<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><volume>11(40)</volume><submitter>Menuhin-Gruman I</submitter><pubmed_abstract>Evolutionary instability is a persistent challenge in synthetic biology, often leading to the loss of heterologous gene expression over time. Here, we present STABLES, a gene fusion strategy that links a gene of interest (GOI) to an essential endogenous gene (EG), with a "leaky" stop codon in between. This ensures both selective pressure against deleterious mutations and the high expression of the GOI. By leveraging a machine learning framework, we predict optimal GOI-EG pairs on the basis of bioinformatic and biophysical features, identify linkers likely to minimize protein misfolding, and optimize DNA sequences for stability and expression. Experimental validation in &lt;i>Saccharomyces cerevisiae&lt;/i> demonstrated substantial improvements in stability and productivity for fluorescent protei</pubmed_abstract><journal>Science advances</journal><pagination>eadx0796</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC12487889</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>AI-directed gene fusing prolongs the evolutionary half-life of synthetic gene circuits.</pubmed_title><pmcid>PMC12487889</pmcid><pubmed_authors>Menuhin-Gruman I</pubmed_authors><pubmed_authors>Naki D</pubmed_authors><pubmed_authors>Bergman S</pubmed_authors><pubmed_authors>Arbel-Groissman M</pubmed_authors><pubmed_authors>Tuller T</pubmed_authors></additional><is_claimable>false</is_claimable><name>AI-directed gene fusing prolongs the evolutionary half-life of synthetic gene circuits.</name><description>Evolutionary instability is a persistent challenge in synthetic biology, often leading to the loss of heterologous gene expression over time. Here, we present STABLES, a gene fusion strategy that links a gene of interest (GOI) to an essential endogenous gene (EG), with a "leaky" stop codon in between. This ensures both selective pressure against deleterious mutations and the high expression of the GOI. By leveraging a machine learning framework, we predict optimal GOI-EG pairs on the basis of bioinformatic and biophysical features, identify linkers likely to minimize protein misfolding, and optimize DNA sequences for stability and expression. Experimental validation in &lt;i>Saccharomyces cerevisiae&lt;/i> demonstrated substantial improvements in stability and productivity for fluorescent protei</description><dates><release>2025-01-01T00:00:00Z</release><publication>2025 Oct</publication><modification>2026-06-04T01:32:51.043Z</modification><creation>2026-05-03T03:14:10.596Z</creation></dates><accession>S-EPMC12487889</accession><cross_references><pubmed>41032600</pubmed><doi>10.1126/sciadv.adx0796</doi></cross_references></HashMap>