Deep mutational learning predicts ACE2 binding and antibody escape to combinatorial mutations in the SARS-CoV-2 receptor-binding domain

The continual evolution of SARS-CoV-2 and the emergence of variants that show resistance to vaccines and neutralizing antibodies threaten to prolong the COVID-19 pandemic. Selection and emergence of SARS-CoV-2 variants are driven in part by mutations within the viral spike protein and in particular the ACE2 receptor-binding domain (RBD), a primary target site for neutralizing antibodies. Here, we develop deep mutational learning (DML), a machine-learning-guided protein engineering technology, which is used to investigate a massive sequence space of combinatorial mutations, representing billions of RBD variants, by accurately predicting their impact on ACE2 binding and antibody escape. A highly diverse landscape of possible SARS-CoV-2 variants is identified that could emerge from a multitude of evolutionary trajectories. DML may be used for predictive profiling on current and prospective variants, including highly mutated variants such as Omicron, thus guiding the development of therapeutic antibody treatments and vaccines for COVID-19.

SARS-CoV-2 reactive and neutralizing antibodies discovered by single-cell sequencing of plasma cells and mammalian display

Characterization of COVID-19 antibodies has largely focused on memory B cells; however, it is the antibody-secreting plasma cells that are directly responsible for the production of serum antibodies, which play a critical role in resolving SARS-CoV-2 infection. Little is known about the specificity of plasma cells, largely because plasma cells lack surface antibody expression, thereby complicating their screening. Here, we describe a technology pipeline that integrates single-cell antibody repertoire sequencing and mammalian display to interrogate the specificity of plasma cells from 16 convalescent patients. Single-cell sequencing allows us to profile antibody repertoire features and identify expanded clonal lineages. Mammalian display screening is used to reveal that 43 antibodies (of 132 candidates) derived from expanded plasma cell lineages are specific to SARS-CoV-2 antigens, including antibodies with high affinity to the SARS-CoV-2 receptor-binding domain (RBD) that exhibit potent neutralization and broad binding to the RBD of SARS-CoV-2 variants (of concern/interest).

De novo designed proteins neutralize lethal snake venom toxins

Snakebite envenoming remains a devastating and neglected tropical disease, claiming over 100,000 lives annually and causing severe complications and long-lasting disabilities for many more1,2. Three-finger toxins (3FTx) are highly toxic components of elapid snake venoms that can cause diverse pathologies, including severe tissue damage3 and inhibition of nicotinic acetylcholine receptors, resulting in life-threatening neurotoxicity4. At present, the only available treatments for snakebites consist of polyclonal antibodies derived from the plasma of immunized animals, which have high cost and limited efficacy against 3FTxs5-7. Here we used deep learning methods to de novo design proteins to bind short-chain and long-chain α-neurotoxins and cytotoxins from the 3FTx family. With limited experimental screening, we obtained protein designs with remarkable thermal stability, high binding affinity and near-atomic-level agreement with the computational models. The designed proteins effectively neutralized all three 3FTx subfamilies in vitro and protected mice from a lethal neurotoxin challenge. Such potent, stable and readily manufacturable toxin-neutralizing proteins could provide the basis for safer, cost-effective and widely accessible next-generation antivenom therapeutics. Beyond snakebite, our results highlight how computational design could help democratize therapeutic discovery, particularly in resource-limited settings, by substantially reducing costs and resource requirements for the development of therapies for neglected tropical diseases.

V-ToCs (Venom Toxin Clustering): A tool for the investigation of sequence and structure similarities in snake venom toxins

Recently, there has been a major push toward the development of next-generation treatments against snakebite envenoming. However, unlike current antivenoms that rely on animal-derived polyclonal antibodies, most of these novel approaches are reliant on an in-depth understanding of the over 2000 known snake venom toxins. Indeed, by identifying similarities (i.e., conserved epitopes) across these different toxins, it is possible to design cross-reactive treatments, such as broadly-neutralising antibodies, that target these similarities. Therefore, in this project, we built an automated pipeline that generates sequence and structural distance matrices and homology trees across all available snake venom toxin sequences and structures. To facilitate analysis, we also developed a user-friendly and high-throughput visualisation tool, coined "Venom TOxin CluStering" (V-ToCs). This tool allows researchers to easily investigate sequence and structure patterns in snake venom toxins for a wide array of purposes, such as elucidating toxin evolution, and will also hopefully help guide the discovery and development of increasingly broadly-neutralising antivenoms in the near future.

Post-assembly Plasmid Amplification for Increased Transformation Yields in E. coli and S. cerevisiae

Many biological disciplines rely upon the transformation of host cells with heterologous DNA to edit, engineer, or examine biological phenotypes. Transformation of model cell strains (Escherichia coli) under model conditions (electroporation of circular supercoiled plasmid DNA; typically pUC19) can achieve >1010 transformants/μg DNA. Yet outside of these conditions, e.g., work with relaxed plasmid DNA from in vitro assembly reactions (cloned DNA) or nonmodel organisms, the efficiency of transformation can drop by multiple orders of magnitude. Overcoming these inefficiencies requires cost- and time-intensive processes, such as generating large quantities of appropriately formatted input DNA or transforming many aliquots of cells in parallel. We sought to simplify the generation of large quantities of appropriately formatted input cloned DNA by using rolling circle amplification (RCA) and treatment with specific endonucleases to generate an efficiently transformable linear DNA product for in vivo circularization in host cells. We achieved an over 6500-fold increase in the yield of input DNA, and demonstrate that the use of a nicking endonuclease to generate homologous single-stranded ends increases the efficiency of E. coli chemical transformation compared to both linear DNA with double-stranded homologous ends and circular Golden-Gate assembly products. Meanwhile, the use of a restriction endonuclease to generate linear DNA with double-stranded homologous ends increases the efficiency of chemical and electrotransformation of Saccharomyces cerevisiae. Importantly, we also optimized the process such that both RCA and endonuclease treatment occur efficiently in the same buffer, streamlining the workflow and reducing product loss through purification steps. We expect that our approach could have utility beyond E. coli and S. cerevisiae and be applicable to areas such as directed evolution, genome engineering, and the manipulation of alternative organisms with even poorer transformation efficiencies.

De novo designed proteins neutralize lethal snake venom toxins

Snakebite envenoming remains a devastating and neglected tropical disease, claiming over 100,000 lives annually and causing severe complications and long-lasting disabilities for many more1,2. Three-finger toxins (3FTx) are highly toxic components of elapid snake venoms that can cause diverse pathologies, including severe tissue damage3 and inhibition of nicotinic acetylcholine receptors (nAChRs) resulting in life-threatening neurotoxicity4. Currently, the only available treatments for snakebite consist of polyclonal antibodies derived from the plasma of immunized animals, which have high cost and limited efficacy against 3FTxs5,6,7. Here, we use deep learning methods to de novo design proteins to bind short- and long-chain α-neurotoxins and cytotoxins from the 3FTx family. With limited experimental screening, we obtain protein designs with remarkable thermal stability, high binding affinity, and near-atomic level agreement with the computational models. The designed proteins effectively neutralize all three 3FTx sub-families in vitro and protect mice from a lethal neurotoxin challenge. Such potent, stable, and readily manufacturable toxin-neutralizing proteins could provide the basis for safer, cost-effective, and widely accessible next-generation antivenom therapeutics. Beyond snakebite, our computational design methodology should help democratize therapeutic discovery, particularly in resource-limited settings, by substantially reducing costs and resource requirements for development of therapies to neglected tropical diseases.