# MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions

arXiv: https://arxiv.org/abs/2608.30636 · HTML: https://mlsanity.com/paper/2608.30636/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning](https://mlsanity.com/paper/2106.01613/) (2021)
- [Chemi-net: a graph convolutional network for accurate drug property prediction](https://mlsanity.com/paper/1803.06236/) (2018)
- [The Interpretable and Effective Graph Neural Additive Networks](https://mlsanity.com/paper/2406.01317/) (2024)
- [Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction](https://mlsanity.com/paper/2107.04119/) (2021)
- [Graph Concept Bottleneck Models](https://mlsanity.com/paper/2508.14255/) (2025)
- [Ligandformer: A Graph Neural Network for Predicting Compound Property with Robust Interpretation](https://mlsanity.com/paper/2202.10873/) (2022)
- [Comparison of generalised additive models and neural networks in applications: A systematic review](https://mlsanity.com/paper/2510.24601/) (2025)
- [Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks](https://mlsanity.com/paper/2510.03351/) (2025)

## Abstract (arXiv)

Optimizing absorption, distribution, metabolism, and excretion (ADME) is an important part of small molecule drug discovery. Many machine learning models have been built to predict ADME properties to facilitate this optimization process, but explaining model predictions is challenging. We propose a new graph neural network architecture with built-in atom attributions. Our model MolLedger learns a global context vector for each molecule and a per-atom head to output atom scores that sum to the predicted property. The atom scores are regularized to align with relevant chemical properties. We prove that MolLedger is a universal approximator and demonstrate empirically that the new architecture obtains explainability with little effect on performance. We show that the interpretations from MolLedger are faithful, concordant with held-out physical properties, and align with the changes between matched molecular pairs. Our case studies comparing interpretations from multiple methods on molecular pairs reveal that MolLedger is much better at producing sensible explanations for predicted property changes.