NRPSpredictor2—a web server for predicting NRPS adenylation domain specificity

By Marc Röttig, Marnix H. Medema, Kai Blin, Tilmann Weber, Christian Rausch, Oliver Kohlbacher. Nucleic Acids Res., 2011

588 citations recorded by the source corpus.

The products of many bacterial non-ribosomal peptide synthetases (NRPS) are highly important secondary metabolites, including vancomycin and other antibiotics. The ability to predict substrate specificity of newly detected NRPS Adenylation (A-) domains by genome sequencing efforts is of great importance to identify and annotate new gene clusters that produce secondary metabolites. Prediction of A-domain specificity based on the sequence alone can be achieved through sequence signatures or, more accurately, through machine learning methods. We present an improved predictor, based on previous work (NRPSpredictor), that predicts A-domain specificity using Support Vector Machines on four hierarchical levels, ranging from gross physicochemical properties of an A-domain’s substrates down to single amino acid substrates. The three more general levels are predicted with an F-measure better than 0.89 and the most detailed level with an average F-measure of 0.80. We also modeled the applicability domain of our predictor to estimate for new A-domains whether they lie in the applicability domain. Finally, since there are also NRPS that play an important role in natural products chemistry of fungi, such as peptaibols and cephalosporins, we added a predictor for fungal A-domains, which predicts gross physicochemical properties with an F-measure of 0.84. The service is available at http://nrps.informatik.uni-tuebingen.de/.

Subfields: Molecular Biology, Pharmacology

View Paper: https://www.semanticscholar.org/paper/c976d10fef75a7c4558a9a3abddca3b65e9f71c3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Pharmacology

Citations in the corpus

Artificial Intelligence For Natural Product Drug Discovery (2023, background): “…applied in the past, for example, to improve substrate specificity predictions of natural product biosynthetic enzymes using transductive support vector machines, where this helped to map the shape of unlabelled sequence space to better know how queries would relate to labelled data points 143 .”
MIBiG 3.0: a community-driven effort to annotate experimentally validated biosynthetic gene clusters (2022, methodology): “This makes MIBiG the largest resource for A-domain substrate data, containing 3–4 times as many labelled data points as the training sets used for the A-domain selectivity predictors SANDPUMA (23) and NRPSPredictor2 (24).”
Improving the coverage of the cyanobacterial phylum using diversity-driven genome sequencing (2012, methodology): “Adenylation domain substrate specificity predictions for NRPS enzymes were made using NRPSpreditor2 (42).”
Comparative Genomics of Plant-Associated Pseudomonas spp.: Insights into Diversity and Inheritance of Traits Involved in Multitrophic Interactions (2012, methodology): “The amino acid composition of products from NRPS sequences were predicted using NRPSpredictor 2 [148].”
A new genome-mining tool redefines the lasso peptide biosynthetic landscape (2016, methodology): “Although SVM has been previously used to predict NRPS substrate specificity 22 , to our knowledge, it has not yet been used to predict NP structures themselves.”
antiSMASH 4.0—improvements in chemistry prediction and gene cluster boundary identification (2017, methodology): “Since the first version of antiSMASH, three algorithms have been used within the pipeline to predict the substrate specificities of non-ribosomal peptide synthetase (NRPS) adenylation (A) domains: the support-vector machine (SVM) and active-site motif (ASM) prediction methods from NRPSPredictor2 (18”