. Here is an example of predicting a phosphorylated protein structure. (from `rf2aa/config/inference/residue_replacement.yaml`)

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

are there any edge cases with running these with protein multimers or cases with small molecules? does order of inputs matter?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants