Introducing BenchBB

The Bench-tested Binder Benchmark: A curated set of standardized protein targets enabling rigorous, consistent evaluation of computational binder design methods.

BenchBB

Why BenchBB?

BenchBB was initiated based on the insights gained from the Adaptyv Protein Design Competition to establish a benchmark for computational protein binder design.

It includes seven carefully selected targets: PD-L1, EGFR, IL7Ra, BHRF1, SpCas9, BBF-14, and MBP. Each target offers unique advantages for benchmarking, from ease of production, to structural challenges and diversity in binding modes.

For more details, read the paper

Standardization

BenchBB addresses the critical need for standardized benchmark targets in computational protein design, enabling consistent evaluation and direct comparison of different methods.

Practical Evaluation

Targets are selected for novel interfaces, challenging conformations, therapeutic relevance, and ease of production.

Advancing the Field

Like benchmarks in machine learning (GLUE, SuperGLUE, MMLU), BenchBB provides a foundation for measuring progress and driving innovation in computational protein design.

Coming Soon

Coming Soon

Model Leaderboard

Track and compare the performance of different protein design models across our benchmark targets.

Coming Soon

Download & Explore

Access comprehensive datasets, analysis tools, and visualization features to dive deep into the results.

Coming Soon

Community Challenges

Participate in regular challenges to test your models and contribute to advancing the field.

Start your BenchBB project

Use the Adaptyv Cloud Lab to benchmark your protein-binder designs against the BenchBB targets.

Benchmark Pricing

ProprietaryOpen Source

DNA & Expression

Includes gene synthesis and protein expression

BLI Characterization

Binding affinity characterization with two target concentrations and two replicates

Data Rights

Data will be open sourced to advance the BenchBB benchmark

Price per Design

$99
1

Select Targets to Benchmark

Choose which protein targets you want to benchmark against

2

Configure Designs

Specify the number of designs or upload sequences for each target

3

Review Project

Review your selections and proceed with your project

Select Targets

Choose which protein targets you want to benchmark against. Ideally, you should benchmark your model against all targets.

Protein bhrf1
BHRF1
170 AA
19.7 kDa
Viral
Bcl-2 homolog from Epstein-Barr virus, an anti-apoptotic protein.
Protein cas9
Cas9
1368 AA
160 kDa
Bacterial
CRISPR-associated nuclease from Streptococcus pyogenes.
Protein egfr
EGFR
620 AA
70 kDa
Human
Human epidermal growth factor receptor, a key therapeutic target in cancer.
Protein il7ra
IL-7Rα
219 AA
25.2 kDa
Human
Interleukin-7 receptor alpha chain, a cytokine receptor subunit.
Protein mbp
MBP
370 AA
42.5 kDa
Bacterial
Maltose-binding protein from E. coli, a common protein expression tag.
Protein pdl1
PD-L1
290 AA
33 kDa
Human
Programmed death-ligand 1, an immune checkpoint protein.
Protein bbf-14
BBF-14
112 AA
13.8 kDa
Synthetic
A synthetic 112-AA β-barrel protein.