# Why risk matters for protein binder design

arXiv: https://arxiv.org/abs/2504.00146 · HTML: https://mlsanity.com/paper/2504.00146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)
- [Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users](https://mlsanity.com/paper/2007.06823/) (2020)
- [The Road Less Scheduled](https://mlsanity.com/paper/2405.15682/) (2024)
- [Maximizing acquisition functions for Bayesian optimization](https://mlsanity.com/paper/1805.10196/) (2018)
- [Recent Advances in Bayesian Optimization](https://mlsanity.com/paper/2206.03301/) (2022)
- [Understanding Random Forests: From Theory to Practice](https://mlsanity.com/paper/1407.7502/) (2014)
- [Bayesian Optimization of Risk Measures](https://mlsanity.com/paper/2007.05554/) (2020)
- [Warm Starting Bayesian Optimization](https://mlsanity.com/paper/1608.03585/) (2016)
- [Risk-averse Heteroscedastic Bayesian Optimization](https://mlsanity.com/paper/2111.03637/) (2021)
- [Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks](https://mlsanity.com/paper/2410.22296/) (2024)
- [Diagnosing and fixing common problems in Bayesian optimization for molecule design](https://mlsanity.com/paper/2406.07709/) (2024)
- [Closed-Form Test Functions for Biophysical Sequence Optimization Algorithms](https://mlsanity.com/paper/2407.00236/) (2024)

## Abstract (arXiv)

Bayesian optimization (BO) has recently become more prevalent in protein engineering applications and hence has become a fruitful target of benchmarks. However, current BO comparisons often overlook real-world considerations like risk and cost constraints. In this work, we compare 72 model combinations of encodings, surrogate models, and acquisition functions on 11 protein binder fitness landscapes, specifically from this perspective. Drawing from the portfolio optimization literature, we adopt metrics to quantify the cold-start performance relative to a random baseline, to assess the risk of an optimization campaign, and to calculate the overall budget required to reach a fitness threshold. Our results suggest the existence of Pareto-optimal models on the risk-performance axis, the shift of this preference depending on the landscape explored, and the robust correlation between landscape properties such as epistasis with the average and worst-case model performance. They also highlight that rigorous model selection requires substantial computational and statistical efforts.