AI model PlantBGC enhances discovery of plant gene clusters

Researchers have developed PlantBGC, a novel AI-driven tool designed to identify plant biosynthetic gene clusters (BGCs). This system utilizes an encoder-only Transformer model, trained on microbial BGCs and adapted for plant genomes using label-free domain adaptation. PlantBGC demonstrates significant improvements in recovering known BGCs and defining their boundaries more accurately compared to existing methods like plantiSMASH. Additionally, weak supervision derived from Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways further refines the discovery process by reducing false positives. AI

IMPACT This research could accelerate the discovery of novel plant compounds by improving the efficiency and accuracy of genomic analysis.

RANK_REASON The cluster describes a new AI model and methodology published in an arXiv paper for a specific scientific domain. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Hugging Face
• Kegg
• Minimum Information about a Biosynthetic Gene cluster Repository
• Pfam
• PlantBGC
• Transformer

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →