Biology subjects

Paull, E.

Publications and source records attributed to Paull, E..

3 recordsLinked to original sources

bioRxiv2026

DoFormer: Causal Transformer for Gene Perturbation

Learning causal gene regulatory mechanisms from single-cell data, and thereby predicting the effects of unseen perturbations, remains challenging. Observational RNA-seq data alone is insufficient for causal modeling, whereas perturbational data is essential. Classical causal inference methods often rely on unrealistic directed acyclic graph (DAG) assumptions and are not well suited to integrating multimodal data. Current transcriptomic foundation models also typically treat observational and perturbational data identically, limiting their ability to model perturbations. We present DoFormer, a causal multimodal Transformer that makes no DAG assumptions and leverages rich perturbational data to accurately predict previously unseen perturbations. DoFormer enables principled in silico perturbations by adapting the causal do-operator within the attention mechanism: the perturbed gene is set to the intervention value and prevented from attending to other genes, allowing the model to fully distinguish observational from interventional regimes. We train DoFormer using biologically informed loss functions and evaluate it with comprehensive perturbation prediction metrics. DoFormer substantially improves perturbation prediction relative to baseline and prior foundation models, underscoring the importance of intervention-aware architectures and biologically grounded objectives for causal modeling in single-cell genomics.

bioinformatics↗

bioRxiv2025

GREmLN: A Cellular Regulatory Network-Aware Transcriptomics Foundation Model

AO_SCPLOWBSTRACTC_SCPLOWThe ever-increasing availability of large-scale single-cell profiles presents an opportunity to develop foundation models to capture cell properties and behavior. However, standard language models such as transformers benefits from sequentially structured data with well defined absolute or relative positional relationships, while single cell RNA data have orderless gene features. Molecular-interaction graphs, such as gene regulatory networks (GRN) or protein-protein interaction (PPI) networks, offer graph structure-based models that effectively encode both non-local gene token dependencies, as well as potential causal relationships. We introduce GREmLN (Gene Regulatory Embedding-based Large Neural model), a foundation model that leverages graph signal processing to embed gene token graph structure directly within its attention mechanism, producing biologically informed single cell specific gene embeddings. Our model faithfully captures transcriptomics landscapes and achieves superior performance relative to state-of-the-art baselines on cell type annotation, graph structure understanding, and fine-tuned reverse perturbation prediction tasks. It offers a unified and interpretable framework for learning high-capacity foundational representations that capture complex, long-range regulatory dependencies from high-dimensional single-cell transcriptomic data. Moreover, the incorporation of graph-structured inductive biases enables more parameter-efficient architectures and accelerates training convergence.

bioinformatics↗

bioRxiv2021

Interrogation of genome-wide, experimentally dissected gene regulatory networks reveals mechanisms underlying dynamic cellular state control

Pooled CRISPRi-mediated silencing of >1,000 transcriptional regulators expressed in single colorectal adenocarcinoma cells, followed by single-cell RNA-seq profiling at two timepoints, 1 day and 4 days, allowed reverse engineering the underlying tumor context-specific, causal regulatory network. Furthermore, the availability of experimentally derived, highly multiplexed gene reporter assays for each regulator, as identified by this analysis, allowed accurate assessment of differential protein activity following silencing of each regulator, thus providing proof-of-concept for generating comprehensive, tissue-specific networks of transcriptional and post-translational interactions. Analysis of this causal network allowed elucidation of complex autoregulatory mechanisms that have eluded previous computational approaches and supported systematic elucidation of cooperative mechanisms, where one regulatory protein can modulate the activity of another regulatory protein, as well as transcriptional mimicry, where one regulatory protein can phenocopy others.

systems biology↗