A systematic review of deep learning chemical language models in recent era

Hector Flores-Hernandez, Emmanuel Martinez-Ledesma · 2024

Read A systematic review of deep learning chemical language models in recent era by Hector Flores-Hernandez, Emmanuel Martinez-Ledesma (2024) 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-11571686.txt.

Description

Hector Flores-Hernandez and Emmanuel Martinez-Ledesma review deep learning models that generate molecules from text-like chemical codes, in a 2024 paper. Designing new compounds is costly, and models that write chemical strings have sped the search.

The team gathered seventy-two articles from database and citation searches. Most used chemical language models, with the rest using graph forms. Five model families dominate, from transformers to autoencoders. Tricks like transfer and reinforcement learning steer output toward wanted regions of chemical space. The review compares data sets, model sizes, and the trade-off between validity and novelty. It ends with the field's main challenges and openings.

Catalog record

CREATORHector Flores-Hernandez, Emmanuel Martinez-Ledesma
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE92 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11571686

Browse the full library · About the Tower of Babel