Specificity prediction of adenylation domains in nonribosomal peptide synthetases (NRPS) using transductive support vector machines (TSVMs)

By Christian Rausch, Tilmann Weber, Oliver Kohlbacher, Wolfgang Wohlleben, Daniel H. Huson. Nucleic Acids Research, 2005

429 citations recorded by the source corpus.

We present a new support vector machine (SVM)-based approach to predict the substrate specificity of subtypes of a given protein sequence family. We demonstrate the usefulness of this method on the example of aryl acid-activating and amino acid-activating adenylation domains (A domains) of nonribosomal peptide synthetases (NRPS). The residues of gramicidin synthetase A that are 8 Å around the substrate amino acid and corresponding positions of other adenylation domain sequences with 397 known and unknown specificities were extracted and used to encode this physico-chemical fingerprint into normalized real-valued feature vectors based on the physico-chemical properties of the amino acids. The SVM software package SVMlight was used for training and classification, with transductive SVMs to take advantage of the information inherent in unlabeled data. Specificities for very similar substrates that frequently show cross-specificities were pooled to the so-called composite specificities and predictive models were built for them. The reliability of the models was confirmed in cross-validations and in comparison with a currently used sequence-comparison-based method. When comparing the predictions for 1230 NRPS A domains that are currently detectable in UniProt, the new method was able to give a specificity prediction in an additional 18% of the cases compared with the old method. For 70% of the sequences both methods agreed, for <6% they did not, mainly on low-confidence predictions by the existing method. None of the predictive methods could infer any specificity for 2.4% of the sequences, suggesting completely new types of specificity.

Subfields: Microbiology, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/ca4bb9ae128789c6e77d3f8e17d839df756c7518

How researchers see this paper

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

In Microbiology

Nadine Ziemert

In Molecular Biology

Citations in the corpus

antiSMASH: rapid identification, annotation and analysis of secondary metabolite biosynthesis gene clusters in bacterial and fungal genome sequences (2011, methodology): “NRPS A domain speciﬁcities are predicted using both the signature sequence method and the support-vector machines-based method of NRPSPredictor2 (18,19), and using the method of Minowa et al. (17).”
antiSMASH 2.0—a versatile platform for genome mining of secondary metabolite producers (2013, background): “NRPSpredictor (13,14), NRPSSP (15) and the PKS/NRPS predictive BLAST Server (16) are sophisticated tools for the prediction of substrate speciﬁcities of key biosynthetic steps, allowing an approximate prediction of the chemical structure of bioactive end compounds based on the genome sequence…”
Mass spectral molecular networking of living microbial colonies (2012, background): “(E) Comparison of the syringomycin gene cluster to the thanamycin gene cluster and the corresponding “best” predictions of the adenylation domain specificity according to the Stachelhaus rules (45, 46).”
NRPSpredictor2—a web server for predicting NRPS adenylation domain specificity (2011, background): “One reason might be the observed promiscuity of the A-domains utilizing these substrates (10).”
The Natural Product Domain Seeker NaPDoS: A Phylogeny Based Bioinformatic Tool to Classify Secondary Metabolite Gene Diversity (2012, background): “When the challenges associated with PKS and NRPS gene assembly can be overcome, a number of effective bioinformatics tools have been developed for domain parsing [19,20] and domain string analysis [21,22].”