2024

EvoAug-TF: Extending evolution-inspired data augmentations for genomic deep learning to TensorFlow
Y Yu, S Muthukumarn, PK Koo
Bioinformatics (Paper, Code)

Evaluating the representational power of pre-trained DNA language models for regulatory genomics
Z Tang, PK Koo
bioRxiv (Paper, Code)

2023

Interpreting Cis-Regulatory Mechanisms from Genomic Deep Neural Networks using Surrogate Models
E Seits, DM McCandlish, JB Kinney, PK Koo
bioRxiv (Preprint, Code)

Interpreting Cis-Regulatory Interactions from Large-Scale Deep Neural Networks for Genomics
S Toneyan, PK Koo
bioRxiv (Preprint, Code)

Building foundation models for regulatory genomics requires rethinking large language models
Z Tang, PK Koo
ICML 2023 Workshop on Computational Biology (Workshop paper)

EvoAug: improving generalization and interpretability of genomic deep neural networks with evolution-inspired data augmentations
NK Lee, S Toneyan, Z Tang, PK Koo
Genome Biology (Paper, Code)

Correcting gradient-based interpretations of deep neural networks for genomics
A Majdandzic, C Rajesh, PK Koo
Genome Biology (Paper, Code)

ChampKit: A framework for rapid evaluation of deep neural networks for patch-based histopathology classification
JR Kaczmarzyk, R Gupta, TM Kurc, S Abousamra, JH Saltz, PK Koo
Computer Methods and Programs in Biomedicine (Paper, Code)

ETV6 dependency in Ewing sarcoma by antagonism of EWS-FLI1-mediated enhancer activation
Y Gao, XY He, …, S Toneyan, …, PK Koo, …, C Vakoc
Nature Cell Biology (Paper)

ResidualBind: Uncovering Sequence-Structure Preferences of RNA-Binding Proteins with Deep Neural Networks
PK Koo, M Ploenzke, P Anand, S Paul, A Majdandzic
RNA Structure Prediction, Methods in Molecular Biology (Chapter)

2022

Selecting deep neural networks that yield consistent attribution-based interpretations for genomics
A Majdandzic, C Rajesh, Z Tang, S Toneyan, E Labelson, R Tripathy, PK Koo
Machine Learning in Computational Biology (Paper, Code)

Learning single-cell chromatin accessibility profiles using meta-analytic marker genes
RK Kawaguchi, Z Tang, S Fischer, Chandana Rajesh, R Tripathy, PK Koo, J Gillis
Briefings in Bioinformatics (Paper, Code)

Evaluating deep learning for predicting epigenomic profiles
S Toneyan, Z Tang, PK Koo
Nature Machine Intelligence (Paper, Code)

Interpreting Potts and Transformer Protein Models Through the Lens of Simplified Attention
N Bhattacharya, N Thomas, R Rao, J Dauparas, PK Koo, D Baker, YS Song, S Ovchinnikov
Pacific Symposium on Biocomputing (Article, Code)

2021

Uncovering motif interactions from convolutional-attention networks for genomics
R Ghotra, N Lee, PK Koo
NeurIPS 2021 AI for Science Workshop (Workshop paper, Code)
Selected for oral presentationBest Paper Award

Towards trustworthy explanations with gradient-based attribution methods
EL Labelson, R Tripathy, PK Koo
NeurIPS 2021 AI for Science Workshop (Workshop paper, Code)

End-to-end learning of multiple sequence alignmentswith differentiable Smith-Waterman
S Petty, N Bhattacharya, R Rao, J Dauparas, N Thomas, J Zhou, AM Rush, PK Koo, S Ovchinnikov
NeurIPS 2021 Machine Learning for Structural Biology Workshop (Workshop paper, Code)
Selected for oral presentation

Statistical correction of input gradients for black box models trained with categorical input features
A Majdandzic, PK Koo
ICML 2021 Workshop on Computational Biology (Workshop paper, Code)
Selected for spotlight presentation

Designing Interpretable Convolution-Based Hybrid Networks for Genomics
R Ghotra, NK Lee, R Tripathy, PK Koo
ICML 2021 Workshop on Computational Biology (Workshop paper, Code)

Representation learning of genomic sequence motifs via information maximization
NK Lee, PK Koo
ICML 2021 Workshop on Computational Biology (Workshop paper)

Global Importance Analysis: A Method to Quantify Importance of Genomic Features in Deep Neural Networks
PK Koo, A Majdandzic, M Ploenzke, P Anand, S Paul
PLOS Computational Biology (Article, Code)

Improving Representations of Genomic Sequence Motifs in Convolutional Networks with Exponential Activations
PK Koo, M Ploenzke
Nature Machine Intelligence (Article, Code)

Exploiting marker genes for robust classification and characterization of single-cell chromatin accessibility
RK Kawaguchi, Z Tang, S Fischer, R Tripathy, PK Koo, J Gillis
bioRxiv (Preprint, Code)

Single Layers of Attention Suffice to Predict Protein Contacts
N Bhattacharya, N Thomas, R Rao, J Dauparas, PK Koo, D Baker, YS Song, S Ovchinnikov
ICLR 2021 Workshop on Energy Based Models (Workshop paper, Code)

2020

Deep Learning for Inferring Transcription Factor Binding Sites
PK Koo, M Ploenzke
Current Opinion in Systems Biology (Review)

ZBED2 is an antagonist of interferon regulatory factor1 and modifies cell identity in pancreatic cancer
TD Somerville, Y Xu, XS Wu, D Maia-Silva, SK Hur, LMN de Almeida, JB Preall, PK Koo, CR Vakoc
Proceedings of the National Academy of Sciences (Article)

N-WASP Regulates the Mobility of the B Cell Receptor and Co-Receptors During Signaling Activation
I Rey-Suarez, B Wheatley, PK Koo, Z Shu, S Mochrie, W Song, H Shroff, A Upadhyaya
Nature Communications (Article)

The Structure-Fitness Landscape of Pairwise Relations in Generative Sequence Models
D Marshall, H Wang, M Stiffler, J Dauparas, PK Koo, S Ovchinnikov
NeurIPS 2020 Workshop on Machine Learning for Structural Biology (Workshop paper, Code)

2019

Representation Learning of Genomic Sequence Motifs with Convolutional Neural Networks
PK Koo, SR Eddy
PLOS Computational Biology (Article, Code)

Interpreting Deep Neural Networks Beyond Local Attribution Methods: Quantifying Global Importance of Features
PK Koo*, M Ploenzke*
Machine Learning in Computational Biology Meeting, 2019 (Extended abstract)

Improving Convolutional Network Interpretability with Exponential Activations
PK Koo*, M Ploenzke*
ICML 2019 Workshop for Computational Biology (Workshop paper, Code)

Robust Neural Networks are More Interpretable for Genomics
PK Koo, S Qian, G Kaplun, V Volf, D Kalimeris
ICML 2019 Workshop for Computational Biology (Workshop paper, Code)

Unified framework for modeling multivariate distributions in biological sequences
J Dauparas, H Wang, A Swartz, PK Koo, M Nitzan, S Ovchinnikov
ICML 2019 Workshop for Computational Biology (Workshop paper, Code)

A Demonstration of Unsupervised Machine Learning in Species Delimitation
S Derkarabetian, S Castillo, PK Koo, S Ovchinnikov, M Hedin
Molecular Phylogenetics and Evolution 139, 106562 (Article)


2018

Inferring Sequence-Structure Preferences of RNA-Binding Proteins with Convolutional Residual Networks
PK Koo, P Anand, SB Paul, SR Eddy
bioRxiv, 418459 (Preprint)

Representation Learning of Genomic Sequence Motifs with Convolutional Neural Networks
PK Koo, SR Eddy
bioRxiv, 362756 (Preprint, Code)

Applying Perturbation Expectation-Maximization to Protein Trajectories of Rho GTPases
PK Koo, SR Eddy
Rho GTPases, 57-70 (Chapter, Code)


2017

Inferring Functional Neural Connectivity With Deep Residual Convolutional Networks
TW Dunn, PK Koo
bioRxiv, 141010 (Preprint, Code)


2016

Systems-level Approach to Uncovering Diffusive States and Their Transitions from Single-Particle Trajectories
PK Koo, SGJ Mochrie
Phsical Review E 94 (5), 052412 (Article, Code)

Improved Determination of Subnuclear Position Enabled by Three-Dimensional Membrane Reconstruction
Y Zhao, SM Schreiner, PK Koo, P Colombi, MC King, SGJ Mochrie
Biophysical Journal 111 (1), 19-24 (Article, Code)


2015

The Tethering of Chromatin to the Nuclear Envelope Supports Nuclear Mechanics
SM Schreiner*, PK Koo*, Y Zhao, SGJ Mochrie, MC King
Nature Communications 6, 7159 (Article)

Extracting Diffusive States of Rho GTPase in Live Cells: Towards In Vivo Biochemistry
PK Koo*, M Weitzman*, CR Sabanaygam, KL van Golen, SGJ Mochrie
PLOS Comptuational Biology 11 (10), e1004297 (Article, Code)
* Shared co-first author

For a full list, click here.