Deep learning for optimization of protein expression

Nikolados, Evangelos-Marios; Oyarzún, Diego A.

doi:10.1016/j.copbio.2023.102941

Cited by 10 publications

(10 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning architectures have demon-strated great predictive power across a range of sequence- to-expression tasks [19]. Convolutional neural networks (CNN), in particular, have been extensively employed to regress protein expres-sion, often achieving high performance [8, 9, 12, 13].…”

Section: Resultsmentioning

confidence: 99%

“…Several studies have embedded such models into algorithms for discovery of new variants using optimization methods [8] and techniques from generative models [14, 15, 16, 17]. Although the current literature has a strong focus on improvements to model architectures that can deliver greater predictive power [18], with the size of sequence- to-expression datasets growing into thousands up to millions of variants, it is becoming increasingly clear that off-the-shelf deep learning architectures such as convolutional neural networks, recurrent neural networks or transformers can readily provide high predictive accuracy [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving the generalization of protein expression models with mechanistic sequence information

Shen,

Kudla,

Oyarzún

2024

Preprint

View full text Add to dashboard Cite

The increasing demand for biological products drives many efforts to engineer cells that produce heterologous proteins at maximal yield. Recent advances in massively parallel reporter assays can deliver data suitable for training machine learning models and sup-port the design of microbial strains with optimized protein expression phenotypes. The best performing sequence- to-expression models have been trained on one-hot encodings, a mechanism-agnostic representation of nucleotide sequences. Despite their excellent local pre-dictive power, however, such models suffer from a limited ability to generalize predictions far away from the training data. Here, we show that libraries of genetic constructs can have substantially different cluster structure depending on the chosen sequence representation, and demonstrate that such differences can be leveraged to improve generalization perfor-mance. Using a large sequence- to-expression dataset fromEscherichia coli, we show that non-deep regressors and convolutional neural networks trained on one-hot encodings fail to generalize predictions, and that learned representations using state-of-the-art large language models also struggle with out-of-domain accuracy. In contrast, we show that despite their poorer local performance, mechanistic sequence features such as codon bias, nucleotide con-tent or mRNA stability, provide promising gains on model generalization. We explore several strategies to integrate different feature sets into a single predictive model, including feature stacking, ensemble model stacking, and geometric stacking, a novel architecture based on graph convolutional neural networks. Our work suggests that integration of domain-agnostic and domain-aware sequence features offers an unexplored route for improving the quality of sequence- to-expression models and facilitate their adoption in the biotechnology and phar-maceutical sectors.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving the generalization of protein expression models with mechanistic sequence information

Shen,

Kudla,

Oyarzún

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, most ML-based predictors represent primary protein sequences at the level of amino acids. However, synonymous mutations that do not change the amino acid sequence can still significantly impact protein expression and function , or can even relate to particular structural features. , Predictors working on the level of nucleotides or codons may thus be better tools for protein design and modification, particularly in areas such as prediction of expression, solubility, and aggregation. The fact that the 64-letter codon alphabet serves to encode richer information than the 20-letter amino acid alphabet can be directly exploited by ML models for improving performance on a wide range of tasks that are now being tackled at the protein sequence level .…”

Section: Major Gaps In the State Of The Artmentioning

confidence: 99%

Machine Learning-Guided Protein Engineering

Kouba,

Kohout,

Haddadi

et al. 2023

ACS Catal.

View full text Add to dashboard Cite

Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.

show abstract

“…Studies that have tackled the design of overlapping sequences, and their effects on transcriptional regulatory logic, often rely on ad hoc methods or generate a limited set of short sequences 26,[28][29][30] , thus restricting the generation of large libraries. Meanwhile, generative AI techniques are starting to show promise in emulating the complexity of contextdependent promoters [31][32][33][34][35][36][37] . However, these models often struggle with interpretability, and fine-tuning them to include or exclude specific binding sites still requires specialized expertise 38 .…”

Section: Introductionmentioning

confidence: 99%

Generating information-dense promoter sequences with optimal string packing

Andreani,

South,

Dunlop

2023

Preprint

View full text Add to dashboard Cite

Dense arrangements of binding sites within nucleotide sequences can collectively influence downstream transcription rates or initiate biomolecular interactions. For example, natural promoter regions can harbor many overlapping transcription factor binding sites that influence the rate of transcription initiation. Despite the prevalence of overlapping binding sites in nature, rapid design of nucleotide sequences with many overlapping sites remains a challenge. Here, we show that this is an NP-hard problem, coined here as the nucleotide String Packing Problem (SPP). We then introduce a computational technique that efficiently assembles sets of DNA-protein binding sites into dense, contiguous stretches of double-stranded DNA. For the efficient design of nucleotide sequences spanning hundreds of base pairs, we reduce the SPP to an Orienteering Problem with integer distances, and then leverage modern integer linear programming solvers. Our method optimally packs libraries of 20-100 binding sites into dense nucleotide arrays of 50-300 base pairs in 0.05-10 seconds. Unlike approximation algorithms or meta-heuristics, our approach finds provably optimal solutions. We demonstrate how our method can generate large sets of diverse sequences suitable for library generation, where the frequency of binding site usage across the returned sequences can be controlled by modulating the objective function. The nucleotide string packing approach we present can accelerate the design of sequences with complex DNA-protein interactions. When used in combination with synthesis and high-throughput screening, this design strategy can help interrogate how complex binding site arrangements impact either gene expression or biomolecular mechanisms in varied cellular contexts.

show abstract

Deep learning for optimization of protein expression

Cited by 10 publications

References 45 publications

Improving the generalization of protein expression models with mechanistic sequence information

Improving the generalization of protein expression models with mechanistic sequence information

Machine Learning-Guided Protein Engineering

Generating information-dense promoter sequences with optimal string packing

Contact Info

Product

Resources

About