Central Dogma Transformer: Towards Mechanism-Oriented AI for Cellular Understanding

• URL: http://arxiv.org/abs/2601.01089v2
• Date: Sat, 10 Jan 2026 00:37:48 GMT
• Title: Central Dogma Transformer: Towards Mechanism-Oriented AI for Cellular Understanding
• Authors: Nobuyuki Ota,
• Abstract summary: We present the Central Dogma Transformer (CDT), an architecture that integrates pre-trained language models for DNA, RNA, and protein.<n>We validate CDT v1 on CRISPRi enhancer perturbation data from K562 cells, achieving a Pearson correlation of 0.503.<n>These results suggest that AI architectures aligned with biological information flow can achieve both predictive accuracy and mechanistic interpretability.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding cellular mechanisms requires integrating information across DNA, RNA, and protein - the three molecular systems linked by the Central Dogma of molecular biology. While domain-specific foundation models have achieved success for each modality individually, they remain isolated, limiting our ability to model integrated cellular processes. Here we present the Central Dogma Transformer (CDT), an architecture that integrates pre-trained language models for DNA, RNA, and protein following the directional logic of the Central Dogma. CDT employs directional cross-attention mechanisms - DNA-to-RNA attention models transcriptional regulation, while RNA-to-Protein attention models translational relationships - producing a unified Virtual Cell Embedding that integrates all three modalities. We validate CDT v1 - a proof-of-concept implementation using fixed (non-cell-specific) RNA and protein embeddings - on CRISPRi enhancer perturbation data from K562 cells, achieving a Pearson correlation of 0.503, representing 63% of the theoretical ceiling set by cross-experiment variability (r = 0.797). Attention and gradient analyses provide complementary interpretive windows: in detailed case studies, these approaches highlight largely distinct genomic regions, with gradient analysis identifying a CTCF binding site that Hi-C data showed as physically contacting both enhancer and target gene. These results suggest that AI architectures aligned with biological information flow can achieve both predictive accuracy and mechanistic interpretability.

Related papers

• Central Dogma Transformer II: An AI Microscope for Understanding Cellular Regulatory Mechanisms [0.0]
  We present CDT-II, an "AI microscope" whose attention maps are directly interpretable as regulatory structure.<n>By mirroring the central dogma in its architecture, CDT-II ensures that each attention mechanism corresponds to a specific biological relationship.<n>Applying to K562 CRISPRi data, CDT-II predicts perturbation effects and recovers the GFI1B regulatory network without supervision.
  arXiv  Detail & Related papers  (2026-02-09T14:54:31Z)
• Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling [74.25438319700929]
  We propose CHMR (Cell-aware Hierarchical Multi-modal Representations), a robust framework that models local-global dependencies between molecules and cellular responses.<n> evaluated on nine public benchmarks spanning 728 tasks, CHMR outperforms state-of-the-art baselines.<n>Results demonstrate the advantage of hierarchy-aware, multimodal learning for reliable and biologically grounded molecular representations.
  arXiv  Detail & Related papers  (2025-11-26T07:15:00Z)
• TRIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesis [56.9460577864211]
  TRIDENT is a cascade generative framework that synthesizes realistic cellular morphology by conditioning on both the perturbation and the corresponding gene expression profile.<n> TRIDENT significantly outperforms state-of-the-art approaches, achieving up to 7-fold improvement with strong generalization to unseen compounds.
  arXiv  Detail & Related papers  (2025-11-23T04:43:27Z)
• Learning Explicit Single-Cell Dynamics Using ODE Representations [33.16920280365721]
  Cell-Mechanistic Neural Networks (Cell-MNN) is an encoder-decoder architecture whose latent representation is a locally linearized ODE governing the dynamics of cellular evolution from stem to tissue cells.<n>We show that Cell-MNN achieves competitive performance on single-cell benchmarks, surpasses state-of-the-art baselines in scaling to larger datasets and joint training across multiple datasets, while also learning interpretable gene interactions that we validate against the TRRUST database of gene interactions.
  arXiv  Detail & Related papers  (2025-10-03T11:15:16Z)
• Enhanced Single-Cell RNA-seq Embedding through Gene Expression and Data-Driven Gene-Gene Interaction Integration [0.05156484100374057]
  We present a novel embedding approach that integrates both gene expression profiles and data-driven gene-gene interactions.<n>By incorporating both expression levels and gene-gene interactions, our approach provides a more comprehensive representation of cellular states.
  arXiv  Detail & Related papers  (2025-09-01T21:19:27Z)
• Clustering with Communication: A Variational Framework for Single Cell Representation Learning [2.275097126764287]
  We propose CCCVAE, a variational autoencoder framework that incorporates CCC signals into single-cell representation learning.<n>We show that CCCVAE improves clustering performance, achieving higher evaluation scores than standard VAE baselines.
  arXiv  Detail & Related papers  (2025-05-08T01:53:36Z)
• Interpretable Graph Kolmogorov-Arnold Networks for Multi-Cancer Classification and Biomarker Identification using Multi-Omics Data [36.92842246372894]
  Multi-Omics Graph Kolmogorov-Arnold Network (MOGKAN) is a deep learning framework that utilizes messenger-RNA, micro-RNA sequences, and DNA methylation samples.<n>By integrating multi-omics data with graph-based deep learning, our proposed approach demonstrates robust predictive performance and interpretability.
  arXiv  Detail & Related papers  (2025-03-29T02:14:05Z)
• UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials [62.72989417755985]
  We present UniGenX, a unified generative model for function in natural systems.<n>UniGenX represents heterogeneous inputs as a mixed stream of symbolic and numeric tokens.<n>It achieves state-of-the-art or competitive performance for the function-aware generation across domains.
  arXiv  Detail & Related papers  (2025-03-09T16:43:07Z)
• Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification [55.98854157265578]
  Life-Code is a comprehensive framework that spans different biological functions.<n>We propose a unified pipeline to integrate multi-omics data by reverse-transcribing RNA and reverse-translating amino acids into nucleotide-based sequences.<n>Life-Code achieves state-of-the-art results on various tasks across three omics, highlighting its potential for advancing multi-omics analysis and interpretation.
  arXiv  Detail & Related papers  (2025-02-11T06:53:59Z)
• Multimodal Analysis of White Blood Cell Differentiation in Acute Myeloid Leukemia Patients using a β-Variational Autoencoder [38.13262557169157]
  We introduce an unsupervised method that explores and reconstructs morphological and transcriptomic data. Our method is based on a beta-variational autoencoder (ss-VAE) with a customized loss function. It provides a unique tool to improve the understanding of white blood cell maturation for biomedicine and diagnostics.
  arXiv  Detail & Related papers  (2024-08-13T08:24:52Z)
• Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View [49.03501451546763]
  We identify the importance of implicit correspondences across biological contexts for exploiting domain-invariant pathological composition. We propose self-adaptive dynamic distillation to secure instance-aware trade-offs across different model constituents.
  arXiv  Detail & Related papers  (2024-07-14T04:41:16Z)
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model [68.28309982199902]
  We present NeuralPLexer, a computational approach that can directly predict protein-ligand complex structures. Our study suggests that a data-driven approach can capture the structural cooperativity between proteins and small molecules, showing promise in accelerating the design of enzymes, drug molecules, and beyond.
  arXiv  Detail & Related papers  (2022-09-30T01:46:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.