Predict multi-type drug-drug interactions in cold start scenario

DDINet: Drug-drug interaction prediction network based on multi-molecular fingerprint features and multi-head attention centered weighted autoencoder

Drug-drug interactions (DDIs) pose a major concern in polypharmacy due to their potential to cause unexpected side effects that can adversely affect a patient's health. Therefore, it is crucial to identify DDIs effectively during the early stages of drug discovery and development. In this paper, a novel DDI prediction network (DDINet) is proposed to enhance the predictive performance over conventional DDI methods. Leveraging the DrugBank dataset, drugs are represented using the Simplified Molecular Input Line-Entry System (SMILES), with the RDKit software pre-processing the SMILES strings into their canonical forms. Multiple molecular fingerprinting techniques such as Extended Connectivity Fingerprints (ECFPs), Molecular ACCess System keys (MACCSkeys), PubChem Fingerprints, 3D molecular fingerprints (3D-FP), and molecular dynamics fingerprints (MDFPs) are employed to encode drug chemical structures into feature vectors. Drug similarities are computed using the Tanimoto coefficient (TC), and the final Structural Similarity Profile (SSP) is obtained by averaging the five molecular fingerprint types. The novelty of the approach lies in the integration of a Multi-head Attention centered Weighted Autoencoder (Mul_WAE) as the interaction prediction module, which leverages the Multi-head Attention (MHA) layer to focus on the most significant input features. Furthermore, we introduce the Upgraded Bald Eagle Search Optimization (UBesO) algorithm, which optimally selects the learnable parameters of the Mul_WAE based on cross-entropy loss, improving the model's convergence and performance. The proposed DDINet model achieves an accuracy of 99.77%, 99.66% of AUC, 99.5% average precision, 99.4% precision, and 99.49% recall, providing a comprehensive evaluation of the model's robustness. Beyond high accuracy, DDINet offers advantages in scalability, making it well suited for handling large datasets due to its efficient feature extraction and optimization processes. The unique combination of multiple molecular fingerprinting methods with the MHA layer and UBesO algorithm highlights the innovative aspects of our model and significantly improves prediction performance compared to existing approaches.

Knowledge Graphs in Pharmacovigilance: A Scoping Review

PURPOSE

To critically assess the role and added value of knowledge graphs in pharmacovigilance, focusing on their ability to predict adverse drug reactions.

METHODS

A systematic scoping review was conducted in which detailed information, including objectives, technology, data sources, methodology, and performance metrics, were extracted from a set of peer-reviewed publications reporting the use of knowledge graphs to support pharmacovigilance signal detection.

FINDINGS

The review, which included 47 peer-reviewed articles, found knowledge graphs were utilized for detecting/predicting single-drug adverse reactions and drug-drug interactions, with variable reported performance and sparse comparisons to legacy methods.

IMPLICATIONS

Research to date suggests that knowledge graphs have the potential to augment predictive signal detection in pharmacovigilance, but further research using more reliable reference sets of adverse drug reactions and comparison with legacy pharmacovigilance methods are needed to more clearly define best practices and to establish their place in holistic pharmacovigilance systems.

Knowledge Graphs in Pharmacovigilance: A Step-By-Step Guide

PURPOSE

This work aims to demystify Knowledge Graphs (KGs) in pharmacovigilance (PV). It complements the scoping review within this issue. By bridging knowledge gaps and stimulating interest, further engagement with this topic by pharmacovigilance professionals will be facilitated.

METHODS

We elucidate fundamental KGs concepts and terminology, followed by delineating a sequence of implementation steps: use case definition, data type selection, data sourcing, KG construction, KG embedding, and deriving actionable insights. Information technology options and limitations are also explored.

FINDINGS

KGs in pharmacovigilance is a multi-disciplinary field involving information technology, machine learning, biology, and PV. We were able to synthesize the relevant core concepts to create an intuitive exposition of KGs in PV.

IMPLICATIONS

This work demystifies KGs with a pharmacovigilance focus, preparing readers for the accompanying in-depth scoping review. that follows. It lays the groundwork for advancing PV research and practice by emphasizing the importance of engaging with vigilance experts. This approach enhances knowledge sharing and collaboration, contributing to more effective and informed pharmacovigilance efforts and optimal assessment and deployment of KGs in PV.

Emerging drug interaction prediction enabled by a flow-based graph neural network with biomedical network

Drug-drug interactions (DDIs) for emerging drugs offer possibilities for treating and alleviating diseases, and accurately predicting these with computational methods can improve patient care and contribute to efficient drug development. However, many existing computational methods require large amounts of known DDI information, which is scarce for emerging drugs. Here we propose EmerGNN, a graph neural network that can effectively predict interactions for emerging drugs by leveraging the rich information in biomedical networks. EmerGNN learns pairwise representations of drugs by extracting the paths between drug pairs, propagating information from one drug to the other, and incorporating the relevant biomedical concepts on the paths. The edges of the biomedical network are weighted to indicate the relevance for the target DDI prediction. Overall, EmerGNN has higher accuracy than existing approaches in predicting interactions for emerging drugs and can identify the most relevant information on the biomedical network.

MATT-DDI: Predicting multi-type drug-drug interactions via heterogeneous attention mechanisms

The joint use of multiple drugs can result in adverse drug-drug interactions (DDIs) and side effects that harm the body. Accurate identification of DDIs is crucial for avoiding accidental drug side effects and understanding potential mechanisms underlying DDIs. Several computational methods have been proposed for multi-type DDI prediction, but most rely on the similarity profiles of drugs as the drug feature vectors, which may result in information leakage and overoptimistic performance when predicting interactions between new drugs. To address this issue, we propose a novel method, MATT-DDI, for predicting multi-type DDIs based on the original feature vectors of drugs and multiple attention mechanisms. MATT-DDI consists of three main modules: the top k most similar drug pair selection module, heterogeneous attention mechanism module and multi‑type DDI prediction module. Firstly, based on the feature vector of the input drug pair (IDP), k drug pairs that are most similar to the input drug pair from the training dataset are selected according to cosine similarity between drug pairs. Then, the vectors of k selected drug pairs are averaged to obtain a new drug pair (NDP). Next, IDP and NDP are fed into heterogeneous attention modules, including scaled dot product attention and bilinear attention, to extract latent feature vectors. Finally, these latent feature vectors are taken as input of the classification module to predict DDI types. We evaluated MATT-DDI on three different tasks. The experimental results show that MATT-DDI provides better or comparable performance compared to several state-of-the-art methods, and its feasibility is supported by case studies. MATT-DDI is a robust model for predicting multi-type DDIs with excellent performance and no information leakage.

Drug-drug interaction prediction based on local substructure features and their complements

The properties of drugs may undergo changes when multiple drugs are co-administered to treat co-existing or complex diseases, potentially leading to unforeseen drug-drug interactions (DDIs). Therefore, predicting potential drug-drug interactions has been an important task in pharmaceutical research. However, the following challenges remain: (1) existing methods do not work very well in cold-start scenarios, and (2) the interpretability of existing methods is not satisfactory. To address these challenges, we proposed a multi-channel feature fusion method based on local substructure features of drugs and their complements (LSFC). The local substructure features are extracted from each drug, interacted with those of another drug, and then integrated with the global features of two drugs for DDI prediction. We evaluated LSFC on two real-world DDI datasets in worm-start and cold-start scenarios. Comprehensive experiments demonstrate that LSFC consistently improved DDI prediction performance compared with the start-of-the-art methods. Moreover, visual inspection results showed that LSFC can detect crucial substructures of drugs for DDIs, providing interpretable DDI prediction. The source codes and data are available at https://github.com/Zhang-Yang-ops/LSFC.

3D graph neural network with few-shot learning for predicting drug-drug interactions in scaffold-based cold start scenario

Understanding drug-drug interactions (DDI) of new drugs is critical for minimizing unexpected adverse drug reactions. The modeling of new drugs is called a cold start scenario. In this scenario, Only a few structural information or physicochemical information about new drug is available. The 3D conformation of drug molecules usually plays a crucial role in chemical properties compared to the 2D structure. 3D graph network with few-shot learning is a promising solution. However, the 3D heterogeneity of drug molecules and the discretization of atomic distributions lead to spatial confusion in few-shot learning. Here, we propose a 3D graph neural network with few-shot learning, Meta3D-DDI, to predict DDI events in cold start scenario. The 3DGNN ensures rotation and translation invariance by calculating atomic pairwise distances, and incorporates 3D structure and distance information in the information aggregation stage. The continuous filter interaction module can continuously simulate the filter to obtain the interaction between the target atom and other atoms. Meta3D-DDI further develops a FSL strategy based on bilevel optimization to transfer meta-knowledge for DDI prediction tasks from existing drugs to new drugs. In addition, the existing cold start setting may cause the scaffold structure information in the training set to leak into the test set. We design scaffold-based cold start scenario to ensure that the drug scaffolds in the training set and test set do not overlap. The extensive experiments demonstrate that our architecture achieves the SOTA performance for DDI prediction under scaffold-based cold start scenario on two real-world datasets. The visual experiment shows that Meta3D-DDI significantly improves the learning for DDI prediction of new drugs. We also demonstrate how Meta3D-DDI can reduce the amount of data required to make meaningful DDI predictions.

MDDI-SCL: predicting multi-type drug-drug interactions via supervised contrastive learning

The joint use of multiple drugs may cause unintended drug-drug interactions (DDIs) and result in adverse consequence to the patients. Accurate identification of DDI types can not only provide hints to avoid these accidental events, but also elaborate the underlying mechanisms by how DDIs occur. Several computational methods have been proposed for multi-type DDI prediction, but room remains for improvement in prediction performance. In this study, we propose a supervised contrastive learning based method, MDDI-SCL, implemented by three-level loss functions, to predict multi-type DDIs. MDDI-SCL is mainly composed of three modules: drug feature encoder and mean squared error loss module, drug latent feature fusion and supervised contrastive loss module, multi-type DDI prediction and classification loss module. The drug feature encoder and mean squared error loss module uses self-attention mechanism and autoencoder to learn drug-level latent features. The drug latent feature fusion and supervised contrastive loss module uses multi-scale feature fusion to learn drug pair-level latent features. The prediction and classification loss module predicts DDI types of each drug pair. We evaluate MDDI-SCL on three different tasks of two datasets. Experimental results demonstrate that MDDI-SCL achieves better or comparable performance as the state-of-the-art methods. Furthermore, the effectiveness of supervised contrastive learning is validated by ablation experiment, and the feasibility of MDDI-SCL is supported by case studies. The source codes are available at https://github.com/ShenggengLin/MDDI-SCL.