Interactome-based deep learning and path-level decomposition reveal TGFβ-IFNα competition in MASH
- 1Department of Biological Engineering, Massachusetts Institute of Technology
Abstract
Dysregulated signaling drives Metabolic Dysfunction-Associated Steatohepatitis (MASH) through a complex crosstalk between pro- and anti-fibrotic cues. We previously observed potential competition between IFN-mediated JAK-STAT signaling and TGF{beta} in modulating MASH fibrosis, but the precise mechanism of that competition, and whether it can act directly on hepatocytes, is yet unknown. We used DT-LEMBAS, an interactome-based deep learning framework, training an ensemble of 50 models on drug-induced transcriptomics from primary human hepatocytes. The ensemble captured transcriptional changes induced by simulated receptor knockouts and aligned predicted profiles with known TGF{beta}- and IFN-induced phenotypes. Systematic simulations demonstrate their competitive modulation of MASH phenotype scores benchmarked against human cohorts. To extract mechanistic insights, we developed a gradient-based approach, where we computed the Jacobian of the used recurrent signaling network and applied chain rule decomposition to identify a four-node module of SMAD3, TP63, STAT2, and STAT3. Mechanistic hypotheses involving these canonical and non-canonical TF mediators were experimentally validated in primary hepatocyte spheroids. This work establishes a generalizable and scalable approach to decode large signaling neural networks into interpretable biological subnetworks.
Related
- Multilayer interaction networks reveal multidimensional ecological strategies and context-dependent competition in soil actinobacteria
- The PSD-95 interactome of hippocampal synapses potentiated in response to an in vivo learning task
- Crop-Level Screening and Physiological Evaluation Reveal Drought-Protective Effects of Plant-Derived Extracts in Cucumber Seedlings
- Language-aligned models and structured scene descriptions reveal sensitivity to compositional scene structure in the high-level visual cortex
- Chromosome-level genome and caste transcriptomes for Africa's most widespread social wasp (Belonogaster juncea) reveal unexpected genomic diversity
BibTeX
@misc{meimetis2026interactomebased,
title = {{Interactome-based deep learning and path-level decomposition reveal TGFβ-IFNα competition in MASH}},
author = {N. Meimetis and T. Matsuzaki and X. Mou and L. Foster and L. G. Griffith and D. A. Lauffenburger},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.24.761530},
url = {https://www.biorxiv.org/content/10.64898/2026.10.24.761530v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Interactome-based deep learning and path-level decomposition reveal TGFβ-IFNα competition in MASH
AU - N. Meimetis
AU - T. Matsuzaki
AU - X. Mou
AU - L. Foster
AU - L. G. Griffith
AU - D. A. Lauffenburger
PY - 2026
DA - 2026/10/24
PB - bioRxiv
DO - 10.64898/2026.10.24.761530
UR - https://www.biorxiv.org/content/10.64898/2026.10.24.761530v1
AB - Dysregulated signaling drives Metabolic Dysfunction-Associated Steatohepatitis (MASH) through a complex crosstalk between pro- and anti-fibrotic cues. We previously observed potential competition between IFN-mediated JAK-STAT signaling and TGF{beta} in modulating MASH fibrosis, but the precise mechanism of that competition, and whether it can act directly on hepatocytes, is yet unknown. We used DT-LEMBAS, an interactome-based deep learning framework, training an ensemble of 50 models on drug-induced transcriptomics from primary human hepatocytes. The ensemble captured transcriptional changes induced by simulated receptor knockouts and aligned predicted profiles with known TGF{beta}- and IFN-induced phenotypes. Systematic simulations demonstrate their competitive modulation of MASH phenotype scores benchmarked against human cohorts. To extract mechanistic insights, we developed a gradient-based approach, where we computed the Jacobian of the used recurrent signaling network and applied chain rule decomposition to identify a four-node module of SMAD3, TP63, STAT2, and STAT3. Mechanistic hypotheses involving these canonical and non-canonical TF mediators were experimentally validated in primary hepatocyte spheroids. This work establishes a generalizable and scalable approach to decode large signaling neural networks into interpretable biological subnetworks.
ER -