# Researchers combine GPT-Neo with Random Forest to predict Agrobacterium promoters at 97% accuracy

Digest AI · Research · published 2026-10-27T00:00:00Z

Canonical: https://digestai.news/story/researchers-combine-gpt-neo-with-random-forest-to-predict-agrobacteriu

## Summary

A team from Princess Nourah bint Abdulrahman University developed a promoter prediction method for Agrobacterium tumefaciens that pairs a GPT-Neo transformer with Random Forest feature engineering. The model tokenizes nucleotide sequences into embeddings, which the Random Forest classifier then uses for probabilistic feature extraction. With SMOTE applied to address class imbalance, the system reached 97% accuracy and 0.99 AUC, outperforming conventional approaches. The work is published in Scientific Reports under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 license.

## Key points

- GPT-Neo embeddings plus Random Forest achieve 97% accuracy and 0.99 AUC on Agrobacterium promoter prediction
- SMOTE balances classes to equalize sensitivity and specificity
- Published open access in Scientific Reports with CC BY-NC-ND 4.0 license

## Why it matters

Shows LLM embeddings can boost classical ML on genomic tasks, offering a reusable pattern for bacterial gene regulation studies.

## Sources

1. [A novel LLM-based GPT-neo transformer with machine learning architecture for promoters prediction in Agrobacterium](https://nature.com/articles/s41598-025-14337-w) (Nature Machine Learning, 2026-10-27, primary source)

## Cite

Digest AI, "Researchers combine GPT-Neo with Random Forest to predict Agrobacterium promoters at 97% accuracy", 27 October 2026, https://digestai.news/story/researchers-combine-gpt-neo-with-random-forest-to-predict-agrobacteriu

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-combine-gpt-neo-with-random-forest-to-predict-agrobacteriu.json