ProteDNA: a sequence-based predictor of sequence-specific DNA-binding residues in transcription factors

Chu, Weidong; Huang, Yu‐Feng; Huang, Chun-Chin; Cheng, Yi-Sheng; Huang, Chien-Kang; Oyang, Yen-Jen

doi:10.1093/nar/gkp449

Cited by 42 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(B) ORF1 harbors a putative helix-turn-helix DNA-binding motif in its N-terminal domain, and the two ␣ helices, ␣1 and ␣2, are shown boxed in black in the wild-type sequence. ␣1 and ␣2 were predicted using the software programs Phyre (35) and ProteDNA (14). ditional mutation.…”

Section: Fig 2 Cp Mutants In Orf1 and Orf7mentioning

confidence: 99%

Phage-Borne Factors and Host LexA Regulate the Lytic Switch in Phage GIL01

2011

View full text Add to dashboard Cite

The Bacillus thuringiensis temperate phage GIL01 does not integrate into the host chromosome but exists stably as an independent linear replicon within the cell. Similar to that of the lambdoid prophages, the lytic cycle of GIL01 is induced as part of the cellular SOS response to DNA damage. However, no CI-like maintenance repressor has been detected in the phage genome, suggesting that GIL01 uses a novel mechanism to maintain lysogeny. To gain insights into the GIL01 regulatory circuit, we isolated and characterized a set of 17 clear plaque (cp) mutants that are unable to lysogenize. Two phage-encoded proteins, gp1 and gp7, are required for stable lysogen formation. Analysis of cp mutants also identified a 14-bp palindromic dinBox1 sequence within the P1-P2 promoter region that resembles the known LexA-binding site of Gram-positive bacteria. Mutations at conserved positions in dinBox1 result in a cp phenotype. Genomic analysis identified a total of three dinBox sites within GIL01 promoter regions. To investigate the possibility that the host LexA regulates GIL01, phage induction was measured in a host carrying a noncleavable lexA (Ind ؊ ) mutation. GIL01 formed stable lysogens in this host, but lytic growth could not be induced by treatment with mitomycin C. Also, mitomycin C induced ␤-galactosidase expression from GIL01-lacZ promoter fusions, and induction was similarly blocked in the lexA (Ind ؊ ) mutant host. These data support a model in which host LexA binds to dinBox sequences in GIL01, repressing phage gene expression during lysogeny and providing the switch necessary to enter lytic development.

show abstract

Section: Fig 2 Cp Mutants In Orf1 and Orf7mentioning

confidence: 99%

Phage-Borne Factors and Host LexA Regulate the Lytic Switch in Phage GIL01

2011

View full text Add to dashboard Cite

show abstract

“…Secondary structure is an important structural feature of protein that can significantly improve the function prediction performance [46,47]. In this study, secondary structure calculation is carried out by PSIPRED v3.0 [48], which is one of the state-of-the-art protein secondary structure prediction methods with an accuracy of up to 80%.…”

Section: Methodsmentioning

confidence: 99%

An improved sequence based prediction protocol for DNA-binding proteins using SVM and comprehensive feature analysis

Zou

Gong

2013

BMC Bioinformatics

View full text Add to dashboard Cite

BackgroundDNA-binding proteins (DNA-BPs) play a pivotal role in both eukaryotic and prokaryotic proteomes. There have been several computational methods proposed in the literature to deal with the DNA-BPs, many informative features and properties were used and proved to have significant impact on this problem. However the ultimate goal of Bioinformatics is to be able to predict the DNA-BPs directly from primary sequence.ResultsIn this work, the focus is how to transform these informative features into uniform numeric representation appropriately and improve the prediction accuracy of our SVM-based classifier for DNA-BPs. A systematic representation of some selected features known to perform well is investigated here. Firstly, four kinds of protein properties are obtained and used to describe the protein sequence. Secondly, three different feature transformation methods (OCTD, AC and SAA) are adopted to obtain numeric feature vectors from three main levels: Global, Nonlocal and Local of protein sequence and their performances are exhaustively investigated. At last, the mRMR-IFS feature selection method and ensemble learning approach are utilized to determine the best prediction model. Besides, the optimal features selected by mRMR-IFS are illustrated based on the observed results which may provide useful insights for revealing the mechanisms of protein-DNA interactions. For five-fold cross-validation over the DNAdset and DNAaset, we obtained an overall accuracy of 0.940 and 0.811, MCC of 0.881 and 0.614 respectively.ConclusionsThe good results suggest that it can efficiently develop an entirely sequence-based protocol that transforms and integrates informative features from different scales used by SVM to predict DNA-BPs accurately. Moreover, a novel systematic framework for sequence descriptor-based protein function prediction is proposed here.

show abstract

“…Different from the previous protein-DNA binding site dataset, PDNA-543 (9549 binding residues and 134,995 non-binding residues) and PDNA-41 (734 binding residues and 14,021 non-binding residues) are datasets constructed by Hu et al [61]. SXGBsite constructed the prediction model by the PDNA-543 training set, obtained prediction results on the PDNA-41 independent test set, and the comparison of SXGBsite with BindN [37], ProteDNA [62], BindN+ [63], MetaDBSite [32], DP-Bind [39], DNABind [64], TargetDNA [61], and EC-RUS(DNA) [44] is provided in Table 10. SXGBsite achieved the best MCC (0.272) under Sen ≈ Spec, and achieved MCC after EC-RUS(DNA) and TargetDNA under FPR ≈ 5% (FPR = 1 -SP).…”

Section: Running Time Comparisonmentioning

confidence: 99%

SXGBsite: Prediction of Protein–Ligand Binding Sites Using Sequence Information and Extreme Gradient Boosting

Zhao

2019

Genes

View full text Add to dashboard Cite

The prediction of protein–ligand binding sites is important in drug discovery and drug design. Protein–ligand binding site prediction computational methods are inexpensive and fast compared with experimental methods. This paper proposes a new computational method, SXGBsite, which includes the synthetic minority over-sampling technique (SMOTE) and the Extreme Gradient Boosting (XGBoost). SXGBsite uses the position-specific scoring matrix discrete cosine transform (PSSM-DCT) and predicted solvent accessibility (PSA) to extract features containing sequence information. A new balanced dataset was generated by SMOTE to improve classifier performance, and a prediction model was constructed using XGBoost. The parallel computing and regularization techniques enabled high-quality and fast predictions and mitigated overfitting caused by SMOTE. An evaluation using 12 different types of ligand binding site independent test sets showed that SXGBsite performs similarly to the existing methods on eight of the independent test sets with a faster computation time. SXGBsite may be applied as a complement to biological experiments.

show abstract

ProteDNA: a sequence-based predictor of sequence-specific DNA-binding residues in transcription factors

Cited by 42 publications

References 18 publications

Phage-Borne Factors and Host LexA Regulate the Lytic Switch in Phage GIL01

Phage-Borne Factors and Host LexA Regulate the Lytic Switch in Phage GIL01

An improved sequence based prediction protocol for DNA-binding proteins using SVM and comprehensive feature analysis

SXGBsite: Prediction of Protein–Ligand Binding Sites Using Sequence Information and Extreme Gradient Boosting

Contact Info

Product

Resources

About