Protein-DNA Binding Residues Prediction Using a Deep Learning Model With Hierarchical Feature Extraction

Guan, Shixuan; Zou, Quan; Wu, Hongjie; Ding, Yuanzhao

doi:10.1109/tcbb.2022.3190933

Cited by 10 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the strong performance of the proposed ULDNA, we made a comparison with 12 existing popular DNA-binding site predictors, including BindN [ 57 ], ProteDNA [ 58 ], BindN+ [ 59 ], MetaDBSite [ 28 ], DP-Bind [ 60 ], DNABind [ 61 ], TargetDNA [ 27 ], iProDNA-CapsNet [ 34 ], DNAPred [ 13 ], Guan’s method [ 32 ], COACH [ 16 ] and PredDBR [ 33 ], on the PDNA-41 test dataset under independent validation, as summarized in Table 2 .…”

Section: Resultsmentioning

confidence: 99%

“…Specifically, most of these methods are driven by simple and straightforward feature representation methods, such as sequence composition coding and evolution conservation analysis, which fail to capture the complex patterns of protein–DNA interaction [ 30 , 31 ]. To partially address this challenge, deep learning techniques have been employed in recently proposed DNA-binding site prediction methods, such as Guan’s method [ 32 ], PredDBR [ 33 ], iProDNA-CapsNet [ 34 ] and GraphBind [ 35 ]. The significant advantage of deep learning techniques over traditional machine learning methods is that they tend to derive more discriminative feature representations using complicated networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ULDNA: integrating unsupervised multi-source language models with LSTM-attention network for high-accuracy protein–DNA binding site prediction

Zhu,

Liu,

Liu

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Efficient and accurate recognition of protein–DNA interactions is vital for understanding the molecular mechanisms of related biological processes and further guiding drug discovery. Although the current experimental protocols are the most precise way to determine protein–DNA binding sites, they tend to be labor-intensive and time-consuming. There is an immediate need to design efficient computational approaches for predicting DNA-binding sites. Here, we proposed ULDNA, a new deep-learning model, to deduce DNA-binding sites from protein sequences. This model leverages an LSTM-attention architecture, embedded with three unsupervised language models that are pre-trained on large-scale sequences from multiple database sources. To prove its effectiveness, ULDNA was tested on 229 protein chains with experimental annotation of DNA-binding sites. Results from computational experiments revealed that ULDNA significantly improves the accuracy of DNA-binding site prediction in comparison with 17 state-of-the-art methods. In-depth data analyses showed that the major strength of ULDNA stems from employing three transformer language models. Specifically, these language models capture complementary feature embeddings with evolution diversity, in which the complex DNA-binding patterns are buried. Meanwhile, the specially crafted LSTM-attention network effectively decodes evolution diversity-based embeddings as DNA-binding results at the residue level. Our findings demonstrated a new pipeline for predicting DNA-binding sites on a large scale with high accuracy from protein sequence alone.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ULDNA: integrating unsupervised multi-source language models with LSTM-attention network for high-accuracy protein–DNA binding site prediction

Zhu,

Liu,

Liu

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…To demonstrate the strong performance of the proposed ULDNA, we compared it with iProDNA-CapsNet [32], DNAPred [10], Guan's method [30], COACH [13], and…”

Section: Comparison With Existing Dna-binding Site Predictorsmentioning

confidence: 99%

“…; https://doi.org/10.1101/2023.05. 30.542787 doi: bioRxiv preprint of informative feature representation methods, as most of the approaches are based on simple feature representations, such as amino acid coding, physiochemical properties, and evolution conservation, which cannot fully extract the complex pattern of protein-DNA interaction [28,29]. To partly overcome this barrier, several methods, e.g., Guan's method [30], PredDBR [31], iProDNA-CapsNet [32], and GraphBind [33], utilize deep learning technology to predict DNA-binding sites.…”

Section: Introductionmentioning

confidence: 99%

“…30.542787 doi: bioRxiv preprint of informative feature representation methods, as most of the approaches are based on simple feature representations, such as amino acid coding, physiochemical properties, and evolution conservation, which cannot fully extract the complex pattern of protein-DNA interaction [28,29]. To partly overcome this barrier, several methods, e.g., Guan's method [30], PredDBR [31], iProDNA-CapsNet [32], and GraphBind [33], utilize deep learning technology to predict DNA-binding sites. Compared to traditional machine learning approaches, one advantage of deep learning technologies is that they could extract more discriminative feature embeddings from sequences and structures through designing complex neural networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ULDNA: Integrating Unsupervised Multi-Source Language Models with LSTM-Attention Network for Protein-DNA Binding Site Prediction

Zhu

2023

Preprint

View full text Add to dashboard Cite

Accurate identification of protein-DNA interactions is critical to understand the molecular mechanisms of proteins and design new drugs. We proposed a novel deeplearning method, ULDNA, to predict DNA-binding sites from protein sequences through a LSTM-attention architecture embedded with three unsupervised language models pretrained in multiple large-scale sequence databases. The method was systematically tested on 1287 proteins with DNA-binding site annotation from Protein Data Bank. Experimental results showed that ULDNA achieved a significant increase of the DNA-binding site prediction accuracy compared to the state-of-the-art approaches. Detailed data analyses showed that the major advantage of ULDNA lies in the utilization of three pre-trained transformer language models which can extract the complementary DNA-binding patterns buried in evolution diversity-based feature embeddings in residue-level. Meanwhile, the designed LSTM-attention network could further enhance the correlation between evolution diversity and protein-DNA interaction. These results demonstrated a new avenue for high-accuracy deep-learning DNA-binding site prediction that is applicable to large-scale protein-DNA binding annotation from sequence alone.

show abstract

Feature Extraction Approach for Predicting Protein-DNA Binding Residues Using Transformer Encoder-Decoder Architecture

Qiu,

Cheng,

et al. 2024

Advanced Intelligent Computing in Bioinformatics

View full text Add to dashboard Cite

Protein-DNA Binding Residues Prediction Using a Deep Learning Model With Hierarchical Feature Extraction

Cited by 10 publications

References 42 publications

ULDNA: integrating unsupervised multi-source language models with LSTM-attention network for high-accuracy protein–DNA binding site prediction

ULDNA: integrating unsupervised multi-source language models with LSTM-attention network for high-accuracy protein–DNA binding site prediction

ULDNA: Integrating Unsupervised Multi-Source Language Models with LSTM-Attention Network for Protein-DNA Binding Site Prediction

Feature Extraction Approach for Predicting Protein-DNA Binding Residues Using Transformer Encoder-Decoder Architecture

Contact Info

Product

Resources

About