Semantically Rich Local Dataset Generation for Explainable AI in Genomics

Created by W.Langdon from gp-bibliography.bib Revision:1.7941

@InProceedings{barbosa:2024:GECCO,

• author = "Pedro Barbosa and Rosina Savisaar and Alcides Fonseca",
• title = "Semantically Rich Local Dataset Generation for Explainable {AI} in Genomics",
• booktitle = "Proceedings of the 2024 Genetic and Evolutionary Computation Conference",
• year = "2024",
• editor = "Jean-Baptiste Mouret and Kai Qin and Julia Handl and Xiaodong Li and Markus Wagner and Mario Garza-Fabre and Kate Smith-Miles and Richard Allmendinger and Ying Bi and Grant Dick and Amir H Gandomi and Marcella Scoczynski Ribeiro Martins and Hirad Assimi and Nadarajen Veerapen and Yuan Sun and Mario Andres Munyoz and Ahmed Kheiri and Nguyen Su and Dhananjay Thiruvady and Andy Song and Frank Neumann and Carla Silva",
• pages = "267--276",
• address = "Melbourne, Australia",
• series = "GECCO '24",
• month = "14-18 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, XAI, evolutionary computation, instance generation, combinatorial optimization, local explainability, RNA splicing, Evolutionary Machine Learning",
• isbn13 = "979-8-4007-0494-9",
• DOI = "doi:10.1145/3638529.3653990",
• size = "10 pages",
• abstract = "Black box deep learning models trained on genomic sequences excel at predicting the outcomes of different gene regulatory mechanisms. Therefore, interpreting these models may provide novel insights into the underlying biology, supporting downstream biomedical applications. Due to their complexity, interpretable surrogate models can only be built for local explanations (e.g., a single instance). However, accomplishing this requires generating a dataset in the neighborhood of the input, which must maintain syntactic similarity to the original data while introducing semantic variability in the model's predictions. This task is challenging due to the complex sequence-to-function relationship of DNA.We propose using Genetic Programming to generate datasets by evolving perturbations in sequences that contribute to their semantic diversity. Our custom, domain-guided individual representation effectively constrains syntactic similarity, and we provide two alternative fitness functions that promote diversity with no computational effort. Applied to the RNA splicing domain, our approach quickly achieves good diversity and significantly outperforms a random baseline in exploring the search space, as shown by our proof-of-concept, short RNA sequence. Furthermore, we assess its generalizability and demonstrate scalability to larger sequences, resulting in a approx30\% improvement over the baseline.",
• notes = "GECCO-2024 EML A Recombination of the 33rd International Conference on Genetic Algorithms (ICGA) and the 29th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Pedro Santos Barbosa Rosina Savisaar Alcides Fonseca

Citations