BoltzMaker

adrb2_gs packed 2026-08-13

1 Proteins
1 Co-folded partners
2 Ligands
0 Pockets
0 Apo structure references
2 Predictions

Campaign summary

Field Value Details
Input file boltz_input.md boltz_input.md
Proteins12 protein block(s) in 1 group(s): ADRB2 (413 aa); AR2NG (413 aa)
Co-folded partners1GNAS (protein, 394 aa)
Ligands2ISO1 (SMILES); PRO1 (SMILES)
Pockets0none -- every ligand folded without a site constraint
Apo structure references0none -- no apo-vs-holo comparison in this campaign
Predictions2ADRB2_ISO1, AR2NG_PRO1
Predict affinity yes pIC50 predicted for every target
Ligand chemistry 2 of 2 flagged ISO1, PRO1 -- see "Ligand preparation" below
Boltz predict runtime 1h 53m 29s 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

IdentityAffinityConfidenceInteractionsStructure
ProteinPartnerLigandSummaryBinderpIC50ScorepTMipTMLigPPIpLDDTHPhobπCIF
ADRB2GNASISO1 1.0010.14 ± 0.340.790.830.830.990.820.78981CIF
ADRB2PRO1 1.0012.41 ± 0.210.830.850.990.990.000.79371CIF

Predictions

One row per prediction. Click one to see its pose and interactions, in the panel below.

Run Prediction Protein Ligand Pocket Class Confidence pIC50 Interactions Flags

Overall structure

Interaction diagram

Detected interactions

Metrics

Ligand pose

Superposed targets

Sequence

Pockets

No named pockets in this campaign -- every ligand was placed without a site constraint.

PocketProteinLigandsTargetsContacts
UnconstrainedADRB2ISO11none -- ligand placed freely
UnconstrainedAR2NGPRO11none -- ligand placed freely

Where the ligands landed

Ligand preparation

2 of 2 ligand(s) flagged for chemistry review -- these are advisory, not errors; verify the input SMILES reflects what you intended before trusting the results below.

Ligand Chemistry notes
ISO1 undefined stereocentre(s) at atom index 5; ionizable group(s) present (primary/secondary amine, phenol) -- verify the SMILES reflects your intended protonation state
PRO1 undefined stereocentre(s) at atom index 5; ionizable group(s) present (primary/secondary amine) -- verify the SMILES reflects your intended protonation state

Ligand structures

No shared scaffold or substructure detected across the set -- ligands are structurally distinct.

Sundefined stereocentreAcarboxylic acidNprimary/secondary aminePhphenolSO3sulfonic acidsaltsalt/disconnected fragment
ISO1SNPh
ISO1 structure
MW 211 · cLogP 1.1 · TPSA 73
PRO1SN
PRO1 structure
MW 259 · cLogP 2.6 · TPSA 41

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)

IdentityShiftHelix geometryBackbone
FamilyTargetLigandMotifKindSourceN resRMSD (A)Centroid delta (A)Axis rot (deg)Kink apo (deg)Kink holo (deg)Kink delta (deg)Flagged phi/psi
ADRB2_GNASADRB2_GNAS_ISO1ISO1H8helixgpcr131.691.438.2225.8920.90-4.991
ADRB2_GNASADRB2_GNAS_ISO1ISO1TM1helixgpcr331.740.894.476.1212.556.430
ADRB2_GNASADRB2_GNAS_ISO1ISO1TM2helixgpcr310.700.412.0620.0917.08-3.010
ADRB2_GNASADRB2_GNAS_ISO1ISO1TM3helixgpcr361.030.711.9815.0211.97-3.062
ADRB2_GNASADRB2_GNAS_ISO1ISO1TM4helixgpcr271.000.572.8710.9617.926.960
ADRB2_GNASADRB2_GNAS_ISO1ISO1TM5helixgpcr341.520.923.589.3111.792.481
ADRB2_GNASADRB2_GNAS_ISO1ISO1TM6helixgpcr375.843.2814.3931.6827.14-4.553
ADRB2_GNASADRB2_GNAS_ISO1ISO1TM7helixgpcr252.171.464.6828.6117.87-10.743
ADRB2_GNASADRB2_GNAS_ISO1ISO1ECL1loopgpcr40.560.37N/AN/AN/AN/A0
ADRB2_GNASADRB2_GNAS_ISO1ISO1ECL2loopgpcr30.580.52N/AN/AN/AN/A0
ADRB2_GNASADRB2_GNAS_ISO1ISO1ECL3loopgpcr133.0733.07N/AN/AN/AN/A1
ADRB2_GNASADRB2_GNAS_ISO1ISO1H8looploopgpcr21.480.71N/AN/AN/AN/A0
ADRB2_GNASADRB2_GNAS_ISO1ISO1ICL1loopgpcr41.731.72N/AN/AN/AN/A0
ADRB2_GNASADRB2_GNAS_ISO1ISO1ICL2loopgpcr85.243.48N/AN/AN/AN/A6
ADRB2ADRB2_PRO1PRO1H8helixgpcr130.500.421.8925.8925.29-0.590
ADRB2ADRB2_PRO1PRO1TM1helixgpcr330.580.080.876.128.132.010
ADRB2ADRB2_PRO1PRO1TM2helixgpcr310.250.080.2520.0917.40-2.690
ADRB2ADRB2_PRO1PRO1TM3helixgpcr360.530.211.4115.0215.020.001
ADRB2ADRB2_PRO1PRO1TM4helixgpcr270.410.320.6810.9611.480.520
ADRB2ADRB2_PRO1PRO1TM5helixgpcr340.690.560.849.319.520.221
ADRB2ADRB2_PRO1PRO1TM6helixgpcr373.061.133.3231.6828.93-2.754
ADRB2ADRB2_PRO1PRO1TM7helixgpcr250.500.161.1028.6124.03-4.590
ADRB2ADRB2_PRO1PRO1ECL1loopgpcr40.490.36N/AN/AN/AN/A0
ADRB2ADRB2_PRO1PRO1ECL2loopgpcr30.600.53N/AN/AN/AN/A0
ADRB2ADRB2_PRO1PRO1ECL3loopgpcr124.7624.76N/AN/AN/AN/A1
ADRB2ADRB2_PRO1PRO1H8looploopgpcr20.910.56N/AN/AN/AN/A0
ADRB2ADRB2_PRO1PRO1ICL1loopgpcr40.580.54N/AN/AN/AN/A0
ADRB2ADRB2_PRO1PRO1ICL2loopgpcr85.604.11N/AN/AN/AN/A6

Download CSV

Family coverage and SSE shifts

FamilyStatusDetail
ADRB2_GNASOK14 motif row(s) across 1 target(s), annotator=gpcr
ADRB2OK14 motif row(s) across 1 target(s), annotator=gpcr

Overall shift statistics

  • 2 target(s), 28 motif(s) compared
  • Mean Ca RMSD: 3.49 A (median 0.95 A) — largest shift: 33.07 A at ADRB2_GNAS_ISO1 / ECL3
  • Mean centroid shift: 2.98 A
  • Flagged phi/psi outlier residues: 30
  • 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.

ADRB2_GNAS

ADRB2

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 adrb2_gs campaign predicted structures for two ADRB2 targets, ISO1 and PRO1. One of the two targets was marked caution and the other proceed. The campaign was not successful because one of the two targets carried at least one flag.

Targets2 predicted, 2 with a ligand
ReceptorsADRB2
LigandsISO1, PRO1
Verdicts1 caution, 1 proceed
Confidence1 moderately determined, 1 well determined
Flagged1 of 2
Pose validatedno 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

  • PRO1 on ADRB2_PRO1, predicted pIC50 12.41
  • ISO1 on ADRB2_GNAS_ISO1, predicted pIC50 10.14

Caveats

Overall confidence is below the well-determined threshold, so the structure should be treated with caution.

Per target

TargetVerdictSummaryCaveatWritten by
ADRB2_ISO1cautionThe structure is moderately determined, so it's not very reliable for making decisions. ISO1 is an agonist that binds to the receptor but has a high uncertainty about its potencyOverall confidence is below the well-determined threshold, so the structure should be treated with caution.model
AR2NG_PRO1proceedWell determined, meaning that the predicted structure is likely to be correct. PRO1 is an unspecified ligand with a binder probability of 0.997 and predicted potency of 12.41, with no interaction analysis run.The predicted structure is not supported by experimental data, as no interaction analysis was run.model