# Chemi-net: a graph convolutional network for accurate drug property prediction

arXiv: https://arxiv.org/abs/1803.06236 · HTML: https://mlsanity.com/paper/1803.06236/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2018.

## Built on by (most cited first, 21 of 21)

- [Geometric Deep Learning on Molecular Representations](https://mlsanity.com/paper/2107.12375/) (2021)
- [Few-Shot Graph Learning for Molecular Property Prediction](https://mlsanity.com/paper/2102.07916/) (2021)
- [Scalable algorithms for physics-informed neural and graph networks](https://mlsanity.com/paper/2205.08332/) (2022)
- [SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction](https://mlsanity.com/paper/2206.07015/) (2022)
- [IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System](https://mlsanity.com/paper/2109.04202/) (2021)
- [Formulation Graphs for Mapping Structure-Composition of Battery Electrolytes to Device Performance](https://mlsanity.com/paper/2307.03811/) (2023)
- [Machine Learning Small Molecule Properties in Drug Discovery](https://mlsanity.com/paper/2308.12354/) (2023)
- [Ligandformer: A Graph Neural Network for Predicting Compound Property with Robust Interpretation](https://mlsanity.com/paper/2202.10873/) (2022)
- [Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints](https://mlsanity.com/paper/2403.17954/) (2024)
- [A Graph Data Augmentation Strategy with Entropy Preservation](https://mlsanity.com/paper/2107.06048/) (2021)
- [ChemiRise: a data-driven retrosynthesis engine](https://mlsanity.com/paper/2108.04682/) (2021)
- [Docking-based Virtual Screening with Multi-Task Learning](https://mlsanity.com/paper/2111.09502/) (2021)
- [Molecular modeling with machine-learned universal potential functions](https://mlsanity.com/paper/2103.04162/) (2021)
- [Predicting Molecule-Target Interaction by Learning Biomedical Network and Molecule Representations](https://mlsanity.com/paper/2302.00981/) (2023)
- [AmorProt: Amino Acid Molecular Fingerprints Repurposing based Protein Fingerprint](https://mlsanity.com/paper/2303.16209/) (2023)
- [DiffDTM: A conditional structure-free framework for bioactive molecules generation targeted for dual proteins](https://mlsanity.com/paper/2306.13957/) (2023)
- [Simplicial Message Passing for Chemical Property Prediction](https://mlsanity.com/paper/2307.05392/) (2023)
- [Predicting Drug Effects from High-Dimensional, Asymmetric Drug Datasets by Using Graph Neural Networks: A Comprehensive Analysis of Multitarget Drug Effect Prediction](https://mlsanity.com/paper/2410.09280/) (2024)
- [Metric spaces of walks and Lipschitz duality on graphs](https://mlsanity.com/paper/2508.19709/) (2025)
- [Optimal message passing for molecular prediction is simple, attentive and spatial](https://mlsanity.com/paper/2509.10871/) (2025)
- [MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions](https://mlsanity.com/paper/2608.30636/) (2026)

## Abstract (arXiv)

Absorption, distribution, metabolism, and excretion (ADME) studies are critical for drug discovery. Conventionally, these tasks, together with other chemical property predictions, rely on domain-specific feature descriptors, or fingerprints. Following the recent success of neural networks, we developed Chemi-Net, a completely data-driven, domain knowledge-free, deep learning method for ADME property prediction. To compare the relative performance of Chemi-Net with Cubist, one of the popular machine learning programs used by Amgen, a large-scale ADME property prediction study was performed on-site at Amgen. The results showed that our deep neural network method improved current methods by a large margin. We foresee that the significantly increased accuracy of ADME prediction seen with Chemi-Net over Cubist will greatly accelerate drug discovery.