Bruno Emanuel Ferreira De Sousa Correia

Publications associées (45)

De novo design of protein interactions with learned surface fingerprints

Michael Bronstein, Stephen M Buckley, Bruno Emanuel Ferreira De Sousa Correia, Beat Fierz, Pablo Gainza Cirauqui, Sandrine Madeleine Suzanne Georgeon, Casper Alexander Goverde, Zander Harteveld, Anthony Marchand, Jane Marsden, Dongchun Ni, Elisa Oricchio, Aaron Simone Petruzzella, Charlène Mireille Raymonde Raclot, Stéphane Rosset, Andreas Scheck, Henning Paul-Julius Stahlberg, Freyr Sverrisson, Alexandra Teslenko, Didier Trono, Priscilla Turelli, Alexandra Krina Van Hall-Beauvais, Sarah Wehrle

Physical interactions between proteins are essential for most biological processes governing life. However, the molecular determinants of such interactions have been challenging to understand, even as genomic, proteomic and structural data increase. This knowledge gap has been a major obstacle for the comprehensive understanding of cellular protein–protein interaction networks and for the de novo design of protein binders that are crucial for synthetic biology and translational applications. Here we use a geometric deep-learning framework operating on protein surfaces that generates fingerprints to describe geometric and chemical features that are critical to drive protein–protein interactions10. We hypothesized that these fingerprints capture the key aspects of molecular recognition that represent a new paradigm in the computational design of novel protein interactions. As a proof of principle, we computationally designed several de novo protein binders to engage four protein targets: SARS-CoV-2 spike, PD-1, PD-L1 and CTLA-4. Several designs were experimentally optimized, whereas others were generated purely in silico, reaching nanomolar affinity with structural and mutational characterization showing highly accurate predictions. Overall, our surface-centric approach captures the physical and chemical determinants of molecular recognition, enabling an approach for the de novo design of protein interactions and, more broadly, of artificial proteins with function.

2023

Chargement

De novo protein design by inversion of the AlphaFold structure prediction network

Bruno Emanuel Ferreira De Sousa Correia, Casper Alexander Goverde, Stéphane Rosset

De novo protein design enhances our understanding of the principles that govern protein folding and interactions, and has the potential to revolutionize biotechnology through the engineering of novel protein functionalities. Despite recent progress in computational design strategies, de novo design of protein structures remains challenging, given the vast size of the sequence-structure space. AlphaFold2 (AF2), a state-of-the-art neural network architecture, achieved remarkable accuracy in predicting protein structures from amino acid sequences. This raises the question whether AF2 has learned the principles of protein folding sufficiently for de novo design. Here, we sought to answer this question by inverting the AF2 network, using the prediction weight set and a loss function to bias the generated sequences to adopt a target fold. Initial design trials resulted in de novo designs with an overrepresentation of hydrophobic residues on the protein surface compared to their natural protein family, requiring additional surface optimization. In silico validation of the designs showed protein structures with the correct fold, a hydrophilic surface and a densely packed hydrophobic core. In vitro validation showed that seven out of 39 designs were folded and stable in solution with high melting temperatures. In summary, our design workflow solely based on AF2 does not seem to fully capture basic principles of de novo protein design, as observed in the protein surface's hydrophobic vs. hydrophilic patterning. However, with minimal post-design intervention, these pipelines generated viable sequences as assessed experimental characterization. Thus such pipelines show the potential to contribute to solving outstanding challenges in de novo protein design.

2023

Chargement

, ,

Reliably scoring and ranking candidate models of protein complexes and assigning their oligomeric state from the structure of the crystal lattice represent outstanding challenges. A community-wide effort was launched to tackle these challenges. The latest resources on protein complexes and interfaces were exploited to derive a benchmark dataset consisting of 1677 homodimer protein crystal structures, including a balanced mix of physiological and non-physiological complexes. The non-physiological complexes in the benchmark were selected to bury a similar or larger interface area than their physiological counterparts, making it more difficult for scoring functions to differentiate between them. Next, 252 functions for scoring protein-protein interfaces previously developed by 13 groups were collected and evaluated for their ability to discriminate between physiological and non-physiological complexes. A simple consensus score generated using the best performing score of each of the 13 groups, and a cross-validated Random Forest (RF) classifier were created. Both approaches showed excellent performance, with an area under the Receiver Operating Characteristic (ROC) curve of 0.93 and 0.94, respectively, outperforming individual scores developed by different groups. Additionally, AlphaFold2 engines recalled the physiological dimers with significantly higher accuracy than the non-physiological set, lending support to the reliability of our benchmark dataset annotations. Optimizing the combined power of interface scoring functions and evaluating it on challenging benchmark datasets appears to be a promising strategy.

2023

Chargement

Novel cathepsin inhibitors

Bruno Emanuel Ferreira De Sousa Correia, Elisa Oricchio, Aaron Simone Petruzzella

The present invention relates to a cathepsin inhibitor comprising or consisting of Formula (I) (X1)(X2)(X3)(X4)(Y)(X5)(X6)(X7) wherein (X1) is an amino acid selected from K, L, F and M; (X2) is an amino acid selected from L, A, D, E, F, G, H, I, K, M, N, S, W, Y, Q and R; (X3) is an amino acid selected from R, A and L; (X4) is an amino acid selected from M, I, K, V and Y; (X5) is an amino acid selected from P, A, I, L, V, W and Y; (X6) is an amino acid selected from K, A, E, F, G, I, L, M, N, Q, S, T, V, W, Y and Q; (X7) is an amino acid selected from D, A, E, F, G, I, L, M, N, P, T, V, W, Y, Q and R; and (Y) is a Michael acceptor.

2023

Chargement

Rational Design of Chemically Controlled Antibodies and Protein Therapeutics

Lucia Bonati, Bruno Emanuel Ferreira De Sousa Correia, Pablo Gainza Cirauqui, Sandrine Madeleine Suzanne Georgeon, Anthony Marchand, Stéphane Rosset, Leo Scheller, Sailan Shui, Li Tang

Protein-based therapeutics, such as monoclonal antibodies and cytokines, are important therapies for various pathophysiological conditions such as oncology, autoimmune disorders, and viral infections. However, the wide application of such protein therapeutics is often hindered by dose-limiting toxicities and adverse effects, namely, cytokine storm syndrome, organ failure, and others. Therefore, spatiotemporal control of the activities of these proteins is crucial to further expand their application. Here, we report the design and application of small-molecule-controlled switchable protein therapeutics by taking advantage of a previously engineered OFF-switch system. We used the Rosetta modeling suite to computationally optimize the affinity between B-cell lymphoma 2 (Bcl-2) protein and a previously developed computationally designed protein partner (LD3) to obtain a fast and efficient heterodimer disruption upon the addition of a competing drug (Venetoclax). The incorporation of the engineered OFF-switch system into anti-CTLA4, anti-HER2 antibodies, or an Fc-fused IL-15 cytokine demonstrated an efficient disruption in vitro, as well as fast clearance in vivo upon the addition of the competing drug Venetoclax. These results provide a proof-of-concept for the rational design of controllable biologics by introducing a drug-induced OFF-switch into existing protein-based therapeutics.

2023

Chargement

Track: Machine Learning in Protein Science De Novo Design of Viral Epitope Mimetics with Non-Regular Structural Features

Karla Montserrat Castro Gilabert, Bruno Emanuel Ferreira De Sousa Correia, Anastassia Andreevna Vorobieva, Jue Wang

WILEY2023

Chargement

, , , , ,

De novo protein design enables the exploration of novel sequences and structures absent from the natural protein universe. De novo design also stands as a stringent test for our understanding of the underlying physical principles of protein folding and may lead to the development of proteins with unmatched functional characteristics. The first fundamental challenge of de novo design is to devise "designable" structural templates leading to sequences that will adopt the predicted fold. Here, we built on the TopoBuilder (TB) de novo design method, to automatically assemble structural templates with native-like features starting from string descriptors that capture the overall topology of proteins. Our framework eliminates the dependency of hand-crafted and fold-specific rules through an iterative, data-driven approach that extracts geometrical parameters from structural tertiary motifs. We evaluated the TopoBuilder framework by designing sequences for a set of five protein folds and experimental characterization revealed that several sequences were folded and stable in solution. The TopoBuilder de novo design framework will be broadly useful to guide the generation of artificial proteins with customized geometries, enabling the exploration of the protein universe.

NATL ACAD SCIENCES2022

Chargement

, ,

Recent advances in protein-design methodology have led to a dramatic increase in reliability and scale. With these advances, dozens and even thousands of designed proteins are automatically generated and screened. Nevertheless, the success rate, particularly in design of functional proteins, is low and fundamental goals such as reliable de novo design of efficient enzymes remain beyond reach. Experimental analyses have consistently indicated that a major reason for design failure is inaccuracy and misfolding relative to the design conception. To address this challenge, we describe complementary methods to diagnose and ameliorate suboptimal regions in designed proteins: first, we develop a Rosetta atomistic computational mutation scanning approach to detect energetically suboptimal positions in designs (available on a web server ); second, we demonstrate that AlphaFold2 ab initio structure prediction flags regions that may misfold in designed enzymes and binders; and third, we focus FuncLib design calculations on suboptimal positions in a previously designed low-efficiency enzyme, improving its catalytic efficiency by 330-fold. Furthermore, applied to a de novo designed protein that exhibited limited stability, the same approach markedly improved stability and expressibility. Thus, foldability analysis and enhancement may dramatically increase the success rate in design of functional proteins.

WILEY2022

Chargement

Computational design of novel protein–protein interactions – An overview on methodological approaches and applications

Bruno Emanuel Ferreira De Sousa Correia, Anthony Marchand, Alexandra Krina Van Hall-Beauvais

Protein–protein interactions (PPIs) govern numerous cellular functions in terms of signaling, transport, defense and many others. Designing novel PPIs poses a fundamental challenge to our understanding of molecular interactions. The capability to robustly engineer PPIs has immense potential for the development of novel synthetic biology tools and protein-based therapeutics. Over the last decades, many efforts in this area have relied purely on experimental approaches, but more recently, computational protein design has made important contributions. Template-based approaches utilize known PPIs and transplant the critical residues onto heterologous scaffolds. De novo design instead uses computational methods to generate novel binding motifs, allowing for a broader scope of the sites engaged in protein targets. Here, we review successful design cases, giving an overview of the methodological approaches used for templated and de novo PPI design.

2022

Chargement

Computational design of vaccine immunogens

Karla Montserrat Castro Gilabert, Bruno Emanuel Ferreira De Sousa Correia, Andreas Scheck, Shuhao Xiao

Computational protein engineering has enabled the rational design of customized proteins, which has propelled both sequence-based and structure-based immunogen engineering and delivery. By discerning antigenic determinants of viral pathogens, computational methods have been implemented to successfully engineer representative viral strains able to elicit broadly neutralizing responses or present antigenic sites of viruses for focused immune responses. Combined with improvements in customizable nanoparticle design, immunogens are multivalently displayed to enhance immune responses. These rationally designed immunogens offer unique and powerful approaches to engineer vaccines for pathogens, which have eluded traditional approaches.

CURRENT BIOLOGY LTD2022

Chargement