Tom Mitchell

This study evaluates the effectiveness of biosecurity screening tools against AI-generated synthetic homologs of proteins of concern, finding some tools can detect fragments as short as 50 nucleotides.

The paper develops a rubric to define sequences of concern by analyzing test sequences and refining categorization through stakeholder review, reducing disputed categorization by 44.3% for controlled viruses.

The paper evaluates sequence screening tools using a NIST dataset to assess their consistency in identifying sequences of concern.

The paper evaluates vulnerabilities in biosecurity screening tools by testing their ability to detect splitting-based obfuscation of synthetic DNA sequences.

The paper evaluates biosecurity screening tools for detecting AI-generated synthetic protein homologs and reports improved detection rates through patches.

This paper introduces DART, a DBTL loop for synthetic genetic circuit design, showing that complex circuits can be more robust and reproducible than simpler ones in budding yeast.

The paper develops a computational method to predict synthetic circuit robustness across growth conditions and validates it with experimental results in budding yeast.

The paper replicates yeast-based logic circuit design assessments using a high-throughput robotic framework, generating more flow cytometry data than the original study.

The paper describes challenges in scientific collaboration and presents a flexible data-sharing model to improve information flow and experimentation in multidisciplinary research.

The paper introduces Prymetime, a workflow for accurate whole genome sequencing of engineered yeasts, showing it can assemble and annotate synthetic parts and detect unintended modifications.

The paper identifies unique amino acid sequences in 2019-nCoV that distinguish it from other Coronaviridae viruses.