Agentomics-ML: Autonomous Machine Learning Experimentation Agent for Genomic and Transcriptomic Data

TL;DR

Agentomics-ML is an autonomous machine learning system that automates the process of developing classification models for genomic and transcriptomic data, improving generalization and success rates over existing methods.

Contribution

This work introduces Agentomics-ML, a fully autonomous agent-based system that automates ML experimentation specifically for heterogeneous biological datasets, achieving state-of-the-art results.

Findings

Outperforms existing agent-based methods in generalization and success rates.

Narrowed the performance gap between autonomous systems and domain experts.

Achieved state-of-the-art performance on one benchmark dataset.

Abstract

The adoption of machine learning (ML) and deep learning methods has revolutionized molecular medicine by driving breakthroughs in genomics, transcriptomics, drug discovery, and biological systems modeling. The increasing quantity, multimodality, and heterogeneity of biological datasets demand automated methods that can produce generalizable predictive models. Recent developments in large language model-based agents have shown promise for automating end-to-end ML experimentation on structured benchmarks. However, when applied to heterogeneous computational biology datasets, these methods struggle with generalization and success rates. Here, we introduce Agentomics-ML, a fully autonomous agent-based system designed to produce a classification model and the necessary files for reproducible training and inference. Our method follows predefined steps of an ML experimentation process, repeatedly interacting with the file system through Bash to complete individual steps. Once an ML model is produced, training and validation metrics provide scalar feedback to a reflection step to identify issues such as overfitting. This step then creates verbal feedback for future iterations, suggesting adjustments to steps such as data representation, model architecture, and hyperparameter choices. We have evaluated Agentomics-ML on several established genomic and transcriptomic benchmark datasets and show that it outperforms existing state-of-the-art agent-based methods in both generalization and success rates. While state-of-the-art models built by domain experts still lead in absolute performance on the majority of the computational biology datasets used in this work, Agentomics-ML narrows the gap for fully autonomous systems and achieves state-of-the-art performance on one of the used benchmark datasets. The code is available at https://github.com/BioGeMT/Agentomics-ML.