Shedding light on neural learning to rank models for anticancer drug prioritization

Faraz Sarmeili, Benyamin Ghahremani-Nezhad, Mohammad Khalilpour, Karim Abbasi, Rassoul Dinarvand, Hamid R Rabiee · 2026

Read Shedding light on neural learning to rank models for anticancer drug prioritization by Faraz Sarmeili, Benyamin Ghahremani-Nezhad, Mohammad Khalilpour, Karim Abbasi, Rassoul Dinarvand, Hamid R Rabiee (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-0345854.txt.

Description

Faraz Sarmeili and colleagues benchmarked ranking methods that order cancer drugs by likely benefit for a given cell line. Ranking fits the real task better than predicting exact response values. Their 2026 study compared six ranking loss functions and five ways of describing drugs across two large screening datasets.

List-based losses led on both early and overall ranking quality. Mixing molecular fingerprints with basic chemical descriptors improved results further. The team added attention maps and an explanation tool that flagged genes and drug fragments behind each ranking. The explanations separated two breast cancer subtypes and highlighted known active parts of real drugs. Sarmeili and colleagues present the work as a step toward ranking tools doctors can inspect.

Catalog record

CREATORFaraz Sarmeili, Benyamin Ghahremani-Nezhad, Mohammad Khalilpour, Karim Abbasi, Rassoul Dinarvand, Hamid R Rabiee
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE88065
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0345854

Browse the full library · About the Tower of Babel