MathFeature: feature extraction package for DNA, RNA and protein sequences based on mathematical descriptors

Abstract

One of the main challenges in applying machine learning algorithms to biological sequence data is how to numerically represent a sequence in a numeric input vector. Feature extraction techniques capable of extracting numerical information from biological sequences have been reported in the literature. However, many of these techniques are not available in existing packages, such as mathematical descriptors. This paper presents a new package, MathFeature, which implements mathematical descriptors able to extract relevant numerical information from biological sequences, i.e. DNA, RNA and proteins (prediction of structural features along the primary sequence of amino acids). MathFeature makes available 20 numerical feature extraction descriptors based on approaches found in the literature, e.g. multiple numeric mappings, genomic signal processing, chaos game theory, entropy and complex networks. MathFeature also allows the extraction of alternative features, complementing the existing packages. To ensure that our descriptors are robust and to assess their relevance, experimental results are presented in nine case studies. According to these results, the features extracted by MathFeature showed high performance (0.6350–0.9897, accuracy), both applying only mathematical descriptors, but also hybridization with well-known descriptors in the literature. Finally, through MathFeature, we overcame several studies in eight benchmark datasets, exemplifying the robustness and viability of the proposed package. MathFeature has advanced in the area by bringing descriptors not available in other packages, as well as allowing non-experts to use feature extraction techniques.

BioAutoML: automated feature engineering and metalearning to predict noncoding RNAs in bacteria

“…This module, which is the first feature engineering stage, extracts feature descriptors using the MathFeature package [ 28 ], e.g. Mathematical descriptors (Fourier, Shannon, Tsallis, among others) and Conventional descriptors [Nucleic Acid Composition (NAC), dinucleotide composition (DNC), trinucleotide composition (TNC), ORF Features, Xmer k-Spaced Ymer composition frequency (kGap), Fickett score, among others].…”

“…These tasks can include different ways of preprocessing or feature engineering, as well as algorithms and optimization of its parameters (hyper-parameter tuning) [ 24–26 ]. In this study, BioAutoML calls the MathFeature package [ 27 , 28 ] to extract feature descriptors representing relevant numerical information from ncRNA sequences ( Feature Extraction module ). After receiving the feature values, BioAutoML, automatically recommends, using Bayesian Optimization [ 29 ], the best pair of selected features and predictive model.…”

iFeatureOmega:an integrative platform for engineering, visualization and analysis of features from molecular sequences, structural and ligand data sets

“…Many feature engineering tools that target DNA, RNA, proteins and ligands were released in recent years. They include PseAAC ( 12 ), PROFEAT ( 13 ), PseAAC-Builder ( 14 ), PyDPI ( 15 ), ChemoPy ( 16 ), propy ( 17 ), RDKit ( 18 ), PseAAC-General ( 19 ), Rcpi ( 20 ), ProFET ( 21 ), protr/ProtrWeb ( 22 ), BioTriangle ( 23 ), repRNA ( 24 ), POSSUM ( 25 ), PseKRAAC ( 26 ), iFeature ( 27 ), PyFeat ( 28 ), Seq2Feature ( 29 ), MRMD2.0 ( 30 ) and MathFeature ( 31 ). Besides these feature engineering tools, several platforms for the development of machine learning predictors, including BioSeq-Analysis2.0 ( 32 ), PFeature ( 33 ), iLearn ( 34 ) and iLearnPlus ( 5 ), also provide feature extraction facilities.…”

“…Only BioTriangle covers DNA, RNA, ligands and protein sequences, however, it does not consider protein structures. MathFeature ( 31 ) and some of the recent machine learning platforms, such as BioSeq-Analysis2.0 ( 32 ), iLearn ( 34 ) and iLearnPlus ( 5 ), provide a relatively rich collection of feature sets for nucleic acids and proteins, outperforming the older feature engineering tools, however, they do not consider ligands and protein structures, except for PFeature ( 33 ) that considers only protein sequences and structures. A few current tools, including PIC ( 46 ), PDBparam ( 47 ) and PFeature, encode features from protein structure, facilitating important applications, such as rational drug development ( 48 ) and prediction of protein functions ( 49–52 ).…”

Information Theory for Biological Sequence Classification: A Novel Feature Extraction Technique Based on Tsallis Entropy

“…Nevertheless, ML algorithms applied to the analysis of biological sequences present challenges, such as feature extraction [ 10 ]. For non-structured data, as is the case of biological sequences, feature extraction is a key step for the success of ML applications [ 11 , 12 , 13 ].…”