Pan-microalgal dark proteome mapping via interpretable deep learning and synthetic chimeras.

ABSTRACT: Microalgal genomes contain a vast "dark proteome"-sequences lacking detectable homology that evade conventional classification tools. We developed LA⁴SR (language modeling with AI for algal amino acid sequence representation), a framework using transformer- and state-space models to classify translated ORFeomes across ten algal phyla. Training on ∼77 million sequences, LA⁴SR achieves near-complete recall, accelerates classification by ∼10,701× relative to BLASTP⁺, and generalizes robustly to unseen sequences using less than 2% of available data. Models trained on synthetic, chimeric (terminal information [TI]-free) sequences maintained high accuracy, demonstrating that internal sequence features alone can drive robust classification. Inference speed and sca

SUBMITTER: Nelson DR 

PROVIDER: S-EPMC12664985 | biostudies-literature | 2025 Nov

REPOSITORIES: biostudies-literature