A Modular Fusion Neural Network Approach to Efficiently Predict Multi-Metal Binding Sites in Protein Sequences
Li, J.; Fan, C.; LAU, H. Y.; Wu, T.
Show abstract
Accurate identification of metal-binding residues is essential for the study of metalloproteins, like zinc finger proteins, haemoglobin, and DNA polymerase. Due to the high cost and time demands of experimental methods, computational prediction has been applied. However, computational complexity and inextensibility of rigid frameworks impeded the application. This work presents a two-stage, sequence-based deep learning framework, which can predict zinc, iron, and magnesium binding amino acids of proteins. In the first stage, tokenized sequences are processed by independent one-dimensional convolutional neural networks (CNNs) to generate single-residue probability maps. In the second stage, a lightweight fusion network integrates these maps to model inter-metal dependencies and refine predictions. The framework employs an imbalance-aware loss function and the ensemble evaluation to improve robustness. Structural agnostic and modular design enable efficient training and inference, making it suitable for the annotation of large-scale proteome. CCS CONCEPTS* Applied computing; * Life and medical sciences; * Bioinformatics
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- CaLMPhosKAN: Prediction of General Phosphorylation Sites in Proteins via Fusion of Codon Aware Embeddings with Amino Acid Aware Embeddings and Wavelet-based Kolmogorov Arnold Network 94%
- Beyond the Leaderboard: Leveraging Predictive Modeling for Protein-Ligand Insights and Discovery 93%
- mebipred: identifying metal-binding potential in protein sequences. 93%
Similar papers in this journal
- Interpretable PROTAC degradation prediction with structure-informed deep ternary attention framework 93%
- Automatically Defining Protein Words for Diverse Functional Predictions Based on Attention Analysis of a Protein Language Model 91%
- ProSiteHunter: A unified framework for sequence-based prediction of protein-nucleic acid and protein-protein binding sites 91%
Similar papers in this journal
- Improving classification of correct and incorrect protein-protein docking models by augmenting the training set 92%
- SAINT-Angle: self-attention augmented inception-inside-inception network and transfer learning improve protein backbone torsion angle prediction 92%
- TemBERTure: Advancing protein thermostability prediction with Deep Learning and attention mechanisms 91%
Similar papers in this journal
Similar papers in this journal
- NanoTox: Development of a parsimonious in silico model for toxicity assessment of metal-oxide nanoparticles using physicochemical features 92%
- Predictive Models and Impact of Interfacial Contacts and Amino Acids on Protein-protein Binding Affinity 92%
- EGGNet, a generalizable geometric deep learning framework for protein complex pose scoring 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.