Decoding the Grammar of Evolution: Foundation Models and deep learning Population Genomic Inference

Population genetics has undergone a radical transformation: from a field constrained by summary statistics to one leveraging high-dimensional genomic architectures. The contemporary challenge is not data scarcity—it is interpretability amid complexity. Genomic Foundation Models (gLMs) and deep learning architectures now enable us to extract evolutionary signals directly from raw sequences, transcending the limitations of hand-crafted statistics. Yet this transition demands rigorous engagement with three critical frontiers: (1) principled inference under realistic evolutionary scenarios, (2) robust interpretation of learned representations, and (3) scalable application across species and genomic contexts.

This Research Topic seeks to brings together methodological innovations, theoretical frameworks, and empirical applications to establish deep learning as a foundational toolkit for modern population genomics. We explicitly move beyond pattern recognition toward causal inference, emphasizing uncertainty quantification, model robustness, and the reconciliation of neural approaches with classical population genetic theory. By convening this community, we aim to catalyze the next generation of evolutionary genomic research—one where machine learning complements, rather than replaces, evolutionary intuition.

We invite submissions on: 1. Foundation Models as Evolutionary Interpreters (Emphasis: Non-coding constraint, variant effect prediction, and mechanistic understanding) 2. Generative Models for Genomic Simulation and Inference ( Realistic data generation, LD-aware synthesis, and parameter estimation) 3. Deep Learning for Demographic History and Selection Inference (Robust inference, interpretability, and handling confounding factors) 4. Pan-genome Graphs and Structural Variation Inference ( Evolutionary dynamics within graph genomes, and complex variation impact) 5. Emerging Challenges & Methodological Foundations (Robustness, generalization, and critical appraisal)

In Scope:

Computational & methodological papers developing novel algorithms for population genomic inference

Empirical applications of AI foundation models and deep learning to real genomic datasets (human, non-human primates, model organisms, plants, microbes)

Theoretical papers examining the population genetic foundations of deep learning approaches

Review and perspective papers synthesizing the state-of-the-art and identifying open problems

Benchmark and comparison studies evaluating multiple methods across standardized datasets

Interpretability and visualization approaches for understanding deep learning in evolutionary context

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Data Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Data Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Policy and Practice Reviews
• Review
• Systematic Review
• Technology and Code

Keywords: Generative AI, DNA language models, Evolutionary inference, Genomic Foundation Models, Variant deleteriousness

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.