Explainable Artificial Intelligence (XAI)

Probing machine-learning classifiers using noise, bubbles, and reverse correlation

The paper introduces a method to interpret machine-learning classifiers by analyzing how noise and reverse correlation affect classification decisions across various data types and models.

R.ROSETTA: an interpretable machine learning framework

R.ROSETTA is an interpretable machine learning framework that identifies biological semantics from omics data, revealing potential gene interdependencies in autism case-control studies.

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

This paper argues for global importance analysis to quantify population-level importance of genomic features in deep neural networks, beyond traditional attribution methods.

Critiquing Protein Family Classification Models Using Sufficient Input Subsets

The paper critiques protein family classification models by identifying sufficient input subsets to understand their decision-making criteria.

RFEX: Simple Random Forest Model and Sample Explainer for non-Machine Learning experts

The paper introduces RFEX, a simple Random Forest explainer for non-ML experts, improving model and sample explainability with a tabular output and case study.

Improving interpretability of deep learning models: splicing codes as a case study

The paper extends the Integrated Gradients method for better interpretability of deep learning models in genomics by incorporating nonlinear paths and alternative baselines.

Robust Neural Networks are More Interpretable for Genomics

This study shows that training deep neural networks with robustness methods improves interpretability in genomics tasks.

Gkmexplain: Fast and Accurate Interpretation of Nonlinear Gapped k-mer Support Vector Machines Using Integrated Gradients

gkmexplain provides a fast and accurate method to interpret gkm-SVM models of regulatory DNA sequences, outperforming existing methods in identifying predictive patterns and mutation impact scores.

Interpretable genotype-to-phenotype classifiers with performance guarantees

The paper develops interpretable genotype-to-phenotype classifiers with performance guarantees, validated on antimicrobial resistance prediction across 12 species and 56 antibiotics.

Contextual Regression: An Accurate and Conveniently Interpretable Nonlinear Model for Mining Discovery from Scientific Data

The paper introduces contextual regression, a nonlinear model that combines interpretability and accuracy, demonstrating its effectiveness on simulated data and open chromatin prediction.