Skip to content

MathFeature #

Find similar titles

1회 업데이트 됨.

Edit
  • 최초 작성자
  • 최근 업데이트

Introduction #

Transform the text to numerical data set is crucial to execute the machine learning. Here, the biomolecules such as DNA, RNA and protein sequences need to be transformed to numerical features, which can be take forward to machine learning predictions. Here, Math Features is one of recent method which used to calculate the mathematical features from given DNA and proteins sequences. MathFeature showed high performance (0.6350–0.9897, accuracy), both applying only mathematical descriptors, but also hybridization with well-known descriptors in the literature.

List of general features widely used in peptide functional predictions #

1) Amino acid composition

2) Pseudo-amino acid composition

3) Composition, translation, distribution

4) Sequence-order

5) Conjoint triad

6) Proteochemometric descriptors

7) Profile-based features

8) Nucleic acid composition

9) Pseudo nucleic acid composition

10) Structure composition

11) Sequence similarity

12) Autocorrelation

13) Numerical mapping

14) K-nearest neighbor

15) Physiochemical properties

List of Mathfeatures #

1) Numerical Mapping

2) Fourier Transform

3) Chaos game

4) Entropy

5) Graphs

Execution: #

The complete list of python scripts are present in https://bonidia.github.io/MathFeature/ with detail documentation.

Reference: #

Robson P Bonidia, Douglas S Domingues, Danilo S Sanches, André C P L F de Carvalho, MathFeature: feature extraction package for DNA, RNA and protein sequences based on mathematical descriptors, Briefings in Bioinformatics, 2021; bbab434, https://doi.org/10.1093/bib/bbab434.

0.0.1_20240214_1_v81