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

By Sam Sinai, Richard Wang, Alexander Whatley, Stewart Slocum, Elina Locane, Eric D. Kelsic. 2020

113 citations recorded by the source corpus.

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: this http URL) 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.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Adam Lerer
2. Alexander Rives
3. Jason Liu
4. Tom Sercu
5. Smita Krishnaswamy
6. Zeming Lin
7. Brian L. Hie
8. Jakob N. Foerster

In Computational Theory and Mathematics

1. Alexander Rives
2. Robert Verkuil
3. Adam Lerer
4. Jason Liu
5. Tom Sercu
6. Zeming Lin
7. Brian L. Hie

Citations in the corpus

• Learning inverse folding from millions of predicted structures (2022, methodology): “Additionally, as an alternative to sequence generation models, model-guided algorithms design sequences based on predictive models as oracles (Yang et al., 2019; Angermueller et al., 2019; Brookes et al., 2019; Sinai et al., 2020).”
• Guided Generative Protein Design using Regularized Transformers (2022, background): “Recent efforts haven sought to standardize this approach by introducing a benchmark environment Sinai et al. [2020].”