Machine learning is a popular technique to predict the retention times of molecules based on descriptors. Descriptors and associated labels (e.g., retention times) of a set of molecules can be used to train a machine learning algorithm. However, descriptors are fixed molecular features which are not necessarily optimized for the given machine learning problem (e.g., to predict retention times). Recent advances in molecular machine learning make use of so-called graph convolutional networks (GCNs) to learn molecular representations from atoms and their bonds to adjacent atoms to optimize the molecular representation for the given problem. In this study, two GCNs were implemented to predict the retention times of molecules for three different chromatographic data sets and compared to seven benchmarks (including two state-of-the art machine learning models). Additionally, saliency maps were computed from trained GCNs to better interpret the importance of certain molecular sub-structures in the data sets. Based on the overall observations of this study, the GCNs performed better than all benchmarks, either significantly outperforming them (5-25% lower mean absolute error) or performing similar to them (<5% difference). Saliency maps revealed a significant difference in molecular sub-structures that are important for predictions of different chromatographic data sets (reversed-phase liquid chromatography vs hydrophilic interaction liquid chromatography).

Graph Convolutional Networks for Improved Prediction and Interpretability of Chromatographic Retention Data.

Background The ever-increasing volume of medical literature necessitates the classification of medical literature. Medical relation extraction is a typical method of classifying a large volume of medical literature. With the development of arithmetic power, medical relation extraction models have evolved from rule-based models to neural network models. The single neural network model discards the shallow syntactic information while discarding the traditional rules. Therefore, we propose a syntactic information–based classification model that complements and equalizes syntactic information to enhance the model. Objective We aim to complete a syntactic information–based relation extraction model for more efficient medical literature classification. Methods We devised 2 methods for enhancing syntactic information in the model. First, we introduced shallow syntactic information into the convolutional neural network to enhance nonlocal syntactic interactions. Second, we devise a cross-domain pruning method to equalize local and nonlocal syntactic interactions. Results We experimented with 3 data sets related to the classification of medical literature. The F1 values were 65.5% and 91.5% on the BioCreative ViCPR (CPR) and Phenotype-Gene Relationship data sets, respectively, and the accuracy was 88.7% on the PubMed data set. Our model outperforms the current state-of-the-art baseline model in the experiments. Conclusions Our model based on syntactic information effectively enhances medical relation extraction. Furthermore, the results of the experiments show that shallow syntactic information helps obtain nonlocal interaction in sentences and effectively reinforces syntactic features. It also provides new ideas for future research directions.

/pdf/a-syntactic-information-based-classification-model-for-1f24h6if.pdf

A Syntactic Information–Based Classification Model for Medical Literature: Algorithm Development and Validation Study

Extractive text summarization selects the most important sentences from a document, preserves their original meaning, and produces an objective and fact-based summary. It is faster and less computationally intensive than abstract summarization techniques. Learning cross-sentence relationships is crucial for extractive text summarization. However, most of the language models currently in use process text data sequentially, which makes it difficult to capture such inter-sentence relations, especially in long documents. This paper proposes an extractive summarization model based on the graph neural network (GNN) to address this problem. The model effectively represents cross-sentence relationships using a graph-structured document representation. In addition to sentence nodes, we introduce two nodes with different granularity in the graph structure, words and topics, which bring different levels of semantic information. The node representations are updated by the graph attention network (GAT). The final summary is obtained using the binary classification of the sentence nodes. Our text summarization method was demonstrated to be highly effective, as supported by the results of our experiments on the CNN/DM and NYT datasets. To be specific, our approach outperformed baseline models of the same type in terms of ROUGE scores on both datasets, indicating the potential of our proposed model for enhancing text summarization tasks. 

/pdf/a-multi-granularity-heterogeneous-graph-for-extractive-text-23nrc3n5.pdf

A Multi-Granularity Heterogeneous Graph for Extractive Text Summarization

Recommender systems provide useful item suggestions (products or services) to users as part of their decision-making processes. The effectiveness of recommender systems is now clearly confirmed in various fields of application (e.g., YouTube, Amazon, Facebook, ResearchGate). In the literature, many research works have addressed the application of recommendations in the field of health in what are called health recommender systems (HRS). HRS is an innovative alternative when it comes to providing information to help doctors in the diagnosis/treatment of diseases, as well as helping patients with recommendations on how to maintain their well-being. However, the proposed development approaches in this field are limited to traditional models that lack the accuracy and effectiveness, which are vital in healthcare. This paper presents a design model for collaborative filtering-based health recommender systems using graph neural networks (GNN) via its promising Graph Convolutional Network (GCN) architecture. In this model, the convolution layer works with a simplified and efficient GCN algorithm named LightGCN. GCN-based methods are among the new cutting-edge approaches in recommender systems, and LightGCN has proven its superiority in recommendation accuracy. 

Graph Convolutional Networks for Designing Collaborative Filtering-Based Health Recommender Systems

Traditional recommendation systems usually use single user-item interaction information, which ignore the multiple relationships that exist for other interactions (e.g., likes, clicks). Multi-behavioral recommendation models compensate for the shortcomings of traditional models. The existing multi-behavior recommendation models focus on obtaining behavioral information by distinguishing the interaction differences of multiple user behaviors but ignore the common preferences of items related to user different interactions. In this paper, we propose a Multi-Behavior Heterogeneous Contrastive learning Recommendation (MBHCR) model. Specifically, MBHCR stresses the information fusion between different interaction behaviors and differences in the behavior view. Firstly, we design a unified heterogeneous graph based on the complexity of user multi-behavioral interaction information to distinguish behavioral differences while preserving their complete semantic information. Secondly, we propose a multi-behavior relational aggregator component to model the unified heterogeneous graph only once to capture the potential common representations of users and their different interactions and to mitigate user sparsity. Thirdly, we also design a behavior comparison learning enhancer to complement the interaction differences between the user’s target behavior and auxiliary behaviors on the behavior view and extract valid information. Experiments were conducted on two real-world datasets to demonstrate the validity of MBHCR and designed ablation experiments to verify the contribution of model components. 

Heterogeneous Multi-Behavior Recommendation Based on Graph Convolutional Networks

Graph convolutional networks (GCNs), as an extension of classic convolutional neural networks (CNNs) in graph processing, have achieved good results in completing semi-supervised learning tasks. Traditional GCNs usually use fixed graph to complete various semi-supervised classification tasks, such as chemical molecules and social networks. Graph is an important basis for the classification of GCNs model, and its quality has a large impact on the performance of the model. For low-quality input graph, the classification results of the GCNs model are often not ideal. In order to improve the classification effect of GCNs model, we propose a graph learning method to generate high-quality topological graph, which is more suitable for GCNs model classification. We use the correlation between the data to generate a data similarity matrix, and apply Laplacian rank constraint to similarity matrix, so that the number of connected components of the topological graph is consistent with the number of categories of the original data. Experimental results on 10 real datasets show that our method is better than the comparison method in classification effect.

Haiqi Zhang

Papers

Semi-Supervised Classification of Graph Convolutional Networks with Laplacian Rank Constraints