In the past few decades, polymers, high-molecular-weight compounds formed by
bonding numerous identical or similar monomers covalently, have played an
essential role in various scientific fields. In this context, accurate
prediction of their properties is becoming increasingly crucial. Typically, the
properties of a polymer, such as plasticity, conductivity, bio-compatibility,
and so on, are highly correlated with its 3D structure. However, current
methods for predicting polymer properties heavily rely on information from
polymer SMILES sequences (P-SMILES strings) while ignoring crucial 3D
structural information, leading to sub-optimal performance. In this work, we
propose MMPolymer, a novel multimodal multitask pretraining framework
incorporating both polymer 1D sequential information and 3D structural
information to enhance downstream polymer property prediction tasks. Besides,
to overcome the limited availability of polymer 3D data, we further propose the
"Star Substitution" strategy to extract 3D structural information effectively.
During pretraining, MMPolymer not only predicts masked tokens and recovers 3D
coordinates but also achieves the cross-modal alignment of latent
representation. Subsequently, we further fine-tune the pretrained MMPolymer for
downstream polymer property prediction tasks in the supervised learning
paradigm. Experimental results demonstrate that MMPolymer achieves
state-of-the-art performance in various polymer property prediction tasks.
Moreover, leveraging the pretrained MMPolymer and using only one modality
(either P-SMILES string or 3D conformation) during fine-tuning can also surpass
existing polymer property prediction methods, highlighting the exceptional
capability of MMPolymer in polymer feature extraction and utilization. Our
online platform for polymer property prediction is available at
this https URL

该研究提出了 MMPolymer，一种新颖的多模态多任务预训练框架，结合了聚合物的 1D 顺序信息和 3D 结构信息，以增强下游聚合物性质预测任务。实验证明，MMPolymer 在各种聚合物性质预测任务中实现了最先进的性能。

基于多模态多任务预训练的预测聚合物性质

Predicting Polymer Properties Based on Multimodal Multitask Pretraining

In this work, we present a method to generate a configurational level
fingerprint for polymers using the Bead-Spring-Model. Unlike some of the
previous fingerprinting approaches that employ monomer-level information where
atomistic descriptors are computed using quantum chemistry calculations, this
approach incorporates configurational information from a coarse-grained model
of a long polymer chain. The proposed approach may be advantageous for the
study of behavior resulting from large molecular weights. To create this
fingerprint, we make use of two kinds of descriptors. First, we calculate
certain geometric descriptors like Re2, Rg2 etc. and label them as Calculated
Descriptors. Second, we generate a set of data-driven descriptors using an
unsupervised autoencoder model and call them Learnt Descriptors. Using a
combination of both of them, we are able to learn mappings from the structure
to various properties of the polymer chain by training ML models. We test our
fingerprint to predict the probability of occurrence of a configuration at
equilibrium, which is approximated by a simple linear relationship between the
instantaneous internal energy and equilibrium average internal energy.

使用粗粒化模型生成聚合物的构象级指纹，通过计算几何描述符和数据驱动描述符，通过训练机器学习模型将结构与聚合物链的各种性质进行映射，并测试指纹以预测平衡态下配置出现的概率。

使用机器学习进行性质预测的粗粒度构型聚合物指纹

Coarse-Grained Configurational Polymer Fingerprints for Property  Prediction using Machine Learning

Polymers are a vital part of everyday life. Their chemical universe is so
large that it presents unprecedented opportunities as well as significant
challenges to identify suitable application-specific candidates. We present a
complete end-to-end machine-driven polymer informatics pipeline that can search
this space for suitable candidates at unprecedented speed and accuracy. This
pipeline includes a polymer chemical fingerprinting capability called polyBERT
(inspired by Natural Language Processing concepts), and a multitask learning
approach that maps the polyBERT fingerprints to a host of properties. polyBERT
is a chemical linguist that treats the chemical structure of polymers as a
chemical language. The present approach outstrips the best presently available
concepts for polymer property prediction based on handcrafted fingerprint
schemes in speed by two orders of magnitude while preserving accuracy, thus
making it a strong candidate for deployment in scalable architectures including
cloud infrastructures.

一种快速高效的机器学习驱动的聚合物信息学管道，使用一种名为 polyBERT 的化学指纹能力来识别聚合物的化学结构，并将其映射到一系列物性。该管道通过 2 个数量级的速度优势远超过手工指纹方案，同时保持准确性，是部署在可扩展架构中的强有力选项。