Local Latent Space Bayesian Optimization over Structured Inputs

Maus, Natalie; Moore, Juston S.; Kusner, Matt J.; Bradshaw, John L.; Gardner, Jacob R.

doi:10.48550/arxiv.2201.11872

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure S1 shows optimization of latent space has continuous improvement, but after decoding to an actual sequence and evaluating g( u) there is a plateau. This may be unique to UniRep or because or be task specific because other recent work has successfully used latent spaces for BayesOpt 68,69 and work on improving extrapolation from latent spaces. 70 Nevertheless, avoiding latent space negates this potential agreement problem between u and x.…”

Section: B Bayesian Optimizationmentioning

confidence: 99%

Now What Sequence? Pre-trained Ensembles for Bayesian Optimization of Protein Sequences

Yang

Milas

White

2022

Preprint

View full text Add to dashboard Cite

Pre-trained models have been transformative in natural language, computer vision, and now protein sequences by enabling accuracy with few training examples. We show how to use pre-trained sequence models in Bayesian optimization to design new protein sequences with minimal labels (i.e., few experiments). Pre-trained models give good predictive accuracy at low data and Bayesian optimization guides the choice of which sequences to test. Pre-trained sequence models also obviate the common requirement of finite pools. Any sequence can be considered. We show significantly fewer labeled sequences are required for many sequence design tasks, including creating novel peptide inhibitors with AlphaFold. This work should enable calibrated predictions with few examples and iterative design with low data (1-50).

show abstract

Section: B Bayesian Optimizationmentioning

confidence: 99%

Now What Sequence? Pre-trained Ensembles for Bayesian Optimization of Protein Sequences

Yang

Milas

White

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The shortcomings of objectives like logP and QED appear to be well-known (Nigam et al, 2019;Tripp et al, 2021;Fu et al, 2020;Maus et al, 2022), but a superior alternative has not yet been accepted by the research community. For example, at the time of writing the only molecule generation benchmark in TorchDrug is maximization of QED and logP of ZINC-like molecules.…”

Section: Appendicesmentioning

confidence: 99%

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

Stanton¹,

Maddox²,

Gruver³

et al. 2022

Preprint

View full text Add to dashboard Cite

Bayesian optimization is a gold standard for query-efficient continuous optimization. However, its adoption for drug and antibody sequence design has been hindered by the discrete, highdimensional nature of the decision variables. We develop a new approach (LaMBO) which jointly trains a denoising autoencoder with a discriminative multi-task Gaussian process head, enabling gradient-based optimization of multi-objective acquisition functions in the latent space of the autoencoder. These acquisition functions allow LaMBO to balance the explore-exploit trade-off over multiple design rounds, and to balance objective tradeoffs by optimizing sequences at many different points on the Pareto frontier. We evaluate LaMBO on a small-molecule task based on the ZINC dataset and introduce a new large-molecule task targeting fluorescent proteins. In our experiments, LaMBO outperforms genetic optimizers and does not require a large pretraining corpus, demonstrating that Bayesian optimization is practical and effective for biological sequence design.

show abstract

“…Numerous deep learning-based methods have been developed for de novo drug design, including approaches based on reinforcement learning (Olivecrona et al, 2017;Zhou et al, 2019;You et al, 2018;Jin et al, 2020;Yang et al, 2021;Horwood & Noutahi, 2020;Gottipati et al, 2020;Neil et al, 2018) and variational autoencoders (Gómez-Bombarelli et al, 2018;Maus et al, 2022;Jin et al, 2018;Bradshaw et al, 2020). These approaches use several different ways to encode molecules into something that the model can learn, such as fingerprint-, string-and graph-based encodings.…”

Section: Introductionmentioning

confidence: 99%

Utilizing reinforcement learning for de novo drug design

Gummesson Svensson,

Tyrchan,

Engkvist

et al. 2024

Mach Learn

View full text Add to dashboard Cite

Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years. Recent studies have demonstrated promising performance for string-based generation of novel molecules utilizing reinforcement learning. In this paper, we develop a unified framework for using reinforcement learning for de novo drug design, wherein we systematically study various on- and off-policy reinforcement learning algorithms and replay buffers to learn an RNN-based policy to generate novel molecules predicted to be active against the dopamine receptor DRD2. Our findings suggest that it is advantageous to use at least both top-scoring and low-scoring molecules for updating the policy when structural diversity is essential. Using all generated molecules at an iteration seems to enhance performance stability for on-policy algorithms. In addition, when replaying high, intermediate, and low-scoring molecules, off-policy algorithms display the potential of improving the structural diversity and number of active molecules generated, but possibly at the cost of a longer exploration phase. Our work provides an open-source framework enabling researchers to investigate various reinforcement learning methods for de novo drug design.

show abstract

Local Latent Space Bayesian Optimization over Structured Inputs

Cited by 5 publications

References 0 publications

Now What Sequence? Pre-trained Ensembles for Bayesian Optimization of Protein Sequences

Now What Sequence? Pre-trained Ensembles for Bayesian Optimization of Protein Sequences

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

Utilizing reinforcement learning for de novo drug design

Contact Info

Product

Resources

About