Pre-trained Mol2Vec Embeddings as a Tool for Predicting Polymer Properties  

作　　者：Ivan Zlobin Nikita Toroptsev Gleb Averochkin Alexander Pavlov 

机构地区：[1]Center NTI“Digital Materials Science:New Materials and Substances”,Bauman Moscow State Technical University,2S1 Baumanskaya St.,5/1,105005,Moscow,Russia [2]A.N.Nesmeyanov Institute of Organoelement Compounds of Russian Academy of Sciences,Vavilova St.,28,Bld.1,119334,Moscow,Russia

出　　处：《Chinese Journal of Polymer Science》2024年第12期2059-2068,I0014,共11页高分子科学（英文版）

基　　金：the framework of the program of state support for the centers of the National Technology Initiative(NTI)on the basis of educational institutions of higher education and scientific organizations(Center NTI"Digital Materials Science:New Materials and Substances"on the basis of the Bauman Moscow State Technical University).

摘　　要：Machine learning-assisted prediction of polymer properties prior to synthesis has the potential to significantly accelerate the discovery and development of new polymer materials.To date,several approaches have been implemented to represent the chemical structure in machine learning models,among which Mol2Vec embeddings have attracted considerable attention in the cheminformatics community since their introduction in 2018.However,for small datasets,the use of chemical structure representations typically increases the dimensionality of the input dataset,resulting in a decrease in model performance.Furthermore,the limited diversity of polymer chemical structures hinders the training of reliable embeddings,necessitating complex task-specific architecture implementations.To address these challenges,we examined the efficacy of Mol2Vec pre-trained embeddings in deriving vectorized representations of polymers.This study assesses the impact of incorporating Mol2Vec compound vectors into the input features on the efficacy of a model reliant on the physical properties of 214 polymers.The results will hopefully highlight the potential for improving prediction accuracy in polymer studies by incorporating pre-trained embeddings or promote their utilization when dealing with modestly sized polymer databases.

关 键 词：Properties prediction High dimensional embeddings Machine learning Mol2Vec 

分 类 号：TQ317[化学工程—高聚物工业] TP181[自动化与计算机技术—控制理论与控制工程]