New layers in understanding and predicting α-linolenic acid content in plants using amino acid characteristics of omega-3 fatty acid desaturase

Zinati, Zahra; Zamansani, Fatemeh; Kayvanjoo, Amir Hossein; Ebrahimi, Mahdi; Ebrahimi, Mansour; Ebrahimie, Esmaeil; Mohammadi‐Dehcheshmeh, Manijeh

doi:10.1016/j.compbiomed.2014.08.019

Cited by 16 publications

(16 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies related to druggable protein predictions concentrated on only a few attributes, which are unlikely to represent all aspects of protein-drug interactions and also have issues related to limitations of estimations and assumptions [17,39]. However, in this study, we increased the number of features to find the key ones, which is one of the reasons for the high accuracy of prediction in this study [19,23,24,26].…”

Section: Discussionmentioning

confidence: 96%

“…In these approaches, simple sequence properties, such as amino acid and di-peptide content and/or frequency, are used to predict potential targets [16][17][18]. Computationally calculated structural amino acid and/or protein features are useful because they can be easily calculated based on sequence and frequently predict protein function accurately [19][20][21][22][23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DrugMiner: comparative analysis of machine learning algorithms for prediction of potential druggable proteins

Jamali

Ferdousi

Razzaghi

et al. 2016

Drug Discovery Today

Self Cite

View full text Add to dashboard Cite

Application of computational methods in drug discovery has received increased attention in recent years as a way to accelerate drug target prediction. Based on 443 sequence-derived protein features, we applied the most commonly used machine learning methods to predict whether a protein is druggable as well as to opt for superior algorithm in this task. In addition, feature selection procedures were used to provide the best performance of each classifier according to the optimum number of features. When run on all features, Neural Network was the best classifier, with 89.98% accuracy, based on a k-fold cross-validation test. Among all the algorithms applied, the optimum number of most-relevant features was 130, according to the Support Vector Machine-Feature Selection (SVM-FS) algorithm. This study resulted in the discovery of new drug target which potentially can be employed in cell signaling pathways, gene expression, and signal transduction. The DrugMiner web tool was developed based on the findings of this study to provide researchers with the ability to predict druggable proteins. DrugMiner is freely available at www.DrugMiner.org.

show abstract

Section: Discussionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

DrugMiner: comparative analysis of machine learning algorithms for prediction of potential druggable proteins

Jamali

Ferdousi

Razzaghi

et al. 2016

Drug Discovery Today

Self Cite

View full text Add to dashboard Cite

show abstract

“…Weighting algorithms provide useful information about those attributes which are most significant for prediction or classification. In this investigation, 70 % of the weighting algorithms selected features such as non-reduced coefficient pertaining to Cys extinction, non-reduced absorption within 280 nm, length, the hydrogen, Val, carbon, Ala, hydrophilic residues frequencies, and the counts of Phe-Phe, Val, Ala-Ile, Phe-Leu, Val-Ala, Asp, Ser, Arg, Phe, Tyr, hydrophilic residues as the most important protein attributes in classification , thermo stability ) and α-linolenic acid content (Zinati et al 2014).…”

Section: Discussionmentioning

confidence: 99%

“…These mentioned approaches have been taken to specify important structural attributes, prediction and classification of protein thermo-stability (Ebrahimi et al 2009), P glycoprotein pump (Hammann et al 2009) halo-stability , olive cultivars (Beiki et al 2012), α-linolenic acid content (Zinati et al 2014) as well as genotype discrimination (Nasiri et al 2015).…”

Section: Discussionmentioning

confidence: 99%

Computational approaches for classification and prediction of P-type ATPase substrate specificity in Arabidopsis

Zinati

Alemzadeh

Kayvanjoo

2016

Physiol Mol Biol Plants

Self Cite

View full text Add to dashboard Cite

As an extended gamut of integral membrane (extrinsic) proteins, and based on their transporting specificities, P-type ATPases include five subfamilies in Arabidopsis, inter alia, P4ATPases (phospholipid-transporting ATPase), P3AATPases (plasma membrane H(+) pumps), P2A and P2BATPases (Ca(2+) pumps) and P1B ATPases (heavy metal pumps). Although, many different computational methods have been developed to predict substrate specificity of unknown proteins, further investigation needs to improve the efficiency and performance of the predicators. In this study, various attribute weighting and supervised clustering algorithms were employed to identify the main amino acid composition attributes, which can influence the substrate specificity of ATPase pumps, classify protein pumps and predict the substrate specificity of uncharacterized ATPase pumps. The results of this study indicate that both non-reduced coefficients pertaining to absorption and Cys extinction within 280 nm, the frequencies of hydrogen, Ala, Val, carbon, hydrophilic residues, the counts of Val, Asn, Ser, Arg, Phe, Tyr, hydrophilic residues, Phe-Phe, Ala-Ile, Phe-Leu, Val-Ala and length are specified as the most important amino acid attributes through applying the whole attribute weighting models. Here, learning algorithms engineered in a predictive machine (Naive Bays) is proposed to foresee the Q9LVV1 and O22180 substrate specificities (P-type ATPase like proteins) with 100 % prediction confidence. For the first time, our analysis demonstrated promising application of bioinformatics algorithms in classifying ATPases pumps. Moreover, we suggest the predictive systems that can assist towards the prediction of the substrate specificity of any new ATPase pumps with the maximum possible prediction confidence.

show abstract

“…Feature selection is an essential tool with many applications, including bioinformatics where we encounter high-dimensional data (Bakhtiarizadeh et al, 2014;Ebrahimi et al, 2014;Zinati et al, 2014). During the last decade, the motivation for applying feature selection (attribute weighting) techniques in bioinformatics has shifted from being an illustrative example to becoming a real prerequisite for model building (Krämer et al, 2009).…”

Section: Introductionmentioning

confidence: 99%

Research paper Determining the structural amino acid attributes which are important in both protein thermostability and alkalophilicity: a case study on xylanase

Delavari¹,

Zare²,

Ghaemi³

et al. 2014

bta

Self Cite

View full text Add to dashboard Cite

Xylanases are used in the recycling of biomass and have other industrial applications including pulp bleaching. These enzymes are also applied in the baking industry and for the manufacture of animal feed. Such technologies as, for example, pulp bleaching entail high temperatures and high pHs. As a result, there is great demand from industry for thermostable and halostable forms of xylanase. Due to the relatively high variation in the thermo-and halo-stability of xylanases, feature selection was employed as a model to discover the important attributes of their amino acid sequences affecting the thermo-and halo-stability of the enzyme. A data set containing the amino acid sequences of xylanases with different thermo-and halostabilities was collected. Seventy-four amino acid attributes were obtained for each enzyme sequence. After running a feature selection algorithm for each of the thermo-and halostablity variables, features were classified as either important, unimportant or marginal. The results showed a significant correlation between structural amino acid attitudes and stability in harsh temperatures or alkaline conditions. Features such as lysine, glutamic acid, and positively/negatively charged residues showed a positive correlation with both the thermostability and alkalophilicity attributes of the protein. For the first time, we found attributes which were important for both stability at high temperatures as well as in alkaline conditions by mining sequence-derived amino acid attributes using data mining.

show abstract

New layers in understanding and predicting α-linolenic acid content in plants using amino acid characteristics of omega-3 fatty acid desaturase

Cited by 16 publications

References 48 publications

DrugMiner: comparative analysis of machine learning algorithms for prediction of potential druggable proteins

DrugMiner: comparative analysis of machine learning algorithms for prediction of potential druggable proteins

Computational approaches for classification and prediction of P-type ATPase substrate specificity in Arabidopsis

Research paper Determining the structural amino acid attributes which are important in both protein thermostability and alkalophilicity: a case study on xylanase

Contact Info

Product

Resources

About