Accurate top protein variant discovery via low-N pick-and-validate machine learning.

A strategy to obtain the greatest number of best-performing variants with least amount of experimental effort over the vast combinatorial mutational landscape would have enormous utility in boosting resource producibility for protein engineering. Toward this goal, we present a simple and effective machine learning-based strategy that outperforms other state-of-the-art methods. Our strategy integrates zero-shot prediction and multi-round sampling to direct active learning via experimenting with only a few predicted top variants. We find that four rounds of low-N pick-and-validate sampling of 12 variants for machine learning yielded the best accuracy of up to 92.6% in selecting the true top 1% variants in combinatorial mutant libraries, whereas two rounds of 24 variants can also be used. We demonstrate our strategy in successfully discovering high-performance protein variants from diverse families including the CRISPR-based genome editors, supporting its generalizable application for solving protein engineering tasks. A record of this paper's transparent peer review process is included in the supplemental information.

High-throughput screening of genetic and cellular drivers of syncytium formation induced by the spike protein of SARS-CoV-2.

Mapping mutations and discovering cellular determinants that cause the spike protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) to induce infected cells to form syncytia would facilitate the development of strategies for blocking the formation of such cell-cell fusion. Here we describe high-throughput screening methods based on droplet microfluidics and the size-exclusion selection of syncytia, coupled with large-scale mutagenesis and genome-wide knockout screening via clustered regularly interspaced short palindromic repeats (CRISPR), for the large-scale identification of determinants of cell-cell fusion. We used the methods to perform deep mutational scans in spike-presenting cells to pinpoint mutable syncytium-enhancing substitutions in two regions of the spike protein (the fusion peptide proximal region and the furin-cleavage site). We also used a genome-wide CRISPR screen in cells expressing the receptor angiotensin-converting enzyme 2 to identify inhibitors of clathrin-mediated endocytosis that impede syncytium formation, which we validated in hamsters infected with SARS-CoV-2. Finding genetic and cellular determinants of the formation of syncytia may reveal insights into the physiological and pathological consequences of cell-cell fusion.

Parallel engineering and activity profiling of a base editor system.

Selecting the most suitable existing base editors and engineering new variants for installing specific base conversions with maximal efficiency and minimal undesired edits are pivotal for precise genome editing applications. Here, we present a platform for creating and analyzing a library of engineered base editor variants to enable head-to-head evaluation of their editing performance at scale. Our comprehensive comparison provides quantitative measures on each variant's editing efficiency, purity, motif preference, and bias in generating single and multiple base conversions, while uncovering undesired higher indel generation rate and noncanonical base conversion for some of the existing base editors. In addition to engineering the base editor protein, we further applied this platform to investigate a hitherto underexplored engineering route and created guide RNA scaffold variants that augment the editor's base-editing activity. With the unknown performance and compatibility of the growing number of engineered parts including deaminase, CRISPR-Cas enzyme, and guide RNA scaffold variants for assembling the expanding collection of base editor systems, our platform addresses the unmet need for an unbiased, scalable method to benchmark their editing outcomes and accelerate the engineering of next-generation precise genome editors.

Machine learning-coupled combinatorial mutagenesis enables resource-efficient engineering of CRISPR-Cas9 genome editor activities.

The genome-editing Cas9 protein uses multiple amino-acid residues to bind the target DNA. Considering only the residues in proximity to the target DNA as potential sites to optimise Cas9's activity, the number of combinatorial variants to screen through is too massive for a wet-lab experiment. Here we generate and cross-validate ten in silico and experimental datasets of multi-domain combinatorial mutagenesis libraries for Cas9 engineering, and demonstrate that a machine learning-coupled engineering approach reduces the experimental screening burden by as high as 95% while enriching top-performing variants by ∼7.5-fold in comparison to the null model. Using this approach and followed by structure-guided engineering, we identify the N888R/A889Q variant conferring increased editing activity on the protospacer adjacent motif-relaxed KKH variant of Cas9 nuclease from Staphylococcus aureus (KKH-SaCas9) and its derived base editor in human cells. Our work validates a readily applicable workflow to enable resource-efficient high-throughput engineering of genome editor's activity.

High-fidelity KKH variant of Staphylococcus aureus Cas9 nucleases with improved base mismatch discrimination.

The Cas9 nuclease from Staphylococcus aureus (SaCas9) holds great potential for use in gene therapy, and variants with increased fidelity have been engineered. However, we find that existing variants have not reached the greatest accuracy to discriminate base mismatches and exhibited much reduced activity when their mutations were grafted onto the KKH mutant of SaCas9 for editing an expanded set of DNA targets. We performed structure-guided combinatorial mutagenesis to re-engineer KKH-SaCas9 with enhanced accuracy. We uncover that introducing a Y239H mutation on KKH-SaCas9's REC domain substantially reduces off-target edits while retaining high on-target activity when added to a set of mutations on REC and RuvC domains that lessen its interactions with the target DNA strand. The Y239H mutation is modelled to have removed an interaction from the REC domain with the guide RNA backbone in the guide RNA-DNA heteroduplex structure. We further confirmed the greatly improved genome-wide editing accuracy and single-base mismatch discrimination of our engineered variants, named KKH-SaCas9-SAV1 and SAV2, in human cells. In addition to generating broadly useful KKH-SaCas9 variants with unprecedented accuracy, our findings demonstrate the feasibility for multi-domain combinatorial mutagenesis on SaCas9's DNA- and guide RNA- interacting residues to optimize its editing fidelity.

A Combinatorial CRISPR-Cas9 Screen Identifies Ifenprodil as an Adjunct to Sorafenib for Liver Cancer Treatment.

Systematic testing of existing drugs and their combinations is an attractive strategy to exploit approved drugs for repurposing and identifying the best actionable treatment options. To expedite the search among many possible drug combinations, we designed a combinatorial CRISPR-Cas9 screen to inhibit druggable targets. Coblockade of the N-methyl-d-aspartate receptor (NMDAR) with targets of first-line kinase inhibitors reduced hepatocellular carcinoma (HCC) cell growth. Clinically, HCC patients with low NMDAR1 expression showed better survival. The clinically approved NMDAR antagonist ifenprodil synergized with sorafenib to induce the unfolded protein response, trigger cell-cycle arrest, downregulate genes associated with WNT signaling and stemness, and reduce self-renewal ability of HCC cells. In multiple HCC patient-derived organoids and human tumor xenograft models, the drug combination, but neither single drug alone, markedly reduced tumor-initiating cancer cell frequency. Because ifenprodil has an established safety history for its use as a vasodilator in humans, our findings support the repurposing of this drug as an adjunct for HCC treatment to improve clinical outcome and reduce tumor recurrence. These results also validate an approach for readily discovering actionable combinations for cancer therapy. SIGNIFICANCE: Combinatorial CRISPR-Cas9 screening identifies actionable targets for HCC therapy, uncovering the potential of combining the clinically approved drugs ifenprodil and sorafenib as a new effective treatment regimen.

Facilitating Machine Learning-Guided Protein Engineering with Smart Library Design and Massively Parallel Assays.

Protein design plays an important role in recent medical advances from antibody therapy to vaccine design. Typically, exhaustive mutational screens or directed evolution experiments are used for the identification of the best design or for improvements to the wild-type variant. Even with a high-throughput screening on pooled libraries and Next-Generation Sequencing to boost the scale of read-outs, surveying all the variants with combinatorial mutations for their empirical fitness scores is still of magnitudes beyond the capacity of existing experimental settings. To tackle this challenge, in-silico approaches using machine learning to predict the fitness of novel variants based on a subset of empirical measurements are now employed. These machine learning models turn out to be useful in many cases, with the premise that the experimentally determined fitness scores and the amino-acid descriptors of the models are informative. The machine learning models can guide the search for the highest fitness variants, resolve complex epistatic relationships, and highlight bio-physical rules for protein folding. Using machine learning-guided approaches, researchers can build more focused libraries, thus relieving themselves from labor-intensive screens and fast-tracking the optimization process. Here, we describe the current advances in massive-scale variant screens, and how machine learning and mutagenesis strategies can be integrated to accelerate protein engineering. More specifically, we examine strategies to make screens more economical, informative, and effective in discovery of useful variants.

Publisher Correction: Combinatorial mutagenesis en masse optimizes the genome editing activities of SpCas9.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Combinatorial mutagenesis en masse optimizes the genome editing activities of SpCas9.

The combined effect of multiple mutations on protein function is hard to predict; thus, the ability to functionally assess a vast number of protein sequence variants would be practically useful for protein engineering. Here we present a high-throughput platform that enables scalable assembly and parallel characterization of barcoded protein variants with combinatorial modifications. We demonstrate this platform, which we name CombiSEAL, by systematically characterizing a library of 948 combination mutants of the widely used Streptococcus pyogenes Cas9 (SpCas9) nuclease to optimize its genome-editing activity in human cells. The ease with which the editing activities of the pool of SpCas9 variants can be assessed at multiple on- and off-target sites accelerates the identification of optimized variants and facilitates the study of mutational epistasis. We successfully identify Opti-SpCas9, which possesses enhanced editing specificity without sacrificing potency and broad targeting range. This platform is broadly applicable for engineering proteins through combinatorial modifications en masse.

Assessing the benefits of horizontal gene transfer by laboratory evolution and genome sequencing.

BACKGROUND: Recombination is widespread across the tree of life, because it helps purge deleterious mutations and creates novel adaptive traits. In prokaryotes, it often takes the form of horizontal gene transfer from a donor to a recipient bacterium. While such transfer is widespread in natural communities, its immediate fitness benefits are usually unknown. We asked whether any such benefits depend on the environment, and on the identity of donor and recipient strains. To this end, we adapted Escherichia coli to two novel carbon sources over several hundred generations of laboratory evolution, exposing evolving populations to various DNA donors. RESULTS: At the end of these experiments, we measured fitness and sequenced the genomes of 65 clones from 34 replicate populations to study the genetic changes associated with adaptive evolution. Furthermore, we identified candidate de novo beneficial mutations. During adaptive evolution on the first carbon source, 4-Hydroxyphenylacetic acid (HPA), recombining populations adapted better, which was likely mediated by acquiring the hpa operon from the donor. In contrast, recombining populations did not adapt better to the second carbon source, butyric acid, even though they suffered fewer extinctions than non-recombining populations. The amount of DNA transferred, but not its benefit, strongly depended on the donor-recipient strain combination. CONCLUSIONS: To our knowledge, our study is the first to investigate the genomic consequences of prokaryotic recombination and horizontal gene transfer during laboratory evolution. It shows that the benefits of recombination strongly depend on the environment and the foreign DNA donor.

From hormones to secondary metabolism: the emergence of metabolic gene clusters in plants.

Gene clusters for the synthesis of secondary metabolites are a common feature of microbial genomes. Well-known examples include clusters for the synthesis of antibiotics in actinomycetes, and also for the synthesis of antibiotics and toxins in filamentous fungi. Until recently it was thought that genes for plant metabolic pathways were not clustered, and this is certainly true in many cases; however, five plant secondary metabolic gene clusters have now been discovered, all of them implicated in synthesis of defence compounds. An obvious assumption might be that these eukaryotic gene clusters have arisen by horizontal gene transfer from microbes, but there is compelling evidence to indicate that this is not the case. This raises intriguing questions about how widespread such clusters are, what the significance of clustering is, why genes for some metabolic pathways are clustered and those for others are not, and how these clusters form. In answering these questions we may hope to learn more about mechanisms of genome plasticity and adaptive evolution in plants. It is noteworthy that for the five plant secondary metabolic gene clusters reported so far, the enzymes for the first committed steps all appear to have been recruited directly or indirectly from primary metabolic pathways involved in hormone synthesis. This may or may not turn out to be a common feature of plant secondary metabolic gene clusters as new clusters emerge.