CSHL Menu
Peter Koo

Peter Koo

Assistant Professor
Cancer Center Member

Ph.D., Yale University, 2015

koo@cshl.edu | 516-367-5520

Koo Lab Website   Faculty Profile

Deep learning has the potential to make a significant impact in basic biology and cancer, but a major challenge is understanding the reasons behind their predictions. My research develops methods to interpret this powerful class of black box models, with a goal of elucidating data-driven insights into the underlying mechanisms of sequence-function relationships.

Deep learning is being applied rapidly in many areas of genomics, demonstrating improved performance over previous methods on benchmark datasets. Despite the promise of deep learning, it remains unclear whether improved predictions will translate to new biological discoveries because of their low interpretability, which has earned them a reputation as a black box. Understanding the reasons underlying a deep learning model’s prediction may reveal new biological insights not captured by previous methods. Our group develops methods to interpret high-performing deep learning models to distill knowledge that they learn from big, noisy, biological sequence data. Our goal is to elucidate biological mechanisms that underlie sequence-function relationships for gene regulation and protein (dys)function. Recently, we have teamed up with other members of the CSHL Cancer Center to investigate the sequence basis of epigenomic differences across healthy and cancer cells.

See all Koo news

All Publications

ETV6 dependency in Ewing sarcoma by antagonism of EWS-FLI1-mediated enhancer activation

19 Jan 2023 | Nature Cell Biology
Gao, Yuan, He, Xue-Yan, Wu, Xiaoli, Huang, Yu-Han, Toneyan, Shushan, Ha, Taehoon, Ipsaro, Jonathan, Koo, Peter, Joshua-Tor, Leemor, Bailey, Kelly, Egeblad, Mikala, Vakoc, Christopher

End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman

01 Jan 2023 | Bioinformatics
Petti, Samantha, Bhattacharya, Nicholas, Rao, Roshan, Dauparas, Justas, Thomas, Neil, Zhou, Juannan, Rush, Alexander, Koo, Peter, Ovchinnikov, Sergey, Borgwardt, Karsten

ResidualBind: Uncovering Sequence-Structure Preferences of RNA-Binding Proteins with Deep Neural Networks

2023 | Methods in Molecular Biology | 2586:197-215
Koo, Peter, Ploenzke, Matt, Anand, Praveen, Paul, Steffan, Majdandzic, Antonio

Learning single-cell chromatin accessibility profiles using meta-analytic marker genes

22 Dec 2022 | Briefings in Bioinformatics | :bbac541
Karakida Kawaguchi, Risa, Tang, Ziqi, Fischer, Stephan, Rajesh, Chandana, Tripathy, Rohit, Koo, Peter, Gillis, Jesse

Evaluating deep learning for predicting epigenomic profiles

2022 | Nature Machine Intelligence
Toneyan, Shushan, Tang, Ziqi, Koo, Peter

Evolution-inspired augmentations improve deep learning for regulatory genomics

4 Nov 2022 | Cold Spring Harbor Laboratory
Lee, Nicholas, Tang, Ziqi, Toneyan, Shushan, Koo, Peter

Evaluating deep learning for predicting epigenomic profiles

1 May 2022 | bioRxiv
Toneyan, Shushan, Tang, Ziqi, Koo, Peter

Statistical correction of input gradients for black box models trained with categorical input features

1 May 2022 | bioRxiv
Majdandzic, Antonio, Koo, Peter

Interpreting Potts and Transformer Protein Models Through the Lens of Simplified Attention

2022 | Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing | 27:34-45
Bhattacharya, Nicholas, Thomas, Neil, Rao, Roshan, Dauparas, Justas, Koo, Peter, Baker, David, Song, Yun, Ovchinnikov, Sergey

End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman

24 Oct 2021 | bioRxiv
Petti, Samantha, Bhattacharya, Nicholas, Rao, Roshan, Dauparas, Justas, Thomas, Neil, Zhou, Juannan, Rush, Alexander, Koo, Peter, Ovchinnikov, Sergey

See more publications