Taxonomy Classification using Genomic Footprint of Mitochondrial Sequences

Area of Science:

• Genomics
• Bioinformatics
• Computational Biology

Background:

• Advances in sequencing technology generate massive genomic datasets.
• Organizing and analyzing these sequences by taxonomic order is crucial.

Purpose of the Study:

• To enhance the GenFooT method for improved taxonomic classification.
• To analyze adaptive parameter selection for GenFooT2.

Main Methods:

• GenFooT2 maps genome sequences into a 2D coordinate space for feature extraction.
• Adaptive selection of block size and fragment number parameters was analyzed.
• The enhanced GenFooT2 method was tested on ten biological datasets.

Main Results:

• GenFooT2 achieved a 3% improvement in classification performance compared to GenFooT.
• Logistic regression classifier was used with GenFooT2.
• Statistical tests confirmed GenFooT2's superior performance against state-of-the-art methods.

Conclusions:

• GenFooT2 demonstrates significantly improved performance in taxonomic classification.
• The adaptive parameter analysis contributes to the method's effectiveness.
• GenFooT2 offers a more accurate approach for organizing genomic data.