PlasmidGPT: a generative framework for plasmid design and annotation

PlasmidGPT is a generative language-model framework trained on 153,000 engineered plasmid sequences from Addgene, designed to generate de novo plasmid DNA while keeping low sequence identity to training data. The authors show that it can produce plasmid sequences in a controlled way using either an input sequence or explicit design constraints, and that it learns embeddings enabling efficient prediction of multiple sequence-related attributes across engineered and natural plasmids. The main caveat noted is implicit in the reliance on the Addgene plasmid corpus, which may constrain the range of sequence characteristics it can learn and generate. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works