Conditioning by adaptive sampling for robust design

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.

[1]  Stefan Schaal,et al.  Reinforcement learning by reward-weighted regression for operational space control , 2007, ICML '07.

[2]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[3]  Reuven Y. Rubinstein,et al.  Optimization of computer simulation models with rare events , 1997 .

[4]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[5]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[6]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine Learning.

[7]  James Zou,et al.  Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions , 2018, ArXiv.

[8]  David E. Kim,et al.  Simultaneous Optimization of Biomolecular Energy Functions on Features from Small Molecules and Macromolecules. , 2016, Journal of chemical theory and computation.

[9]  Leonid Peshkin,et al.  Learning from Scarce Experience , 2002, ICML.

[10]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[11]  G Schneider,et al.  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. , 1994, Biophysical journal.

[12]  Myle Ott,et al.  Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences , 2019, Proceedings of the National Academy of Sciences.

[13]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[14]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Adam Roberts,et al.  Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models , 2017, ICLR.

[16]  Yee Whye Teh,et al.  Do Deep Generative Models Know What They Don't Know? , 2018, ICLR.

[17]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[18]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[19]  Dmitry Chudakov,et al.  Local fitness landscape of the green fluorescent protein , 2016, Nature.

[20]  R. Rubinstein.  The Cross-Entropy Method for Combinatorial and Continuous Optimization , 1999 .

[21]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

[22]  Thomas Brox,et al.  Synthesizing the preferred inputs for neurons in neural networks via deep generator networks , 2016, NIPS.

[23]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[24]  Hau-San Wong,et al.  Introduction to the Peptide Binding Problem of Computational Immunology: New Results , 2014, Found. Comput. Math..

[25]  Anne Auger,et al.  Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles , 2011, J. Mach. Learn. Res..

[26]  Yasemin Altun,et al.  Relative Entropy Policy Search , 2010 .

[27]  James Zou,et al.  Feedback GAN for DNA optimizes protein functions , 2019, Nature Machine Intelligence.

[28]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[29]  G. Schneider,et al.  Peptide design by artificial neural networks and computer-based evolutionary search. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[30]  Pieter Abbeel,et al.  On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient , 2010, NIPS.

[31]  Sanjoy Dasgupta,et al.  Off-Policy Temporal Difference Learning with Function Approximation , 2001, ICML.

[32]  David M. Blei,et al.  Variational Inference: A Review for Statisticians , 2016, ArXiv.

[33]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[34]  Brendan J. Frey,et al.  Generating and designing DNA with deep generative models , 2017, ArXiv.

[35]  Yoshua Bengio,et al.  Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Isabelle Bloch,et al.  Estimation of Distribution Algorithms: A New Evolutionary Computation Approach for Graph Matching Problems , 2001, EMMCVPR.

[37]  Frances H. Arnold,et al.  Enzyme Engineering for Nonaqueous Solvents: Random Mutagenesis to Enhance Activity of Subtilisin E in Polar Organic Media , 1991, Bio/Technology.