Motif-Vocab: StatisticallyCalibrated Transcription-Factor-Identity Tokenization forGenomic Language Models

arXiv:2609.28386 · q-bio.GN · Submitted 2026-09-23 · Read on arXiv

q-bio.GN

Submitted: 2026-09-23

Updated: 2026-09-23

Terminology

• Tokenization — 21× in this paper · explained in 2 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Core — 9× in this paper · explained in 2 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Calibration — 6× in this paper · explained in 7 episodes
• Foundation Model — 5× in this paper · explained in 3 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Foundation Models — 4× in this paper · explained in 7 episodes
• Nucleotide Transformer — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Degeneracy — 3× in this paper · explained in 3 episodes
• Genomic Benchmarks — 3× in this paper
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Abundance — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Embeddings — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Find Individual Motif Occurrences — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Genome Understanding Evaluation — 1× in this paper
• Inverse Problem — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 4 episodes

Sources

• On the Opportunities and Risks of Foundation Models
• EvoLen: Evolution-Guided Tokenization for DNA Language Model
• DNACHUNKER: Learnable Tokenization for DNA Language Models
• HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
• Technical Note on Transcription Factor Motif Discovery from Importance Scores (TF-MoDISco) version 0.5.6.5
• DNAMotifTokenizer: Towards Biologically Informed Tokenization of Genomic Sequences

Related papers

• WTKO-CNN: Deep Learning Reveals Sequence Motifs Distinguishing Wild-Type and Knockout ATAC-seq Peaks
• Stable-Shift: Biologically Structured Prediction of Transcriptional Responses to Unseen Gene Perturbations