Improved enzyme annotation with EC-specific cutoffs using DETECT v2

Artificial Intelligence Technology Assists Enzyme Prediction and Rational Design

Since the structure of enzymes determines their function, elucidating the structure of enzymes lays a solid foundation for deciphering their catalytic mechanism and enabling rational design. The development of artificial intelligence (AI) has sparked a technological revolution, infusing new vitality into theoretical studies of enzymology and the advancement of enzyme engineering techniques. This Review outlines the development process and main methods of AI applied in the structural elucidation and functional prediction of enzymes. Furthermore, it emphasizes AI-based rational design of enzymes and provides a detailed exposition of representative AI algorithms and case studies. With the support of AI technology, the comprehension of enzyme structure and function and their relationship will become deeper and more efficient, thereby promoting the widespread application of enzyme engineering in various fields.

In silico mining and identification of a novel lipase from Paenibacillus larvae: Rational protein design for improving catalytic performance

Lipases play a vital role in various biological processes, from lipid metabolism to industrial applications. However, the ever-evolving challenges and diverse substrates necessitate the continual exploration of novel high-performance lipases. In this study, we employed an in silico mining approach to search for lipases with potential high sn-1,3 selectivity and catalytic activity. The identified novel lipase, PLL, from Paenibacillus larvae subsp. larvae B-3650 exhibited a specific activity of 111.2 ± 5.5 U/mg towards the substrate p-nitrophenyl palmitate (pNPP) and 6.9 ± 0.8 U/mg towards the substrate olive oil when expressed in Escherichia coli (E. coli). Computational design of cysteine mutations was employed to enhance the catalytic performance of PLL. Superior stability was achieved with the mutant K7C/A386C/H159C/K108C (2M3/2M4), showing an increase in melting temperature (Tm) by 1.9°C, a 2.05-fold prolonged half-life at 45°C, and no decrease in enzyme activity. Another mutant, K7C/A386C/A174C/A243C (2M1/2M3), showed a 4.9-fold enhancement in specific activity without compromising stability. Molecular dynamics simulations were conducted to explore the mechanisms of these two mutants. Mutant 2M3/2M4 forms putative disulfide bonds in the loop region, connecting the N- and C-termini of PLL, thus enhancing overall structural rigidity without impacting catalytic activity. The cysteines introduced in mutant 2M1/2M3 not only form new intramolecular hydrogen bonds but also alter the polarity and volume of the substrate-binding pocket, facilitating the entry of large substrate pNPP. These results highlight an efficient in silico exploration approach for novel lipases, offering a rapid and efficient method for enhancing catalytic performance through rational protein design.

Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges

Machine learning (ML), particularly deep learning (DL), has made rapid and substantial progress in synthetic biology in recent years. Biotechnological applications of biosystems, including pathways, enzymes, and whole cells, are being probed frequently with time. The intricacy and interconnectedness of biosystems make it challenging to design them with the desired properties. ML and DL have a synergy with synthetic biology. Synthetic biology can be employed to produce large data sets for training models (for instance, by utilizing DNA synthesis), and ML/DL models can be employed to inform design (for example, by generating new parts or advising unrivaled experiments to perform). This potential has recently been brought to light by research at the intersection of engineering biology and ML/DL through achievements like the design of novel biological components, best experimental design, automated analysis of microscopy data, protein structure prediction, and biomolecular implementations of ANNs (Artificial Neural Networks). I have divided this review into three sections. In the first section, I describe predictive potential and basics of ML along with myriad applications in synthetic biology, especially in engineering cells, activity of proteins, and metabolic pathways. In the second section, I describe fundamental DL architectures and their applications in synthetic biology. Finally, I describe different challenges causing hurdles in the progress of ML/DL and synthetic biology along with their solutions.

MVDINET: A Novel Multi-Level Enzyme Function Predictor With Multi-View Deep Interactive Learning

As a class of extremely significant of biocatalysts, enzymes play an important role in the process of biological reproduction and metabolism. Therefore, the prediction of enzyme function is of great significance in biomedicine fields. Recently, computational methods for predicting enzyme function have been proposed, and they effectively reduce the cost of enzyme function prediction. However, there are still deficiencies for effectively mining the discriminant information for enzyme function recognition in existing methods. In this study, we present MVDINET, a novel method for multi-level enzyme function prediction. First, the initial multi-view feature data is extracted by the enzyme sequence. Then, the above initial views are fed into various deep specific network modules to learn the depth-specificity information. Further, a deep view interaction network is designed to extract the interaction information. Finally, the specificity information and interaction information are fed into a multi-view adaptively weighted classification. We compressively evaluate MVDINET on benchmark datasets and demonstrate that MVDINET is superior to existing methods.

MetaPro: a scalable and reproducible data processing and analysis pipeline for metatranscriptomic investigation of microbial communities

BACKGROUND

Whole microbiome RNASeq (metatranscriptomics) has emerged as a powerful technology to functionally interrogate microbial communities. A key challenge is how best to process, analyze, and interpret these complex datasets. In a typical application, a single metatranscriptomic dataset may comprise from tens to hundreds of millions of sequence reads. These reads must first be processed and filtered for low quality and potential contaminants, before being annotated with taxonomic and functional labels and subsequently collated to generate global bacterial gene expression profiles.

RESULTS

Here, we present MetaPro, a flexible, massively scalable metatranscriptomic data analysis pipeline that is cross-platform compatible through its implementation within a Docker framework. MetaPro starts with raw sequence read input (single-end or paired-end reads) and processes them through a tiered series of filtering, assembly, and annotation steps. In addition to yielding a final list of bacterial genes and their relative expression, MetaPro delivers a taxonomic breakdown based on the consensus of complementary prediction algorithms, together with a focused breakdown of enzymes, readily visualized through the Cytoscape network visualization tool. We benchmark the performance of MetaPro against two current state-of-the-art pipelines and demonstrate improved performance and functionality.

CONCLUSIONS

MetaPro represents an effective integrated solution for the processing and analysis of metatranscriptomic datasets. Its modular architecture allows new algorithms to be deployed as they are developed, ensuring its longevity. To aid user uptake of the pipeline, MetaPro, together with an established tutorial that has been developed for educational purposes, is made freely available at https://github.com/ParkinsonLab/MetaPro . The software is freely available under the GNU general public license v3. Video Abstract.

Enzyme Commission Number Prediction and Benchmarking with Hierarchical Dual-core Multitask Learning Framework

Enzyme commission (EC) numbers, which associate a protein sequence with the biochemical reactions it catalyzes, are essential for the accurate understanding of enzyme functions and cellular metabolism. Many ab initio computational approaches were proposed to predict EC numbers for given input protein sequences. However, the prediction performance (accuracy, recall, and precision), usability, and efficiency of existing methods decreased seriously when dealing with recently discovered proteins, thus still having much room to be improved. Here, we report HDMLF, a hierarchical dual-core multitask learning framework for accurately predicting EC numbers based on novel deep learning techniques. HDMLF is composed of an embedding core and a learning core; the embedding core adopts the latest protein language model for protein sequence embedding, and the learning core conducts the EC number prediction. Specifically, HDMLF is designed on the basis of a gated recurrent unit framework to perform EC number prediction in the multi-objective hierarchy, multitasking manner. Additionally, we introduced an attention layer to optimize the EC prediction and employed a greedy strategy to integrate and fine-tune the final model. Comparative analyses against 4 representative methods demonstrate that HDMLF stably delivers the highest performance, which improves accuracy and F1 score by 60% and 40% over the state of the art, respectively. An additional case study of tyrB predicted to compensate for the loss of aspartate aminotransferase aspC, as reported in a previous experimental study, shows that our model can also be used to uncover the enzyme promiscuity. Finally, we established a web platform, namely, ECRECer (https://ecrecer.biodesign.ac.cn), using an entirely could-based serverless architecture and provided an offline bundle to improve usability.

Synthetic Biology Meets Machine Learning

This chapter outlines the myriad applications of machine learning (ML) in synthetic biology, specifically in engineering cell and protein activity, and metabolic pathways. Though by no means comprehensive, the chapter highlights several prominent computational tools applied in the field and their potential use cases. The examples detailed reinforce how ML algorithms can enhance synthetic biology research by providing data-driven insights into the behavior of living systems, even without detailed knowledge of their underlying mechanisms. By doing so, ML promises to increase the efficiency of research projects by modeling hypotheses in silico that can then be tested through experiments. While challenges related to training dataset generation and computational costs remain, ongoing improvements in ML tools are paving the way for smarter and more streamlined synthetic biology workflows that can be readily employed to address grand challenges across manufacturing, medicine, engineering, agriculture, and beyond.

Architect: A tool for aiding the reconstruction of high-quality metabolic models through improved enzyme annotation

Constraint-based modeling is a powerful framework for studying cellular metabolism, with applications ranging from predicting growth rates and optimizing production of high value metabolites to identifying enzymes in pathogens that may be targeted for therapeutic interventions. Results from modeling experiments can be affected at least in part by the quality of the metabolic models used. Reconstructing a metabolic network manually can produce a high-quality metabolic model but is a time-consuming task. At the same time, current methods for automating the process typically transfer metabolic function based on sequence similarity, a process known to produce many false positives. We created Architect, a pipeline for automatic metabolic model reconstruction from protein sequences. First, it performs enzyme annotation through an ensemble approach, whereby a likelihood score is computed for an EC prediction based on predictions from existing tools; for this step, our method shows both increased precision and recall compared to individual tools. Next, Architect uses these annotations to construct a high-quality metabolic network which is then gap-filled based on likelihood scores from the ensemble approach. The resulting metabolic model is output in SBML format, suitable for constraints-based analyses. Through comparisons of enzyme annotations and curated metabolic models, we demonstrate improved performance of Architect over other state-of-the-art tools, notably with higher precision and recall on the eukaryote C. elegans and when compared to UniProt annotations in two bacterial species. Code for Architect is available at https://github.com/ParkinsonLab/Architect. For ease-of-use, Architect can be readily set up and utilized using its Docker image, maintained on Docker Hub.

Tools for computational design and high-throughput screening of therapeutic enzymes

Therapeutic enzymes are valuable biopharmaceuticals in various biomedical applications. They have been successfully applied for fibrinolysis, cancer treatment, enzyme replacement therapies, and the treatment of rare diseases. Still, there is a permanent demand to find new or better therapeutic enzymes, which would be sufficiently soluble, stable, and active to meet specific medical needs. Here, we highlight the benefits of coupling computational approaches with high-throughput experimental technologies, which significantly accelerate the identification and engineering of catalytic therapeutic agents. New enzymes can be identified in genomic and metagenomic databases, which grow thanks to next-generation sequencing technologies exponentially. Computational design and machine learning methods are being developed to improve catalytically potent enzymes and predict their properties to guide the selection of target enzymes. High-throughput experimental pipelines, increasingly relying on microfluidics, ensure functional screening and biochemical characterization of target enzymes to reach efficient therapeutic enzymes.

Genome-scale metabolic modeling reveals key features of a minimal gene set

Mesoplasma florum, a fast-growing near-minimal organism, is a compelling model to explore rational genome designs. Using sequence and structural homology, the set of metabolic functions its genome encodes was identified, allowing the reconstruction of a metabolic network representing ˜ 30% of its protein-coding genes. Growth medium simplification enabled substrate uptake and product secretion rate quantification which, along with experimental biomass composition, were integrated as species-specific constraints to produce the functional iJL208 genome-scale model (GEM) of metabolism. Genome-wide expression and essentiality datasets as well as growth data on various carbohydrates were used to validate and refine iJL208. Discrepancies between model predictions and observations were mechanistically explained using protein structures and network analysis. iJL208 was also used to propose an in silico reduced genome. Comparing this prediction to the minimal cell JCVI-syn3.0 and its parent JCVI-syn1.0 revealed key features of a minimal gene set. iJL208 is a stepping-stone toward model-driven whole-genome engineering.

Machine learning for metabolic engineering: A review

Machine learning provides researchers a unique opportunity to make metabolic engineering more predictable. In this review, we offer an introduction to this discipline in terms that are relatable to metabolic engineers, as well as providing in-depth illustrative examples leveraging omics data and improving production. We also include practical advice for the practitioner in terms of data management, algorithm libraries, computational resources, and important non-technical issues. A variety of applications ranging from pathway construction and optimization, to genetic editing optimization, cell factory testing, and production scale-up are discussed. Moreover, the promising relationship between machine learning and mechanistic models is thoroughly reviewed. Finally, the future perspectives and most promising directions for this combination of disciplines are examined.

Systems biology analysis of the Clostridioides difficile core-genome contextualizes microenvironmental evolutionary pressures leading to genotypic and phenotypic divergence

Hospital acquired Clostridioides (Clostridium) difficile infection is exacerbated by the continued evolution of C. difficile strains, a phenomenon studied by multiple laboratories using stock cultures specific to each laboratory. Intralaboratory evolution of strains contributes to interlaboratory variation in experimental results adding to the challenges of scientific rigor and reproducibility. To explore how microevolution of C. difficile within laboratories influences the metabolic capacity of an organism, three different laboratory stock isolates of the C. difficile 630 reference strain were whole-genome sequenced and profiled in over 180 nutrient environments using phenotypic microarrays. The results identified differences in growth dynamics for 32 carbon sources including trehalose, fructose, and mannose. An updated genome-scale model for C. difficile 630 was constructed and used to contextualize the 28 unique mutations observed between the stock cultures. The integration of phenotypic screens with model predictions identified pathways enabling catabolism of ethanolamine, salicin, arbutin, and N-acetyl-galactosamine that differentiated individual C. difficile 630 laboratory isolates. The reconstruction was used as a framework to analyze the core-genome of 415 publicly available C. difficile genomes and identify areas of metabolism prone to evolution within the species. Genes encoding enzymes and transporters involved in starch metabolism and iron acquisition were more variable while C. difficile distinct metabolic functions like Stickland fermentation were more consistent. A substitution in the trehalose PTS system was identified with potential implications in strain virulence. Thus, pairing genome-scale models with large-scale physiological and genomic data enables a mechanistic framework for studying the evolution of pathogens within microenvironments and will lead to predictive modeling to combat pathogen emergence.

Spatially remote motifs cooperatively affect substrate preference of a ruminal GH26-type endo-β-1,4-mannanase

β-Mannanases from the glycoside hydrolase 26 (GH26) family are retaining hydrolases that are active on complex heteromannans and whose genes are abundant in rumen metagenomes and metatranscriptomes. These enzymes can exhibit distinct modes of substrate recognition and are often fused to carbohydrate-binding modules (CBMs), resulting in a molecular puzzle of mechanisms governing substrate preference and mode of action that has not yet been pieced together. In this study, we recovered a novel GH26 enzyme with a CBM35 module linked to its N terminus (CrMan26) from a cattle rumen metatranscriptome. CrMan26 exhibited a preference for galactomannan as substrate and the crystal structure of the full-length protein at 1.85 Å resolution revealed a unique orientation of the ancillary domain relative to the catalytic interface, strategically positioning a surface aromatic cluster of the ancillary domain as an extension of the substrate-binding cleft, contributing to galactomannan preference. Moreover, systematic investigation of nonconserved residues in the catalytic interface unveiled that residues Tyr195 (-3 subsite) and Trp234 (-5 subsite) from distal negative subsites have a key role in galactomannan preference. These results indicate a novel and complex mechanism for substrate recognition involving spatially remote motifs, distal negative subsites from the catalytic domain, and a surface-associated aromatic cluster from the ancillary domain. These findings expand our molecular understanding of the mechanisms of substrate binding and recognition in the GH26 family and shed light on how some CBMs and their respective orientation can contribute to substrate preference.

Bio2Rxn: sequence-based enzymatic reaction predictions by a consensus strategy

Summary

The development of sequencing technologies has generated large amounts of protein sequence data. The automated prediction of the enzymatic reactions of uncharacterized proteins is a major challenge in the field of bioinformatics. Here, we present Bio2Rxn as a web-based tool to provide putative enzymatic reaction predictions for uncharacterized protein sequences. Bio2Rxn adopts a consensus strategy by incorporating six types of enzyme prediction tools. It allows for the efficient integration of these computational resources to maximize the accuracy and comprehensiveness of enzymatic reaction predictions, which facilitates the characterization of the functional roles of target proteins in metabolism. Bio2Rxn further links the enzyme function prediction with more than 300 000 enzymatic reactions, which were manually curated by more than 100 people over the past 9 years from more than 580 000 publications.

Availability and implementation

Bio2Rxn is available at: http://design.rxnfinder.org/bio2rxn/.

Contact

qnhu@sibs.ac.cn

Supplementary information

Supplementary data are available at Bioinformatics online.

Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers

High-quality and high-throughput prediction of enzyme commission (EC) numbers is essential for accurate understanding of enzyme functions, which have many implications in pathologies and industrial biotechnology. Several EC number prediction tools are currently available, but their prediction performance needs to be further improved to precisely and efficiently process an ever-increasing volume of protein sequence data. Here, we report DeepEC, a deep learning-based computational framework that predicts EC numbers for protein sequences with high precision and in a high-throughput manner. DeepEC takes a protein sequence as input and predicts EC numbers as output. DeepEC uses 3 convolutional neural networks (CNNs) as a major engine for the prediction of EC numbers, and also implements homology analysis for EC numbers that cannot be classified by the CNNs. Comparative analyses against 5 representative EC number prediction tools show that DeepEC allows the most precise prediction of EC numbers, and is the fastest and the lightest in terms of the disk space required. Furthermore, DeepEC is the most sensitive in detecting the effects of mutated domains/binding site residues of protein sequences. DeepEC can be used as an independent tool, and also as a third-party software component in combination with other computational platforms that examine metabolic reactions.

Comparative Genome-Scale Metabolic Modeling of Metallo-Beta-Lactamase-Producing Multidrug-Resistant Klebsiella pneumoniae Clinical Isolates

The emergence and spread of metallo-beta-lactamase–producing multidrug-resistant (MDR) Klebsiella pneumoniae is a serious public health threat, which is further complicated by the increased prevalence of colistin resistance. The link between antimicrobial resistance acquired by strains of Klebsiella and their unique metabolic capabilities has not been determined. Here, we reconstruct genome-scale metabolic models for 22 K. pneumoniae strains with various resistance profiles to different antibiotics, including two strains exhibiting colistin resistance isolated from Cairo, Egypt. We use the models to predict growth capabilities on 265 different sole carbon, nitrogen, sulfur, and phosphorus sources for all 22 strains. Alternate nitrogen source utilization of glutamate, arginine, histidine, and ethanolamine among others provided discriminatory power for identifying resistance to amikacin, tetracycline, and gentamicin. Thus, genome-scale model based predictions of growth capabilities on alternative substrates may lead to construction of classification trees that are indicative of antibiotic resistance in Klebsiella isolates.