Tsetlin Machine in DNA sequence classification

The Tsetlin machine (TM) is a logic-based machine learning model with the crucial advantages of transparency and hardware-friendliness. In TM, groups of Tsetlin Automata (TAs) produce Boolean expressions in the form of conjunctive clauses in AND-rules. In this work, we show that the DNA nucleotide sequence, coded using the four-letter alphabet A, C, G, T, is a perfect match to the Boolean logic-based TM. A coalesced integer-weighted TM is applied to the problem of prokaryote gene prediction demonstrating beyond state-of-the-art performance on reference genomes. This paves the way for highly efficient bioinformatic analysis in a large range of applications.