Genome-wide machine learning analysis of anosmia and ageusia with COVID-19
Lucas Pietan, Elizabeth Phillippi, Marcelo Melo, Hatem El-Shanti, Brian J Smith, Benjamin Darbro, Terry Braun, Thomas Casavant · 2026
Read Genome-wide machine learning analysis of anosmia and ageusia with COVID-19 by Lucas Pietan, Elizabeth Phillippi, Marcelo Melo, Hatem El-Shanti, Brian J Smith, Benjamin Darbro, Terry Braun, Thomas Casavant (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0355832.txt.
Description
Lucas Pietan and colleagues hunted for genes behind the loss of smell and taste that many COVID-19 patients report. These symptoms can linger, and their biology is still partly unclear. Their 2026 study applied machine learning to genome data from two American patient cohorts of different sizes.
The team built a pipeline that ranks genes and variants by how well they separate patients with sensory loss. Best models sorted patients moderately well on held-out data. The shortlist mixed new candidates with known factors tied to immune response, nerve signalling, and calcium signalling. Pietan and colleagues say the results support earlier ideas about how the virus disturbs smell and taste, and they offer targets for follow-up.
Catalog record
| CREATOR | Lucas Pietan, Elizabeth Phillippi, Marcelo Melo, Hatem El-Shanti, Brian J Smith, Benjamin Darbro, Terry Braun, Thomas Casavant |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 82817 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |