Apr 26, 2026
Fragment Assembly Risk Scorer (FARS): Empirical Characterization of Split-Order Detection Boundaries for Benchtop DNA Synthesizers
Hritika Chaturvedi
Benchtop DNA synthesizers have no mandatory screening today — and existing tools have a structural blind spot: they evaluate DNA fragments individually, missing split-order attacks where multiple innocuous-looking fragments assemble into a sequence of concern. We present the Fragment Assembly Risk Scorer (FARS), a prototype on-device detector that scores orders by collective assembly potential rather than individual fragment identity. Tested against 960 simulated orders across three real 1918 H1N1 genomic segments from NCBI GenBank, FARS achieves 100% detection of high- and medium-coverage split orders with zero false positives. Most importantly, on partial split orders, FARS detects 80% compared to 40% for an individual-sequence baseline modeled on IBBIS commec's methodology, doubling detection while eliminating false positives entirely. The 20% that evade local detection define a precise empirical boundary motivating shared cross-device infrastructure. Our head-to-head comparison is the first
empirical quantification of what assembly-awareness buys in split-order detection on real genomic data — and directly characterizes the gap left by S.3741's mandated screening approach.
I liked the well-defined scope and clear result of this submission. While a discussion of the limitations is present, I would have appreciated a more in-depth discussion on the implications of these. For example, the limitation of AI-enabled design is flagged but not really grappled with. For example, the results section could have discussed what the detection boundary would look like against codon-optimized or AI-designed sequences.
Additionally, while a great technical paper, the submission could have benefited from a summary in simple terms so that educated people in the field with no specific knowledge of synthesis screening could better grasp the problem and the corresponding solution.
Cite this work
@misc {
title={
(HckPrj) Fragment Assembly Risk Scorer (FARS): Empirical Characterization of Split-Order Detection Boundaries for Benchtop DNA Synthesizers
},
author={
Hritika Chaturvedi
},
date={
4/26/26
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}
