An efficient curriculum learning-based strategy for molecular graph learning

Abstract

Computational methods have been widely applied to resolve various core issues in drug discovery, such as molecular property prediction. In recent years, a data-driven computational method-deep learning had achieved a number of impressive successes in various domains. In drug discovery, graph neural networks (GNNs) take molecular graph data as input and learn graph-level representations in non-Euclidean space. An enormous amount of well-performed GNNs have been proposed for molecular graph learning. Meanwhile, efficient use of molecular data during training process, however, has not been paid enough attention. Curriculum learning (CL) is proposed as a training strategy by rearranging training queue based on calculated samples' difficulties, yet the effectiveness of CL method has not been determined in molecular graph learning. In this study, inspired by chemical domain knowledge and task prior information, we proposed a novel CL-based training strategy to improve the training efficiency of molecular graph learning, called CurrMG. Consisting of a difficulty measurer and a training scheduler, CurrMG is designed as a plug-and-play module, which is model-independent and easy-to-use on molecular data. Extensive experiments demonstrated that molecular graph learning models could benefit from CurrMG and gain noticeable improvement on five GNN models and eight molecular property prediction tasks (overall improvement is 4.08%). We further observed CurrMG’s encouraging potential in resource-constrained molecular property prediction. These results indicate that CurrMG can be used as a reliable and efficient training strategy for molecular graph learning. Availability: The source code is available in https://github.com/gu-yaowen/CurrMG.

Employing Molecular Conformations for Ligand-Based Virtual Screening with Equivariant Graph Neural Network and Deep Multiple Instance Learning

“…First, from the data quality control aspect, some of the sub-datasets and targets in our integrated benchmark dataset should be filtered as all tested LBVS methods could not give reliable predictions on them, but they are still retained in the current version; Second, from the model training aspect, a predictable optimization is to pre-train EGNN-based models using molecular conformation and finetune them for the downstream bioactivity prediction [ 57 , 58 , 59 ]. Also, improving the GNN model training period with chemical domain knowledge insights is another promising strategy [ 60 , 61 ]. Thirdly, based on the architecture design aspect, more advanced GNN backbones that use 3D graphs as inputs should be adopted for conformer-based representation learning, such as SchNet [ 62 ], GemNet [ 63 ], PaiNN [ 64 ], etc.…”

Graph representation of multi-dimensional materials

“…In the area of polymer generation, hypergraph-based methods have emerged as a promising representation. Guo et al devised a learnable graph grammar approach to represent the chain structure, their inherent scale, and structural complexity [135,136]. A hyperedge can join all nodes in a ring structure or only two nodes in a polymer chain [135].…”

“…Guo et al devised a learnable graph grammar approach to represent the chain structure, their inherent scale, and structural complexity [135,136]. A hyperedge can join all nodes in a ring structure or only two nodes in a polymer chain [135]. A bottom-up search builds up production rules from the finest-grained level.…”

Yin-yang in drug discovery: rethinking de novo design and development of predictive models

“…The development of reliable machine learning algorithms has been limited due to the lack of standard benchmark datasets to compare the efficacy of the methods proposed (Jain and Nicholls, 2008). Furthermore, machine learning in chemistry compared with other areas such as computer speech and vision has a main disadvantage, the data recovery (Wu et al, 2018;Guo et al, 2022), because of measuring chemical properties often requires specialized instruments; as a result, datasets with experimentally determined results are small and often not sufficiently large to cover the high-demanding needs of machine-learning tasks (Wu et al, 2018). Another challenge is data splitting (the way in which datasets are split into training data and testing data).…”