Bayesian Optimization for Synthetic Gene Design

By Javier I. González, Joseph Longworth, D. James, Neil D. Lawrence. 2015

85 citations recorded by the source corpus.

We address the problem of synthetic gene design using Bayesian optimization. The main issue when designing a gene is that the design space is defined in terms of long strings of characters of different lengths, which renders the optimization intractable. We propose a three-step approach to deal with this issue. First, we use a Gaussian process model to emulate the behavior of the cell. As inputs of the model, we use a set of biologically meaningful gene features, which allows us to define optimal gene designs rules. Based on the model outputs we define a multi-task acquisition function to optimize simultaneously severals aspects of interest. Finally, we define an evaluation function, which allow us to rank sets of candidate gene sequences that are coherent with the optimal design strategy. We illustrate the performance of this approach in a real gene design experiment with mammalian cells.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Management Science and Operations Research

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

In Computational Theory and Mathematics

In Management Science and Operations Research

Citations in the corpus

Unified rational protein engineering with sequence-based deep representation learning (2019, background): “While the high dimensionality and discrete nature of sequence space make sequence search a challenging and unsolved problem, we are optimistic about how UniRep-powered models may combine with ongoing work in simulated annealing 3 , adaptive sampling 43 and Bayesian optimization 44–50 .”
Multi-fidelity Bayesian Optimisation with Continuous Approximations (2017, background): “, 2007) and scientific experiments (Gonzalez et al., 2014; Parkinson et al., 2006).”
AdaLead: A simple and robust adaptive greedy search algorithm for sequence design (2020, background): “Many successful attempts have followed since (e.g. Gonzalez et al. (2015) and Yang et al. (2019)), however in each of these cases a speciﬁc model of the design space is assumed to shrink the search space signiﬁcantly.”
Parallelised Bayesian Optimisation via Thompson Sampling (2018, background): “Bayesian optimisation (BO) refers to a suite of methods for blackbox optimisation under Bayesian assumptions on f that has been successfully applied in hyper-parameter tuning, drug discovery and other applications in policy search, online advertising, and scientific experimentation [12, 17, 30, 32, ”
Machine learning applications in drug development (2019, background): “For instance, in [56], the authors apply BO to design gene sequences which maximize transcription and translation rates, from initial sequences.”
High Dimensional Bayesian Optimisation and Bandits via Additive Models (2015, methodology): “Expensive high dimensional functions occur in several problems in ﬁelds such as computer vision (Yamins et al., 2013), antenna design (Hornby et al., 2006), computational astrophysics (Parkinson et al., 2006) and biology (Gonzalez et al., 2014).”
Batch Bayesian Optimization via Local Penalization (2015, background): “Many problems, such as the conﬁguration of machine learning algorithms [Snoek et al., 2012] or the experimental design of biological experiments [Gonz´alez et al., 2014] require the optimization of an unknown, possibly noisy, function f .”
Asynchronous Parallel Bayesian Optimisation via Thompson Sampling (2017, background): “Bayesian optimisation (BO) refers to a suite of methods for black-box optimisation under Bayesian assumptions on f that has been successfully applied in many of the above applications [11, 15, 26, 28, 35].”
Multi-fidelity Gaussian Process Bandit Optimisation (2016, unknown): “, 2007), and scientific experiments (Gonzalez et al., 2014; Parkinson et al., 2006).”
Bayesian Optimization over Sets (2019, methodology): “It has proven useful in several applications, including hyperparameter optimization [27, 17], neural architecture search [29, 18], material design [8], and synthetic gene design [13].”