GeoBind: segmentation of nucleic acid binding interface on protein surface with geometric deep learning

Li, Pengpai; Liu, Zhi-Ping

doi:10.1093/nar/gkad288

Cited by 16 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, unlike methods that only explore the C α models of proteins 25,40 , GPSite exploits a comprehensive geometric featurizer to fully refine knowledge in the backbone and sidechain atoms. Third, the employed message propagation on residue graphs is global structure-aware and time-efficient compared to the methods based on surface point clouds 21,22 , and memory-efficient unlike methods based on full atom graphs 23,24 . Last but not least, instead of predicting binding sites for a single molecule type or learning binding patterns separately for different molecules, GPSite applies multi-task learning to better model the latent relationships among different binding partners.…”

Section: Resultsmentioning

confidence: 99%

“…To demonstrate the effectiveness of our method, we compared GPSite with 8 sequence-based predictors including DRNApred 12 , NCBRPred 43 , SVMnuc 44 , PepBind 14 , PepNN-Seq 45 , PepBCL 17 , TargetS 15 , and LMetalSite 18 , as well as 15 structure-based predictors including NucBind 44 , COACH-D 46 , GraphBind 25 , GeoBind 22 , aaRNA 47 , PepNN-Struct 45 , DeepPPISP 48 , SPPIDER 49 , MaSIF-site 21 , GraphPPIS 26 , ScanNet 23 , PeSTo 24 , DELIA 19 , MIB 50 , and IonCom 51 (see Appendix 1-’Brief introductions to the competitive methods’ for more details). For most competitive methods, we used their webservers or standalone programs for evaluation.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Genome-scale annotation of protein binding sites via language model and geometric deep learning

Yuan,

Tian,

Yang

2023

Preprint

View full text Add to dashboard Cite

Revealing protein binding sites with other molecules, such as nucleic acids, peptides, or small ligands, sheds light on disease mechanism elucidation and novel drug design. With the explosive growth of proteins in sequence databases, how to accurately and efficiently identify these binding sites from sequences becomes essential. However, current methods mostly rely on expensive multiple sequence alignments or experimental protein structures, limiting their genome-scale applications. Besides, these methods haven’t fully explored the geometry of the protein structures. Here, we propose GPSite, a multi-task network for simultaneously predicting binding residues of DNA, RNA, peptide, protein, ATP, HEM, and metal ions on proteins. GPSite was trained on informative sequence embeddings and predicted structures from protein language models, while comprehensively extracting residual and relational geometric contexts in an end-to-end manner. Experiments demonstrate that GPSite substantially surpasses state-of-the-art sequence-based and structure-based approaches on various benchmark datasets, even when the structures are not well-predicted. The low computational cost of GPSite enables rapid genome-scale binding residue annotations for over 568,000 sequences, providing opportunities to unveil unexplored associations of binding sites with molecular functions, biological processes, and genetic variants. The GPSite webserver and annotation database can be freely accessed athttps://bio-web1.nscc-gz.cn/app/GPSite.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Genome-scale annotation of protein binding sites via language model and geometric deep learning

Yuan,

Tian,

Yang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In fact, the ESM2-generated feature embedding information has been successfully employed to lots of bioinformatics research fields, such as B-cell epitope identification, 31 antihypertensive peptide screening, 32 and protein-nucleic binding site prediction. 33 The ESM2 model is trained by a deep transformer neural network module on millions of diverse amino acid sequences for simulating protein language patterns, allowing us to extract information-rich feature vectors, which are robust to sequence diversity while being trained on a relatively small data set. 34 There are several pretrained models of ESM2 (see https://github.com/ facebookresearch/esm).…”

Section: ■ Materials and Methodsmentioning

confidence: 99%

“…In this study, we employ ESM2, a pretrained protein language model introduced previously by Facebook to help us to dig out fast and automatically extract the high-latent discriminative representations of protein sequences relevant for protein functions. In fact, the ESM2-generated feature embedding information has been successfully employed to lots of bioinformatics research fields, such as B-cell epitope identification, antihypertensive peptide screening, and protein-nucleic binding site prediction . The ESM2 model is trained by a deep transformer neural network module on millions of diverse amino acid sequences for simulating protein language patterns, allowing us to extract information-rich feature vectors, which are robust to sequence diversity while being trained on a relatively small data set .…”

Section: Methodsmentioning

confidence: 99%

E2EATP: Fast and High-Accuracy Protein–ATP Binding Residue Prediction via Protein Language Model Embedding

Rao,

Yu,

Bai

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Identifying the ATP-binding sites of proteins is fundamentally important to uncover the mechanisms of protein functions and explore drug discovery. Many computational methods are proposed to predict ATP-binding sites. However, due to the limitation of the quality of feature representation, the prediction performance still has a big room for improvement. In this study, we propose an end-to-end deep learning model, E2EATP, to dig out more discriminative information from a protein sequence for improving the ATP-binding site prediction performance. Concretely, we employ a pretrained deep learning-based protein language model (ESM2) to automatically extract high-latent discriminative representations of protein sequences relevant for protein functions. Based on ESM2, we design a residual convolutional neural network to train a protein−ATP binding site prediction model. Furthermore, a weighted focal loss function is used to reduce the negative impact of imbalanced data on the model training stage. Experimental results on the two independent testing data sets demonstrate that E2EATP could achieve higher Matthew's correlation coefficient and AUC values than most existing state-of-the-art prediction methods. The speed (about 0.05 s per protein) of E2EATP is much faster than the other existing prediction methods. Detailed data analyses show that the major advantage of E2EATP lies at the utilization of the pretrained protein language model that extracts more discriminative information from the protein sequence only. The standalone package of E2EATP is freely available for academic at https://github.com/jun-csbio/e2eatp/.

show abstract

“…Their method has been applied to protein-ligand, protein-NA, protein-ion and protein-lipid binding. GeoBind 21 utilizes quasi-geodesic convolutions over point clouds for DNA and RNA binding site prediction with features closely based on dMaSIF 22 . Other recent methods which do not utilize GNNs but are closely related include MaSIF 23 which predicts protein-protein binding interfaces and small-ligand binding sites and PST-PRNA 24 which predicts RNA bind sites.…”

Section: Introductionmentioning

confidence: 99%

PNAbind: Structure-based prediction of protein-nucleic acid binding using graph neural networks

Sagendorf,

Mitra,

Huang

et al. 2024

Preprint

View full text Add to dashboard Cite

The recognition and binding of nucleic acids (NAs) by proteins depends upon complementary chemical, electrostatic and geometric properties of the protein-NA binding interface. Structural models of protein-NA complexes provide insights into these properties but are scarce relative to models of unbound proteins. We present a deep learning approach for predicting protein-NA binding given the apo structure of a protein (PNAbind). Our method utilizes graph neural networks to encode spatial distributions of physicochemical and geometric properties of the protein molecular surface that are predictive of NA binding. Using global physicochemical encodings, our models predict the overall binding function of a protein and can discriminate between specificity for DNA or RNA binding. We show that such predictions made on protein structures modeled with AlphaFold2 can be used to gain mechanistic understanding of chemical and structural features that determine NA recognition. Using local encodings, our models predict the location of NA binding sites at the level of individual binding residues. Binding site predictions were validated against benchmark datasets, achieving AUROC scores in the range of 0.92-0.95. We applied our models to the HIV-1 restriction factor APOBEC3G and show that our predictions are consistent with experimental RNA binding data.

show abstract

GeoBind: segmentation of nucleic acid binding interface on protein surface with geometric deep learning

Cited by 16 publications

References 47 publications

Genome-scale annotation of protein binding sites via language model and geometric deep learning

Genome-scale annotation of protein binding sites via language model and geometric deep learning

E2EATP: Fast and High-Accuracy Protein–ATP Binding Residue Prediction via Protein Language Model Embedding

PNAbind: Structure-based prediction of protein-nucleic acid binding using graph neural networks

Contact Info

Product

Resources

About