ABLE: Choosing Perturbation Experiments to Recover Gene Logic

Yin Jun Phua, Foo Wei Ten

Additional Submission Instructions: For the camera-ready version, please include the author names and affiliations, funding disclosures, and acknowledgements.

Track: Track 1: Original Research/Position/Education/Attention Track

Keywords: neuro-symbolic AI, Boolean networks, gene regulatory networks, active learning

TL;DR: ABLE is a neuro-symbolic system that recovers executable Boolean gene regulatory rules from perturbation data, issues per-rule uniqueness certificates when the evidence suffices, and requests targeted experiments when it does not.

Abstract: Scientific knowledge requires claims stated formally, checked against evidence, and paired with what remains undecided. Perturb-seq and CRISPR screens promise genome-scale interventional data, yet current machine-learning tools return ranked edge lists rather than executable regulatory logic. We address this for Boolean gene regulation under an idealized _in silico_ Boolean intervention oracle, a setting where three capabilities are each necessary and none suffices alone. A neural proposer amortizes candidate-rule search at biological scale, replacing combinatorial enumeration with a sub-second forward pass. A symbolic verifier, LiftCert, issues support-conditional uniqueness certificates on the declared regulator support and abstains explicitly when the data do not determine a rule. A coverage-guided active loop then closes the remaining gaps by naming the exact missing input combination. ABLE (Active Boolean Learning Engine) realizes these capabilities as a single propose-verify-query loop. Trained once on synthetic data, ABLE delivers support-conditional certified recovery across published biological Boolean models and certifies every rule in curated biological networks from modest warm starts. ABLE thus instantiates neuro-symbolic methodology for AI4Science, showing that the verifier and active loop, not the neural architectural prior, earn certification and yield a recoverability map where every rule is a checkable claim or a named missing observation.

Submission Number: 13