Binding of and ligands to proteins is crucial for biological processes, making accurate prediction of their binding sites essential. However, the limited number of known binding residues poses a challenge for improving prediction accuracy. To address this, we selected features from both fragment and single-residue levels, ensuring comprehensive information. In this study, we integrated the SMOTE algorithm, Self-Attention mechanism, and DCNN algorithm to propose a new integrated algorithm, SS-DCNN. This effectively overcomes the limitations of DCNN, which struggles with low accuracy for small samples and capturing global features. When the fused features of and ligands were input into SS-DCNN, the MCC values for 5-cross-validation reached 0.848 8 and 0.740 9, and for independent tests, 0.169 5 and 0.190 2, respectively, outperforming the DCNN model and previous predictions.
LEVB, CHENNATHM, CRANFIELDC G, et al. Involvement of the alpha-subunit N-terminus in the mechanism of the Na+, K+-ATPase[J]. Biochimica et Biophysica Acta (BBA): Molecular Cell Research, 2023, 1870(7): 119539.
[2]
GULATIA, KOKANES, PEREZ-BOEREMAA, et al. Structure and mechanism of the K+/H+ exchanger KefC[J]. Nature Communications, 2024, 15(1): 4751.
[3]
LINC T, LINK L, YANGC H, et al. Protein metal binding residue prediction based on neural networks[J]. International Journal of Neural Systems, 2005, 15(1/2): 71-84.
[4]
HUX Z, DONGQ W, YANGJ Y, et al. Recognizing metal and acid radical ion-binding sites by integrating ab initio modeling with template-based transferals[J]. Bioinformatics, 2016, 32(21): 3260-3269.
[5]
HUX Z, FENGZ X, ZHANGX J, et al. The identification of metal ion ligand-binding residues by adding the reclassified relative solvent accessibility[J]. Frontiers in Genetics, 2020, 11: 214.
[6]
LIUL, HUX Z, FENGZ X, et al. Recognizing ion ligand-binding residues by random forest algorithm based on optimized dihedral angle[J]. Frontiers in Bioengineering and Biotechnology, 2020, 8: 493.
[7]
WANGS, HUX Z, FENGZ X, et al. Recognition of ion ligand binding sites based on amino acid features with the fusion of energy, physicochemical and structural features[J]. Current Pharmaceutical Design, 2021, 27(8): 1093-1102.
[8]
XUS, HUX Z, FENGZ X, et al. Recognition of metal ion ligand-binding residues by adding correlation features and propensity factors[J]. Frontiers in Genetics, 2021, 12: 793800.
HAOS X, HUX Z, FENGZ X, et al. Prediction of metal ion ligand binding residues by adding disorder value and propensity factors based on deep learning algorithm[J]. Frontiers in Genetics, 2022, 13: 969412.
YOUX X, HUX Z, FENGZ X, et al. Recognizing protein-metal ion ligands binding residues by random forest algorithm with adding orthogonal properties[J]. Computational Biology and Chemistry, 2022, 98: 107693.
[13]
陈少华, 胡秀珍, 胡慧敏, 等. 融合单残基信息的U-RF算法识别 S O 4 2 - 和 P O 4 3 - 配体结合位点[J]. 内蒙古大学学报(自然科学版), 2024, 55(2): 183-192.
[14]
XIAT, ZHAOB, LIB, et al. MRI-based radiomics and deep learning in biological characteristics and prognosis of hepatocellular carcinoma: opportunities and challenges[J]. Journal of Magnetic Resonance Imaging, 2024, 59(3): 767-783.
[15]
SHAIKHS, RAHUA G, RAHUM U R. Identifying DNA-binding proteins using local features DPC-PSSM and AB-PSSM with primary sequences based on 2DCNN[DB/OL]. (2024-03-09)[2025-02-15].
HADDADIS J, FARSHIDVARDA, SILVAF D S, et al. Customer churn prediction in imbalanced datasets with resampling methods: a comparative study[J]. Expert Systems With Applications, 2024, 246: 123086.
[18]
ZHANGY, LIUC Q, LIUM J I, et al. Attention is all you need:utilizing attention in AI-enabled drug discovery[J]. Briefings in Bioinformatics, 2023, 25(1): bbad467.
[19]
PAPANASTASIOUG, DIKAIOSN, HUANGJ H, et al. Is attention all you need in medical image analysis? A review[J]. IEEE Journal of Biomedical and Health Informatics, 2024, 28(3): 1398-1411.
PEARCER, LIY, OMENNG S, et al. Fast and accurate ab initio protein structure prediction using deep learning potentials[J]. PLoS Computational Biology, 2022, 18(9): e1010539.
[22]
WANGG, SUNQ, WEIM, et al. Plastic film residue reshaped protist communities and induced soil nutrient deficiency under field conditions[J]. Agronomy, 2025, 15(2): 419.