Small molecules play a pivotal role in modern medicine, and scrutinizing
their interactions with protein targets is essential for the discovery and
development of novel, life-saving therapeutics. The term "bioactivity"
encompasses various biological effects resulting from these interactions,
including both binding and functional responses. The magnitude of bioactivity
dictates the therapeutic or toxic pharmacological outcomes of small molecules,
rendering accurate bioactivity prediction crucial for the development of safe
and effective drugs. However, existing structural datasets of small
molecule-protein interactions are often limited in scale and lack
systematically organized bioactivity labels, thereby impeding our understanding
of these interactions and precise bioactivity prediction. In this study, we
introduce a comprehensive dataset of small molecule-protein interactions,
consisting of over a million binding structures, each annotated with real
biological activity labels. This dataset is designed to facilitate unbiased
bioactivity prediction. We evaluated several classical models on this dataset,
and the results demonstrate that the task of unbiased bioactivity prediction is
challenging yet essential.

这项研究介绍了一个包含超过一百万个结合结构及其真实生物活性标签的小分子 - 蛋白质相互作用全面数据集，用于推动无偏生物活性预测，并评估了几种经典模型在该数据集上的效果，结果表明无偏生物活性预测任务既具有挑战性又是必不可少的。

SIU: 百万级结构化小分子 - 蛋白质相互作用数据集用于无偏生物活性预测

SIU: A Million-Scale Structural Small Molecule-Protein Interaction  Dataset for Unbiased Bioactivity Prediction

Empirical scoring functions based on either molecular force fields or
cheminformatics descriptors are widely used, in conjunction with molecular
docking, during the early stages of drug discovery to predict potency and
binding affinity of a drug-like molecule to a given target. These models
require expert-level knowledge of physical chemistry and biology to be encoded
as hand-tuned parameters or features rather than allowing the underlying model
to select features in a data-driven procedure. Here, we develop a general
3-dimensional spatial convolution operation for learning atomic-level chemical
interactions directly from atomic coordinates and demonstrate its application
to structure-based bioactivity prediction. The atomic convolutional neural
network is trained to predict the experimentally determined binding affinity of
a protein-ligand complex by direct calculation of the energy associated with
the complex, protein, and ligand given the crystal structure of the binding
pose. Non-covalent interactions present in the complex that are absent in the
protein-ligand sub-structures are identified and the model learns the
interaction strength associated with these features. We test our model by
predicting the binding free energy of a subset of protein-ligand complexes
found in the PDBBind dataset and compare with state-of-the-art cheminformatics
and machine learning-based approaches. We find that all methods achieve
experimental accuracy and that atomic convolutional networks either outperform
or perform competitively with the cheminformatics based methods. Unlike all
previous protein-ligand prediction systems, atomic convolutional networks are
end-to-end and fully-differentiable. They represent a new data-driven,
physics-based deep learning model paradigm that offers a strong foundation for
future improvements in structure-based bioactivity prediction.

本文提出了一种基于原子层次化学相互作用的空间卷积神经网络来预测蛋白质 - 配体复合物的生物活性，并展示了其优于化学信息处理方法的实验结果。

原子卷积网络用于预测蛋白质 - 配体结合亲和力

Atomic Convolutional Networks for Predicting Protein-Ligand Binding  Affinity

Deep convolutional neural networks comprise a subclass of deep neural
networks (DNN) with a constrained architecture that leverages the spatial and
temporal structure of the domain they model. Convolutional networks achieve the
best predictive performance in areas such as speech and image recognition by
hierarchically composing simple local features into complex models. Although
DNNs have been used in drug discovery for QSAR and ligand-based bioactivity
predictions, none of these models have benefited from this powerful
convolutional architecture. This paper introduces AtomNet, the first
structure-based, deep convolutional neural network designed to predict the
bioactivity of small molecules for drug discovery applications. We demonstrate
how to apply the convolutional concepts of feature locality and hierarchical
composition to the modeling of bioactivity and chemical interactions. In
further contrast to existing DNN techniques, we show that AtomNet's application
of local convolutional filters to structural target information successfully
predicts new active molecules for targets with no previously known modulators.
Finally, we show that AtomNet outperforms previous docking approaches on a
diverse set of benchmarks by a large margin, achieving an AUC greater than 0.9
on 57.8% of the targets in the DUDE benchmark.

AtomNet 是第一个基于结构的深度卷积神经网络，用于预测小分子在药物研发应用中的生物活性。它使用局部卷积滤波器处理结构目标信息，并在多个基准测试中表现出比现有技术更好的性能。