t4_lysozyme packed 2026-08-13
Campaign summary
| Field | Value | Details |
|---|---|---|
| Input file | boltz_input.md | boltz_input.md |
| Proteins | 1 | T4L (164 aa) |
| Co-folded partners | 0 | none |
| Ligands | 1 | BNZ1 (SMILES) |
| Pockets | 0 | none -- every ligand folded without a site constraint |
| Apo structure references | 0 | none -- no apo-vs-holo comparison in this campaign |
| Predictions | 1 | T4L_BNZ1 |
| Predict affinity | yes | pIC50 predicted for every target |
| Ligand chemistry | clean | no stereo/protonation/fragment concerns detected |
| Boltz predict runtime | 3m 6s | single run invocation |
| Accelerator | gpu | gpu = Metal/CUDA backend used; cpu = no GPU available |
| Workers | 2 | parallel data-loading workers (Boltz's own default is 2) |
| MPS watermark | 1.0 | PYTORCH_MPS_HIGH_WATERMARK_RATIO cap -- lower avoids swap on Apple unified memory |
| Max parallel samples | 1 | Boltz's own --max_parallel_samples |
pIC50 vs confidence score
Click a point to open that target, in the panel below the Targets table.
pIC50 vs binder probability
Click a point to open that target, in the panel below the Targets table.
Ranked predicted pIC50
Click a point to open that target, in the panel below the Targets table.
Ranked confidence
Click a point to open that target, in the panel below the Targets table.
Summary table
| Identity | Affinity | Confidence | Interactions | Structure | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Protein | Ligand | Summary | Binder | pIC50 | Score | pTM | ipTM | Lig | pLDDT | Phob | CIF |
| T4L | BNZ1 | 0.55 | 8.89 ± 0.37 | 0.98 | 0.99 | 0.97 | 0.97 | 0.98 | 6 | CIF | |
Predictions
One row per prediction. Click one to see its pose and interactions, in the panel below.
| Run | Prediction | Protein | Ligand | Class | Confidence | pIC50 | Interactions | Flags |
|---|
Overall structure
Interaction diagram
Detected interactions
Metrics
Sequence
Pockets
No named pockets in this campaign -- every ligand was placed without a site constraint.
| Protein | Ligands | Targets | Contacts | |
|---|---|---|---|---|
| Unconstrained | T4L | BNZ1 | 1 | none -- ligand placed freely |
Where the ligands landed
Ligand preparation
No stereocentre, protonation-state, or disconnected-fragment concerns detected.
Ligand structures
Download PDF · Download SMILES
Scaffolds: Bemis-Murcko, exact match first, then Tanimoto-clustered (Morgan r=2, 2048-bit, threshold 0.60) whole-group MCS as a verified fallback. Minimum highlighted substructure size: 8 heavy atoms. Stereocentre/ionizable-group highlighting from this campaign's own ligand-preparation check (see above).
Interaction counts by type
Click a point to open that target, in the panel below the Targets table.
SSE motif shifts (apo vs holo)
| Identity | Shift | Backbone | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Family | Target | Ligand | Motif | Kind | Source | N res | RMSD (A) | Centroid delta (A) | Flagged phi/psi |
| T4L | T4L_BNZ1 | BNZ1 | Phage_lysozyme | loop | pfam | 140 | 0.31 | 0.00 | 0 |
Family coverage and SSE shifts
| Family | Status | Detail |
|---|---|---|
| T4L | OK | 1 motif row(s) across 1 target(s), annotator=pfam |
Overall shift statistics
- 1 target(s), 1 motif(s) compared
- Mean Ca RMSD: 0.31 A (median 0.31 A) — largest shift: 0.31 A at T4L_BNZ1 / Phage_lysozyme
- Mean centroid shift: 0.00 A
- Flagged phi/psi outlier residues: 0
- Kinase state changes detected: 0 DFG, 0 alphaC
Per-motif Ca RMSD
Loops
Transmembrane
Motif x target RMSD
Residue interaction fingerprints
Which residues each ligand touches, per protein. One scale for all of them, so a strong contact looks the same in every plot.
T4L
Landlord narration
1 of 1 target summaries written on-device by the Apple Neural Engine; 0 rendered from the template. Every number here is checked against the figures the analysis computed; a summary stating one it was not given was replaced by the template.
The T4 lysozyme prediction campaign tested the ability of computational methods to predict the experimental structure of the T4 lysozyme-BNZ1 complex.
| Targets | 1 predicted, 1 with a ligand |
|---|---|
| Receptors | T4L |
| Ligands | BNZ1 |
| Verdicts | 1 proceed |
| Confidence | 1 well determined |
| Flagged | 0 of 1 |
| Pose validated | no experimental structure to compare against |
Key findings
- Of 1 targets, 1 are marked proceed, 0 caution and 0 discard.
- 1 of 1 targets are well determined; 0 are not.
Highest predicted potency
- BNZ1 on T4L_BNZ1, predicted pIC50 8.89
Caveats
The prediction of the experimental structure of T4L_BNZ1 is not reproduced by the computational prediction.
Per target
| Target | Verdict | Summary | Caveat | Written by |
|---|---|---|---|---|
T4L_BNZ1 | proceed | T4L_BNZ1 is well determined, with high confidence scores for all the computational methods used to predict its structure. BNZ1 is not specified as a ligand class, and there is no interaction analysis available to evaluate its binding interactions with T4L. | The prediction of the experimental structure of T4L_BNZ1 is not reproduced by the computational prediction. | model |