RecSNO: Prediction of Protein S-Nitrosylation Sites Using a Recurrent Neural Network

Siraj, Arslan; Chantsalnyam, Tuvshinbayar; Tayara, Hilal; Chong, Kil To

doi:10.1109/access.2021.3049142

Cited by 18 publications

(12 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, deep learning is also capable of identifying and recognizing the patterns in unstructured data with low-level involvement of manual configuration [41] . Thus, deep learning has breakthroughs in the fields of natural language processing [42] , speech recognition [43] , image recognition [44] , precision agriculture [45] , [46] , [47] , potential drug molecules [48] , post-translation modifications [49] , [50] , RNA binding proteins [51] , [52] , post-transcriptional modifications [53] , [54] , [55] , identification of promoters [56] , [57] , [58] , DNA modifications [59] , [60] , [61] , [62] , and prediction of disease association [63] , [64] , [65] . In the present study, we proposed deep learning architecture piRDA consist of CNN and fully connected layers, CNN is the most commonly used deep learning method considering its efficacy and efficiency in various applications.…”

Section: Introductionmentioning

confidence: 99%

Identification of piRNA disease associations using deep learning

Tayara

Chong

2022

Computational and Structural Biotechnology Journal

Self Cite

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Identification of piRNA disease associations using deep learning

Tayara

Chong

2022

Computational and Structural Biotechnology Journal

Self Cite

View full text Add to dashboard Cite

“…In this study, we applied four standard measures that are widely used in binary classification tasks to evaluate the performance of bioinformatics tools [37][38][39][40][41][42][43], namely, accuracy (ACC), sensitivity (SN), specificity (SP), and Matthew correlation coefficient (MCC). Mathematically, these measures are expressed as follows:…”

Section: Evaluation Measuresmentioning

confidence: 99%

i4mC-Deep: An Intelligent Predictor of N4-Methylcytosine Sites Using a Deep Learning Approach with Chemical Properties

Alam

Tayara

Chong

2021

Genes

Self Cite

View full text Add to dashboard Cite

DNA is subject to epigenetic modification by the molecule N4-methylcytosine (4mC). N4-methylcytosine plays a crucial role in DNA repair and replication, protects host DNA from degradation, and regulates DNA expression. However, though current experimental techniques can identify 4mC sites, such techniques are expensive and laborious. Therefore, computational tools that can predict 4mC sites would be very useful for understanding the biological mechanism of this vital type of DNA modification. Conventional machine-learning-based methods rely on hand-crafted features, but the new method saves time and computational cost by making use of learned features instead. In this study, we propose i4mC-Deep, an intelligent predictor based on a convolutional neural network (CNN) that predicts 4mC modification sites in DNA samples. The CNN is capable of automatically extracting important features from input samples during training. Nucleotide chemical properties and nucleotide density, which together represent a DNA sequence, act as CNN input data. The outcome of the proposed method outperforms several state-of-the-art predictors. When i4mC-Deep was used to analyze G. subterruneus DNA, the accuracy of the results was improved by 3.9% and MCC increased by 10.5% compared to a conventional predictor.

show abstract

“…Another possibility is that NO directly activates CFTR via s-nitrosylation. Analysis of the chicken CFTR sequence with the bioinformatics program RecSNO (Siraj et al, 2021 ) predicts nine likely s-nitrosylation sites. However, our observation of NO-dependent Ca 2+ elevations leads us to prioritize investigating the role of AdC1.…”

Section: Introductionmentioning

confidence: 99%

Adenylate Cyclase 1 Links Calcium Signaling to CFTR-Dependent Cytosolic Chloride Elevations in Chick Amacrine Cells

Zhong

Gleason

2021

Front. Cell. Neurosci.

View full text Add to dashboard Cite

The strength and sign of synapses involving ionotropic GABA and glycine receptors are dependent upon the Cl− gradient. We have shown that nitric oxide (NO) elicits the release of Cl− from internal acidic stores in retinal amacrine cells (ACs); temporarily altering the Cl− gradient and the strength or even sign of incoming GABAergic or glycinergic synapses. The underlying mechanism for this effect of NO requires the cystic fibrosis transmembrane regulator (CFTR) but the link between NO and CFTR activation has not been determined. Here, we test the hypothesis that NO-dependent Ca2+ elevations activate the Ca2+-dependent adenylate cyclase 1 (AdC1) leading to activation of protein kinase A (PKA) whose activity is known to open the CFTR channel. Using the reversal potential of GABA-gated currents to monitor cytosolic Cl−, we established the requirement for Ca2+ elevations. Inhibitors of AdC1 suppressed the NO-dependent increases in cytosolic Cl− whereas inhibitors of other AdC subtypes were ineffective suggesting that AdC1 is involved. Inhibition of PKA also suppressed the action of NO. To address the sufficiency of this pathway in linking NO to elevations in cytosolic Cl−, GABA-gated currents were measured under internal and external zero Cl− conditions to isolate the internal Cl− store. Activators of the cAMP pathway were less effective than NO in producing GABA-gated currents. However, coupling the cAMP pathway activators with the release of Ca2+ from stores produced GABA-gated currents indistinguishable from those stimulated with NO. Together, these results demonstrate that cytosolic Ca2+ links NO to the activation of CFTR and the elevation of cytosolic Cl−.

show abstract

RecSNO: Prediction of Protein S-Nitrosylation Sites Using a Recurrent Neural Network

Cited by 18 publications

References 68 publications

Identification of piRNA disease associations using deep learning

Identification of piRNA disease associations using deep learning

i4mC-Deep: An Intelligent Predictor of N4-Methylcytosine Sites Using a Deep Learning Approach with Chemical Properties

Adenylate Cyclase 1 Links Calcium Signaling to CFTR-Dependent Cytosolic Chloride Elevations in Chick Amacrine Cells

Contact Info

Product

Resources

About