Machine learning solutions are very popular in the field of chemoinformatics,
where they have numerous applications, such as novel drug discovery or
molecular property prediction. Molecular fingerprints are algorithms commonly
used for vectorizing chemical molecules as a part of preprocessing in this kind
of solution. However, despite their popularity, there are no libraries that
implement them efficiently for large datasets, utilizing modern, multicore
architectures. On top of that, most of them do not provide the user with an
intuitive interface, or one that would be compatible with other machine
learning tools.
In this project, we created a Python library that computes molecular
fingerprints efficiently and delivers an interface that is comprehensive and
enables the user to easily incorporate the library into their existing machine
learning workflow. The library enables the user to perform computation on large
datasets using parallelism. Because of that, it is possible to perform such
tasks as hyperparameter tuning in a reasonable time. We describe tools used in
implementation of the library and asses its time performance on example
benchmark datasets. Additionally, we show that using molecular fingerprints we
can achieve results comparable to state-of-the-art ML solutions even with very
simple models.

该研究论文介绍了一个高效的 Python 库，用于计算化学分子指纹，并提供了全面的接口，使用户能够轻松将该库整合到现有的机器学习工作流中，能够在大型数据集上使用并行计算，在合理的时间内执行诸如超参数调优等任务，同时证明了即使使用简单模型，通过使用化学分子指纹，也能够实现与最先进的机器学习解决方案相媲美的结果。

高效计算分子指纹的 Python 库

A Python library for efficient computation of molecular fingerprints

Our work introduces an innovative approach to graph learning by leveraging
Hyperdimensional Computing. Graphs serve as a widely embraced method for
conveying information, and their utilization in learning has gained significant
attention. This is notable in the field of chemoinformatics, where learning
from graph representations plays a pivotal role. An important application
within this domain involves the identification of cancerous cells across
diverse molecular structures.
We propose an HDC-based model that demonstrates comparable Area Under the
Curve results when compared to state-of-the-art models like Graph Neural
Networks (GNNs) or the Weisfieler-Lehman graph kernel (WL). Moreover, it
outperforms previously proposed hyperdimensional computing graph learning
methods. Furthermore, it achieves noteworthy speed enhancements, boasting a 40x
acceleration in the training phase and a 15x improvement in inference time
compared to GNN and WL models. This not only underscores the efficacy of the
HDC-based method, but also highlights its potential for expedited and
resource-efficient graph learning.

我们的研究引入了一种创新的基于超维计算的图学习方法，与图神经网络和 Weisfieler-Lehman 图核心相比，在癌细胞识别等应用领域取得了可比拟的结果，并且在训练和推断阶段实现了显著的加速和资源效率的提升。