AdaLead: A simple and robust adaptive greedy search algorithm for sequence design

TL;DR

AdaLead is a simple, scalable, and robust greedy algorithm for biological sequence design that outperforms complex state-of-the-art methods in various challenges, leveraging an open-source evaluation environment.

Contribution

The paper introduces AdaLead, a straightforward evolutionary greedy algorithm, and demonstrates its superior performance over complex methods using the FLEXS benchmarking environment.

Findings

AdaLead outperforms complex algorithms in sequence design tasks.

The algorithm is scalable and robust across different challenges.

FLEXS provides a standardized environment for evaluating sequence optimization algorithms.

Abstract

Efficient design of biological sequences will have a great impact across many industrial and healthcare domains. However, discovering improved sequences requires solving a difficult optimization problem. Traditionally, this challenge was approached by biologists through a model-free method known as "directed evolution", the iterative process of random mutation and selection. As the ability to build models that capture the sequence-to-function map improves, such models can be used as oracles to screen sequences before running experiments. In recent years, interest in better algorithms that effectively use such oracles to outperform model-free approaches has intensified. These span from approaches based on Bayesian Optimization, to regularized generative models and adaptations of reinforcement learning. In this work, we implement an open-source Fitness Landscape EXploration Sandbox (FLEXS: github.com/samsinai/FLEXS) environment to test and evaluate these algorithms based on their optimality, consistency, and robustness. Using FLEXS, we develop an easy-to-implement, scalable, and robust evolutionary greedy algorithm (AdaLead). Despite its simplicity, we show that AdaLead is a remarkably strong benchmark that out-competes more complex state of the art approaches in a variety of biologically motivated sequence design challenges.