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.

Data-Driven Synthetic Cell Factories Development for Industrial Biomanufacturing

Revolutionary breakthroughs in artificial intelligence (AI) and machine learning (ML) have had a profound impact on a widerange of scientific disciplines, including the development of artificial cell factories for biomanufacturing. In this paper, wereview the latest studies on the application of data-driven methods for the design of new proteins, pathways, and strains. Wefirst briefly introduce the various types of data and databases relevant to industrial biomanufacturing, which are the basis fordata-driven research. Different types of algorithms, including traditional ML and more recent deep learning methods, are alsopresented. We then demonstrate how these data-based approaches can be applied to address various issues in cell factorydevelopment using examples from recent studies, including the prediction of protein function, improvement of metabolicmodels, and estimation of missing kinetic parameters, design of non-natural biosynthesis pathways, and pathway optimization.In the last section, we discuss the current limitations of these data-driven approaches and propose that data-driven methodsshould be integrated with mechanistic models to complement each other and facilitate the development of synthetic strains forindustrial biomanufacturing.

Improving pathway prediction accuracy of constraints-based metabolic network models by treating enzymes as microcompartments

Metabolic network models have become increasingly precise and accurate as the most widespread and practical digital representations of living cells.The prediction functions were significantly expanded by integrating cellular resources and abiotic constraints in recent years.However,if unreasonable modeling methods were adopted due to a lack of consideration of biological knowledge,the conflicts between stoichiometric and other constraints,such as thermodynamic feasibility and enzyme resource availability,would lead to distorted predictions.In this work,we investigated a prediction anomaly of EcoETM,a constraints-based metabolic network model,and introduced the idea of enzyme compartmentalization into the analysis process.Through rational combination of reactions,we avoid the false prediction of pathway feasibility caused by the unrealistic assumption of free intermediate metabolites.This allowed us to correct the pathway structures of L-serine and L-tryptophan.A specific analysis explains the application method of the EcoETM-like model and demonstrates its potential and value in correcting the prediction results in pathway structure by resolving the conflict between different constraints and incorporating the evolved roles of enzymes as reaction compartments.Notably,this work also reveals the trade-off between product yield and thermodynamic feasibility.Our work is of great value for the structural improvement of constraints-based models.

Construction and application of high-quality genome-scale metabolic model of Zymomonas mobilis to guide rational design of microbial cell factories

High-quality genome-scale metabolic models(GEMs)could play critical roles on rational design of microbial cell factories in the classical Design-Build-Test-Learn cycle of synthetic biology studies.Despite of the constant establishment and update of GEMs for model microorganisms such as Escherichia coli and Saccharomyces cerevisiae,high-quality GEMs for non-model industrial microorganisms are still scarce.Zymomonas mobilis subsp.mobilis ZM4 is a non-model ethanologenic microorganism with many excellent industrial characteristics that has been developing as microbial cell factories for biochemical production.Although five GEMs of Z.mobilis have been constructed,these models are either generating ATP incorrectly,or lacking information of plasmid genes,or not providing standard format file.In this study,a high-quality GEM iZM516 of Z.mobilis ZM4 was constructed.The information from the improved genome annotation,literature,datasets of Biolog Phenotype Microarray studies,and recently updated Gene-Protein-Reaction information was combined for the curation of iZM516.Finally,516 genes,1389 reactions,1437 metabolites,and 3 cell compartments are included in iZM516,which also had the highest MEMOTE score of 91%among all published GEMs of Z.mobilis.Cell growth was then predicted by iZM516,which had 79.4%agreement with the experimental results of the substrate utilization.In addition,the potential endogenous succinate synthesis pathway of Z.mobilis ZM4 was proposed through simulation and analysis using iZM516.Furthermore,metabolic engineering strategies to produce succinate and 1,4-butanediol(1,4-BDO)were designed and then simulated under anaerobic condition using iZM516.The results indicated that 1.68 mol/mol succinate and 1.07 mol/mol 1,4-BDO can be achieved through combinational metabolic engineering strategies,which was comparable to that of the model species E.coli.Our study thus not only established a high-quality GEM iZM516 to help understand and design microbial cell factories for economic biochemical production using Z.mobilis as the chassis,but also provided guidance on building accurate GEMs for other non-model industrial microorganisms.

Reconstruction and metabolic profiling of the genome-scale metabolic network model of Pseudomonas stutzeri A1501

Pseudomonas stutzeri A1501 is a non-fluorescent denitrifying bacteria that belongs to the gram-negative bacterial group.As a prominent strain in the fields of agriculture and bioengineering,there is still a lack of comprehensive understanding regarding its metabolic capabilities,specifically in terms of central metabolism and substrate utilization.Therefore,further exploration and extensive studies are required to gain a detailed insight into these aspects.This study reconstructed a genome-scale metabolic network model for P.stutzeri A1501 and conducted extensive curations,including correcting energy generation cycles,respiratory chains,and biomass composition.The final model,iQY1018,was successfully developed,covering more genes and reactions and having higher prediction accuracy compared with the previously published model iPB890.The substrate utilization ability of 71 carbon sources was investigated by BIOLOG experiment and was utilized to validate the model quality.The model prediction accuracy of substrate utilization for P.stutzeri A1501 reached 90%.The model analysis revealed its new ability in central metabolism and predicted that the strain is a suitable chassis for the production of Acetyl CoA-derived products.This work provides an updated,high-quality model of P.stutzeri A1501for further research and will further enhance our understanding of the metabolic capabilities.

Construction and analysis of an integrated biological network of Escherichia coli

Escherichia coli is a model organism with a clear genetic background that is widely used in metabolic engineering and synthetic biology research.To gain a complete picture of the complexly metabolic and regulatory interactions in E.coli,researchers often need to retrieve information from various databases which cover diferent types of interactions.A central one-stop service integrating various molecular interactions in E.coli would be helpful for the community.We constructed a database called E.coli integrated network(EcoIN)by integrating known molecular interaction information from databases and literature.EcoIN contains nearly 160,000 pairs of interactions and users can easily search the diferent types of interacting partners for a metabolite,gene or protein,and thus gain access to a more comprehensive interaction map of E.coli.To illustrate the application of EcoIN,we used the full path algorithm to identify metabolic feedback/feedforward regulatory loops having at least two diferent types of regulatory interactions.Applying this algorithm to analyze the regulatory loops for the amino acid biosynthetic pathways,we found some multi-step regulation loops which may afect the metabolic fux and are potential new engineering targets.The EcoIN database is freely accessible at http://ecoin.ibiodesign.net/and analysis codes are available at GitHub:https://github.com/maozhitao/EcoIN.