IntroductionThe current methodologies for enzyme annotation primarily rely on established databases and classifications such as KEGG Orthology (KO), Enzyme Commission (EC) numbers, and Gene Ontology (GO) annotations, each with its specific focus and methodology. For instance, the EC system categorizes enzymes based on the chemical reactions they catalyze, providing a hierarchical numerical classification. KO links gene products to their functional orthologs across different species, whereas GO offers a broader ontology for describing the roles of genes and proteins in any organism. Despite their widespread use, these systems have notable limitations. The EC classification, while widely used, sometimes groups vastly different enzymes under the same category or subdivides similar ones excessively, based on the substrates they interact with--leading to ambiguities in enzyme function characterization.

Enzymes, as catalysts of biological systems, are the workhorses of various biological functions [35, 52, 13] (Figure 1a).

Chemist Omar Yaghi invented materials called MOFs, a few grams of which have the surface area of a football field. In school, we learn about the Stone Age, the Bronze Age - and we are currently in a silicon age characterised by computers and phones. What might define the next age? Omar Yaghi at the University of California, Berkeley, thinks a family of materials he helped pioneer in the 1990s has a good shot. They are metal-organic frameworks (MOFs), and working out how to make them earned him a share of the 2025 Nobel prize in chemistry .

Innovative research into the gene-editing tool targets influenza's ability to replicate--stopping it in its tracks. As he addressed an audience of virologists from China, Australia, and Singapore at October's Pandemic Research Alliance Symposium, Wei Zhao introduced an eye-catching idea. The gene-editing technology Crispr is best known for delivering groundbreaking new therapies for rare diseases, tweaking or knocking out rogue genes in conditions ranging from sickle cell disease to hemophilia . But Zhao and his colleagues at Melbourne's Peter Doherty Institute for Infection and Immunity have envisioned a new application. They believe Crispr could be tailored to create a next-generation treatment for influenza, whether that's the seasonal strains which plague both the northern and southern hemispheres on an annual basis, or the worrisome new variants in birds and other wildlife that might trigger the next pandemic.

Enzymes, with their specific catalyzed reactions, are necessary for all aspects of life, enabling diverse biological processes and adaptations. Predicting enzyme functions is essential for understanding biological pathways, guiding drug development, enhancing bioproduct yields, and facilitating evolutionary studies.Addressing the inherent complexities, we introduce a new approach to annotating enzymes based on their catalyzed reactions. This method provides detailed insights into specific reactions and is adaptable to newly discovered reactions, diverging from traditional classifications by protein family or expert-derived reaction classes. We employ machine learning algorithms to analyze enzyme reaction datasets, delivering a much more refined view on the functionality of enzymes.Our evaluation leverages the largest enzyme-reaction dataset to date, derived from the SwissProt and Rhea databases with entries up to January 8, 2024. We frame the enzyme-reaction prediction as a retrieval problem, aiming to rank enzymes by their catalytic ability for specific reactions. With our model, we can recruit proteins for novel reactions and predict reactions in novel proteins, facilitating enzyme discovery and function annotation https://github.com/WillHua127/ReactZyme.

Applying differentiable programming techniques and machine learning algorithms to foreign programs requires developers to either rewrite their code in a machine learning framework, or otherwise provide derivatives of the foreign code. This paper presents Enzyme, a high-performance automatic differentiation (AD) compiler plugin for the LLVM compiler framework capable of synthesizing gradients of statically analyzable programs expressed in the LLVM intermediate representation (IR). Enzyme synthesizes gradients for programs written in any language whose compiler targets LLVM IR including C, C++, Fortran, Julia, Rust, Swift, MLIR, etc., thereby providing native AD capabilities in these languages. Unlike traditional source-to-source and operator-overloading tools, Enzyme performs AD on optimized IR. On a machine-learning focused benchmark suite including Microsoft's ADBench, AD on optimized IR achieves a geometric mean speedup of 4.2 times over AD on IR before optimization allowing Enzyme to achieve state-of-the-art performance. Packaging Enzyme for PyTorch and TensorFlow provides convenient access to gradients of foreign code with state-of-the-art performance, enabling foreign code to be directly incorporated into existing machine learning workflows.