Inferring protein fitness landscapes from laboratory evolution experiments.

Directed laboratory evolution applies iterative rounds of mutation and selection to explore the protein fitness landscape and provides rich information regarding the underlying relationships between protein sequence, structure, and function. Laboratory evolution data consist of protein sequences sampled from evolving populations over multiple generations and this data type does not fit into established supervised and unsupervised machine learning approaches. We develop a statistical learning framework that models the evolutionary process and can infer the protein fitness landscape from multiple snapshots along an evolutionary trajectory. We apply our modeling approach to dihydrofolate reductase (DHFR) laboratory evolution data and the resulting landscape parameters capture important aspects of DHFR structure and function. We use the resulting model to understand the structure of the fitness landscape and find numerous examples of epistasis but an overall global peak that is evolutionarily accessible from most starting sequences. Finally, we use the model to perform an in silico extrapolation of the DHFR laboratory evolution trajectory and computationally design proteins from future evolutionary rounds.

Neural networks to learn protein sequence-function relationships from deep mutational scanning data.

The mapping from protein sequence to function is highly complex, making it challenging to predict how sequence changes will affect a protein's behavior and properties. We present a supervised deep learning framework to learn the sequence-function mapping from deep mutational scanning data and make predictions for new, uncharacterized sequence variants. We test multiple neural network architectures, including a graph convolutional network that incorporates protein structure, to explore how a network's internal representation affects its ability to learn the sequence-function mapping. Our supervised learning approach displays superior performance over physics-based and unsupervised prediction methods. We find that networks that capture nonlinear interactions and share parameters across sequence positions are important for learning the relationship between sequence and function. Further analysis of the trained models reveals the networks' ability to learn biologically meaningful information about protein structure and mechanism. Finally, we demonstrate the models' ability to navigate sequence space and design new proteins beyond the training set. We applied the protein G B1 domain (GB1) models to design a sequence that binds to immunoglobulin G with substantially higher affinity than wild-type GB1.

Single-cell nucleic acid profiling in droplets (SNAPD) enables high-throughput analysis of heterogeneous cell populations.

Experimental methods that capture the individual properties of single cells are revealing the key role of cell-to-cell variability in countless biological processes. These single-cell methods are becoming increasingly important across the life sciences in fields such as immunology, regenerative medicine and cancer biology. In addition to high-dimensional transcriptomic techniques such as single-cell RNA sequencing, there is a need for fast, simple and high-throughput assays to enumerate cell samples based on RNA biomarkers. In this work, we present single-cell nucleic acid profiling in droplets (SNAPD) to analyze sets of transcriptional markers in tens of thousands of single mammalian cells. Individual cells are encapsulated in aqueous droplets on a microfluidic chip and the RNA markers in each cell are amplified. Molecular logic circuits then integrate these amplicons to categorize cells based on the transcriptional markers and produce a detectable fluorescence output. SNAPD is capable of analyzing over 100,000 cells per hour and can be used to quantify distinct cell types within heterogeneous populations, detect rare cells at frequencies down to 0.1% and enrich specific cell types using microfluidic sorting. SNAPD provides a simple, rapid, low cost and scalable approach to study complex phenotypes in heterogeneous cell populations.

Active and machine learning-based approaches to rapidly enhance microbial chemical production.

In order to make renewable fuels and chemicals from microbes, new methods are required to engineer microbes more intelligently. Computational approaches, to engineer strains for enhanced chemical production typically rely on detailed mechanistic models (e.g., kinetic/stoichiometric models of metabolism)-requiring many experimental datasets for their parameterization-while experimental methods may require screening large mutant libraries to explore the design space for the few mutants with desired behaviors. To address these limitations, we developed an active and machine learning approach (ActiveOpt) to intelligently guide experiments to arrive at an optimal phenotype with minimal measured datasets. ActiveOpt was applied to two separate case studies to evaluate its potential to increase valine yields and neurosporene productivity in Escherichia coli. In both the cases, ActiveOpt identified the best performing strain in fewer experiments than the case studies used. This work demonstrates that machine and active learning approaches have the potential to greatly facilitate metabolic engineering efforts to rapidly achieve its objectives.

Exploring protein fitness landscapes by directed evolution.

Directed evolution circumvents our profound ignorance of how a protein's sequence encodes its function by using iterative rounds of random mutation and artificial selection to discover new and useful proteins. Proteins can be tuned to adapt to new functions or environments by simple adaptive walks involving small numbers of mutations. Directed evolution studies have shown how rapidly some proteins can evolve under strong selection pressures and, because the entire 'fossil record' of evolutionary intermediates is available for detailed study, they have provided new insight into the relationship between sequence and function. Directed evolution has also shown how mutations that are functionally neutral can set the stage for further adaptation.

In Vivo Selection of a Computationally Designed SCHEMA AAV Library Yields a Novel Variant for Infection of Adult Neural Stem Cells in the SVZ.

Directed evolution continues to expand the capabilities of complex biomolecules for a range of applications, such as adeno-associated virus vectors for gene therapy; however, advances in library design and selection strategies are key to develop variants that overcome barriers to clinical translation. To address this need, we applied structure-guided SCHEMA recombination of the multimeric adeno-associated virus (AAV) capsid to generate a highly diversified chimeric library with minimal structural disruption. A stringent in vivo Cre-dependent selection strategy was implemented to identify variants that transduce adult neural stem cells (NSCs) in the subventricular zone. A novel variant, SCH9, infected 60% of NSCs and mediated 24-fold higher GFP expression and a 12-fold greater transduction volume than AAV9. SCH9 utilizes both galactose and heparan sulfate as cell surface receptors and exhibits increased resistance to neutralizing antibodies. These results establish the SCHEMA library as a valuable tool for directed evolution and SCH9 as an effective gene delivery vector to investigate subventricular NSCs.

Dissecting enzyme function with microfluidic-based deep mutational scanning.

Natural enzymes are incredibly proficient catalysts, but engineering them to have new or improved functions is challenging due to the complexity of how an enzyme's sequence relates to its biochemical properties. Here, we present an ultrahigh-throughput method for mapping enzyme sequence-function relationships that combines droplet microfluidic screening with next-generation DNA sequencing. We apply our method to map the activity of millions of glycosidase sequence variants. Microfluidic-based deep mutational scanning provides a comprehensive and unbiased view of the enzyme function landscape. The mapping displays expected patterns of mutational tolerance and a strong correspondence to sequence variation within the enzyme family, but also reveals previously unreported sites that are crucial for glycosidase function. We modified the screening protocol to include a high-temperature incubation step, and the resulting thermotolerance landscape allowed the discovery of mutations that enhance enzyme thermostability. Droplet microfluidics provides a general platform for enzyme screening that, when combined with DNA-sequencing technologies, enables high-throughput mapping of enzyme sequence space.

Navigating the protein fitness landscape with Gaussian processes.

Knowing how protein sequence maps to function (the "fitness landscape") is critical for understanding protein evolution as well as for engineering proteins with new and useful properties. We demonstrate that the protein fitness landscape can be inferred from experimental data, using Gaussian processes, a Bayesian learning technique. Gaussian process landscapes can model various protein sequence properties, including functional status, thermostability, enzyme activity, and ligand binding affinity. Trained on experimental data, these models achieve unrivaled quantitative accuracy. Furthermore, the explicit representation of model uncertainty allows for efficient searches through the vast space of possible sequences. We develop and test two protein sequence design algorithms motivated by Bayesian decision theory. The first one identifies small sets of sequences that are informative about the landscape; the second one identifies optimized sequences by iteratively improving the Gaussian process model in regions of the landscape that are predicted to be optimized. We demonstrate the ability of Gaussian processes to guide the search through protein sequence space by designing, constructing, and testing chimeric cytochrome P450s. These algorithms allowed us to engineer active P450 enzymes that are more thermostable than any previously made by chimeragenesis, rational design, or directed evolution.

Self-driving laboratories to autonomously navigate the protein fitness landscape.

Protein engineering has nearly limitless applications across chemistry, energy and medicine, but creating new proteins with improved or novel functions remains slow, labor-intensive and inefficient. Here we present the Self-driving Autonomous Machines for Protein Landscape Exploration (SAMPLE) platform for fully autonomous protein engineering. SAMPLE is driven by an intelligent agent that learns protein sequence-function relationships, designs new proteins and sends designs to a fully automated robotic system that experimentally tests the designed proteins and provides feedback to improve the agent's understanding of the system. We deploy four SAMPLE agents with the goal of engineering glycoside hydrolase enzymes with enhanced thermal tolerance. Despite showing individual differences in their search behavior, all four agents quickly converge on thermostable enzymes. Self-driving laboratories automate and accelerate the scientific discovery process and hold great potential for the fields of protein engineering and synthetic biology.

Neural network extrapolation to distant regions of the protein fitness landscape.

Machine learning (ML) has transformed protein engineering by constructing models of the underlying sequence-function landscape to accelerate the discovery of new biomolecules. ML-guided protein design requires models, trained on local sequence-function information, to accurately predict distant fitness peaks. In this work, we evaluate neural networks' capacity to extrapolate beyond their training data. We perform model-guided design using a panel of neural network architectures trained on protein G (GB1)-Immunoglobulin G (IgG) binding data and experimentally test thousands of GB1 designs to systematically evaluate the models' extrapolation. We find each model architecture infers markedly different landscapes from the same data, which give rise to unique design preferences. We find simpler models excel in local extrapolation to design high fitness proteins, while more sophisticated convolutional models can venture deep into sequence space to design proteins that fold but are no longer functional. We also find that implementing a simple ensemble of convolutional neural networks enables robust design of high-performing variants in the local landscape. Our findings highlight how each architecture's inductive biases prime them to learn different aspects of the protein fitness landscape and how a simple ensembling approach makes protein engineering more robust.

Biophysics-based protein language models for protein engineering.

Protein language models trained on evolutionary data have emerged as powerful tools for predictive problems involving protein sequence, structure, and function. However, these models overlook decades of research into biophysical factors governing protein function. We propose Mutational Effect Transfer Learning (METL), a protein language model framework that unites advanced machine learning and biophysical modeling. Using the METL framework, we pretrain transformer-based neural networks on biophysical simulation data to capture fundamental relationships between protein sequence, structure, and energetics. We finetune METL on experimental sequence-function data to harness these biophysical signals and apply them when predicting protein properties like thermostability, catalytic activity, and fluorescence. METL excels in challenging protein engineering tasks like generalizing from small training sets and position extrapolation, although existing methods that train on evolutionary signals remain powerful for many types of experimental assays. We demonstrate METL's ability to design functional green fluorescent protein variants when trained on only 64 examples, showcasing the potential of biophysics-based protein language models for protein engineering.

Random field model reveals structure of the protein recombinational landscape.

We are interested in how intragenic recombination contributes to the evolution of proteins and how this mechanism complements and enhances the diversity generated by random mutation. Experiments have revealed that proteins are highly tolerant to recombination with homologous sequences (mutation by recombination is conservative); more surprisingly, they have also shown that homologous sequence fragments make largely additive contributions to biophysical properties such as stability. Here, we develop a random field model to describe the statistical features of the subset of protein space accessible by recombination, which we refer to as the recombinational landscape. This model shows quantitative agreement with experimental results compiled from eight libraries of proteins that were generated by recombining gene fragments from homologous proteins. The model reveals a recombinational landscape that is highly enriched in functional sequences, with properties dominated by a large-scale additive structure. It also quantifies the relative contributions of parent sequence identity, crossover locations, and protein fold to the tolerance of proteins to recombination. Intragenic recombination explores a unique subset of sequence space that promotes rapid molecular diversification and functional adaptation.

Directed evolution of angiotensin-converting enzyme 2 peptidase activity profiles for therapeutic applications.

Angiotensin-converting enzyme 2 (ACE2) has been investigated for its ability to beneficially modulate the angiotensin receptor (ATR) therapeutic axis to treat multiple human diseases. Its broad substrate scope and diverse physiological roles, however, limit its potential as a therapeutic agent. In this work, we address this limitation by establishing a yeast display-based liquid chromatography screen that enabled use of directed evolution to discover ACE2 variants that possess both wild-type or greater Ang-II hydrolytic activity and improved specificity toward Ang-II relative to the off-target peptide substrate Apelin-13. To obtain these results, we screened ACE2 active site libraries to reveal three substitution-tolerant positions (M360, T371, and Y510) that can be mutated to enhance ACE2's activity profile and followed up on these hits with focused double mutant libraries to further improve the enzyme. Relative to wild-type ACE2, our top variant (T371L/Y510Ile) displayed a sevenfold increase in Ang-II turnover number (kcat ), a sixfold diminished catalytic efficiency (kcat /Km ) on Apelin-13, and an overall decreased activity on other ACE2 substrates that were not directly assayed in the directed evolution screen. At physiologically relevant substrate concentrations, T371L/Y510Ile hydrolyzes as much or more Ang-II than wild-type ACE2 with concomitant Ang-II:Apelin-13 specificity improvements reaching 30-fold. Our efforts have delivered ATR axis-acting therapeutic candidates with relevance to both established and unexplored ACE2 therapeutic applications and provide a foundation for further ACE2 engineering efforts.

Neural network extrapolation to distant regions of the protein fitness landscape.

Machine learning (ML) has transformed protein engineering by constructing models of the underlying sequence-function landscape to accelerate the discovery of new biomolecules. ML-guided protein design requires models, trained on local sequence-function information, to accurately predict distant fitness peaks. In this work, we evaluate neural networks' capacity to extrapolate beyond their training data. We perform model-guided design using a panel of neural network architectures trained on protein G (GB1)-Immunoglobulin G (IgG) binding data and experimentally test thousands of GB1 designs to systematically evaluate the models' extrapolation. We find each model architecture infers markedly different landscapes from the same data, which give rise to unique design preferences. We find simpler models excel in local extrapolation to design high fitness proteins, while more sophisticated convolutional models can venture deep into sequence space to design proteins that fold but are no longer functional. Our findings highlight how each architecture's inductive biases prime them to learn different aspects of the protein fitness landscape.

Microfluidic deep mutational scanning of the human executioner caspases reveals differences in structure and regulation.

The human caspase family comprises 12 cysteine proteases that are centrally involved in cell death and inflammation responses. The members of this family have conserved sequences and structures, highly similar enzymatic activities and substrate preferences, and overlapping physiological roles. In this paper, we present a deep mutational scan of the executioner caspases CASP3 and CASP7 to dissect differences in their structure, function, and regulation. Our approach leverages high-throughput microfluidic screening to analyze hundreds of thousands of caspase variants in tightly controlled in vitro reactions. The resulting data provides a large-scale and unbiased view of the impact of amino acid substitutions on the proteolytic activity of CASP3 and CASP7. We use this data to pinpoint key functional differences between CASP3 and CASP7, including a secondary internal cleavage site, CASP7 Q196 that is not present in CASP3. Our results will open avenues for inquiry in caspase function and regulation that could potentially inform the development of future caspase-specific therapeutics.

Machine learning to navigate fitness landscapes for protein engineering.

Machine learning (ML) is revolutionizing our ability to understand and predict the complex relationships between protein sequence, structure, and function. Predictive sequence-function models are enabling protein engineers to efficiently search the sequence space for useful proteins with broad applications in biotechnology. In this review, we highlight the recent advances in applying ML to protein engineering. We discuss supervised learning methods that infer the sequence-function mapping from experimental data and new sequence representation strategies for data-efficient modeling. We then describe the various ways in which ML can be incorporated into protein engineering workflows, including purely in silico searches, ML-assisted directed evolution, and generative models that can learn the underlying distribution of the protein function in a sequence space. ML-driven protein engineering will become increasingly powerful with continued advances in high-throughput data generation, data science, and deep learning.

Competitive SNP-LAMP probes for rapid and robust single-nucleotide polymorphism detection.

In this work, we developed a simple and robust assay to rapidly detect SNPs in nucleic acid samples. Our approach combines loop-mediated isothermal amplification (LAMP)-based target amplification with fluorescent probes to detect SNPs with high specificity. A competitive "sink" strand preferentially binds to non-SNP amplicons and shifts the free energy landscape to favor specific activation by SNP products. We demonstrated the broad utility and reliability of our SNP-LAMP method by detecting three distinct SNPs across the human genome. We also designed an assay to rapidly detect highly transmissible severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants from crude biological samples. This work demonstrates that competitive SNP-LAMP is a powerful and universal method that could be applied in point-of-care settings to detect any target SNP with high specificity and sensitivity. We additionally developed a publicly available web application for researchers to design SNP-LAMP probes for any target sequence of interest.

Yeast surface display-based identification of ACE2 mutations that modulate SARS-CoV-2 spike binding across multiple mammalian species.

Understanding how SARS-CoV-2 interacts with different mammalian angiotensin-converting enzyme II (ACE2) cell entry receptors elucidates determinants of virus transmission and facilitates development of vaccines for humans and animals. Yeast display-based directed evolution identified conserved ACE2 mutations that increase spike binding across multiple species. Gln42Leu increased ACE2-spike binding for human and four of four other mammalian ACE2s; Leu79Ile had a effect for human and three of three mammalian ACE2s. These residues are highly represented, 83% for Gln42 and 56% for Leu79, among mammalian ACE2s. The above findings can be important in protecting humans and animals from existing and future SARS-CoV-2 variants.

Yeast surface display-based identification of ACE2 mutations that modulate SARS-CoV-2 spike binding across multiple mammalian species.

Understanding how severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) interacts with different mammalian angiotensin-converting enzyme II (ACE2) cell entry receptors elucidates determinants of virus transmission and facilitates development of vaccines for humans and animals. Yeast display-based directed evolution identified conserved ACE2 mutations that increase spike binding across multiple species. Gln42Leu increased ACE2-spike binding for human and four of four other mammalian ACE2s; Leu79Ile had an effect for human and three of three mammalian ACE2s. These residues are highly represented, 83% for Gln42 and 56% for Leu79, among mammalian ACE2s. The above findings can be important in protecting humans and animals from existing and future SARS-CoV-2 variants.

Discovery of human ACE2 variants with altered recognition by the SARS-CoV-2 spike protein.

Understanding how human ACE2 genetic variants differ in their recognition by SARS-CoV-2 can facilitate the leveraging of ACE2 as an axis for treating and preventing COVID-19. In this work, we experimentally interrogate thousands of ACE2 mutants to identify over one hundred human single-nucleotide variants (SNVs) that are likely to have altered recognition by the virus, and make the complementary discovery that ACE2 residues distant from the spike interface influence the ACE2-spike interaction. These findings illuminate new links between ACE2 sequence and spike recognition, and could find substantial utility in further fundamental research that augments epidemiological analyses and clinical trial design in the contexts of both existing strains of SARS-CoV-2 and novel variants that may arise in the future.