Interpreting Deep Neural Networks Beyond Attribution Methods: Quantifying Global Importance of Genomic Features

Koo, Peter K.; Ploenzke, Matthew

doi:10.1101/2020.02.19.956896

Cited by 7 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although recent progress is extending these class of methods to second-order attributions 53,[56][57][58] , they cannot uncover the effect size of motifs on model predictions. Global interpretability analysis via in silico experiments is one avenue that shows great promise in uncovering the importance of whole features 59 .…”

Section: Discussionmentioning

confidence: 99%

Improving representations of genomic sequence motifs in convolutional networks with exponential activations

Koo

Ploenzke

2021

Nat Mach Intell

Self Cite

View full text Add to dashboard Cite

Deep convolutional neural networks (CNNs) trained on regulatory genomic sequences tend to build representations in a distributed manner, making it a challenge to extract learned features that are biologically meaningful, such as sequence motifs.Here we perform a comprehensive analysis on synthetic sequences to investigate the role that CNN activations have on model interpretability. We show that employing an exponential activation to first layer filters consistently leads to interpretable and robust representations of motifs compared to other commonly used activations. Strikingly, we demonstrate that CNNs with better test performance do not necessarily imply more interpretable representations with attribution methods. We find that CNNs with exponential activations significantly improve the efficacy of recovering biologically meaningful representations with attribution methods. We demonstrate these results generalise to real DNA sequences across several in vivo datasets. Together, this work demonstrates how a small modification to existing CNNs, i.e. setting exponential activations in the first layer, can significantly improve the robustness and interpretabilty of learned representations directly in convolutional filters and indirectly with attribution methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Improving representations of genomic sequence motifs in convolutional networks with exponential activations

Koo

Ploenzke

2021

Nat Mach Intell

Self Cite

View full text Add to dashboard Cite

show abstract

“…For instance, a method can point out certain motifs or associations that are important for the model in predicting the target, but how this reflects actual physicochemical interactions can be rather hard to interpret from the model alone. Nevertheless, this is an active area of research and new solutions are frequently developed ( Lundberg and Lee, 2017 ; Chen and Capra, 2020 ; Koo and Ploenzke, 2020b ), where rigorous testing as well as experimentally verifying predictions will highlight the most promising approaches ( Ancona et al, 2017 ). On the other hand, an alternative trend that is arguably more appropriate than interpreting black box models is the development of inherently interpretable models ( Rudin, 2019 ), where prior knowledge of gene expression can be built into the deep network structure itself ( Ma et al, 2018 ; Tareen and Kinney, 2019 ; Liu et al, 2020 ).…”

Section: Learning the Protein-dna Interactions Initiating Gene Expressionmentioning

confidence: 99%

Learning the Regulatory Code of Gene Expression

Zrimec

Buric

Kokina

et al. 2021

Front. Mol. Biosci.

View full text Add to dashboard Cite

Data-driven machine learning is the method of choice for predicting molecular phenotypes from nucleotide sequence, modeling gene expression events including protein-DNA binding, chromatin states as well as mRNA and protein levels. Deep neural networks automatically learn informative sequence representations and interpreting them enables us to improve our understanding of the regulatory code governing gene expression. Here, we review the latest developments that apply shallow or deep learning to quantify molecular phenotypes and decode the cis-regulatory grammar from prokaryotic and eukaryotic sequencing data. Our approach is to build from the ground up, first focusing on the initiating protein-DNA interactions, then specific coding and non-coding regions, and finally on advances that combine multiple parts of the gene and mRNA regulatory structures, achieving unprecedented performance. We thus provide a quantitative view of gene expression regulation from nucleotide sequence, concluding with an information-centric overview of the central dogma of molecular biology.

show abstract

“…e . global interpretability) remains challenging[25]. Noteworthy, neither approach is transparent as to how the model makes predictions.…”

Section: Introductionmentioning

confidence: 99%

ExplaiNN: interpretable and transparent neural networks for genomics

Novakovsky

Fornés

Saraswat

et al. 2022

Preprint

View full text Add to dashboard Cite

Sequence-based deep learning models, particularly convolutional neural networks (CNNs), have shown superior performance on a wide range of genomic tasks. A key limitation of these models is the lack of interpretability, slowing their broad adoption by the genomics community. Current approaches to model interpretation do not readily reveal how a model makes predictions, can be computationally intensive, and depend on the implemented architecture. Here, we introduce ExplaiNN, an adaptation of neural additive models1 for genomic tasks wherein predictions are computed as a linear combination of multiple independent CNNs, each consisting of a single convolutional filter and fully connected layers. This approach brings together the expressivity of CNNs with the interpretability of linear models, providing global (cell state level) as well as local (individual sequence level) insights of the biological processes studied. We use ExplaiNN to predict transcription factor (TF) binding and chromatin accessibility states, demonstrating performance levels comparable to state-of-the-art methods, while providing a transparent view of the model’s predictions in a straightforward manner. Applied to de novo motif discovery, ExplaiNN detects equivalent motifs to those obtained from specialized algorithms across a range of datasets. Finally, we present ExplaiNN as a plug and play platform in which pre-trained TF binding models and annotated position weight matrices from reference databases can be combined in a simple framework. We expect that ExplaiNN will accelerate the adoption of deep learning by biological domain experts in their daily genomic sequence analyses.

show abstract

Interpreting Deep Neural Networks Beyond Attribution Methods: Quantifying Global Importance of Genomic Features

Cited by 7 publications

References 34 publications

Improving representations of genomic sequence motifs in convolutional networks with exponential activations

Improving representations of genomic sequence motifs in convolutional networks with exponential activations

Learning the Regulatory Code of Gene Expression

ExplaiNN: interpretable and transparent neural networks for genomics

Contact Info

Product

Resources

About