Search

Engineered proteins have emerged as novel diagnostics, therapeutics, and catalysts. Often, poor protein developability – quantified by expression, solubility, and stability – hinders utility. The ability to predict protein developability from amino acid sequence would reduce the experimental burden when selecting candidates. Recent advances in screening technologies enabled a high-throughput developability dataset for 105of 1020possible variants of protein ligand scaffold Gp2. In this work, we evaluate the ability of neural networks to learn a developability representation from a high-throughput dataset and transfer this knowledge to predict recombinant expression beyond observed sequences. The model convolves learned amino acid properties to predict expression levels 44% closer to the experimental variance compared to a non-embedded control. Analysis of learned amino acid embeddings highlights the uniqueness of cysteine, the importance of hydrophobicity and charge, and the unimportance of aromaticity, when aiming to improve the developability of small proteins. We identify clusters of similar sequences with increased developability through nonlinear dimensionality reduction and we explore the inferred developability landscape via nested sampling. The analysis enables the first direct visualization of the fitness landscape and highlights the existence of evolutionary bottlenecks in sequence space giving rise to competing subpopulations of sequences with different developability. The work advances applied protein engineering efforts by predicting and interpreting protein scaffold developability from a limited dataset. Furthermore, our statistical mechanical treatment of the problem advances foundational efforts to characterize the structure of the protein fitness landscape and the amino acid characteristics that influence protein developability.Significance statementProtein developability prediction and understanding constitutes a critical limiting step in biologic discovery and engineering due to limited experimental throughput. We demonstrate the ability of a machine learning model to learn sequence-developability relationships first through the use of high-throughput assay data, followed by the transfer of the learned developability representation to predict the true metric of interest, recombinant yield in bacterial production. Model performance is 44% better than a model not pre-trained using the high-throughput assays. Analysis of model behavior reveals the importance of cysteine, charge, and hydrophobicity to developability, as well as of an evolutionary bottleneck that greatly limited sequence diversity above 1.3 mg/L yield. Experimental characterization of model predicted candidates confirms the benefit of this transfer learning and in-silico evolution approach.

[Image: see text] Evolving specific molecular recognition function of proteins requires strategic navigation of a complex mutational landscape. Protein scaffolds aid evolution via a conserved platform on which a modular paratope can be evolved to alter binding specificity. Although numerous protein scaffolds have been discovered, the underlying properties that permit binding evolution remain unknown. We present an algorithm to predict a protein scaffold’s ability to evolve novel binding function based upon computationally calculated biophysical parameters. The ability of 17 small proteins to evolve binding functionality across seven discovery campaigns was determined via magnetic activated cell sorting of 10(10) yeast-displayed protein variants. Twenty topological and biophysical properties were calculated for 787 small protein scaffolds and reduced into independent components. Regularization deduced which extracted features best predicted binding functionality, providing a 4/6 true positive rate, a 9/11 negative predictive value, and a 4/6 positive predictive value. Model analysis suggests a large, disconnected paratope will permit evolved binding function. Previous protein engineering endeavors have suggested that starting with a highly developable (high producibility, stability, solubility) protein will offer greater mutational tolerance. Our results support this connection between developability and evolvability by demonstrating a relationship between protein production in the soluble fraction of Escherichia coli and the ability to evolve binding function upon mutation. We further explain the necessity for initial developability by observing a decrease in proteolytic stability of protein mutants that possess binding functionality over nonfunctional mutants. Future iterations of protein scaffold discovery and evolution will benefit from a combination of computational prediction and knowledge of initial developability properties.

Developing potent antimicrobials, and platforms for their study and engineering, is critical as antibiotic resistance grows. A high-throughput method to quantify antimicrobial peptide and protein (AMP) activity across a broad continuum would be powerful to elucidate sequence-activity landscapes and identify potent mutants. Yet the complexity of antimicrobial activity has largely constrained the scope and mechanistic bandwidth of AMP variant analysis. We developed a platform to efficiently perform sequence-activity mapping of AMPs via depletion (SAMP-Dep): a bacterial host culture is transformed with an AMP mutant library, induced to intracellularly express AMPs, grown under selective pressure, and deep sequenced to quantify mutant depletion. The slope of mutant growth rate versus induction level indicates potency. Using SAMP-Dep, we mapped the sequence-activity landscape of 170 000 mutants of oncocin, a proline-rich AMP, for intracellular activity against Escherichia coli. Clonal validation supported the platform's sensitivity and accuracy. The mapped landscape revealed an extended oncocin pharmacophore contrary to earlier structural studies, clarified the C-terminus role in internalization, identified functional epistasis, and guided focused, successful synthetic peptide library design, yielding a mutant with 2-fold enhancement in both intracellular and extracellular activity. The efficiency of SAMP-Dep poises the platform to transform AMP engineering, characterization, and discovery.

Proteins require high developability—quantified by expression, solubility, and stability—for robust utility as therapeutics, diagnostics, and in other biotechnological applications. Measuring traditional developability metrics is low throughput in nature, often slowing the developmental pipeline. We evaluated the ability of 10 variations of three high-throughput developability assays to predict the bacterial recombinant expression of paratope variants of the protein scaffold Gp2. Enabled by a phenotype/genotype linkage, assay performance for 10(5) variants was calculated via deep sequencing of populations sorted by proxied developability. We identified the most informative assay combination via cross-validation accuracy and correlation feature selection and demonstrated the ability of machine learning models to exploit nonlinear mutual information to increase the assays’ predictive utility. We trained a random forest model that predicts expression from assay performance that is 35% closer to the experimental variance and trains 80% more efficiently than a model predicting from sequence information alone. Utilizing the predicted expression, we performed a site-wise analysis and predicted mutations consistent with enhanced developability. The validated assays offer the ability to identify developable proteins at unprecedented scales, reducing the bottleneck of protein commercialization.

The symptoms of many blood diseases can often be attributed to irregularities in cellular dynamics produced by abnormalities in blood cells, particularly red blood cells (RBCs). Contingent on the disease and its severity, RBCs can be afflicted with increased membrane rigidity as seen in malaria and sickle cell disease. Despite this understanding, little experimental work has been conducted toward understanding the effect of RBC rigidity on cellular dynamics in physiologic blood flow. Though many have computationally modeled complex blood flow to postulate how RBC rigidity may disrupt normal hemodynamics, to date, there lacks a clear understanding of how rigid RBCs affect the blood cell segregation behavior in blood flow, known as margination, and the resulting change in the adhesion of white blood cells (WBCs). In this work, we utilized an in vitro blood flow model to examine how different RBC rigidities and volume fractions of rigid RBCs impact cell margination and the downstream effect on white blood cell (WBC) adhesion in blood flow. Healthy RBC membranes were rigidified and reconstituted into whole blood and then perfused over activated endothelial cells under physiologically relevant shear conditions. Rigid RBCs were shown to reduce WBC adhesion by up to 80%, contingent on the RBC rigidity and the fraction of treated RBCs present in blood flow. Furthermore, the RBC core was found to be slightly expanded with the presence of rigid RBCs, by up to ∼30% in size fully composed of rigid RBCs. Overall, the obtained results demonstrate an impact of RBC rigidity on cellular dynamics and WBC adhesion, which possibly contributes to the pathological understanding of diseases characterized by significant RBC rigidity.

Objective : Vascular-targeting remains a promising strategy for improving the diagnosis and treatment of coronary artery disease (CAD) by providing localized delivery of imaging and therapeutic agents to atherosclerotic lesions. In this work we evaluate how size and shape affects the capacity for a vascular-targeted carrier system to bind inflamed endothelial cells over plaque using ApoE −/− mice with developed atherosclerosis. Method : We investigated the adhesion levels along mouse aortae of ellipsoidal and spherical particles targeted to the inflammatory molecules E-selectin and VCAM-1, as well as the biodistribution of targeted and untargeted particles in major organs following injection via tail-vein and a 30-min circulation time. Results : We found that targeted ellipsoidal microparticles adhered to mouse aortae at higher levels than microspheres of similar volume, particularly at segments that contained atherosclerotic plaques. Moreover, both ellipsoidal and spherical nanoparticles displayed the same minimal adhesion levels compared to both types of microparticles evaluated, likely due to poor localization of nanoparticles to the vessel wall in blood flow. We found that microparticles targeted to plaque-associated inflammation were retained at higher levels in the lungs than untargeted particles, largely due to molecular interaction with the pulmonary endothelium. The level of the mechanical entrapment of ellipsoidal microparticles in the lungs was also not significantly different from that of microspheres of the same volume despite a ∼3-fold higher major axis length for the ellipsoids. Conclusions : Particle shape and size should be considered in the design of carrier systems to target atherosclerosis, as these parameters can be tuned to improve carrier performance.

The ability of vascular-targeted drug carriers (VTCs) to localize and bind to a targeted, diseased endothelium determines their overall clinical utility. Here, we investigate how particle modulus and size determine adhesion of VTCs to the vascular wall under physiological blood flow conditions. In general, deformable microparticles (MPs) outperformed nanoparticles (NPs) in all experimental conditions tested. Our results indicate that MP modulus enhances particle adhesion in a shear-dependent manner. In low shear human blood flow profiles in vitro, low modulus particles showed favorable adhesion, while at high shear, rigid particles showed superior adhesion. This was confirmed in vivo by studying particle adhesion under venous shear profiles in a mouse model of mesenteric inflammation, where MP adhesion was 127% greater (p < 0.0001) for low modulus particles compared to more rigid ones. Mechanistically, we establish that particle collisions with leukocytes drive these trends, rather than differences in particle deformation, localization, or detachment. Overall, this work demonstrates the importance of VTC modulus as a design parameter for enhanced VTC interaction with vascular walls, and thus, contributes important knowledge for development of successful clinical theranostics with applications for many diseases.