AdaLead: A simple and robust adaptive greedy search algorithm for sequence design
arXiv:2010.02141
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.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Scikit-learn: Machine Learning in Python
- A Tutorial on Bayesian Optimization
- Improving Online Algorithms via ML Predictions
- Generating and designing DNA with deep generative models
- Evaluating Protein Transfer Learning with TAPE
- Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions
- Variational auto-encoding of protein sequences
- Conditioning by adaptive sampling for robust design
- Bayesian Optimization for Synthetic Gene Design
- ProGen: Language Modeling for Protein Generation
- Design by adaptive sampling
- Information-geometric optimization with natural selection
Cited by in corpus (5)
- Conformal Prediction Under Feedback Covariate Shift for Biomolecular Design
- Is novelty predictable?
- Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC
- A primer on model-guided exploration of fitness landscapes for biological sequence design
- Semantically Rich Local Dataset Generation for Explainable AI in Genomics