Genes, shells, and AI: using computer vision to detect cryptic morphological divergence between genetically distinct populations of limpets
Jack D Hollister, David A Paz-García, Rodrigo Beas-Luna, Tammy Horton, Xiaohao Cai, Phillip B Fenberg · 2025
Read Genes, shells, and AI: using computer vision to detect cryptic morphological divergence between genetically distinct populations of limpets by Jack D Hollister, David A Paz-García, Rodrigo Beas-Luna, Tammy Horton, Xiaohao Cai, Phillip B Fenberg (2025) 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/pmc-12783718.txt.
Description
Jack D Hollister and co-authors use computer vision to find hidden shape differences between limpet groups with distinct genes, in a 2025 study. Many species split into gene groups with no clear outward split, which hides true diversity. Four limpet species along the Baja California and California coasts served as tests.
A trained image network sorted shell photos into the right gene groups with high accuracy across repeated runs. Control groups with shuffled labels scored far worse, which confirms the signal is real. Heat maps showed which shell parts the network used, such as a keyhole rim and ridge tips. Shape analysis then verified real differences at those spots. The authors offer the workflow for wider biodiversity work.
Catalog record
| CREATOR | Jack D Hollister, David A Paz-García, Rodrigo Beas-Luna, Tammy Horton, Xiaohao Cai, Phillip B Fenberg |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |