Evaluating machine learning algorithms at predicting developmental trajectories using sequential dataset truncation of voluntary alcohol consumption in adolescent mice

Nathan Yu, Steven Buyske, Uthman Qureshi, Lei Yu · 2026

Read Evaluating machine learning algorithms at predicting developmental trajectories using sequential dataset truncation of voluntary alcohol consumption in adolescent mice by Nathan Yu, Steven Buyske, Uthman Qureshi, Lei Yu (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-0352197.txt.

Description

Nathan Yu and colleagues tested twelve machine learning tools on a question about young drinkers. How early can a drinking pattern forecast the drinker someone becomes? The subjects were adolescent mice, and the drinking records were simulated from published mouse work. Long real records are scarce, so simulation filled the gap. The team fed each tool the record cut at growing lengths. That mimics a researcher deciding when a forecast can be trusted.

Six tools classified the final drinking paths with outstanding accuracy. They were near perfect by the end of the record and already strong at its midpoint. Four more tools did acceptably, and two lagged behind. The ranking gives addiction researchers a practical shortlist. It also shows how much observation an early, reliable signal costs.

Catalog record

CREATORNathan Yu, Steven Buyske, Uthman Qureshi, Lei Yu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE34972
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0352197

Browse the full library · About the Tower of Babel