pH-sensitive binder design with Proton-PottsMPNN
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (Arcadia Science)
Abstract
Physiological compartments span a wide pH range, from blood plasma near pH 7.4 through the mildly acidic tumor microenvironment to the acidified endosome and lysosome, and binders whose affinity responds to these differences underpin recycling antibodies, catalytic extracellular degraders and tumor-conditional therapeutics. Such binders are still obtained mainly by combinatorial histidine scanning and display selection, which is laborious and yields few transferable design rules. Recent computational approaches have enabled the design of pH-sensitive binders that engage at physiological pH and release under acidic conditions, by introducing histidines at key positions so that protonation generates electrostatic repulsion, evaluated through physics-based calculations. However, because the design model has no explicit representation of protonation state, it cannot shape the residues around a titratable site to favor one state over the other, leaving pH sensitivity to be screened for rather than specified. Here we present Proton-PottsMPNN, a sequence-design model that explicitly represents the protonated and deprotonated states of histidine, aspartate and glutamate as distinct sequence tokens. Because protonation state is specified rather than inferred, the model redesigns the microenvironment around a titratable residue so that the chosen protonation state is energetically favored over its alternative. Using Proton-PottsMPNN we designed a library of 8,407 de novo PD-L1 candidate binders in which sequence-structure compatibility and protonation state preference were designed jointly under a single energy function, with no structure-prediction filtering applied. The full library was synthesized and displayed on yeast, then screened against PD-L1 across a series of pH values by fluorescence- and magnetic-activated cell sorting, recovering 237 and 288 unique pH-dependent designs respectively. Transition pH values spanned 4.0 to 5.8, and switches were centered on protonated aspartate and glutamate as well as histidine. Recovered designs showed a stronger model preference for their designed protonation state than designs from the same backbone that were not recovered, and this preference was strongest in the designs that required the most acidic conditions to bind. Proton-PottsMPNN therefore designs binders that engage PD-L1 under acidic conditions fully de novo, directly from a specified protonation state.
Article activity feed
-
Nice paper! The case for making protonation state an explicit design variable in binder design is clear, and screening the full library without structure-prediction filtering makes the result easy to trust. A few suggestions: I’d like to see Proton-PottsMPNN compared directly with the Baker lab’s approach (doi.org/10.1101/2025.09.29.678932). The unmodified seeds show that the redesign adds pH dependence, but not how much the protonation tokens add beyond histidine-biased ProteinMPNN. Grouping folds by PDB entry allows near-identical proteins on both sides of a split. I think clustering by sequence identity (or structural similarity) would give a more conservative estimate. All designs switch at pH 5.8 or below, which better matches endosomal pH than the tumor microenvironment mentioned in the introduction. I’d love to see whether your …
Nice paper! The case for making protonation state an explicit design variable in binder design is clear, and screening the full library without structure-prediction filtering makes the result easy to trust. A few suggestions: I’d like to see Proton-PottsMPNN compared directly with the Baker lab’s approach (doi.org/10.1101/2025.09.29.678932). The unmodified seeds show that the redesign adds pH dependence, but not how much the protonation tokens add beyond histidine-biased ProteinMPNN. Grouping folds by PDB entry allows near-identical proteins on both sides of a split. I think clustering by sequence identity (or structural similarity) would give a more conservative estimate. All designs switch at pH 5.8 or below, which better matches endosomal pH than the tumor microenvironment mentioned in the introduction. I’d love to see whether your tool can make designs that switch at a higher pH! Counter-screen pH. The HSA and CD98 counter-screen was run at pH 5.0. A counter-screen at pH 4.0 would strengthen the pH 4.0-only designs, which are the most exposed to non-specific binding.
Minor figure tweaks: Figure 1b says pH 7.0, but Figure 1c uses pH 7.4. The axes in Figures 1c and 3c are unlabeled.
-
