Quadratic descriptors and reduction methods in a two-layered model for compound inference

Jianshen Zhu, Naveed Ahmed Azam, Shengjuan Cao, Ryota Ido, Kazuya Haraguchi, Liang Zhao, Hiroshi Nagamochi, Tatsuya Akutsu · 2025

Read Quadratic descriptors and reduction methods in a two-layered model for compound inference by Jianshen Zhu, Naveed Ahmed Azam, Shengjuan Cao, Ryota Ido, Kazuya Haraguchi, Liang Zhao, Hiroshi Nagamochi, Tatsuya Akutsu (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-11814466.txt.

Description

Jianshen Zhu and seven co-authors improve machine learning guesses of chemical properties by adding to molecular descriptors, in a two thousand twenty-five chemoinformatics paper. Models for inferring compounds live or die by how well their descriptors capture what matters in a molecule.

The team brings in quadratic descriptors, products of pairs of graph-based descriptors, inside a two-layered inference model. A mixed-integer linear programming setup closely matches the descriptors, and several pruning methods trim the enlarged feature set to avoid overfitting and heavy work. Across thirty-two monomer properties and ten polymer properties, the learned functions gave close answers. Checking new compounds took from seconds to about a minute, backing useful drug and materials screening.

Catalog record

CREATORJianshen Zhu, Naveed Ahmed Azam, Shengjuan Cao, Ryota Ido, Kazuya Haraguchi, Liang Zhao, Hiroshi Nagamochi, Tatsuya Akutsu
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE54 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11814466

Browse the full library · About the Tower of Babel