Efficient Biological Data Acquisition through Inference Set Design

ICLR 2025 Conference Submission12794 Authors

Keywords: Active Learning, Data Acquisition, ML for Drug Discovery

TL;DR: We propose an active learning method for drug discovery, acquiring labels for some samples and training a model to predict the rest. Our models prune the most difficult examples from the target set to achieve high accuracy and reduce costs.

Abstract: In drug discovery, highly automated high-throughput laboratories are used to screen a large number of compounds in search of effective drugs. These experiments are expensive, so we might hope to reduce their cost by experimenting on a subset of the compounds, and predicting the outcomes of the remaining experiments. In this work, we model this problem as a sequential subset selection problem: we aim to sequentially select the smallest set of candidates in order to achieve some desired level of accuracy for the system as a whole. Our key observation is that, if there is heterogeneity in the difficulty of the prediction problem across the input space, selectively obtaining the labels for the hardest examples in the acquisition pool will leave only the relatively easy examples to remain in the inference set, leading to better overall system performance. We call this problem inference set design, and propose an active learning solution using the model's confidence to prune out these challenging examples. Our algorithm includes an explicit stopping criterion that stops running the experiments when it is sufficiently confident that the system has reached the target performance. Our empirical studies on images and molecular datasets, as well as a real-world case, show that deploying active learning for inference set design leads to significant reduction in experimental cost while obtaining better system performance.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 12794