MechMoE: Discovering Task-Aligned Perturbational Mechanisms for Out-of-Distribution Molecular Perturbation Prediction

Sepideh Maleki, Jan-Christian Huetter, Alexander P Wu, Gabriele Scalia, Sara MostafaviOpenReview 2027 · Submission to ICLR 2027 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Predicting transcriptional responses to molecular perturbations is a key challenge in computational drug discovery, particularly when generalizing to unseen compounds and cellular contexts. Although biological priors such as chemical similarity, annotated targets, and mechanism-of-action labels can provide useful structure, small-molecule responses often arise through indirect, context-dependent, and off-target effects that are only partially captured by predefined annotations. We introduce MechMoE, a mechanism-aware mixture model for out-of-distribution molecular perturbation prediction. MechMoE encodes molecular perturbations, basal cellular state, and expression-conditioned gene tokens, then uses learnable mechanism queries to extract candidate perturbational programs from contextualized gene representations. A sparse router selects a small subset of mechanism slots for each drug-cell pair, producing a perturbation-specific mechanism mixture used to predict the perturbation-induced expression change. We evaluate MechMoE on molecular perturbation data under strict held-out molecule and held-out cell-line settings. MechMoE improves transcriptome-wide response prediction across correlation, cosine similarity, reconstruction error, direction accuracy, and perturbation discrimination metrics, while remaining competitive on differential-expression recovery. Ablations show that sparse routing and the global perturbation decoder are both important for performance. These results suggest that small-molecule perturbation responses are effectively modeled as sparse combinations of learned, task-aligned latent mechanisms rather than fixed predefined biological categories.
BibTeX
@misc{maleki2027mechmoe,
  author = {Sepideh Maleki and Jan-Christian Huetter and Alexander P Wu and Gabriele Scalia and Sara Mostafavi},
  title = {{MechMoE: Discovering Task-Aligned Perturbational Mechanisms for Out-of-Distribution Molecular Perturbation Prediction}},
  year = {2027},
  url = {https://openreview.net/forum?id=UWhlIwyRmJ},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2027},
}

Loading related content...

Figure