Drug-Drug Interaction Prediction: a Purely SMILES Based Approach

Bumgardner, Bri; Tanvir, Farhan; Saifuddin, Khaled Mohammed; Akbaş, Esra

doi:10.1109/bigdata52589.2021.9671766

Cited by 8 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to recognize that a single medication alone may not always be the most effective treatment approach. The majority of diseases in patients are brought on by intricate biological mechanisms that cannot be cured by one particular medication and often require multiple medications (Bumgardner et al,2021).…”

Section: Drug-drug Interactionsmentioning

confidence: 99%

“…DDIs are typically examined in medicinal chemistry; however, a significant number of interactions go unnoticed, resulting in a wide range of medication combinations (Vilar et al,2014). Given that many diseases require multiple medications due to complex biological mechanisms, it is impractical to identify every potential DDIs during the early stages of drug development (Bumgardner et al,2021). In addition, a significant number of Adverse Drug Reactions often go unnoticed during pre-approval clinical trials.…”

Section: Drug-drug Interactionsmentioning

confidence: 99%

“…To measure the similarity between medications, common substructures are potentially used instead of entire chemical structures (Bumgardner et al,2021). If medications both A and B interact to generate a particular response, then medications similar to drug A (or drug B) are probable to generate an identical impact as drug B (or drug A).…”

Section: Similarity-based Approachmentioning

confidence: 99%

See 2 more Smart Citations

A comprehensive survey explores Drug-Drug interaction prediction using Machine-Learning techniques

radwan,

gouda,

Abdelbaky

et al. 2024

Benha Journal of Applied Sciences

View full text Add to dashboard Cite

Drug-Drug Interactions is a critical health and safety concern that receives a lot of attention from both academia and business. Polypharmacy is often employed as a strategy to manage complex diseases such as cancer, diabetes, and agerelated ailments. However, combining medications with other drugs can lead to unintended adverse reactions. Interactions between drugs may increase the chance of unanticipated negative effects and even unknown toxicity, putting patients at risk. Detecting and identifying Interactions not only helps clinicians avoid chronic but will also encourage the co-prescription of safe drugs for more effective therapies. It is expensive and time-consuming to identify drug-drug interactions and Adverse Reactions among several medication pairings, both in vivo and in vitro. Recent advancements in computer science, specifically in the field of Artificial Intelligence, have yielded techniques that enable researchers to identify drug-drug interactions. We present comprehensive approaches that enable in-depth analysis of potential interactions by taking into account various factors, including molecular structure, clinical data, network relationships, and existing literature. This paper offers an all-encompassing survey of research studies that utilize Machine Learning and Deep Learning algorithms for the prediction of Drug-Drug interactions.

show abstract

Section: Drug-drug Interactionsmentioning

confidence: 99%

Section: Drug-drug Interactionsmentioning

confidence: 99%

Section: Similarity-based Approachmentioning

confidence: 99%

See 1 more Smart Citation

A comprehensive survey explores Drug-Drug interaction prediction using Machine-Learning techniques

radwan,

gouda,

Abdelbaky

et al. 2024

Benha Journal of Applied Sciences

View full text Add to dashboard Cite

show abstract

“…However, in some cases, drug combinations can cause Adverse Drug Reactions (i.e. side effects) ( Shah and Hajjar 2012 , Zitnik et al 2018 , Nováček and Mohamed 2020 , Bumgardner et al 2021 , Lin et al 2022b ). Drug–drug interactions (DDIs) may alter the activity of the drugs with increasing or decreasing the effect of drugs, and in the worst case may lead to death ( Masumshah et al 2021 , Tanvir et al 2022 ).Therefore, the effective detection of adverse DDIs is an urgent problem in human health ( Masoudi-Nejad et al 2013 , Liu et al 2017 , Yan et al 2018 , Lin et al 2020 , Kim and Shin 2023 , Liu et al 2023 , Wang et al 2023 ).…”

Section: Introductionmentioning

confidence: 99%

DPSP: a multimodal deep learning framework for polypharmacy side effects prediction

Masumshah,

Eslahchi

2023

Bioinformatics Advances

View full text Add to dashboard Cite

Motivation Because unanticipated Drug-Drug Interactions (DDIs) can result in severe bodily harm, identifying the adverse effects of polypharmacy is one of the most important tasks in human health. Over the past few decades, computational methods for predicting the adverse effects of polypharmacy have been developed. Results This article presents DPSP, a framework for predicting polypharmacy side effects based on the construction of novel drug features and the application of a deep neural network to predict DDIs. In the first step, a variety of drug information is evaluated, and a feature extraction method and the Jaccard similarity are used to determine similarities between two drugs. By combining these similarities, a novel feature vector is generated for each drug. In the second step, the method predicts DDIs for specific DDI events using a multimodal framework and drug feature vectors. On three benchmark datasets, the performance of DPSP is measured by comparing its results to those of several well-known methods, such as GNN-DDI, MSTE, MDF-SA-DDI, NNPS, DDIMDL, DNN, DeepDDI, KNN, LR, and RF. DPSP outperforms these classification methods based on a variety of classification metrics. The results indicate that the use of diverse drug information is effective and efficient for identifying DDI adverse effects. Availability The source code and datasets are available at https://github.com/raziyehmasumshah/DPSP. Supplementary information Supplementary data are available at Bioinformatics Advances online.

show abstract

“…The graph data structure has been explored in versatile research domains such as anomaly detection [3], recommendation learning [12], community detection [1,2] etc. Recently, it has also been explored for different types of sequence data classification tasks such as text classification [56], DNA-protein binding prediction [22], protein function prediction [20], drug-drug interaction prediction [11,47], etc. The state-of-the-art sequence-to-graph models can be categorized into similarity-based and order-based graphs [8,15,59].…”

Section: Introductionmentioning

confidence: 99%

Seq-HyGAN: Sequence Classification via Hypergraph Attention Network

Saifuddin¹,

May²,

Tanvir³

et al. 2023

Preprint

View full text Add to dashboard Cite

Sequence classification has a wide range of real-world applications in different domains, such as genome classification in health and anomaly detection in business. However, the lack of explicit features in sequence data makes it difficult for machine learning models. While Neural Network (NN) models address this with learning features automatically, they are limited to capturing adjacent structural connections and ignore global, higher-order information between the sequences. To address these challenges in the sequence classification problems, we propose a novel Hypergraph Attention Network model, namely Seq-HyGAN. To capture the complex structural similarity between sequence data, we first create a hypergraph where the sequences are depicted as hyperedges and subsequences extracted from sequences are depicted as nodes. Additionally, we introduce an attention-based Hypergraph Neural Network model that utilizes a two-level attention mechanism. This model generates a sequence representation as a hyperedge while simultaneously learning the crucial subsequences for each sequence. We conduct extensive experiments on four data sets to assess and compare our model with several state-of-the-art methods. Experimental results demonstrate that our proposed Seq-HyGAN model can effectively classify sequence data and significantly outperform the baselines. We also conduct case studies to investigate the contribution of each module in Seq-HyGAN.

show abstract

Drug-Drug Interaction Prediction: a Purely SMILES Based Approach

Cited by 8 publications

References 31 publications

A comprehensive survey explores Drug-Drug interaction prediction using Machine-Learning techniques

A comprehensive survey explores Drug-Drug interaction prediction using Machine-Learning techniques

DPSP: a multimodal deep learning framework for polypharmacy side effects prediction

Seq-HyGAN: Sequence Classification via Hypergraph Attention Network

Contact Info

Product

Resources

About