The energetics and evolution of oxidoreductases in deep time.

The core metabolic reactions of life drive electrons through a class of redox protein enzymes, the oxidoreductases. The energetics of electron flow is determined by the redox potentials of organic and inorganic cofactors as tuned by the protein environment. Understanding how protein structure affects oxidation-reduction energetics is crucial for studying metabolism, creating bioelectronic systems, and tracing the history of biological energy utilization on Earth. We constructed ProtReDox (https://protein-redox-potential.web.app), a manually curated database of experimentally determined redox potentials. With over 500 measurements, we can begin to identify how proteins modulate oxidation-reduction energetics across the tree of life. By mapping redox potentials onto networks of oxidoreductase fold evolution, we can infer the evolution of electron transfer energetics over deep time. ProtReDox is designed to include user-contributed submissions with the intention of making it a valuable resource for researchers in this field.

MAHOMES II: A webserver for predicting if a metal binding site is enzymatic.

Recent advances have enabled high-quality computationally generated structures for proteins with no solved crystal structures. However, protein function data remains largely limited to experimental methods and homology mapping. Since structure determines function, it is natural that methods capable of using computationally generated structures for functional annotations need to be advanced. Our laboratory recently developed a method to distinguish between metalloenzyme and non-enzyme sites. Here we report improvements to this method by upgrading our physicochemical features to alleviate the need for structures with sub-angstrom precision and using machine learning to reduce training data labeling error. Our improved classifier identifies protein bound metal sites as enzymatic or non-enzymatic with 94% precision and 92% recall. We demonstrate that both adjustments increased predictive performance and reliability on sites with sub-angstrom variations. We constructed a set of predicted metalloprotein structures with no solved crystal structures and no detectable homology to our training data. Our model had an accuracy of 90 - 97.5% depending on the quality of the predicted structures included in our test. Finally, we found the physicochemical trends that drove this model's successful performance were local protein density, second shell ionizable residue burial, and the pocket's accessibility to the site. We anticipate that our model's ability to correctly identify catalytic metal sites could enable identification of new enzymatic mechanisms and improve de novo metalloenzyme design success rates. Significance statement: Identification of enzyme active sites on proteins with unsolved crystallographic structures can accelerate discovery of novel biochemical reactions, which can impact healthcare, industrial processes, and environmental remediation. Our lab has developed an ML tool for predicting sites on computationally generated protein structures as enzymatic and non-enzymatic. We have made our tool available on a webserver, allowing the scientific community to rapidly search previously unknown protein function space.

MAHOMES II: A webserver for predicting if a metal binding site is enzymatic.

Recent advances have enabled high-quality computationally generated structures for proteins with no solved crystal structures. However, protein function data remains largely limited to experimental methods and homology mapping. Since structure determines function, it is natural that methods capable of using computationally generated structures for functional annotations need to be advanced. Our laboratory recently developed a method to distinguish between metalloenzyme and nonenzyme sites. Here we report improvements to this method by upgrading our physicochemical features to alleviate the need for structures with sub-angstrom precision and using machine learning to reduce training data labeling error. Our improved classifier identifies protein bound metal sites as enzymatic or nonenzymatic with 94% precision and 92% recall. We demonstrate that both adjustments increased predictive performance and reliability on sites with sub-angstrom variations. We constructed a set of predicted metalloprotein structures with no solved crystal structures and no detectable homology to our training data. Our model had an accuracy of 90%-97.5% depending on the quality of the predicted structures included in our test. Finally, we found the physicochemical trends that drove this model's successful performance were local protein density, second shell ionizable residue burial, and the pocket's accessibility to the site. We anticipate that our model's ability to correctly identify catalytic metal sites could enable identification of new enzymatic mechanisms and improve de novo metalloenzyme design success rates.

Machine learning for enzyme engineering, selection and design.

Machine learning is a useful computational tool for large and complex tasks such as those in the field of enzyme engineering, selection and design. In this review, we examine enzyme-related applications of machine learning. We start by comparing tools that can identify the function of an enzyme and the site responsible for that function. Then we detail methods for optimizing important experimental properties, such as the enzyme environment and enzyme reactants. We describe recent advances in enzyme systems design and enzyme design itself. Throughout we compare and contrast the data and algorithms used for these tasks to illustrate how the algorithms and data can be best used by future designers.

Machine learning differentiates enzymatic and non-enzymatic metals in proteins.

Metalloenzymes are 40% of all enzymes and can perform all seven classes of enzyme reactions. Because of the physicochemical similarities between the active sites of metalloenzymes and inactive metal binding sites, it is challenging to differentiate between them. Yet distinguishing these two classes is critical for the identification of both native and designed enzymes. Because of similarities between catalytic and non-catalytic  metal binding sites, finding physicochemical features that distinguish these two types of metal sites can indicate aspects that are critical to enzyme function. In this work, we develop the largest structural dataset of enzymatic and non-enzymatic metalloprotein sites to date. We then use a decision-tree ensemble machine learning model to classify metals bound to proteins as enzymatic or non-enzymatic with 92.2% precision and 90.1% recall. Our model scores electrostatic and pocket lining features as more important than pocket volume, despite the fact that volume is the most quantitatively different feature between enzyme and non-enzymatic sites. Finally, we find our model has overall better performance in a side-to-side comparison against other methods that differentiate enzymatic from non-enzymatic sequences. We anticipate that our model's ability to correctly identify which metal sites are responsible for enzymatic activity could enable identification of new enzymatic mechanisms and de novo enzyme design.

Membrane Barrels Are Taller, Fatter, Inside-Out Soluble Barrels.

Up-and-down ß-barrel topology exists in both the membrane and soluble environment. By comparing features of these structurally similar proteins, we can determine what features are particular to the environment rather than the fold. Here we compare structures of membrane ß-barrels to soluble ß-barrels and evaluate their relative size, shape, amino acid composition, hydrophobicity, and periodicity. We find that membrane ß-barrels are generally larger than soluble ß-barrels, with more strands per barrel and more amino acids per strand, making them wider and taller. We also find that membrane ß-barrels are inside-out soluble ß-barrels. The inward region of membrane ß-barrels has similar hydrophobicity to the outward region of soluble ß-barrels, and the outward region of membrane ß-barrels has similar hydrophobicity to the inward region of the soluble ß-barrels. Moreover, even though both types of ß-barrel have been assumed to have strands with amino acids that alternate in direction and hydrophobicity, we find that the membrane ß-barrels have more regular alternation than soluble ß-barrels. These features give insight into how membrane barrels maintain their fold and function in the membrane.

Evolutionary pathways of repeat protein topology in bacterial outer membrane proteins.

Outer membrane proteins (OMPs) are the proteins in the surface of Gram-negative bacteria. These proteins have diverse functions but a single topology: the ß-barrel. Sequence analysis has suggested that this common fold is a ß-hairpin repeat protein, and that amplification of the ß-hairpin has resulted in 8-26-stranded barrels. Using an integrated approach that combines sequence and structural analyses, we find events in which non-amplification diversification also increases barrel strand number. Our network-based analysis reveals strand-number-based evolutionary pathways, including one that progresses from a primordial 8-stranded barrel to 16-strands and further, to 18-strands. Among these pathways are mechanisms of strand number accretion without domain duplication, like a loop-to-hairpin transition. These mechanisms illustrate perpetuation of repeat protein topology without genetic duplication, likely induced by the hydrophobic membrane. Finally, we find that the evolutionary trace is particularly prominent in the C-terminal half of OMPs, implicating this region in the nucleation of OMP folding.

Efflux Pumps Represent Possible Evolutionary Convergence onto the ß-Barrel Fold.

There are around 100 varieties of outer membrane proteins in each Gram-negative bacteria. All of these proteins have the same fold-an up-down ß-barrel. It has been suggested that all membrane ß-barrels excluding lysins are homologous. Here we suggest that ß-barrels of efflux pumps have converged on this fold as well. By grouping structurally solved outer membrane ß-barrels (OMBBs) by sequence we find that the membrane environment may have led to convergent evolution of the barrel fold. Specifically, the lack of sequence linkage to other barrels coupled with distinctive structural differences, such as differences in strand tilt and barrel radius, suggest that the outer membrane factor of efflux pumps evolutionarily converged on the barrel. Rather than being related to other OMBBs, sequence and structural similarity in the periplasmic region of the outer membrane factor of efflux pumps suggests an evolutionary link to the periplasmic subunit of the same pump complex.