• Publications
  • Influence
Opportunities and obstacles for deep learning in biology and medicine
TLDR
It is found that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art.
How Interpretable and Trustworthy are GAMs?
TLDR
It is found that GAMs with high feature sparsity can miss patterns in the data and be unfair to rare subpopulations, and tree-based GAMs represent the best balance of sparsity, fidelity and accuracy and thus appear to be the most trustworthy GAM models.
Precision Lasso: accounting for correlations and linear dependencies in high-dimensional genomic data
TLDR
The Precision Lasso is a Lasso variant that promotes sparse variable selection by regularization governed by the covariance and inverse covariance matrices of explanatory variables that outperforms popular methods of variable selection such as the Lasso, the Elastic Net and Minimax Concave Penalty regression.
Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations
TLDR
Functional Retrofitting is presented, a framework that generalizes current retrofitting methods by explicitly modeling pairwise relations and can directly incorporate a variety of pairwise penalty functions previously developed for knowledge graph completion.
Learning Sample-Specific Models with Low-Rank Personalized Regression
TLDR
This work proposes to estimate sample-specific models that tailor inference and prediction at the individual level, and shows that sample- specific models provide fine-grained interpretations of complicated phenomena without sacrificing predictive accuracy compared to state-of-the-art models such as deep neural networks.
On Dropout, Overfitting, and Interaction Effects in Deep Neural Networks
TLDR
This perspective issues caution against using Dropout to measure term saliency because Dropout regularizes against terms for high-order interactions, and provides insight into the varying effectiveness of Dropout for different architectures and data sets.
Opportunities and obstacles for deep learning in biology and medicine
TLDR
This work examines applications of deep learning to a variety of biomedical problems -- patient classification, fundamental biological processes, and treatment of patients -- to predict whether deep learning will transform these tasks or if the biomedical sphere poses unique challenges.
Experimental and Computational Mutagenesis To Investigate the Positioning of a General Base within an Enzyme Active Site
TLDR
Recognizing the extent, type, and energetic interconnectivity of interactions that contribute to positioning catalytic groups has implications for enzyme evolution and may help reveal the nature and extent of interactions required to design enzymes that rival those found in biology.
Visual Explanations for Convolutional Neural Networks via Input Resampling
TLDR
A framework to analyze predictions in terms of the model's internal features by inspecting information flow through the network by comparing the sets of neurons selected by two metrics, which suggests a way to investigate the internal attention mechanisms of convolutional neural networks.
Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models
TLDR
This work proposes pure interaction effects: variance in the outcome which cannot be represented by any smaller subset of features which has an equivalence with the Functional ANOVA decomposition and presents a fast, exact algorithm that transforms any piecewise-constant function into a purified, canonical representation.
...
...