{"entity": "publication", "iuid": "740fdf09151b47df8a5af5bad9c8be82", "timestamp": "2026-08-20T21:22:46.363Z", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/740fdf09151b47df8a5af5bad9c8be82.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/740fdf09151b47df8a5af5bad9c8be82"}}, "title": "M-Ionic: prediction of metal-ion-binding sites from sequence using residue embeddings.", "authors": [{"family": "Shenoy", "given": "Aditi", "initials": "A", "orcid": "0000-0001-7748-2501", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/35bef00b985a45d59602675316e3d706.json"}}, {"family": "Kalakoti", "given": "Yogesh", "initials": "Y"}, {"family": "Sundar", "given": "Durai", "initials": "D", "orcid": "0000-0002-6549-6663", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/5bf8c45f2b9848f2861604fac7f8613c.json"}}, {"family": "Elofsson", "given": "Arne", "initials": "A", "orcid": "0000-0002-7115-9751", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/248e70e81bd64f31a5f83e6e329bba95.json"}}], "type": "journal article", "published": "2024-01-02", "journal": {"title": "Bioinformatics", "issn": "1367-4811", "volume": "40", "issue": "1", "issn-l": "1367-4803"}, "abstract": "Understanding metal-protein interaction can provide structural and functional insights into cellular processes. As the number of protein sequences increases, developing fast yet precise computational approaches to predict and annotate metal-binding sites becomes imperative. Quick and resource-efficient pre-trained protein language model (pLM) embeddings have successfully predicted binding sites from protein sequences despite not using structural or evolutionary features (multiple sequence alignments). Using residue-level embeddings from the pLMs, we have developed a sequence-based method (M-Ionic) to identify metal-binding proteins and predict residues involved in metal binding.\n\nOn independent validation of recent proteins, M-Ionic reports an area under the curve (AUROC) of 0.83 (recall = 84.6%) in distinguishing metal binding from non-binding proteins compared to AUROC of 0.74 (recall = 61.8%) of the next best method. In addition to comparable performance to the state-of-the-art method for identifying metal-binding residues (Ca2+, Mg2+, Mn2+, Zn2+), M-Ionic provides binding probabilities for six additional ions (i.e. Cu2+, Po43-, So42-, Fe2+, Fe3+, Co2+). We show that the pLM embedding of a single residue contains sufficient information about its neighbours to predict its binding properties.\n\nM-Ionic can be used on your protein of interest using a Google Colab Notebook (https://bit.ly/40FrRbK). The GitHub repository (https://github.com/TeamSundar/m-ionic) contains all code and data.", "doi": "10.1093/bioinformatics/btad782", "pmid": "38175787", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC10792727"}, {"db": "pii", "key": "7510839"}], "notes": [], "created": "2026-08-20T09:39:49.393Z", "modified": "2026-08-20T09:39:49.502Z"}