LDBT instead of DBTL: combining machine learning and rapid cell-free testing

2025/11/05 by Alia Clark‐ElSayed, Ian T. Harrison, Mari Olsen +3 · 1 voice
Biochemistry, Genetics and Molecular Biology · Computer Science · #Gene Regulatory Network Analysis #Machine Learning and Algorithms #Single-cell and spatial transcriptomics

paper · pdf · doi:10.1038/s41467-025-65281-2

openalex created_date 2025/11/05 · openalex publication_date 2025/11/05 · openalex updated_date 2026/07/27

Abstract

Synthetic biology is defined by Design-Build-Test-Learn cycles. Recent advances in machine learning are changing the landscape; thus, we propose that “Learning” can precede “Design”. Moreover, adopting cell-free platforms can further accelerate “Building” and “Testing” for megascale data generation and models.

Citations

• Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
• Highly accurate protein structure prediction with AlphaFold
• Machine learning-aided engineering of hydrolases for PET depolymerization
• Robust deep learning–based protein sequence design using ProteinMPNN
• ProGen2: Exploring the boundaries of protein language models
• Cell-Free Gene Expression: Methods and Applications
• ProGen2: Exploring the Boundaries of Protein Language Models

Discussions

• LDBT instead of DBTL: combining machine learning and rapid cell-free testing doi.org/10.1038/s414... [bsky, 3 points, 0 comments]

Related

• Human Comprehensible Active Learning of Genome-Scale Metabolic Networks
• Single cell data explosion: Deep learning to the rescue
• Automated Biodesign Engineering by Abductive Meta-Interpretive Learning
• DeepMetabolism: A Deep Learning System to Predict Phenotype from Genome Sequencing
• DNA Circuits That Learn: Biochemical Signal Processing for Personalized Diagnosis and Treatment