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

Fairuz Shadmani Shishir,

Bishnu Sarker, Farzana Rahman

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: March 23, 2023

Abstract Proteins bind to metals such as copper, zinc, magnesium, etc., serving various purposes importing, exporting, or transporting metal in other parts of the cell ligands and maintaining stable protein structure function properly. A binding site indicates single amino acid position where a binds ion. Manually identifying sites is expensive, laborious, time-consuming. tiny fraction millions proteins UniProtKB – most comprehensive database are annotated with sites, leaving many waiting for annotation. Developing computational pipeline thus essential keep pace growing number proteins. significant shortcoming existing methods consideration long-term dependency residues. Other weaknesses include low accuracy, absence positional information, hand-engineered features, pre-determined set residues ions. In this paper, we propose MetaLLM, prediction technique, by leveraging recent progress self-supervised attention-based (e.g. Transformer) large language models (LLMs) considerable amount sequences publicly available. LLMs capable modelling long residual sequence. The proposed MetaLLM uses transformer pre-trained on an extensive later fine-tuned metal-binding multi-label ions prediction. 10-fold cross-validation shows more than 90% precision prevalent

Language: Английский

Mg2+-dependent mechanism of environmental versatility in a multidrug efflux pump DOI Creative Commons
Benjamin Russell Lewis, Muhammad Ramiz Uddin,

Katie M. Kuo

et al.

Structure, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Tripartite resistance nodulation and cell division multidrug efflux pumps span the periplasm are major drivers of among gram-negative bacteria. Cations, such as Mg2+, become concentrated within and, in contrast to cytoplasm, its pH is sensitive conditions outside cell. Here, we reveal an interplay between Mg2+ modulating structural dynamics periplasmic adapter protein, AcrA, function prototypical AcrAB-TolC pump from Escherichia coli. In absence AcrA becomes increasingly plastic acidic conditions, but when bound this ameliorated, resulting instead domain specific organization. We establish a unique histidine residue directs these essential for sustaining activity across acidic, neutral, basic regimes. Overall, propose conserves mobility ensure optimal rapidly changing environments commonly faced during bacterial infection colonization.

Language: Английский

Citations

2
Recent Advances and Future Challenges in Predictive Modelling of Metalloproteins by Artificial Intelligence DOI Open Access
Soohyeong Kim,

Wonseok Lee,

Hugh I. Kim

et al.

Molecules and Cells, Journal Year: 2025, Volume and Issue: unknown, P. 100191 - 100191

Published: Feb. 1, 2025

Metal coordination is essential for structural/catalytic functions of metalloproteins that mediate a wide range biological processes in living organisms. Advances bioinformatics have significantly enhanced our understanding metal-binding sites and their functional roles metalloproteins. State-of-the-art computational models developed seamlessly integrate protein sequence structural data to unravel the complexities metal environments. Our goal this mini-review give an overview these tools highlight current challenges (predicting dynamic sites, determining metalation states, designing intricate networks) remaining predictive sites. Addressing will not only deepen knowledge natural but also accelerate development artificial with novel precisely engineered functionalities.

Language: Английский

Citations

1
Identification of biomarkers in Alzheimer’s disease and COVID-19 by bioinformatics combining single-cell data analysis and machine learning algorithms DOI Creative Commons
Juntu Li,

Linfeng Tao,

Yanyou Zhou

et al.

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(2), P. e0317915 - e0317915

Published: Feb. 18, 2025

Background Since its emergence in 2019, COVID-19 has become a global epidemic. Several studies have suggested link between Alzheimer’s disease (AD) and COVID-19. However, there is little research into the mechanisms underlying these phenomena. Therefore, we conducted this study to identify key genes associated with AD, evaluate their correlation immune cells characteristics metabolic pathways. Methods Transcriptome analyses were used common biomolecular markers of AD Differential expression analysis weighted gene co-expression network (WGCNA) performed on chip datasets (GSE213313, GSE5281, GSE63060) from patients both conditions. Gene ontology (GO) enrichment identified molecular mechanisms. The core using machine learning. Subsequently, evaluated relationship Finally, our findings validated through single-cell analysis. Results 484 differentially expressed (DEGs) by taking intersection black module, containing 132 genes, showed highest association two diseases according WGCNA. GO revealed that mainly affect inflammation, cytokines, immune-related functions, signaling pathways related metal ions. Additionally, learning approach eight genes. We links also found EIF3H oxidative phosphorylation. Conclusion This identifies shared pathways, alterations, changes potentially contributing pathogenesis AD.

Language: Английский

Citations

1
Teleost Piscidins—In Silico Perspective of Natural Peptide Antibiotics from Marine Sources DOI Creative Commons
Patricia Asensio-Calavia, Sergio González-Acosta, Andrea Otazo-Pérez

et al.

Antibiotics, Journal Year: 2023, Volume and Issue: 12(5), P. 855 - 855

Published: May 5, 2023

Fish, like all other animals, are exposed to constant contact with microbes, both on their skin and the surfaces of respiratory digestive systems. Fish have a system non-specific immune responses that provides them initial protection against infection allows survive under normal conditions despite presence these potential invaders. However, fish less protected invading diseases than marine vertebrates because epidermal surface, composed primarily living cells, lacks keratinized serves as an efficient natural barrier in vertebrates. Antimicrobial peptides (AMPs) one type innate present life forms. AMPs been shown broader range biological effects conventional antibiotics, including antibacterial, antiviral, antiprotozoal, antifungal effects. Although AMPs, such defensins hepcidins, found relatively well conserved, piscidins exclusively Teleost not any animal. Therefore, there is information expression bioactivity AMPs. Piscidins highly effective Gram-positive Gram-negative bacteria cause disease humans be used pharmacological anti-infectives biomedicine aquaculture. To better understand benefits limitations using therapeutic agents, we conducting comprehensive study included “reviewed” category UniProt database bioinformatics tools. They amphipathic alpha-helical structures. The architecture piscidin positively charged residues influence antibacterial activity. These alpha-helices intriguing antimicrobial drugs due stability high-salt metal environments. New treatments for multidrug-resistant bacteria, cancer, inflammation may inspired by peptides.

Language: Английский

Citations

14
M-Ionic: prediction of metal-ion-binding sites from sequence using residue embeddings DOI Creative Commons
Aditi Shenoy, Yogesh Kalakoti, Durai Sundar

et al.

Bioinformatics, Journal Year: 2024, Volume and Issue: 40(1)

Published: Jan. 1, 2024

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 annotate metal-binding sites becomes imperative. Quick resource-efficient pre-trained language model (pLM) embeddings have successfully predicted binding from despite not using or evolutionary features (multiple sequence alignments). Using residue-level pLMs, we developed a sequence-based method (M-Ionic) identify proteins residues involved in metal binding.

Language: Английский

Citations

6
Structural Bioinformatics and Deep Learning of Metalloproteins: Recent Advances and Applications DOI Open Access
Claudia Andreini, Antonio Rosato

International Journal of Molecular Sciences, Journal Year: 2022, Volume and Issue: 23(14), P. 7684 - 7684

Published: July 12, 2022

All living organisms require metal ions for their energy production and metabolic biosynthetic processes. Within cells, the involved in formation of adducts interact with metabolites macromolecules (proteins nucleic acids). The proteins that binding to one or more order be able carry out physiological function are called metalloproteins. About third all protein structures Protein Data Bank involve Over past few years there has been tremendous progress number computational tools techniques making use 3D structural information support investigation This trend boosted by successful applications neural networks machine/deep learning approaches molecular biology at large. In this review, we discuss recent advances development availability resources dealing metalloproteins from a structure-based perspective. We start addressing prediction metal-binding sites (MBSs) using on apo-proteins. Then, provide an overview methods lessons learned comparison MBSs fold-independent manner. then move describing databases metalloprotein/MBS structures. Finally, summarizing ML/DL enhancing functional interpretation metalloprotein

Language: Английский

Citations

17
Bio-inspired metal extraction: Tailoring peptides for high-selectivity scandium recovery DOI
Mengyun Zhang, Tian Lei, Denys Villa‐Gomez

et al.

Separation and Purification Technology, Journal Year: 2025, Volume and Issue: 354, P. 128640 - 128640

Published: Feb. 1, 2025

Language: Английский

Citations

0
Twenty years in metalloprotein bioinformatics: A short history of a long journey DOI
Claudia Andreini

Journal of Inorganic Biochemistry, Journal Year: 2025, Volume and Issue: 266, P. 112854 - 112854

Published: Feb. 11, 2025

Language: Английский

Citations

0
Novel Hepcidin Genes in Gilthead Seabream: Implications for Immune Response and Iron Metabolism DOI Creative Commons

Laura García-Navarro,

Jhon A. Serna-Duque, Alberto Cuesta

et al.

Microbial Pathogenesis, Journal Year: 2025, Volume and Issue: unknown, P. 107695 - 107695

Published: May 1, 2025

Language: Английский

Citations

0
Metals and metal isotopes incorporation in insect wings: Implications for geolocation and pollution exposure DOI Creative Commons
Megan S. Reich,

Mira Kindra,

Felipe Dargent

et al.

Frontiers in Ecology and Evolution, Journal Year: 2023, Volume and Issue: 11

Published: Feb. 13, 2023

Anthropogenic activities are exposing insects to elevated levels of toxic metals and altering the bioavailability essential metals. Metals metal isotopes have also become promising tools for geolocation migratory insects. Understanding pathways incorporation in insect tissues is thus important assessing role physiology ecology development as tools. We conducted a diet-switching experiment on monarch butterflies [ Danaus plexippus (L.)] with controlled larval adult diets evaluate sources 23 metalloids, strontium isotopes, lead wing over period 8 weeks. Concentrations Ca, Co, Mo, Sb differed between sexes or body mass. Ni Zn bioaccumulated time, likely from diet, while increases Al, Cr, Cd, Cu, Fe, Pb were, at least partially, external (i.e., dust aerosols). Bioaccumulation wings was confirmed by mainly be sourced anthropogenic sources, revealing potential an indicator tracer pollution exposure along paths. Ba, Cs, Mg, Na, Rb, Sr, Ti, Tl, U appeared unaffected intrinsic factors additions dietary their should further explored. Strontium isotope ratios remained indicative males, supporting its tool. However, difference sexes, well possibility contamination wetting, requires investigation. Our results demonstrate complexity processes value studying develop new quantify exposure, toxicity, micronutrient uptake, mobility.

Language: Английский

Citations

9