Amino acid encoding schemes for machine learning methods

Abstract

In this paper, we investigate the efficiency of a number of commonly used amino acid encodings by using artificial neural networks and substitution scoring matrices. An important step in many machine learning techniques applied in computational biology is encoding the symbolic data of protein sequences reasonably efficient in numeric vector representations. This encoding can be achieved by either considering the amino acid physicochemical properties or a generic numerical encoding. In order to be effective in the context of a machine learning system, an encoding must preserve information relative to the problem at hand, while diminishing superfluous data. To this end, it is important to measure how much an encoding scheme can conserve the underlying similarities and differences that exist among the amino acids. One way to evaluate the effectiveness of an amino acid encoding scheme is to compare it to the roles that amino acids are actually found to play in biological systems. A numerical representation of the similarities and differences between amino acids can be found in substitution matrices commonly used for sequence alignment, since these substitution matrices are based on measures of the interchangeability of amino acids in biological specimens. In this study, a new encoding scheme is also proposed based on the genetic codon coding occurs during protein synthesis. The experimental results indicate better performances compared to the other commonly used encodings.

Machine Learning Detects Anti-DENV Signatures in Antibody Repertoire Sequences

“…The same input data were represented differently in order to select among different encoding methods and, therefore, each encoded input had a variable impact on machine learning measures. In computational biology, encoding of amino acids can be achieved by considering amino acids' physicochemical properties, for instance, using the BLOSUM substitution matrix, or by a generic character-wise encoding like one-hot or integer encoding used also in other ML domains (Zamani and Kremer, 2011).…”

A novel Fibonacci hash method for protein family identification by using recurrent neural networks

“…After feature engineering, deep learning and machine learning algorithms can be applied to the extracted features to perform protein family classification. Yet, in order to apply these methods, sequences are needed to be converted to numerical representations since there is no such a method to perform artificial intelligence with raw protein sequences [7,8].…”

“…In the literature, there are limited methods for converting protein sequences into the numbers. In general, BLOSUM62 (BLOcks SUbstitution Matrix), PAM25 (Point Accepted Mutation), hydrophobicity, EIIP (Electron-Ion Interaction Potential) are applied and the performance of family classification is highly depending on the conversion method [7,9]. Recently, deep learning models are actively used in bioinformatics studies and show promising results.…”

Efficient Feature Selection and Classification of Protein Sequence Data in Bioinformatics

“…In the past, several machine learning approaches have been developed for the classification of protein sequences into functional or structural existing superfamilies [ 16 , 19 – 22 ]. A superfamily is comprised of a set of proteins that possess sequence or structural homology.…”