Machine learning to navigate fitness landscapes for protein engineering

Freschlin, Chase R; Fahlberg, Sarah A; Romero, Philip A.

doi:10.1016/j.copbio.2022.102713

Cited by 61 publications

(51 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Effectively exploring rough (i.e., not smooth) landscapes with limited experimental throughput is a challenge for DE [9–11]. Thankfully, the confluence of advancements in DNA synthesis (bespoke oligonucleotide sequences), DNA sequencing (high throughput screens), and machine learning have enabled a new paradigm of machine learning guided directed evolution (MLDE) [12–15] which can address the challenge of exploring rough landscapes with limited data. In each round of MLDE, a set of (variant, activity) pairs are collected, which a practitioner can use to train a genotype-phenotype model to predict the effect of variants.…”

Section: Introductionmentioning

confidence: 99%

Tuned Fitness Landscapes for Benchmarking Model-Guided Protein Design

Thomas

Agarwala

Belanger

et al. 2022

Preprint

View full text Add to dashboard Cite

Advancements in DNA synthesis and sequencing technologies have enabled a novel paradigm of protein design where machine learning (ML) models trained on experimental data are used to guide exploration of a protein fitness landscape. ML-guided directed evolution (MLDE) builds on the success of traditional directed evolution and unlocks strategies which make more efficient use of experimental data. Building an MLDE pipeline involves many design choices across the design-build-test-learn loop ranging from data collection strategies to modeling, each of which has a large impact on the success of designed sequences. The cost of collecting experimental data makes benchmarking every component of these pipelines on real data prohibitively difficult, necessitating the development of synthetic landscapes where MLDE strategies can be tested. In this work, we develop a framework called SLIP (Synthetic Landscape Inference for Proteins) for constructing biologically-motivated synthetic landscapes with tunable difficulty based on Potts models. This framework can be extended to any protein family for which there is a sequence alignment. We show that without tuning, Potts models are easy to optimize. In contrast, our tuning framework provides landscapes sufficiently challenging to benchmark MLDE pipelines. SLIP is open-source and is available at https://github.com/google-research/slip.

show abstract

Section: Introductionmentioning

confidence: 99%

Tuned Fitness Landscapes for Benchmarking Model-Guided Protein Design

Thomas

Agarwala

Belanger

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, deep representation learning has emerged as an effective method for protein featurization. This approach, which generates a representation of a given sequence, is based on information extracted from the known protein sequence universe ( So and Karplus, 1996a ; Biswas et al, 2021 ; Garruss et al, 2021 ; Freschlin et al, 2022 ; Alley et al, 2019 ). In contrast, our approach is based on features derived from structural and physicochemical properties of amino acids.…”

Section: Resultsmentioning

confidence: 99%

Deep mutational scanning and machine learning reveal structural and molecular rules governing allosteric hotspots in homologous proteins

Leander

Liu

Cui

et al. 2022

eLife

View full text Add to dashboard Cite

A fundamental question in protein science is where allosteric hotspots - residues critical for allosteric signaling - are located, and what properties differentiate them. We carried out deep mutational scanning (DMS) of four homologous bacterial allosteric transcription factors (aTF) to identify hotspots and built a machine learning model with this data to glean the structural and molecular properties of allosteric hotspots. We found hotspots to be distributed protein-wide rather than being restricted to 'pathways' linking allosteric and active sites as is commonly assumed. Despite structural homology, the location of hotspots was not superimposable across the aTFs. However, common signatures emerged when comparing hotspots coincident with long-range interactions, suggesting that the allosteric mechanism is conserved among the homologs despite differences in molecular details. Machine learning with our large DMS datasets revealed that global structural and dynamic properties to be a strong predictor of whether a residue is a hotspot than local and physicochemical properties. Furthermore, a model trained on one protein can predict hotspots in a homolog. In summary, the overall allosteric mechanism is embedded in the structural fold of the aTF family, but the finer, molecular details are sequence-specific.

show abstract

“…In recent years, deep representation learning has emerged as an effective method for protein featurization. This approach, which generates a representation of a given sequence, is based on information extracted from the known protein sequence universe (50,(55)(56)(57)(58). In contrast, our approach is based on features derived from structural and physicochemical properties of amino acids.…”

Section: Comparison With Sequence-based Featurizationmentioning

confidence: 99%

Deep mutational scanning and machine learning reveal structural and molecular rules governing allosteric hotspots in homologous proteins

Leander

Liu

Cui

et al. 2022

Preprint

View full text Add to dashboard Cite

A fundamental question in protein science is where allosteric hotspots – residues critical for allosteric signaling – are located, and what properties differentiate them. We carried out deep mutational scanning (DMS) of four homologous bacterial allosteric transcription factors (aTF) to identify hotspots and built a machine learning model with this data to glean the structural and molecular properties of allosteric hotspots. We found hotspots to be distributed protein-wide rather than being restricted to “pathways” linking allosteric and active sites as is commonly assumed. Despite structural homology, the location of hotspots was not superimposable across the aTFs. However, common signatures emerged when comparing hotspots coincident with long-range interactions, suggesting that the allosteric mechanism is conserved among the homologs despite differences in molecular details. Machine learning with our large DMS datasets revealed that global structural and dynamic properties to be a strong predictor of whether a residue is a hotspot than local and physicochemical properties. Furthermore, a model trained on one protein can predict hotspots in a homolog. In summary, the overall allosteric mechanism is embedded in the structural fold of the aTF family, but the finer, molecular details are sequence-specific.

show abstract

Machine learning to navigate fitness landscapes for protein engineering

Cited by 61 publications

References 40 publications

Tuned Fitness Landscapes for Benchmarking Model-Guided Protein Design

Tuned Fitness Landscapes for Benchmarking Model-Guided Protein Design

Deep mutational scanning and machine learning reveal structural and molecular rules governing allosteric hotspots in homologous proteins

Deep mutational scanning and machine learning reveal structural and molecular rules governing allosteric hotspots in homologous proteins

Contact Info

Product

Resources

About