Variational auto-encoding of protein sequences

Sinai, Sam; Kelsic, Eric D.; Church, George M.; Nowak, Martin A.

doi:10.48550/arxiv.1712.03346

Cited by 19 publications

(22 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While predictive accuracy could be improved by more computationally-expensive simulations or by collecting more data for machine learning, improved variants can already be identified by sampling from a space predicted to be dense in higher fitness variants. Nevertheless, full datasets collected with higher throughput methods such as deep mutational scanning (36) serve as valuable test beds for validating the latest machinelearning algorithms for both regression (37,38) and design (39) that require more data.…”

Section: Discussionmentioning

confidence: 99%

Machine learning-assisted directed protein evolution with combinatorial libraries

Kan

Lewis

et al. 2019

Proc. Natl. Acad. Sci. U.S.A.

468

411

View full text Add to dashboard Cite

To reduce experimental effort associated with directed protein evolution and to explore the sequence space encoded by mutating multiple positions simultaneously, we incorporate machine learning into the directed evolution workflow. Combinatorial sequence space can be quite expensive to sample experimentally, but machine-learning models trained on tested variants provide a fast method for testing sequence space computationally. We validated this approach on a large published empirical fitness landscape for human GB1 binding protein, demonstrating that machine learning-guided directed evolution finds variants with higher fitness than those found by other directed evolution approaches. We then provide an example application in evolving an enzyme to produce each of the two possible product enantiomers (i.e., stereodivergence) of a new-to-nature carbene Si–H insertion reaction. The approach predicted libraries enriched in functional enzymes and fixed seven mutations in two rounds of evolution to identify variants for selective catalysis with 93% and 79% ee (enantiomeric excess). By greatly increasing throughput with in silico modeling, machine learning enhances the quality and diversity of sequence solutions for a protein engineering problem.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning-assisted directed protein evolution with combinatorial libraries

Kan

Lewis

et al. 2019

Proc. Natl. Acad. Sci. U.S.A.

468

411

View full text Add to dashboard Cite

show abstract

“…Schemes to embed biological sequences fall into several general categories, notably VAEs [75,76,47,77,78] and invertible generative models (e.g. Flows or real-NVPs) [79], as well as a plethora of increasingly promising models that have been adapted from natural language processing [80,8,48,81,82].…”

Section: Exploration On Compressed Representations Of Sequencesmentioning

confidence: 99%

A primer on model-guided exploration of fitness landscapes for biological sequence design

Sinai¹,

Kelsic²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning methods are increasingly employed to address challenges faced by biologists. One area that will greatly benefit from this cross-pollination is the problem of biological sequence design, which has massive potential for therapeutic applications. However, significant inefficiencies remain in communication between these fields which result in biologists finding the progress in machine learning inaccessible, and hinder machine learning scientists from contributing to impactful problems in bioengineering. Sequence design can be seen as a search process on a discrete, high-dimensional space, where each sequence is associated with a function. This sequence-to-function map is known as a "Fitness Landscape" [1,2]. Designing a sequence with a particular function is hence a matter of "discovering" such a (often rare) sequence within this space [3]. Today we can build predictive models with good interpolation ability due to impressive progress in the synthesis and testing of biological sequences in large numbers, which enables model training and validation. However, it often remains a challenge to find useful sequences with the properties that we like using these models. In particular, in this primer we highlight that algorithms for experimental design, what we call "exploration strategies", are a related, yet distinct problem from building good models of sequence-to-function maps. We review advances and insights from current literature -by no means a complete treatment-while highlighting desirable features of optimal model-guided exploration, and cover potential pitfalls drawn from our own experience. This primer can serve as a starting point for researchers from different domains that are interested in the problem of searching a sequence space with a model, but are perhaps unaware of approaches that originate outside their field.

show abstract

“…We thank Chris Sander, Frank Poelwijk, David Duvenaud, Sam Sinai, Eric Kelsic and members of the Marks lab for helpful comments and discussions. While in progress Sinai et al also reported on use of variational autoencoders for protein sequences [84]. A.J.R.…”

Section: Acknowledgementsmentioning

confidence: 99%

Deep generative models of genetic variation capture mutation effects

Marks

2017

Preprint

View full text Add to dashboard Cite

The functions of proteins and RNAs are determined by a myriad of interactions between their constituent residues, but most quantitative models of how molecular phenotype depends on genotype must approximate this by simple additive effects. While recent models have relaxed this constraint to also account for pairwise interactions, these approaches do not provide a tractable path towards modeling higher-order dependencies. Here, we show how latent variable models with nonlinear dependencies can be applied to capture beyond-pairwise constraints in biomolecules. We present a new probabilistic model for sequence families, DeepSequence, that can predict the effects of mutations across a variety of deep mutational scanning experiments significantly better than site independent or pairwise models that are based on the same evolutionary data. The model, learned in an unsupervised manner solely from sequence information, is grounded with biologically motivated priors, reveals latent organization of sequence families, and can be used to extrapolate to new parts of sequence space.

show abstract

Variational auto-encoding of protein sequences

Cited by 19 publications

References 14 publications

Machine learning-assisted directed protein evolution with combinatorial libraries

Machine learning-assisted directed protein evolution with combinatorial libraries

A primer on model-guided exploration of fitness landscapes for biological sequence design

Deep generative models of genetic variation capture mutation effects

Contact Info

Product

Resources

About