# Interpretable Deep Learning in Drug Discovery

arXiv: https://arxiv.org/abs/1903.02788 · HTML: https://mlsanity.com/paper/1903.02788/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2019.

## Built on by (most cited first, 14 of 14)

- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [Trustworthy AI: A Computational Perspective](https://mlsanity.com/paper/2107.06641/) (2021)
- [A Comprehensive Survey on Deep Graph Representation Learning](https://mlsanity.com/paper/2304.05055/) (2023)
- [Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces](https://mlsanity.com/paper/2212.14855/) (2022)
- [Interpretability Needs a New Paradigm](https://mlsanity.com/paper/2405.05386/) (2024)
- [Deep Learning Methods for Small Molecule Drug Discovery: A Survey](https://mlsanity.com/paper/2303.00313/) (2023)
- [Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective](https://mlsanity.com/paper/2401.04374/) (2024)
- [Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction](https://mlsanity.com/paper/2103.12983/) (2021)
- [SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training](https://mlsanity.com/paper/2311.05143/) (2023)
- [Riemann Sum Optimization for Accurate Integrated Gradients Computation](https://mlsanity.com/paper/2410.04118/) (2024)
- [Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning](https://mlsanity.com/paper/2211.06843/) (2022)
- [MAMI: Multi-Attentional Mutual-Information for Long Sequence Neuron Captioning](https://mlsanity.com/paper/2401.02744/) (2024)
- [Attribution assignment for deep-generative sequence models enables interpretability analysis using positive-only data](https://mlsanity.com/paper/2506.23182/) (2025)

## Abstract (arXiv)

Without any means of interpretation, neural networks that predict molecular properties and bioactivities are merely black boxes. We will unravel these black boxes and will demonstrate approaches to understand the learned representations which are hidden inside these models. We show how single neurons can be interpreted as classifiers which determine the presence or absence of pharmacophore- or toxicophore-like structures, thereby generating new insights and relevant knowledge for chemistry, pharmacology and biochemistry. We further discuss how these novel pharmacophores/toxicophores can be determined from the network by identifying the most relevant components of a compound for the prediction of the network. Additionally, we propose a method which can be used to extract new pharmacophores from a model and will show that these extracted structures are consistent with literature findings. We envision that having access to such interpretable knowledge is a crucial aid in the development and design of new pharmaceutically active molecules, and helps to investigate and understand failures and successes of current methods.