Timezone: »

Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data
Utku Ozbulak · Solha Kang · Jasper Zuallaert · Stephen Depuydt · Joris Vankerschaver
Event URL: https://openreview.net/forum?id=5vJ8doH-lqE »

Even though deep neural networks (DNNs) achieve state-of-the-art results for a large number of problems involving genomic data, getting DNNs to explain their decision-making process has been a major challenge due to their black-box nature. One way to get DNNs to explain their reasoning for prediction is via attribution methods which are assumed to highlight the parts of the input that contribute to the prediction the most. Given the existence of numerous attribution methods and a lack of quantitative results on the fidelity of those methods, selection of an attribution method for sequence-based tasks has been mostly done qualitatively. In this work, we take a step towards identifying the most faithful attribution method by proposing a computational approach that utilizes point mutations. Providing quantitative results on seven popular attribution methods, we find Layerwise Relevance Propagation (LRP) to be the most appropriate attribution method with LRP identifying two important biological features for translation: the integrity of Kozak sequence as well as the detrimental effects of premature stop codons.

Author Information

Utku Ozbulak (Ghent University)
Solha Kang (University of Edinburgh, University of Edinburgh)
Jasper Zuallaert (Universiteit Gent)
Stephen Depuydt (Universiteit Gent)
Joris Vankerschaver (Ghent University Global Campus)

More from the Same Authors

  • 2021 : Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes »
    Utku Ozbulak · Maura Pintor · Arnout Van Messem · Wesley De Neve
  • 2018 : Accepted papers »
    Sven Gowal · Bogdan Kulynych · Marius Mosbach · Nicholas Frosst · Phil Roth · Utku Ozbulak · Simral Chaudhary · Toshiki Shibahara · Salome Viljoen · Nikita Samarin · Briland Hitaj · Rohan Taori · Emanuel Moss · Melody Guan · Lukas Schott · Angus Galloway · Anna Golubeva · Xiaomeng Jin · Felix Kreuk · Akshayvarun Subramanya · Vipin Pillai · Hamed Pirsiavash · Giuseppe Ateniese · Ankita Kalra · Logan Engstrom · Anish Athalye