Uncertainty Quantification for Deep Learning Models Predicting the Regulatory Activity of DNA Sequences

MCML Authors

Hüseyin Anil Gündüz

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Martin Binder

→ Group Bernd Bischl
 Statistical Learning and Data Science

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

Mina Rezaei

Dr.

→ Group Bernd Bischl
 Statistical Learning and Data Science

Abstract

The field of computational biology has been enhanced by deep learning models, which hold great promise for revolutionizing domains such as protein folding and drug discovery. Recent studies have underscored the tremendous potential of these models, particularly in the realm of gene regulation and the more profound understanding of the non-coding regions of the genome. On the other hand, this raises significant concerns about the reliability and efficacy of such models, which have their own biases by design, along with those learned from the data. Uncertainty quantification allows us to measure where the system is confident and know when it can be trusted. In this paper, we study several uncertainty quantification methods with respect to a multi-target regression task, specifically predicting regulatory activity profiles using DNA sequence data. Using the Basenji model, we investigate how such methods can improve in-domain generalization, out-of-distribution detection, and provide coverage guarantees on prediction intervals.

inproceedings

---

ICMLA 2023

22nd IEEE International Conference on Machine Learning and Applications. Jacksonville, FL, USA, Dec 15-17, 2023.

---

Authors

H. A. Gündüz • S. Giri • M. Binder • B. Bischl • M. Rezaei

---

Links

DOI

---

Research Area

 A1 | Statistical Foundations & Explainability