SVM2Motif—Reconstructing Overlapping DNA Sequence Motifs by Mimicking an SVM Predictor

By Marina M.-C. Vidovic, Nico Görnitz, K. Müller, Gunnar Rätsch, Marius Kloft. 2015

9 citations recorded by the source corpus.

Identifying discriminative motifs underlying the functionality and evolution of organisms is a major challenge in computational biology. Machine learning approaches such as support vector machines (SVMs) achieve state-of-the-art performances in genomic discrimination tasks, but—due to its black-box character—motifs underlying its decision function are largely unknown. As a remedy, positional oligomer importance matrices (POIMs) allow us to visualize the significance of position-specific subsequences. Although being a major step towards the explanation of trained SVM models, they suffer from the fact that their size grows exponentially in the length of the motif, which renders their manual inspection feasible only for comparably small motif sizes, typically k ≤ 5. In this work, we extend the work on positional oligomer importance matrices, by presenting a new machine-learning methodology, entitled motifPOIM, to extract the truly relevant motifs—regardless of their length and complexity—underlying the predictions of a trained SVM model. Our framework thereby considers the motifs as free parameters in a probabilistic model, a task which can be phrased as a non-convex optimization problem. The exponential dependence of the POIM size on the oligomer length poses a major numerical challenge, which we address by an efficient optimization framework that allows us to find possibly overlapping motifs consisting of up to hundreds of nucleotides. We demonstrate the efficacy of our approach on a synthetic data set as well as a real-world human splice site data set.

Subfields: Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Unmasking Clever Hans predictors and assessing what machines really learn (2019, methodology): “[118] use an accomplished SVM classifier that predicts protein splice sites from large gene sequences to also explain which base pair motifs in genes were decisive for the classification.”
Feature Importance Measure for Non-linear Learning Algorithms (2016, methodology): “As visual inspecting POIMs can be tedious, [9, 8] proposed motifPOIMs, a probabilistic non-convex method to automatically extract the biological factors underlying the SVM’s prediction such as promoter elements or transcription factor binding sites –often called motifs.”