The design of functional proteins using tensorized energy calculations

Protein engineering using variational free energy approximation

Engineering proteins is a challenging task requiring the exploration of a vast design space. Traditionally, this is achieved using Directed Evolution (DE), which is a laborious process. Generative deep learning, instead, can learn biological features of functional proteins from sequence and structural datasets and return novel variants. However, most models do not generate thermodynamically stable proteins, thus leading to many non-functional variants. Here we propose a model called PRotein Engineering by Variational frEe eNergy approximaTion (PREVENT), which generates stable and functional variants by learning the sequence and thermodynamic landscape of a protein. We evaluate PREVENT by designing 40 variants of the conditionally essential E. coli phosphotransferase N-acetyl-L-glutamate kinase (EcNAGK). We find 85% of the variants to be functional, with 55% of them showing similar growth rate compared to the wildtype enzyme, despite harbouring up to 9 mutations. Our results support a new approach that can significantly accelerate protein engineering.

A strategy to design protein-based antagonists against type I cytokine receptors

Excessive cytokine signaling resulting from dysregulation of a cytokine or its receptor can be a main driver of cancer, autoimmune, or hematopoietic disorders. Here, we leverage protein design to create tailored cytokine receptor blockers with idealized properties. Specifically, we aimed to tackle the granulocyte-colony stimulating factor receptor (G-CSFR), a mediator of different types of leukemia and autoinflammatory diseases. By modifying designed G-CSFR binders, we engineered hyper-stable proteins that function as nanomolar signaling antagonists. X-ray crystallography showed atomic-level agreement with the experimental structure of an exemplary design. Furthermore, the most potent design blocks G-CSFR in acute myeloid leukemia cells and primary human hematopoietic stem cells. Thus, the resulting designs can be used for inhibiting or homing to G-CSFR-expressing cells. Our results also demonstrate that similarly designed cytokine mimics can be used to derive antagonists to tackle other type I cytokine receptors.

The Damietta Server: a comprehensive protein design toolkit

The growing importance of protein design to various research disciplines motivates the development of integrative computational platforms that enhance the accessibility and interoperability of different design tools. To this end, we describe a web-based toolkit that builds on the Damietta protein design engine, which deploys a tensorized energy calculation framework. The Damietta Server seamlessly integrates different design tools, in addition to other tools such as message-passing neural networks and molecular dynamics routines, allowing the user to perform multiple operations on structural models and forward them across tools. The toolkit can be used for tasks such as core or interface design, symmetric design, mutagenic scanning, or conformational sampling, through an intuitive user interface. With the envisioned integration of more tools, the Damietta Server will provide a central resource for protein design and analysis, benefiting basic and applied biomedical research communities. The toolkit is available with no login requirement through https://damietta.de/.