Mixing features of transcription factors and genes enables accurate prediction of gene regulation relationships for unknown transcription factors

Okubo, R.; Morikura, T.; Hiki, Y.; Tokuoka, Y.; Kobayashi, T. J.; Yamada, T. G.; Funahashi, A.

doi:10.1101/2025.04.17.649264

Home/Archive/bioRxiv

bioRxiv · 10.1101/2025.04.17.649264

Mixing features of transcription factors and genes enables accurate prediction of gene regulation relationships for unknown transcription factors

Okubo, R.·Morikura, T.·Hiki, Y.·Tokuoka, Y.·Kobayashi, T. J.·Yamada, T. G.·Funahashi, A.

View original source ↗Export metadata ↓

Abstract

Identifying regulatory relationships between transcription factors (TFs) and genes is essential to understand diverse biological phenomena related to gene expression. Recently, deep learning-based models to predict TFs that bind to genes from nucleotide sequences of the target genes have been developed, yet these models are trained to predict known TFs only. In this study we developed a deep learning model, GReNIMJA (Gene Regulatory Network Inference by Mixing and Jointing features of Amino acid and nucleotide sequences), to predict gene regulation even by unknown TFs. Our model is designed to mix the features of the TF amino acid sequences and nucleotide sequences of the target genes using a 2D LSTM architecture and to perform binary classification with the aim of determining the presence or absence of a regulatory relationship. The accuracy of our model in predicting regulatory relationships was 84.4% for known TFs (higher than those of conventional models) and 68.5% for unknown TFs; the latter is an unsolved task for conventional deep learning-based models. We expect our model to advance identification of unknown gene regulatory networks and contribute to the understanding of diverse biological phenomena.

Source connections

Published article ↗

Explore related subjects

systems biology Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Okubo, R., Morikura, T., Hiki, Y., Tokuoka, Y., Kobayashi, T. J., Yamada, T. G., Funahashi, A.. 2025-04-23. Mixing features of transcription factors and genes enables accurate prediction of gene regulation relationships for unknown transcription factors. https://doi.org/10.1101/2025.04.17.649264

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Interpretable machine learning coupled to gene regulatory networks uncovers subcircuits underlying cell fate decisions

Gene regulatory networks (GRNs) model causal linkages that control cell fate decisions and differentiation transitions. Prioritizing regulatory subnetworks underlying cell state differences is of critical importance, but current methods including those reliant on topological metrics introduce circularity as the metrics prioritizing TFs are computed from the same networks whose assumptions they inherit. Separately, interpretable machine learning methods can identify latent factors (LFs) that discriminate cellular states with formal statistical guarantees but do not model regulatory linkages. Here, we present FOCAL (Factor-Outcome Coupling for Assessment of Linkages), a paradigm to prioritize regulatory subnetworks by coupling state-specific and dynamic GRNs with outcome-supervised LFs learned using interpretable machine learning without reference to network topology. This shifts GRN focus from macroscopic TF nodes to state-specific and dynamic TF-gene linkages. In B and T cells, FOCAL identified GIFs (GRNs coupled to Interpretable latent Factors), prioritized regulatory subnetworks underlying established states as well as transient regulatory episodes preceding them. By coupling LFs learnt from perturbation experiments of lineage-defining TFs, FOCAL identified transcriptional predisposition to alternative fates within progenitor cell populations before overt differentiation. This uncovered a novel NFATC2-IRF8 interplay in activated B cells, that was validated by in-vitro and in-vivo genetic perturbations. The two transcription factors act cooperatively to restrain extrafollicular plasmablast differentiation and promote germinal center B cell fate.

systems biology↗

bioRxiv2026

Comprehensive in silico analysis reveals candidate regulatory mechanisms underlying selective cerebellar vulnerability in pontocerebellar hypoplasia

Pontocerebellar hypoplasia (PCH) is a group of ultrarare, neurodegenerative disorders characterized by cerebellar and pontine hypoplasia. Genetic analysis over the last two decades has revealed an increasing number of pathogenic variants in a wide range of broadly expressed genes functioning in RNA processing, tRNA metabolism, and translation. However, the mechanisms linking these ubiquitous processes to brain region-specific vulnerability are unknown. Here, we established a multi-level variant-to-function in silico framework to predict the molecular consequences of PCH-associated variants in TSEN complex genes. These variants were predicted to have heterogeneous effects on diverse protein properties, including stability, subcellular localization, and degradation, supporting variant-specific rather than uniform disease mechanisms. Complementary transcriptomic analyses showed that PCH-associated genes were not globally enriched in the prenatal cerebellum. Instead, their expression was coordinated in a stage- and cell type-specific manner during cerebellar development. We therefore hypothesize that multiple PCH-associated genes are regulated by a common set of transcription factors, providing an explanation of the selective vulnerability of the cerebellum and to the phenotypic convergence of genetically diverse PCH subtypes. In summary, this study prioritizes candidate variants for biochemical, cellular, and in vivo validation, and identifies regulatory programs, cell lineages, and developmental windows for targeted, mechanistically informed disease modelling.

systems biology↗

bioRxiv2026

Limit-pushing overexpression reveals constraints on protein abundance

Proteins are often classified as toxic or non-toxic without measuring the abundance reached, leaving constraints on tolerable protein abundance unresolved. We established a limit-pushing approach in Saccharomyces cerevisiae combining strong inducible expression with gTOW-mediated high-copy selection to counteract copy-number compensation while measuring protein abundance and growth. Nearly all of approximately 80 chromosome I proteins severely inhibited growth or reduced viability at sufficiently high abundance. We established IE50, the expression level associated with a 50% reduction in growth rate, to quantify their widely varying overexpression tolerance. IE50 was positively associated with predicted structural order and cytoplasmic localization propensity and negatively associated with sulphur content. Single-cell imaging linked higher tolerance to proteins remaining cytoplasmic without becoming aggregation-positive and revealed abundance-dependent changes in localization and organelle morphology. At extreme abundance, Fun12, Nup60, and Pex22 generated distinct large-scale intracellular states through specific sequence regions. These findings establish overexpression toxicity as a quantitative property linked to protein characteristics and reveal both constraints on tolerable abundance and sequence-dependent capacities for intracellular organization.

systems biology↗