Central Dogma Transformer II: An AI Microscope for Understanding Cellular Regulatory Mechanisms

TL;DR

The paper introduces CDT-II, an interpretable AI model mimicking the central dogma, capable of revealing cellular regulatory mechanisms and predicting perturbation effects with high accuracy, serving as an AI microscope for biological insights.

Contribution

CDT-II is a novel architecture that models gene regulation with interpretability, directly linking learned structures to biological relationships and experimental hypotheses.

Findings

Predicts perturbation effects with mean r = 0.84

Recovers GFI1B regulatory network with 6.6-fold enrichment

Identifies regulatory elements and pathways relevant to clinical outcomes

Abstract

Current biological AI models lack interpretability -- their internal representations do not correspond to biological relationships that researchers can examine. Understanding gene regulation requires models whose learned structure can be directly interrogated to generate experimentally testable hypotheses. CDT-II mirrors the central dogma in its architecture -- DNA self-attention, RNA self-attention, and cross-attention for transcriptional control -- requiring only genomic embeddings and raw per-cell expression. Applied to K562 CRISPRi data with five genes held out entirely, CDT-II predicts perturbation effects (per-gene mean r = 0.84), recovers the GFI1B regulatory network (6.6-fold enrichment, P = 3.5 x 10^{-17}), and shows that cross-attention focuses on ENCODE regulatory elements including CTCF sites (mean 7.67x across 28 targets, P < 0.001). Gradient-based attribution accurately predicts downstream consequences of perturbing therapeutic targets (mean r = 0.82). Applied to TFRC, the target of the anti-TfR1 antibody PPMX-T003, gradient analysis identifies genes involved in erythrocyte structure, iron-dependent DNA synthesis, and oxidative stress -- pathways that align with anemia and reticulocyte decrease reported in Phase 1 trials and ferroptosis demonstrated in preclinical studies, without any clinical data as input, establishing CDT-II as an AI microscope that reveals clinically relevant regulatory structure from perturbation experiments alone.