Skip to content

Adding custom Trajectory rejection thresholds using advanced settings #365

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.

Sign up for GitHub

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

Open
dbeinhauer wants to merge 2 commits into
base: main
Choose a base branch
from
+8 −3
Open

Adding custom Trajectory rejection thresholds using advanced settings #365

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
07baddb
Adding option for custom thresholds for rejecting Trajectories using …
dbeinhauer Apr 15, 2026
ef9b4b6
Adding documentation for custom trajectory rejection thresholds
dbeinhauer Apr 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,11 @@ weights_rg -> Design weight - radius of gyration weight for
use_termini_distance_loss -> Try to minimise distance between N- and C-terminus of binder? Helpful for grafting
weights_termini_loss -> Design weight - N- and C-terminus distance minimisation weight of binder

# Trajectory quality thresholds
trajectory_max_ca_clashes -> Maximum number of CA clashes allowed before discarding trajectory as Clashing (default: 0)
trajectory_min_plddt -> Minimum final pLDDT required to keep trajectory, below this it is marked LowConfidence (default: 0.7)
trajectory_min_contacts -> Minimum number of interface contacts required, below this trajectory is marked LowConfidence (default: 3)

# MPNN settings
mpnn_fix_interface -> whether to fix the interface designed in the starting trajectory
num_seqs -> number of MPNN generated sequences to sample and predict per binder
Expand Down
6 changes: 3 additions & 3 deletions functions/colabdesign_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,14 +184,14 @@ def binder_hallucination(design_name, starting_pdb, chain, target_hotspot_residu
ca_clashes = calculate_clash_score(model_pdb_path, 2.5, only_ca=True)

#if clash_interface > 25 or ca_clashes > 0:
if ca_clashes > 0:
if ca_clashes > advanced_settings.get("trajectory_max_ca_clashes", 0):
af_model.aux["log"]["terminate"] = "Clashing"
update_failures(failure_csv, 'Trajectory_Clashes')
print("Severe clashes detected, skipping analysis and MPNN optimisation")
print("")
else:
# check if low quality prediction
if final_plddt < 0.7:
if final_plddt < advanced_settings.get("trajectory_min_plddt", 0.7):
af_model.aux["log"]["terminate"] = "LowConfidence"
update_failures(failure_csv, 'Trajectory_final_pLDDT')
print("Trajectory starting confidence low, skipping analysis and MPNN optimisation")
Expand All @@ -202,7 +202,7 @@ def binder_hallucination(design_name, starting_pdb, chain, target_hotspot_residu
binder_contacts_n = len(binder_contacts.items())

# if less than 3 contacts then protein is floating above and is not binder
if binder_contacts_n < 3:
if binder_contacts_n < advanced_settings.get("trajectory_min_contacts", 3):
af_model.aux["log"]["terminate"] = "LowConfidence"
update_failures(failure_csv, 'Trajectory_Contacts')
print("Too few contacts at the interface, skipping analysis and MPNN optimisation")
Expand Down
Loading