Selenzyme: Enzyme selection tool for pathway design

Carbonell, Pablo; Wong, Jerry; Swainston, Neil; Takano, Eriko; Turner, Nicholas J.; Scrutton, Nigel S.; Kell, Douglas B.; Breitling, Rainer; Faulon, Jean-Loup

doi:10.1101/188979

Cited by 3 publications

(2 citation statements)

References 18 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technical note references one of those software-based tools. Selenzyme [3], originally developed at the Manchester SYNBIOCHEM biofoundry, is a free online enzymatic selection tool that can be used for a wide range of purposes. An additional code compatible with the original software is presented here, through which new features of Selenzyme are generated.…”

Section: Introductionmentioning

confidence: 99%

Developing an enzyme selection tool supporting multiple hosts contexts

Camarena¹,

Carbonell²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Engineering biological organisms that allow the integration of alternative metabolic pathways to natural ones is one of the goals of synthetic biology. Based on this, some of the most attractive applications in terms of synthetic organisms manufacture include the production of a wide range of pharmacologically useful metabolites produced in a sustainable and environmentally friendly way. Also, the biostable molecules green-production involves different types of therapeutic processes, e.g. prostheses and grafts stabilisation. Regarding the viability of genetically modified organisms, metabolic pathways must be first properly designed, taking into consideration the type of host organism that will be involved in metabolic production, as well as its biochemical and environmental conditions. To ensure the correct growth of these synthetic organisms, the enzyme selection must guarantee both the organism survival (and proliferation) and the optimal production of the desired metabolite. Developing enzyme selection tools is essential to enhance and make cost-effective the metabolic pathways design. This technical note presents the update of Selenzyme, the enzyme selection tool which is based on organisms taxonomic compatibility and allows appropriate enzyme selection considering its amino acid sequence. The purpose of the update is to allow multiple host input, in order to perform an affinity comparison between target organisms and each host. The affinity differences will depend on which host to be considered, allowing the user to select the optimal host for the enzyme concerned.

show abstract

Section: Introductionmentioning

confidence: 99%

Developing an enzyme selection tool supporting multiple hosts contexts

Camarena¹,

Carbonell²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In parallel, the development of trusted sources of curated metabolic pathway information including the Kyoto Encyclopedia of Genes and Genomes (KEGG) [15] and MetaCyc [4] provides training data for the design of more flexible machine learning (ML) algorithms for pathway inference. While ML approaches have been adopted widely in metabolomics research [3,34] they have gained less traction when applied to predicting pathways directly from annotated gene lists.…”

Section: Introductionmentioning

confidence: 99%

Metabolic pathway prediction using non-negative matrix factorization with improved precision

Basher

McLaughlin

Hallam

2020

Preprint

View full text Add to dashboard Cite

Machine learning provides a probabilistic framework for metabolic pathway inference from genomic sequence information at different levels of complexity and completion. However, several challenges including pathway features engineering, multiple mapping of enzymatic reactions and emergent or distributed metabolism within populations or communities of cells can limit prediction performance. Here, we present triUMPF, triple non-negative matrix factorization (NMF) with community detection for metabolic pathway inference, that combines three stages of NMF to capture myriad relationships between enzymes and pathways within a graph network followed by community detection to extract higher order structure based on the clustering of vertices sharing similar statistical properties. We evaluated triUMPF performance using experimental datasets manifesting diverse multi-label properties, including Tier 1 genomes from the BioCyc collection of organismal Pathway/Genome Databases and low complexity microbial communities. Resulting performance metrics equaled or exceeded other prediction methods on organismal genomes with improved prediction outcomes on multi-organism data sets. Availability and implementation: The software package, and installation instructions are published on

show abstract

CatPred: A comprehensive framework for deep learning in vitro enzyme kinetic parametersk_cat,K_mandK_i

Boorla,

Maranas

2024

Preprint

View full text Add to dashboard Cite

Quantification of enzymatic activities still heavily relies on experimental assays, which can be expensive and time-consuming. Therefore, methods that enable accurate predictions of enzyme activity can serve as effective digital twins. A few recent studies have shown the possibility of training machine learning (ML) models for predicting the enzyme turnover numbers (kcat) and Michaelis constants (Km) using only features derived from enzyme sequences and substrate chemical topologies by training onin vitromeasurements. However, several challenges remain such as lack of standardized training datasets, evaluation of predictive performance on out-of-distribution examples, and model uncertainty quantification. Here, we introduce CatPred, a comprehensive framework for ML prediction ofin vitroenzyme kinetics. We explored different learning architectures and feature representations for enzymes including those utilizing pretrained protein language model features and three-dimensional structural features. We systematically evaluate the performance of trained models for predictingkcat,Km, and inhibition constants (Ki) of enzymatic reactions on held-out test sets with a special emphasis on out-of-distribution test samples (corresponding to enzyme sequences dissimilar from those encountered during training). CatPred assumes a probabilistic regression approach offering probability distributions instead of single value predictions. Results on unseen data confirm that accuracy in enzyme parameter predictions made by CatPred positively correlate with lower predicted variances. Incorporating pre-trained language model features are found to be enabling for achieving robust performance on out-of-distribution samples. Test evaluations on both held-out and out-of-distribution test datasets confirm that CatPred performs at least competitively with existing methods while simultaneously offering robust uncertainty quantification. CatPred offers wider scope and larger data coverage (∼23k, 41k, 12k data-points) respectively forkcat, Kmand Ki. A web-resource to use the trained models is available at:https://tiny.cc/catpred

show abstract

Selenzyme: Enzyme selection tool for pathway design

Cited by 3 publications

References 18 publications

Developing an enzyme selection tool supporting multiple hosts contexts

Developing an enzyme selection tool supporting multiple hosts contexts

Metabolic pathway prediction using non-negative matrix factorization with improved precision

CatPred: A comprehensive framework for deep learning in vitro enzyme kinetic parametersk_cat,K_mandK_i

Contact Info

Product

Resources

About

Selenzyme: Enzyme selection tool for pathway design

Cited by 3 publications

References 18 publications

Developing an enzyme selection tool supporting multiple hosts contexts

Developing an enzyme selection tool supporting multiple hosts contexts

Metabolic pathway prediction using non-negative matrix factorization with improved precision

CatPred: A comprehensive framework for deep learning in vitro enzyme kinetic parameterskcat,KmandKi

Contact Info

Product

Resources

About

CatPred: A comprehensive framework for deep learning in vitro enzyme kinetic parametersk_cat,K_mandK_i