MetalloPred: A tool for hierarchical prediction of metal ion binding proteins using cluster of neural networks and sequence derived features

Abstract

Given a protein sequence, how can we identify whether it is a metalloprotein or not? If it is, which main functional class and subclasses it belongs to? This is an important biological question because they are closely related to the biological function of an uncharacterized protein. Particularly, with the avalanche of protein sequences generated in the post genomic era and since conventional techniques are time consuming and expensive, it is highly desirable to develop an automated method by which one can get a fast and accurate answer to these questions. Here, a top-down predictor, called MetalloPred, is developed which consists of 3 level of hierarchical classification using cascade of neural networks from sequence derived features. The 1 st layer of the prediction engine is for identifying a query protein as metalloprotein or not; the 2 nd layer for the main functional class; and the 3 rd layer for the sub-functional class. The overall success rates for all the three layers are higher than 60% that were obtained through rigorous cross-validation tests on the very stringent benchmark datasets in which none of the proteins has 30% sequence identity with any other in the same class or subclass. MetalloPred achieved good prediction accuracies and could nicely complement experimental approaches for identification of metal binding proteins. MetalloPred is freely available to be used in-house as a standalone and is accessible at http://www.juit.ac.in/assets/Metallopred/.

The study of iron‐ and copper‐binding proteome of Fusarium oxysporum and its effector candidates

“…It covers 12 metal ions, provides metal‐bound 3D protein structures, and offers docking results. Compared to other tools like SVM‐Prot, 68 SeqCHED, 69 metallopred, 70 Metal detector, MetalExplorer, MetSite, 71 FINDSITE‐metal, 72 and Ion com, 73 MIB stands out for its user‐friendly interface and its ability to handle multiple ion–ligand binding efficiently, making it a superior choice for metal‐binding prediction and docking. Putative IBPs and CBPs were subsequently functionally annotated by NCBI‐CDD, 37 Pfam, 38 and InterProScan 39 .…”

Positive Evolutionary Selection of an HD Motif on Alzheimer Precursor Protein Orthologues Suggests a Functional Role

“…Surprisingly, the last 60–70 amino acid of all CAEDs were predicted to be metal-binding domains, by 2 different prediction programs, regardless of the presence or absence of the HD motif ( Table S3 ). Both programs Metallopred and SVMProt achieved more than 80% accuracy in validation tests [41] , [42] so the chance that all of these sequentially non-homologous protein segments, with similar functions, would be falsely predicted to have metal-binding capabilities seems to be marginal. Furthermore, the carboxy-terminal region of the extracellular domain of APLP1 and APLP2 orthologues is also predicted to bind metal ions, which suggests that metal-binding capability near the transmembrane anchor are evolutionary maintained and it is indispensable in order that APP orthologues and homologues exert their normal biological functions.…”

Functional and structural identification of iron-binding proteins on tomato (Solanum lycopersicum L.) proteome via in silico approaches

“…Iron-binding proteins can be identified, modeled, or functionally analyzed using bioinformatics tools for plant proteomes. Iron-binding sites of proteins can be analyzed by using protein sequences or structures with online tools like MetalPredator (Valasatava et al 2016), MetSite (Sodhi et al 2004), MetalloPred (Naik et al 2011), or IonCom (Hu et al 2016). Besides, there are various bioinformatic tools available like MetalS 2 (Andreini et al 2013) (Zheng et al 2017).…”