Design by adaptive sampling

Abstract

We present a probabilistic modeling framework and adaptive sampling algorithm wherein unsupervised generative models are combined with black box predictive models to tackle the problem of input design. In input design, one is given one or more stochastic "oracle" predictive functions, each of which maps from the input design space (e.g. DNA sequences or images) to a distribution over a property of interest (e.g. protein fluorescence or image content). Given such stochastic oracles, the problem is to find an input that is expected to maximize one or more properties, or to achieve a specified value of one or more properties, or any combination thereof. We demonstrate experimentally that our approach substantially outperforms other recently presented methods for tackling a specific version of this problem, namely, maximization when the oracle is assumed to be deterministic and unbiased. We also demonstrate that our method can tackle more general versions of the problem.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Categorical Reparameterization with Gumbel-Softmax
• On Calibration of Modern Neural Networks
• Improved Training of Wasserstein GANs
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Generating and designing DNA with deep generative models
• Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions

Cited by in corpus (15)

• Explainable Machine Learning for Scientific Insights and Discoveries
• Machine learning-assisted directed protein evolution with combinatorial libraries
• Population-Based Black-Box Optimization for Biological Sequence Design
• Fast differentiable DNA and protein sequence optimization for molecular design
• AdaLead: A simple and robust adaptive greedy search algorithm for sequence design
• Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
• Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC
• Deep Learning in Protein Structural Modeling and Design
• A primer on model-guided exploration of fitness landscapes for biological sequence design
• Deep Extrapolation for Attribute-Enhanced Generation
• The Differentiable Cross-Entropy Method
• Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces
• Improving Molecular Design by Stochastic Iterative Target Augmentation
• A Hierarchical Approach to Scaling Batch Active Search Over Structured Data
• Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate