Genomic language models: opportunities and challenges

Trends in Genetics, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

---

Evaluating the representational power of pre-trained DNA language models for regulatory genomics

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: March 4, 2024

ABSTRACT The emergence of genomic language models (gLMs) offers an unsupervised approach to learning a wide diversity cis -regulatory patterns in the non-coding genome without requiring labels functional activity generated by wet-lab experiments. Previous evaluations have shown that pre-trained gLMs can be leveraged improve predictive performance across broad range regulatory genomics tasks, albeit using relatively simple benchmark datasets and baseline models. Since these studies were tested upon fine-tuning their weights for each downstream task, determining whether gLM representations embody foundational understanding biology remains open question. Here we evaluate representational power predict interpret cell-type-specific data span DNA RNA regulation. Our findings suggest probing do not offer substantial advantages over conventional machine approaches use one-hot encoded sequences. This work highlights major gap with current gLMs, raising potential issues pre-training strategies genome.

Language: Английский

---

Large language model applications in nucleic acid research

Published: Jan. 1, 2025

Language: Английский

---

Identification, characterization, and design of plant genome sequences using deep learning

The Plant Journal, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 12, 2024

SUMMARY Due to its excellent performance in processing large amounts of data and capturing complex non‐linear relationships, deep learning has been widely applied many fields plant biology. Here we first review the application analyzing genome sequences predict gene expression, chromatin interactions, epigenetic features (open chromatin, transcription factor binding sites, methylation sites) plants. Then, current motif mining functional component design synthesis based on generative adversarial networks, models, attention mechanisms are elaborated detail. The progress protein structure function prediction, genomic model applications is also discussed. Finally, this work provides prospects for future development plants with regard multiple omics data, algorithm optimization, language sequence design, intelligent breeding.

Language: Английский

---

The maize recombination landscape evolved during domestication.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 6, 2024

Abstract Meiotic recombination is an important evolutionary process because it can increase the amount of genetic variation within populations through breakage unfavorable linkages and creation novel allelic combinations. Despite plethora knowledge about population-level benefits numerous theoretical studies examining how rates evolve over time, there a lack empirical evidence for any hypotheses that have been put forward. To alleviate this gap in knowledge, we characterized evolution landscape Zea mays ssp. (maize) during its domestication from parviglumis (teosinte), explored permitted maize tied these alterations to changes basis recombination. Using experimental population genomics approach ancestral graph (ARG) inference, our data demonstrated had 12% genome-wide rate domestication. Although teosinte landscapes are highly correlated, r = 0.85 at 1Mb resolution, has evolved higher recombining regions interstitial chromosome regions, compared which only harbors high sub-telomerically. Our show re-patterning COs towards came reduced CO interference levels maize. Supporting idea maize, found selection acting on trans-acting recombination-modifiers participate class I pathway or directly. Lastly, showed was beneficial significantly increased were targeted gene-rich harboring related loci. Because with significant increases lower deleterious mutation load, decreases recombination, concluded domestication-related acted upon domestication, shielded Hill-Robertson effect. In conclusion, events allowed adapt faster than previously understood.

Language: Английский

---

Genomic resources, opportunities, and prospects for accelerated improvement of millets

Theoretical and Applied Genetics, Journal Year: 2024, Volume and Issue: 137(12)

Published: Nov. 20, 2024

Genomic resources, alongside the tools and expertise required to leverage them, are essential for effective improvement of globally significant millet crop species. Millets global food security nutrition, particularly in sub-Saharan Africa South Asia. They crucial promoting climate resilience, economic development, cultural heritage. Despite their critical role, millets have historically received less investment developing genomic resources than major cereals like wheat, maize, rice. However, recent advancements genomics, next-generation sequencing technologies, offer unprecedented opportunities rapid crops. This review paper provides an overview status harnessing artificial intelligence address challenges boost productivity, end quality. It emphasizes significance genomics tackling issues underscores necessity innovative breeding strategies translate AI into millets.

Language: Английский

---