5HT2A_GQ packed 2026-08-13
Campaign summary
| Field | Value | Details |
|---|---|---|
| Input file | boltz_input.md | boltz_input.md |
| Proteins | 2 | HTR2A (471 aa); HTRAP (471 aa) |
| Co-folded partners | 3 | GNAI1 (protein, 354 aa); GNB1 (protein, 340 aa); GNG2 (protein, 71 aa) |
| Ligands | 1 | 8NU (SMILES) |
| Pockets | 0 | none -- every ligand folded without a site constraint |
| Apo structure references | 1 | HTRAP |
| Predictions | 2 | HTR2A_8NU, HTRAP |
| Predict affinity | yes | pIC50 predicted for every target |
| Ligand chemistry | clean | no stereo/protonation/fragment concerns detected |
| Boltz predict runtime | 1h 43m 52s | across 2 run invocations |
| 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
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 | HTR2A | 8NU | 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 | Helix geometry | Boundary | Backbone | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Family | Target | Ligand | Motif | Kind | Source | N res | RMSD (A) | Centroid delta (A) | Axis rot (deg) | Kink apo (deg) | Kink holo (deg) | Kink delta (deg) | Start delta | End delta | Flagged phi/psi |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | H8 | helix | gpcr | 10 | 0.85 | 0.76 | 3.82 | 18.98 | 23.78 | 4.80 | 142.00 | 134.00 | 0 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | TM1 | helix | gpcr | 25 | 1.09 | 0.97 | 1.36 | 10.92 | 6.30 | -4.62 | N/A | N/A | 2 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | TM2 | helix | gpcr | 31 | 0.84 | 0.56 | 1.49 | 19.22 | 21.79 | 2.57 | N/A | N/A | 1 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | TM3 | helix | gpcr | 36 | 0.61 | 0.17 | 0.60 | 7.36 | 11.03 | 3.67 | 66.00 | 77.00 | 0 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | TM4 | helix | gpcr | 30 | 0.86 | 0.44 | 0.82 | 24.62 | 27.32 | 2.70 | 82.00 | 80.00 | 0 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | TM5 | helix | gpcr | 31 | 1.00 | 0.87 | 1.10 | 9.07 | 9.40 | 0.33 | 85.00 | 86.00 | 3 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | TM6 | helix | gpcr | 35 | 0.74 | 0.68 | 0.06 | 29.00 | 29.19 | 0.18 | 124.00 | 140.00 | 1 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | TM7 | helix | gpcr | 30 | 0.69 | 0.21 | 1.35 | 29.08 | 26.93 | -2.15 | 123.00 | 138.00 | 4 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | ECL1 | loop | gpcr | 4 | 1.00 | 0.94 | N/A | N/A | N/A | N/A | N/A | N/A | 2 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | ECL2 | loop | gpcr | 3 | 0.96 | 0.85 | N/A | N/A | N/A | N/A | 79.00 | 48.00 | 0 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | ICL1 | loop | gpcr | 4 | 0.92 | 0.89 | N/A | N/A | N/A | N/A | N/A | N/A | 2 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | ICL2 | loop | gpcr | 9 | 2.50 | 1.38 | N/A | N/A | N/A | N/A | 82.00 | 80.00 | 4 |
| HTR2A_GNAI1+GNB1+GNG2 | HTR2A_GNAI1+GNB1+GNG2_8NU | 8NU | ICL3 | loop | gpcr | 1 | 1.33 | 1.33 | N/A | N/A | N/A | N/A | N/A | N/A | 0 |
Family coverage and SSE shifts
| Family | Status | Detail |
|---|---|---|
| HTR2A_GNAI1+GNB1+GNG2 | OK | 13 motif row(s) across 1 target(s), annotator=gpcr |
| HTRAP_GNAI1+GNB1+GNG2 | No apo structure configured | No 'Apo structure:' configured for this family |
Overall shift statistics
- 1 target(s), 13 motif(s) compared
- Mean Ca RMSD: 1.03 A (median 0.92 A) — largest shift: 2.50 A at HTR2A_GNAI1+GNB1+GNG2_8NU / ICL2
- Mean centroid shift: 0.77 A
- Flagged phi/psi outlier residues: 19
- Kinase state changes detected: 0 DFG, 0 alphaC
Per-motif Ca RMSD
Loops
Transmembrane
Family x ligand selectivity
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.
HTR2A_GNAI1+GNB1+GNG2
The reports as files
The same panels as BoltzMaker wrote them, if you want the whole page in one file.
Landlord narration
2 of 2 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 5HT2A_GQ campaign tested the predicted structures of two receptors, HTR2A and HTRAP, using the ligand 8NU. One of the two targets, HTR2A_8NU, was deemed to be well-determined with a high binder probability, and was marked proceed. The other, HTRAP, was deemed to be moderately determined, and was marked caution.
| Targets | 2 predicted, 1 with a ligand |
|---|---|
| Receptors | HTR2A, HTRAP |
| Ligands | 8NU |
| Verdicts | 1 proceed, 1 caution |
| Confidence | 1 well determined, 1 moderately determined |
| Flagged | 1 of 2 |
| Pose validated | no experimental structure to compare against |
Key findings
- Of 2 targets, 1 are marked proceed, 1 caution and 0 discard.
- 1 of 2 targets are well determined; 1 are not.
- 1 of 2 targets carry at least one flag.
Highest predicted potency
- 8NU on HTR2A_GNAI1+GNB1+GNG2_8NU, predicted pIC50 12.73
Caveats
The predicted structures of the two targets were not validated against experimental structures, limiting the confidence in the accuracy of the model.
Per target
| Target | Verdict | Summary | Caveat | Written by |
|---|---|---|---|---|
HTR2A_8NU | proceed | The predicted structure of the HTR2A_GNAI1+GNB1+GNG2_8NU target is well determined, with high confidence scores for complex PLDDT, IPTM, and PTM. This indicates that the structure is reliable and can be trusted for further analysis. The ligand 8NU has a binder probability of 0.994 and was ranked as the top predicted ligand by potency. However, the interaction analysis for 8NU was not run, so there is uncertainty about its actual binding properties. | The predicted structure was not validated against an experimental structure, which is a significant caveat as it limits the confidence in the accuracy of the model. | model |
HTRAP | caution | The structure is moderately determined, meaning the data is consistent with a 3D model, but the confidence level is not extremely high. This suggests that while the model is likely correct, there is still some uncertainty. | Overall confidence is below the well-determined threshold, the ligand is poorly placed relative to the receptor, and interaction analysis did not complete for this target. | model |