Generative models for protein sequence modeling: recent advances and future directions.

The widespread adoption of high-throughput omics technologies has exponentially increased the amount of protein sequence data involved in many salient disease pathways and their respective therapeutics and diagnostics. Despite the availability of large-scale sequence data, the lack of experimental fitness annotations underpins the need for self-supervised and unsupervised machine learning (ML) methods. These techniques leverage the meaningful features encoded in abundant unlabeled sequences to accomplish complex protein engineering tasks. Proficiency in the rapidly evolving fields of protein engineering and generative AI is required to realize the full potential of ML models as a tool for protein fitness landscape navigation. Here, we support this work by (i) providing an overview of the architecture and mathematical details of the most successful ML models applicable to sequence data (e.g. variational autoencoders, autoregressive models, generative adversarial neural networks, and diffusion models), (ii) guiding how to effectively implement these models on protein sequence data to predict fitness or generate high-fitness sequences and (iii) highlighting several successful studies that implement these techniques in protein engineering (from paratope regions and subcellular localization prediction to high-fitness sequences and protein design rules generation). By providing a comprehensive survey of model details, novel architecture developments, comparisons of model applications, and current challenges, this study intends to provide structured guidance and robust framework for delivering a prospective outlook in the ML-driven protein engineering field.

Single-Cell B-Cell Sequencing to Generate Natively Paired scFab Yeast Surface Display Libraries.

The immune cell profiling capabilities of single-cell RNA sequencing (scRNA-seq) are powerful tools that can be applied to the design of theranostic monoclonal antibodies (mAbs). Using scRNA-seq to determine natively paired B-cell receptor (BCR) sequences of immunized mice as a starting point for design, this method outlines a simplified workflow to express single-chain antibody fragments (scFabs) on the surface of yeast for high-throughput characterization and further refinement with directed evolution experiments. While not extensively detailed in this chapter, this method easily accommodates the implementation of a growing body of in silico tools that improve affinity and stability among a range of other developability criteria (e.g., solubility and immunogenicity).

Erratum: Engineering Extracellular Vesicles to Target Pancreatic Tissue In Vivo: Erratum.

[This corrects the article DOI: 10.7150/ntno.54879.].

Engineering Extracellular Vesicles to Target Pancreatic Tissue In Vivo.

Extracellular vesicles (EVs) are naturally released, cell-derived vesicles that mediate intracellular communication, in part, by transferring genetic information and, thus, have the potential to be modified for use as a therapeutic gene or drug delivery vehicle. Advances in EV engineering suggest that directed delivery can be accomplished via surface alterations. Here we assess enriched delivery of engineered EVs displaying an organ targeting peptide specific to the pancreas. We first characterized the size, morphology, and surface markers of engineered EVs that were decorated with a recombinant protein specific to pancreatic ß-cells. This ß-cell-specific recombinant protein consists of the peptide p88 fused to the EV-binding domain of lactadherin (C1C2). These engineered EVs, p88-EVs, specifically bound to pancreatic ß-cells in culture and transferred encapsulated plasmid DNA (pDNA) as early as in 10 min suggesting that the internalization of peptide-bearing EVs is a rapid process. Biodistribution of p88-EVs administrated intravenously into mice showed an altered pattern of EV localization and improved DNA delivery to the pancreas relative to control EVs, as well as an accumulation of targeting EVs to the pancreas using luciferase activity as a readout. These findings demonstrate that systemic administration of engineered EVs can efficiently deliver their cargo as gene carriers to targeted organs in live animals.