Models/BoltzGen
STRUCTURE MODEL

BoltzGen

BoltzGen · Papers & sources

BoltzGen: Toward Universal Binder Design

Official project ↗

Wet-lab results

Ab001 / Ab002
Protein nameTargetSubsetDesign workflowSEC purity (%)SDS purity (%)Single-point BLI net responseKᴅ (nM) Kᴅ is the apparent dissociation constant (Kᴅ,app) from the selected binding model. Under comparable conditions, lower values indicate stronger binding. For a 1:1 interaction it equals the Kᴅ from that model. When comparing models, consider assay conditions and fit quality.Nonspecific binding signalBVP ELISA measures nonspecific antibody binding to baculovirus particles. The reported value is a background-corrected net signal. Under matching assay and normalization conditions, lower values generally indicate less nonspecific binding. The assay helps assess polyreactivity and the risk of rapid clearance in vivo.Assay referenceTonset (°C)Tonset is the onset of protein unfolding, where a structure-sensitive signal first departs appreciably from its baseline during heating. Under the same conditions, a higher value generally indicates a later onset of unfolding.Tm₁ (°C)Tm is the midpoint of a thermal unfolding transition. For a single transition, about half the protein is unfolded at this temperature. Tm₁ refers to the first transition. A higher Tm generally indicates greater thermal stability under the same conditions.Tagg (°C)Tagg is the onset of heat-induced aggregation, where a signal such as light scattering or turbidity first changes appreciably. With the same assay conditions and onset criteria, a higher value generally indicates later aggregation.
BoltzGen-IL7RA-013IL-7RαAb002BoltzGen × AntiBMPNN76.895.90.0059
BoltzGen-IL7RA-014IL-7RαAb002BoltzGen × AntiBMPNN43.880.50.0046
BoltzGen-IL7RA-015IL-7RαAb002BoltzGen × AntiBMPNN80.985.20.0025
BoltzGen-IL7RA-016IL-7RαAb002BoltzGen × AntiBMPNN96.398.60.0022
BoltzGen-IL7RA-017IL-7RαAb002BoltzGen × AntiBMPNN9198.30.0091
BoltzGen-IL7RA-018IL-7RαAb002BoltzGen × AntiBMPNN65.198.2-0.0093
BoltzGen-IL7RA-019IL-7RαAb002BoltzGen × AntiBMPNN92.893.4-0.009
BoltzGen-IL7RA-020IL-7RαAb002BoltzGen × AntiBMPNN86.697.3Purification failed
BoltzGen-IL7RA-021IL-7RαAb002BoltzGen × ProteinMPNN95.398.2-0.0008
BoltzGen-IL7RA-022IL-7RαAb002BoltzGen × ProteinMPNN96.295.10.0939
BoltzGen-IL7RA-023IL-7RαAb002BoltzGen × ProteinMPNNAggregation90.20.0014
BoltzGen-IL7RA-024IL-7RαAb002BoltzGen × ProteinMPNNAggregation29.60.0279
BoltzGen-IL7RA-025IL-7RαAb002BoltzGen × ProteinMPNN95.498.80.2371-0.066395
BoltzGen-IL7RA-026IL-7RαAb002BoltzGen × ProteinMPNN98.594.90
BoltzGen-IL7RA-027IL-7RαAb002BoltzGen × ProteinMPNNAggregation98.30.0071
BoltzGen-IL7RA-028IL-7RαAb002BoltzGen × ProteinMPNN91.295.9-0.0037
BoltzGen-IL7RA-029IL-7RαAb002BoltzGen × ProteinMPNN90.198.30.1791-0.085895
BoltzGen-IL7RA-030IL-7RαAb002BoltzGen × ProteinMPNN77.695.80.0249
BoltzGen-IL7RA-031IL-7RαAb002BoltzGen × ProteinMPNNAggregation0.0043
BoltzGen-IL7RA-032IL-7RαAb002BoltzGen × ProteinMPNN93.398.6-0.0032
BoltzGen-IL7RA-033IL-7RαAb002BoltzGen × ProteinMPNN93.697.50.0022
BoltzGen-IL7RA-034IL-7RαAb002BoltzGen × ProteinMPNN94.4990.0103
BoltzGen-IL7RA-035IL-7RαAb002BoltzGen × ProteinMPNN87.195.90.2547
BoltzGen-IL7RA-036IL-7RαAb002BoltzGen × ProteinMPNN5171.6 18.80.0508
BoltzGen-IL7RA-037IL-7RαAb002BoltzGen × ProteinMPNN95.996.80.0101

26–50 of 93 candidates

Compute resources and costs

RESOURCES / MODEL STAGE

Model-stage resources

IL7RA · Model-level aggregate
GPU·h69.52
Sampled peak device memory/ GiB11.08
Estimated GPU cost/ CNY¥382.38
Estimated cost per output/ CNY0.019119

Device with recorded maximum:NVIDIA RTX PRO 5000 72GB Blackwell
Devices in sampled records:NVIDIA RTX PRO 5000 72GB Blackwell

Memory values are device sampling maxima, not continuous monitoring maxima. GPU pricing classes do not verify hardware; unknown hardware is priced as RTX 4090. Costs exclude 30 GPU tasks shorter than 600 s (1.0558 GPU·h); CPU-only records remain included and queue time is excluded.

IL‑7Rα project cost breakdown
IL7RA / PROJECT BUDGET

Estimated project cost breakdown

¥13,847.43 CNY

Totals cover all models and evaluation stages, independently of the selected model. CPU core-hours and GPU hours are priced separately.

Structure generation
¥1,497.2210.8%
Sequence design
¥213.381.5%
Rosetta
¥5,096.936.8%
AF2
¥5,415.9439.1%
AF3
¥1,623.9911.7%