Two-Level Protein Methylation Prediction using structure model-based features

Abstract

protein methylation plays a vital role in cell processing. Many novel methods try to predict methylation sites from protein sequence by sequence information or predicted structural information, but none of them use protein tertiary structure information in prediction. In particular, most of them do not build models for predicting methylation types (mono-, di-, tri-methylation). To address these problems, we propose a novel method, Met-predictor, to predict methylation sites and methylation types using a support vector machine-based network. Met-predictor combines a variety of sequence-based features that are derived from protein sequences with structure model-based features, which are geometric information extracted from predicted protein tertiary structure models, and are firstly used in methylation prediction. Met-predictor was tested on two independent test sets, where the addition of structure model-based features improved AUC from 0.611 and 0.520 to 0.655 and 0.566 for lysine and from 0.723 and 0.640 to 0.734 and 0.643 for arginine. When compared with other state-of-the-art methods, Met-predictor had 13.1% (3.9%) and 8.5% (16.4%) higher accuracy than the best of other methods for methyllysine and methylarginine prediction on the independent test set I (II). Furthermore, Met-predictor also attains excellent performance for predicting methylation types.

The CARM1 transcriptome and arginine methylproteome mediate skeletal muscle integrative biology

“…Using bioinformatic tools, we scanned preferred motif sequences to predict PRMT substrates in skeletal muscle [ 97 , 98 ]. Contrary to PRMT1 and PRMT5 which prefer arginine- and glycine-rich RGG/RG sequences, earlier work indicated that CARM1 targets arginine residues neighboring PGM motifs [ 1 , 5 , 99 , 100 ].…”

Functions of Essential Genes and a Scale-Free Protein Interaction Network Revealed by Structure-Based Function and Interaction Prediction for a Minimal Genome

“…Next, residue-residue contacts are predicted from the MSA by the deep learning-based algorithms TripletRes/ResTriplet 27 and ResPRE 28 (see the Supporting Information Text S1 for details). Meanwhile, LOMETS threading 35 is performed to search for the query protein sequence against the PDB database to align the query to template structures to extract continuous fragments. These fragments are finally assembled into the full length structures by a replica-exchange Monte Carlo (REMC) simulation under the guidance of a composite force field consisting of the deep learning-predicted contacts, template-derived distance restraints, and knowledge-based energy terms calculated based on statistics of PDB structures.…”

Machine learning-based approaches for ubiquitination site prediction in human proteins

“…PTMs can occur at specific sites within the 3D structure of a protein, and therefore, the structural context of a site can be informative for predicting its likelihood of being modified [ 60 – 62 ]. Given recent breakthroughs in predicting functional and structural protein properties using raw protein sequences [ 63 – 65 ], we can infer that predicting Ubi-sites by shortening the number of amino acids in the windows could result in a lower amount of implicit structural features that ML methods could obtain during training, compared to longer window sizes.…”