# Improving Compound Activity Classification via Deep Transfer and Representation Learning

arXiv: https://arxiv.org/abs/2111.07439 · HTML: https://mlsanity.com/paper/2111.07439/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 100 references that are in the map.
- First posted on arXiv 14 Nov 2021.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Molecular Graph Convolutions: Moving Beyond Fingerprints](https://mlsanity.com/paper/1603.00856/) (2016)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Low Data Drug Discovery with One-shot Learning](https://mlsanity.com/paper/1611.03199/) (2016)
- [Few-Shot Graph Learning for Molecular Property Prediction](https://mlsanity.com/paper/2102.07916/) (2021)
- [Self-Tuning for Data-Efficient Deep Learning](https://mlsanity.com/paper/2102.12903/) (2021)
- [Multi-task Neural Networks for QSAR Predictions](https://mlsanity.com/paper/1406.1231/) (2014)
- [Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction](https://mlsanity.com/paper/1712.02734/) (2017)
- [Toxicity Prediction using Deep Learning](https://mlsanity.com/paper/1503.01445/) (2015)
- [Domain Conditional Predictors for Domain Adaptation](https://mlsanity.com/paper/2106.13899/) (2021)

## Built on by (most cited first, 1 of 1)

- [Chemically-Informed Machine Learning Approach for Prediction of Reactivity Ratios in Radical Copolymerization](https://mlsanity.com/paper/2512.19715/) (2025)

## Abstract (arXiv)

Recent advances in molecular machine learning, especially deep neural networks such as Graph Neural Networks (GNNs) for predicting structure activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks are limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another, and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem, and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to its inactive compounds. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc, TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks.