Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction

ICLR 2026 Conference Submission3074 Authors

Keywords: Genetic Perturbation, Gene Expression Prediction, AI for Biology, Neuro-Symbolic AI

TL;DR: We introduce an end-to-end framework aligns neural and symbolic components and performs systematic knowledge refinement for genetic perturbation prediction.

Abstract: The transcriptional response to genetic perturbation reveals fundamental insights into complex cellular systems. While current approaches have made progress in predicting genetic perturbation responses, they provide limited biological understanding and cannot systematically refine existing knowledge. Overcoming these limitations requires an end-to-end integration of data-driven learning and existing knowledge. However, this integration is challenging due to inconsistencies between data and knowledge bases, such as noise, misannotation, and incompleteness. To address this challenge, we propose ALIGNED (Adaptive aLignment for Inconsistent Genetic kNowledgE and Data), a neuro-symbolic framework based on the Abductive Learning (ABL) paradigm. This end-to-end framework aligns neural and symbolic components and performs systematic knowledge refinement. We introduce a balanced consistency metric to evaluate the predictions' consistency against both data and knowledge. Our results show that ALIGNED outperforms state-of-the-art methods by achieving the highest balanced consistency, while also re-discovering biologically meaningful knowledge. Our work advances beyond existing methods to enable both the transparency and the evolution of mechanistic biological understanding.

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

Submission Number: 3074