Conditioning by adaptive sampling for robust design (2019-01-29T00:00:00.000000Z)

TL;DR

This work proposes a new method, Conditioning by Adaptive Sampling, which yields state-of-the-art results on a protein fluorescence problem, as compared to other recently published approaches.

Abstract

We present a new method for design problems wherein the goal is to maximize or specify the value of one or more properties of interest. For example, in protein design, one may wish to find the protein sequence that maximizes fluorescence. We assume access to one or more, potentially black box, stochastic "oracle" predictive functions, each of which maps from input (e.g., protein sequences) design space to a distribution over a property of interest (e.g. protein fluorescence). At first glance, this problem can be framed as one of optimizing the oracle(s) with respect to the input. However, many state-of-the-art predictive models, such as neural networks, are known to suffer from pathologies, especially for data far from the training distribution. Thus we need to modulate the optimization of the oracle inputs with prior knowledge about what makes `realistic' inputs (e.g., proteins that stably fold). Herein, we propose a new method to solve this problem, Conditioning by Adaptive Sampling, which yields state-of-the-art results on a protein fluorescence problem, as compared to other recently published approaches. Formally, our method achieves its success by using model-based adaptive sampling to estimate the conditional distribution of the input sequences given the desired properties.

Authors

David H. Brookes

1 papers

Hahnbeom Park

1 papers

J. Listgarten

1 papers

TL;DR

Abstract

Authors

References43 items

Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences

Feedback GAN for DNA optimizes protein functions

Machine learning in protein engineering

Design by adaptive sampling

Do Deep Generative Models Know What They Don't Know?

Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions

Generating and designing DNA with deep generative models

Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models

Attention is All you Need

Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

Simultaneous Optimization of Biomolecular Energy Functions on Features from Small Molecules and Macromolecules.

Categorical Reparameterization with Gumbel-Softmax

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

Density estimation using Real NVP

Local fitness landscape of the green fluorescent protein

The CMA Evolution Strategy: A Tutorial

Variational Inference: A Review for Statisticians

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

Auto-Encoding Variational Bayes

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Intriguing properties of neural networks

Introduction to the Peptide Binding Problem of Computational Immunology: New Results

Practical Bayesian Optimization of Machine Learning Algorithms

Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles

On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient

Relative Entropy Policy Search

Reinforcement learning by reward-weighted regression for operational space control

Learning from Scarce Experience

Estimation of Distribution Algorithms: A New Evolutionary Computation Approach for Graph Matching Problems

Off-Policy Temporal Difference Learning with Function Approximation

The Cross-Entropy Method for Combinatorial and Continuous Optimization

An Introduction to Variational Methods for Graphical Models

Peptide design by artificial neural networks and computer-based evolutionary search.

Optimization of computer simulation models with rare events

The rational design of amino acid sequences by artificial neural networks and simulated molecular evolution: de novo design of an idealized leader peptidase cleavage site.

Enzyme Engineering for Nonaqueous Solvents: Random Mutagenesis to Enhance Activity of Subtilisin E in Polar Organic Media

Statistical Inference for Probabilistic Functions of Finite State Markov Chains

GENERATIVE ADVERSARIAL NETS

Supplementary materials for: Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

2017) (without adversarial examples), where each model has the architecture Input(L

We derive the CbAS update equation in the variational inference case below, but the update equation can be modified in a corresponding way for any model that permit other forms of approximate MLE

Field of Study

Venue Information

Name

Type

URL

Alternate Names