PyFeat: a Python-based effective feature generation tool for DNA, RNA and protein sequences

Muhammod, Rafsanjani; Ahmed, Sajid; Farid, Dewan Md.; Shatabda, Swakkhar; Sharma, Alok; Dehzangi, Abdollah

doi:10.1093/bioinformatics/btz165

Cited by 91 publications

(81 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several widely used and convenient bio-sequence feature representation tools have been developed (Mrozek et al, 2013;Liu et al, 2015aLiu et al, , 2019cYu et al, 2015Cheng and Hu, 2018;Hu et al, 2019;Muhammod et al, 2019). The two main tools used in this work were iLearn (Hu et al, 2019) and PyFeat (Muhammod et al, 2019).…”

Section: Feature Representationmentioning

confidence: 99%

See 1 more Smart Citation

RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites

Zhang

Ding

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

One of the ubiquitous chemical modifications in RNA, pseudouridine modification is crucial for various cellular biological and physiological processes. To gain more insight into the functional mechanisms involved, it is of fundamental importance to precisely identify pseudouridine sites in RNA. Several useful machine learning approaches have become available recently, with the increasing progress of next-generation sequencing technology; however, existing methods cannot predict sites with high accuracy. Thus, a more accurate predictor is required. In this study, a random forest-based predictor named RF-PseU is proposed for prediction of pseudouridylation sites. To optimize feature representation and obtain a better model, the light gradient boosting machine algorithm and incremental feature selection strategy were used to select the optimum feature space vector for training the random forest model RF-PseU. Compared with previous state-of-the-art predictors, the results on the same benchmark data sets of three species demonstrate that RF-PseU performs better overall. The integrated average leave-one-out cross-validation and independent testing accuracy scores were 71.4% and 74.7%, respectively, representing increments of 3.63% and 4.77% versus the best existing predictor. Moreover, the final RF-PseU model for prediction was built on leave-one-out cross-validation and provides a reliable and robust tool for identifying pseudouridine sites. A web server with a user-friendly interface is accessible at http://148.70.81.170:10228/rfpseu.

show abstract

Section: Feature Representationmentioning

confidence: 99%

“…In this study, X, Y, and k were set to 1, 2, or 3; and eight XYK combinations (except for 3mer-kspaced-3mer) were used for encoding. The PyFeat tool developed by Rafsanjani et al (Muhammod et al, 2019) was used to convert RNA sequences into vectors.…”

Section: Xmer K-spaced Ymer Composition Frequencymentioning

confidence: 99%

RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites

Zhang

Ding

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…1). The 25 feature encoding algorithms are provided in detail in the Supplementary methods; each feature was generated by using a package of comprehensive protein feature generation tools, including 188D [45], Pse-in-One [73], iFeature [42] and pyFeat [43], or custom Python scripts.…”

Section: B Feature Extraction Strategymentioning

confidence: 99%

FunEffector-Pred: Identification of Fungi Effector by Activate Learning and Genetic Algorithm Sampling of Imbalanced Data

Wang

Han

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Fungal pathogens have evolved the ability to cause serious plant diseases and threaten the world food security. Fungal effectors are proteins that exploit the host cellular functions to facilitate infection. Effector identification is crucial for disease control in crops and to understand plant-pathogen interactions. However, fungal effector identification has been challenging as most fungal effectors lack of consensus motifs and data imbalance problem. In this study, a fungal effector predictor was designed to effectively learn from an imbalanced dataset. A granular support vector-based under-sampling (GSV-US) strategy combined with a genetic algorithm was used for majority class sampling. When evaluating on an independent test dataset, the FunEffector-Pred significantly outperformed the existing predictors for fungal effector identification. Several informative feature patterns, such as the patterns of Ile, Gly, Val, Leu and Thr, as well as the combination of aromatic amino acids with positively-charged amino acids, are reported for fungal effector identification for the first time. INDEX TERMS Activate learning, fungal effector, genetic algorithms, imbalanced data.

show abstract

“…Similarly, xxKGAP feature is one variation of Kmer method implemented in PyFeat package [36], where the composition of subsequences with k-gaps is used to describe sequences. In this paper, we choose monoMonoKGap (mMKGap), monoDiKGap (mDKGap) and monoTriKGap (mTKGap) features with k = 1∼3 to construct.…”

Section: ) Xxkgapmentioning

confidence: 99%

iRNA-m5C_NB: A Novel Predictor to Identify RNA 5-Methylcytosine Sites Based on the Naive Bayes Classifier

Dou

Ding

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As one of the widespread RNA post-transcriptional modifications (PTCMs), 5-Methylcytosine (m5C) plays vital roles in better understanding of basic biological mechanisms and major disease treatments. In experiments, traditional high-throughput approaches to find m5C sites are usually expensive and laborious. Additionally, facing with a large number of RNA sequences, developing accurate computational methods to distinguish m5C and non-m5C sites is an efficient solution. Here we introduced a novel predictor, called iRNA-m5C_NB, to identify m5C sites in Home sapiens using Naive Bayes (NB) algorithm. In this method, unbalanced dataset Met935 is firstly analyzed using efficient hybrid-sampling strategy SMOTEEEN. Then top 57 features are selected by the ANOVA F-value from four kinds of well-performance feature extraction techniques, including Bi-profile Bayes (BPB), enhanced Nucleic Acid Composition (ENAC), electron-ion interaction pseudopotentials (EIIP) and mMGap_1. Based on the jackknife test, the evaluated recall for the unbalanced training dataset Met935 is up to 82.81% with MCC of 0.63. And for the independent dataset Test1157, the predictor still shows high recall of 70.06% and MCC of 0.34. It is the first m5C predictor constructed using the unbalanced dataset, and the recall scores are increased by 19.82% and 59.23% for jackknife and independent tests compared with the latest tool RNAm5CPred, respectively. We demonstrate that the proposed predictor iRNA-m5C_NB outperforms other state-of-art models, which hopes to be an efficient and reliable method to identify m5C sites. INDEX TERMS 5-Methylcytosine, bi-profile Bayes, naive Bayes, unbalanced data, feature selection.

show abstract

PyFeat: a Python-based effective feature generation tool for DNA, RNA and protein sequences

Cited by 91 publications

References 12 publications

RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites

RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites

FunEffector-Pred: Identification of Fungi Effector by Activate Learning and Genetic Algorithm Sampling of Imbalanced Data

iRNA-m5C_NB: A Novel Predictor to Identify RNA 5-Methylcytosine Sites Based on the Naive Bayes Classifier

Contact Info

Product

Resources

About