# AssayMatch: Learning to Select Data for Molecular Activity Models

arXiv: https://arxiv.org/abs/2511.16087 · HTML: https://mlsanity.com/paper/2511.16087/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing](https://mlsanity.com/paper/2212.10789/) (2022)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery](https://mlsanity.com/paper/1911.04738/) (2019)
- [Data Shapley in One Training Run](https://mlsanity.com/paper/2406.11011/) (2024)
- [The Shape of Learning Curves: a Review](https://mlsanity.com/paper/2103.10948/) (2021)
- [Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language](https://mlsanity.com/paper/2303.03363/) (2023)
- [Predictive Chemistry Augmented with Text Retrieval](https://mlsanity.com/paper/2312.04881/) (2023)

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

- [Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning](https://mlsanity.com/paper/2512.24959/) (2025)

## Abstract (arXiv)

The performance of machine learning models in drug discovery is highly dependent on the quality and consistency of the underlying training data. Due to limitations in dataset sizes, many models are trained by aggregating bioactivity data from diverse sources, including public databases such as ChEMBL. However, this approach often introduces significant noise due to variability in experimental protocols. We introduce AssayMatch, a framework for data selection that builds smaller, more homogenous training sets attuned to the test set of interest. AssayMatch leverages data attribution methods to quantify the contribution of each training assay to model performance. These attribution scores are used to finetune language embeddings of text-based assay descriptions to capture not just semantic similarity, but also the compatibility between assays. Unlike existing data attribution methods, our approach enables data selection for a test set with unknown labels, mirroring real-world drug discovery campaigns where the activities of candidate molecules are not known in advance. At test time, embeddings finetuned with AssayMatch are used to rank all available training data. We demonstrate that models trained on data selected by AssayMatch are able to surpass the performance of the model trained on the complete dataset, highlighting its ability to effectively filter out harmful or noisy experiments. We perform experiments on two common machine learning architectures and see increased prediction capability over a strong language-only baseline for 9/12 model-target pairs. AssayMatch provides a data-driven mechanism to curate higher-quality datasets, reducing noise from incompatible experiments and improving the predictive power and data efficiency of models for drug discovery. AssayMatch is available at https://github.com/Ozymandias314/AssayMatch.