# Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees Source: [Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees]() Collection index: [llms.txt]() Data updated: 2026-04-16T05:00:04.684Z Authors: Nicolas Huynh, Krzysztof Kacprzyk, Ryan Sheridan, David Bentley, Mihaela van der Schaar Published: 2026-04-13T20:58:01.000Z ## Abstract The analysis of DNA sequences has become critical in numerous fields, from evolutionary biology to understanding gene regulation and disease mechanisms. While deep neural networks can achieve remarkable predictive performance, they typically operate as black boxes. Contrasting these black boxes, axis-aligned decision trees offer a promising direction for interpretable DNA sequence analysis, yet they suffer from a fundamental limitation: considering individual raw features in isolation at each split limits their expressivity, which results in prohibitive tree depths that hinder both interpretability and generalization performance. We address this challenge by introducing DEFT, a novel framework that adaptively generates high-level sequence features during tree construction. DEFT leverages large language models to propose biologically-informed features tailored to the local sequence distributions at each node and to iteratively refine them with a reflection mechanism. Empirically, we demonstrate that DEFT discovers human-interpretable and highly predictive sequence features across a diverse range of genomic tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [DNA Sequence Classification on Pol II Pausing (test)](): DNA sequence classification; Pol II Pausing (test); Accuracy: 86.9. - [DNA Sequence Classification on Promoters (test)](): DNA sequence classification; Promoters (test); Accuracy: 83.3. - [DNA Sequence Classification on Enhancers (test)](): DNA sequence classification; Enhancers (test); Accuracy: 76.7. - [DNA sequence classification on Pol II pausing](): DNA sequence classification; Pol II pausing; Accuracy: 86.9. - [DNA Sequence Classification on Promoters](): DNA sequence classification; Promoters; Accuracy: 83.3. - [DNA Sequence Classification on Enhancers](): DNA sequence classification; Enhancers; Accuracy: 76.7. ## Original sources and implementation [Original paper]() [PDF]()