What does this research mean for the field?

Binder2030 is a comprehensive dataset of 3,384 small-molecule ligands with standardized dissociation constant (Kd) measurements for approximately 400 transmembrane proteins, facilitating AI-driven drug discovery. Novelty: ClaimNovelty.SYNTHESIS. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to create a comprehensive dataset for ligand-binding affinities of membrane proteins to facilitate drug discovery.

February 25, 2026SLAS DISCOVERY0 citationsOpen Access

Binder2030: a quantitative membrane proteome binding dataset enabling AI-driven drug discovery

NTNaoki TaruiFujifilm (Japan)MNMasaharu NakayamaFujifilm (Japan)TNThuy Duong NguyenFujifilm (Japan)

Key Points

The aim is to create a comprehensive dataset for ligand-binding affinities of membrane proteins to facilitate drug discovery.
Developed Binder2030 dataset with 3,384 small-molecule ligands across 400 transmembrane proteins.
Employed affinity selection-mass spectrometry to obtain standardized dissociation constant (Kd) values.
Released a subset aligned with PubChem containing matched activity annotations.
Binder2030 provides Kd measurements facilitating comparative analysis of binding affinities.
Enhanced understanding of chemical space across different target classes was achieved.
Demonstrated integration of dataset in a structure-based modeling workflow, validating predictions with experimental data.

Abstract

Abstract Membrane proteins represent more than half of therapeutic targets but remain underrepresented in quantitative ligand-binding datasets. Here we report Binder2030, a curated affinity selection–mass spectrometry (ASMS) dataset comprising 3,384 small-molecule ligands across approximately 400 transmembrane proteins, including G protein-coupled receptors (GPCRs), solute carrier (SLC) transporters, and ion channels. Using Binder Selection Technology (BST) applied to membrane fractions, Binder2030 provides standardized dissociation constant (Kd) measurements with curated chemical identifiers and target annotations, enabling comparative analysis of affinity distributions and chemical space across target classes. To support external anchoring, we release a PubChem-overlap subset with matched activity annotations and Binder2030 Kd values. Finally, we demonstrate downstream integration in a structure-based modeling workflow by comparing Boltz-2 predicted potencies with experimental affinities for a GlyT-1 ligand set.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper