Hybrid CNN and multi-head attention model for analyzing epigenetic mechanisms and gene expression across fungal phylogenetic distances

Laura Weinstock, Jenna Schambach, Anna Lara, Cameron Kunstadt, Ethan Lee, Elizabeth Koning, William Morrell, Wittney Mays, Warren Davis, Raga Krishnakumar · 2026

Read Hybrid CNN and multi-head attention model for analyzing epigenetic mechanisms and gene expression across fungal phylogenetic distances by Laura Weinstock, Jenna Schambach, Anna Lara, Cameron Kunstadt, Ethan Lee, Elizabeth Koning, William Morrell, Wittney Mays, Warren Davis, Raga Krishnakumar (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/pmc-13506266.txt.

Description

Ten researchers build a deep learning model that predicts gene activity in fungi in a paper from 2026. Gene activity is shaped by chemical marks on DNA and its packaging, called epigenetic marks. How those marks carry across species is poorly known, above all in less studied fungi. Their model, named MAPLE, mixes two neural network styles to read patterns in the marks.

The model scored well within species and held up when moved to other fungi. It beat standard rival methods on both kinds of test. An analysis step showed which marks drove each prediction. The authors say the tool can transfer knowledge from well-mapped fungi to obscure ones. That could speed work in health and industry.

Catalog record

CREATORLaura Weinstock, Jenna Schambach, Anna Lara, Cameron Kunstadt, Ethan Lee, Elizabeth Koning, William Morrell, Wittney Mays, Warren Davis, Raga Krishnakumar
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE72 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13506266

Browse the full library · About the Tower of Babel