aiqbench analysis
This research introduces scBIG, a machine learning framework designed to predict transcriptional responses in single-cell genomics by explicitly modeling coordinated gene programs rather than treating genes independently. By leveraging conditional flow matching and structure-aware alignment objectives, the method significantly improves prediction accuracy for unseen genetic perturbations compared to existing state-of-the-art baselines. The work advances computational biology through a novel architectural approach that captures dynamic biological program reorganization using advanced representation learning techniques.
Beyond Independent Genes: Learning Module-Inductive Representations for Single-Cell Gene Perturbation Prediction
arXiv:2602.04901v2 Announce Type: replace-cross Abstract: Predicting transcriptional responses to genetic perturbations is a central problem in functional genomics. In practice, perturbation responses are rarely gene-independent but instead manifest as coordinated, program-level transcriptional changes among functionally related genes. However, most existing methods do not explicitly model such coordination, due to gene-wise modeling paradigms and reliance on static biological priors that cannot capture dynamic program reorganization. To address these limitations, we propose scBIG, a module-inductive perturbation prediction framework that explicitly models coordinated gene programs. scBIG induces coherent gene programs from data via Gene-Relation Clustering, captures inter-program interactions through a Gene-Cluster-Aware Encoder, and preserves modular coordination using structure-aware alignment objectives. These structured representations are then modeled using conditional flow matching to enable flexible and generalizable perturbation prediction. Extensive experiments on multiple single-cell perturbation benchmarks show that scBIG consistently outperforms state-of-the-art methods, particularly on unseen and combinatorial perturbation settings, achieving an average improvement of 6.7% over the strongest baselines. The code is available at https://github.com/ttruan2426-dot/scBIG.
Abstract:Predicting transcriptional responses to genetic perturbations is a central problem in functional genomics. In practice, perturbation responses are rarely gene-independent but instead manifest as coordinated, program-level transcriptional changes among functionally related genes. However, most existing methods do not explicitly model such coordination, due to gene-wise modeling paradigms and reliance on static biological priors that cannot capture dynamic program reorganization. To address these limitations, we propose scBIG, a module-inductive perturbation prediction framework that explicitly models coordinated gene programs. scBIG induces coherent gene programs from data via Gene-Relation Clustering, captures inter-program interactions through a Gene-Cluster-Aware Encoder, and preserves modular coordination using structure-aware alignment objectives. These structured representations are then modeled using conditional flow matching to enable flexible and generalizable perturbation prediction. Extensive experiments on multiple single-cell perturbation benchmarks show that scBIG consistently outperforms state-of-the-art methods, particularly on unseen and combinatorial perturbation settings, achieving an average improvement of 6.7% over the strongest baselines. The code is available at this https URL.
Genomics (q-bio.GN); Machine Learning (cs.LG)
arXiv:2602.04901 [q-bio.GN]
(or arXiv:2602.04901v2 [q-bio.GN] for this version)
https://doi.org/10.48550/arXiv.2602.04901 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 252 words
Related coverage
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
Deconfusing Corrigibility
AI Alignment Forum · Oct 17, 2026
CellMSA: Context Modeling for Single-Cell Representation Learning
arXiv · Oct 1, 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · Oct 8, 2026