ZetaDial: dialing net charge of protein binders at inference time for therapeutic developability
Abstract
Net charge is a developability-relevant property of therapeutic binders, linked to viscosity, clearance, nonspecific interaction and aggregation, and antibody screens already use charge-related criteria. Yet inverse-folding pipelines expose no way to set it to a target value. ProteinMPNN and BindCraft offer amino-acid biases, weight choices and custom losses, but neither supplies a per-protein feedback loop that measures realised charge after sampling and corrects it to a setpoint. ZetaDial contributes a post-sampling, per-protein secant controller around fixed-backbone ProteinMPNN. On matched stochastic benchmarks the secant loop reduced mean absolute error relative to a fixed-slope loop on RCSB complexes (5.17 vs 6.46 charge units) and Cas13 monomers (5.57 vs 8.23). Relative to the optimised matched global bias, it cut RCSB error from 11.71 to 5.17 (cluster bootstrap p < 0.001) and was statistically indistinguishable on Cas13 (5.47 vs 5.57). Across 800 eight-protein subsets, sensitivity heterogeneity was associated with calibration gain (Pearson r = 0.79); this is descriptive resampling, not a prospective decision rule. Foldability deteriorated as bias magnitude increased. In the full 52-complex seed-0 analysis, reference-based DockQ declined clearly at +/-3 but not at +/-1.5; a selected five-seed replication on eight complexes showed paired declines at every nonzero setting, but does not estimate the effect for all 52. In exploratory BindCraft sweeps, PD-L1 designs moved toward near-neutral charge at similar maximum interface pTM but with overlapping success-rate intervals; IL-7R-alpha responses were non-monotonic and RBD produced no strong designs. A fixed-backbone C-alpha-neighbour analysis found smaller same-sign charge-patch proxies near neutral charge, but this proxy is not a measured electrostatic surface or experimental developability endpoint.
Related
- Context-dependent protein structure prediction analysis and complex stoichiometry inference with MultimerMapper.
- Lactate metabolism and protein lactylation in programmed cell death: From novel mechanism to therapeutic strategies in human diseases
- Functional Autoantibodies Against G-Protein-Coupled Receptors: Insights into Molecular Mechanisms, Clinical Relevance and Therapeutic Perspectives
- Bayesian Gaussian process inference of RNA velocity as a probabilistic vector field on single-cell manifolds
- OrthoFinder: improved phylogenetic orthology inference with enhanced accuracy and scalability
BibTeX
@misc{syed2026zetadial,
title = {{ZetaDial: dialing net charge of protein binders at inference time for therapeutic developability}},
author = {Mohammed Sameer Syed and Tamara Dinneen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.05451},
eprint = {2609.05451},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.05451},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ZetaDial: dialing net charge of protein binders at inference time for therapeutic developability
AU - Mohammed Sameer Syed
AU - Tamara Dinneen
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.05451
UR - https://arxiv.org/abs/2609.05451
AB - Net charge is a developability-relevant property of therapeutic binders, linked to viscosity, clearance, nonspecific interaction and aggregation, and antibody screens already use charge-related criteria. Yet inverse-folding pipelines expose no way to set it to a target value. ProteinMPNN and BindCraft offer amino-acid biases, weight choices and custom losses, but neither supplies a per-protein feedback loop that measures realised charge after sampling and corrects it to a setpoint. ZetaDial contributes a post-sampling, per-protein secant controller around fixed-backbone ProteinMPNN. On matched stochastic benchmarks the secant loop reduced mean absolute error relative to a fixed-slope loop on RCSB complexes (5.17 vs 6.46 charge units) and Cas13 monomers (5.57 vs 8.23). Relative to the optimised matched global bias, it cut RCSB error from 11.71 to 5.17 (cluster bootstrap p < 0.001) and was statistically indistinguishable on Cas13 (5.47 vs 5.57). Across 800 eight-protein subsets, sensitivity heterogeneity was associated with calibration gain (Pearson r = 0.79); this is descriptive resampling, not a prospective decision rule. Foldability deteriorated as bias magnitude increased. In the full 52-complex seed-0 analysis, reference-based DockQ declined clearly at +/-3 but not at +/-1.5; a selected five-seed replication on eight complexes showed paired declines at every nonzero setting, but does not estimate the effect for all 52. In exploratory BindCraft sweeps, PD-L1 designs moved toward near-neutral charge at similar maximum interface pTM but with overlapping success-rate intervals; IL-7R-alpha responses were non-monotonic and RBD produced no strong designs. A fixed-backbone C-alpha-neighbour analysis found smaller same-sign charge-patch proxies near neutral charge, but this proxy is not a measured electrostatic surface or experimental developability endpoint.
ER -