-
Notifications
You must be signed in to change notification settings - Fork 75
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Evcomplex2 #225
base: develop
Are you sure you want to change the base?
Evcomplex2 #225
Conversation
…nt all ECs used for scoring
…nto feature/avoid_self
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Almost complete review, still missing are:
- evcouplings/couplings/protocol.py
- evcouplings/couplings/pairs.py
All small-ish stuff except for evcouplings/compare/protocol.py - I think most of the additions there regarding the machine learning models do not belong into the comparison stage which should really just compare results to experiments. I think this stuff belongs more into the complex submodule, and maybe means another stage for the complex pipeline is needed?
uniprot_to_embl_table: /n/groups/marks/databases/complexes/idmapping/idmapping_uniprot_embl_2017_02.txt | ||
ena_genome_location_table: /n/groups/marks/databases/complexes/ena/2017_02/cds_pro.txt | ||
structurefree_model_file: /n/groups/marks/users/agreen/dev/EVcouplings/evcouplings/compare/aux/residue_strucfree.saved |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We should have these somewhere publicly accessible
temp_dataframe = id_dataframe.copy() | ||
|
||
id_strings = [_split_annotation_string(x) for x in temp_dataframe.id_1] | ||
temp_dataframe["id_string_1"], temp_dataframe["r_s_1"], temp_dataframe["r_e_1"] = \ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
not a big fan of new lines with backslash - nicer to wrap first part of assignment in (...)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I can't picture what you mean here, sorry, was only using the slash because the assignment doesn't seem to nicely support wrapping with ()
Plan for getting this into develop:
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Here is review of second bit - major comments:
-
Please refactor complex_mean_field() and mean_field() like done for plm-based protocols (See detailed comments above)
-
the _postprocess_inference() method should stay as it is (may need making the pymol creation functions more generic to handle segments as well)
Reminder: check that Issue #252 is resolved |
Conflicts: evcouplings/couplings/protocol.py test/TestComplex.py
This pull request includes all the functions used for calculations in Green & Elhabashy, et al. https://www.biorxiv.org/content/10.1101/791293v1