mebipred: identifying metal-binding potential in protein sequence

Abstract

Motivation Metal binding proteins have a central role in maintaining life processes. Nearly one-third of known protein structures contain metal ions that are used for a variety of needs, such as catalysis, DNA/RNA binding, protein structure stability, etc. Identifying metal binding proteins is thus crucial for understanding the mechanisms of cellular activity. However, experimental annotation of protein metal binding potential is severely lacking, while computational techniques are often imprecise and of limited applicability. Results We developed a novel machine learning-based method, mebipred, for identifying metal binding proteins from sequence-derived features. This method is over 80% accurate in recognizing proteins that bind metal ion-containing ligands; the specific identity of eleven ubiquitously-present metal ions can also be annotated. mebipred is reference-free, i.e. no sequence alignments are involved, and is thus faster than alignment-based methods; it also more accurate than other sequence-based prediction methods. Additionally, mebipred can identify protein metal binding capabilities from short sequence stretches, e.g. translated sequencing reads, and, thus, may be useful for the annotation of metal requirements of metagenomic samples. We performed an analysis of available microbiome data and found that ocean, hot spring sediments, and soil microbiomes use a more diverse set of metals than human host-related ones. For human microbiomes, physiological conditions explain the observed metal preferences. Similarly, subtle changes in ocean sample ion concentration affect the abundance of relevant metal binding proteins. These results highlight mebipred’s utility in analysing microbiome metal requirements. Availability mebipred is available as a web server at services.bromberglab.org/mebipred and as a standalone package at https://pypi.org/project/mymetal/. Supplementary information Supplementary data are available from Bioinformatics online repository. Additional data is available from http://dx.doi.org/10.5281/zenodo.5722730 and http://dx.doi.org/10.5281/zenodo.6332940.

Structural Bioinformatics and Deep Learning of Metalloproteins: Recent Advances and Applications

“…Prediction of positions where metal ligands can be introduced, based on protein backbone coordinates, to design artificial MPs [50] Structural comparison of metal sites Sequence-based prediction of MPs using a NN trained with information derived from 3D structures [97] https://github.com/cerm-cirmmp/MBSDL (accessed on 5 July 2022)…”

“…Mebipred is a tool to predict whether a protein is an MP based on sequence information alone [ 97 ]. It is relevant for this review because it was trained using information derived from 3D structures.…”

Metals and metal isotopes incorporation in insect wings: Implications for geolocation and pollution exposure

“…Essential metals are required for metabolic functions such as that the organism cannot survive when the metal is removed from the diet. Essential metals participate in enzyme catalysis, protein structure, cellular signaling, and the creation of electrochemical potentials at membranes (Maret, 2016;Dow, 2017) and it is estimated that up to 30% of proteins are metalloproteins (Aptekmann et al, 2022). Within organisms, these essential metals follow a dose-response curve, in which low doses cause morbidity due to metal deficiency and high doses cause toxicological effects.…”

MetaLLM: Residue-wise Metal ion Prediction Using Deep Transformer Model

“…Predicting the binding sites for metals is a challenging problem in computational biology. Decades of research has been dedicated to discovering computational approaches that can accurately predict the metal ions as well as the positions where they bind to the proteins [3, 17, 8, 5]. A comprehensive review of recent advances in computational approaches for predicting metal binding sites can be found in [30].…”