REDIRECTION: Generating drug repurposing hypotheses using link prediction with DISNET data

Munoz, Adrian Ayuso; Carro, Esther Ugarte; Santamaría, L.; Otero-Carrasco, Belén; Ruiz, Ernestina Menasalvas; Gallardo, Yuliana Pérez; Rodríguez‐González, Alejandro

doi:10.1109/cbms55023.2022.00009

Cited by 9 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That is, using GNN pipelines to embed the information in the network (representing each node as a vector of features) to then decode these embedding vectors optimizing the prediction of new links of the type disease-drug. Following this idea, various models have been developed and presented previously [49][50][51]. In them, the integration of heterogeneous biomedical data organised as a graph has demonstrated its efficacy when combined with GNNs to address the drug repurposing challenge.…”

Section: Enhancing Drug Repurposing Through Graph Neural Network and ...mentioning

confidence: 99%

Machine Learning and Artificial Intelligence in drug repurposing – challenges and perspectives

Anokian,

Bernett,

Freeman

et al. 2024

Preprint

View full text Add to dashboard Cite

Artificial Intelligence (AI) and Machine Learning (ML) techniques play an increasingly crucial role in the field of drug repurposing.As the number of computational tools grows, it is essential to not only understand and carefully select the method itself, but also consider the input data used for building predictive models. This review aims to take a dive into current computational methods that leverage AI and ML to drive and accelerate compound and drug target selection, in addition to address the existing challenges and provide perspectives.While there is no doubt that AI and ML-based tools are transforming traditional approaches, especially with recent advancements in graph-based methods, they present novel challenges that require the human eye and expert intervention. The growing complexity of OMICs data further emphasizes the importance of data standardization and quality.

show abstract

Section: Enhancing Drug Repurposing Through Graph Neural Network and ...mentioning

confidence: 99%

Machine Learning and Artificial Intelligence in drug repurposing – challenges and perspectives

Anokian,

Bernett,

Freeman

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, similar neural network architectures were used for automated phenotyping, by building representations of structured [56][57][58], unstructured [59][60][61][62] EHR data, or both [63][64][65]. As a recent use-case scenario, deep learning methods were applied to COVID-19-related EHR data for epidemiological prediction [66], automatic diagnosis [67], drug repurposing [68][69][70][71], or mortality risk assessment [72][73][74].…”

Section: Introductionmentioning

confidence: 99%

Comparing neural language models for medical concept representation and patient trajectory prediction

Bornet

Proios

Yazdani

et al. 2023

Preprint

View full text Add to dashboard Cite

Effective representation of medical concepts is crucial for secondary analyses of electronic health records. Neural language models have shown promise in automatically deriving medical concept representations from clinical data. However, the comparative performance of different language models for creating these empirical representations, and the extent to which they encode medical semantics, has not been extensively studied. This study aims to address this gap by evaluating the effectiveness of three popular language models - word2vec, fastText, and GloVe - in creating medical concept embeddings. By using a large dataset of digital health records, we created patient trajectories and used them to train the language models. We then assessed the ability of the learned embeddings to encode semantics through an explicit comparison with biomedical terminologies, and implicitly by predicting patient outcomes and trajectories with different degrees of information. Our qualitative analysis shows that empirical clusters of embeddings learned by fastText exhibit the highest similarity with theoretical clustering patterns obtained from biomedical terminologies, with a similarity score between empirical and theoretical clusters of 0.88, 0.80, and 0.92 for diagnosis, procedures, and medication codes, respectively. Conversely, for outcome prediction, word2vec and GloVe tend to outperform fastText, with the former achieving AUROC as high as 0.80, 0.63, and 0.88 for length-of-stay, readmission, and mortality prediction, respectively. In predicting the next steps in patient trajectories, GloVe achieves the highest performance for diagnostic and medication codes (AUPRC of 0.46 and of 0.82, respectively) at the highest level of the semantic hierarchy, while fastText outperforms the other models for procedure codes (AUPRC of 0.67). Our study demonstrates that subword information is crucial for learning medical concept representations, but global embedding vectors are better suited for downstream tasks, such as trajectory prediction. Thus, these models can be harnessed to learn representations that convey clinical meaning, and our insights highlight the potential of using machine learning techniques to semantically encode medical data.

show abstract

“…From these two different networks, we have developed several models based on Graph Neural Network (GNN) pipelines to embed the information in the network (representing each node as a vector of features) to then decode these embedding vectors optimizing the prediction of new links of the type disease-drug. Firstly, REDIRECTION (dRug rEpurposing Disnet lInk pREdiCTION) was presented [3]. REDIRECTION is a model that was trained on the simple graph, which was developed under this encoder-decoder framework to predict 'dis_dru_the' links.…”

mentioning

confidence: 99%

Enhancing drug repurposing through graph neural networks and link prediction

Prieto Santamaría,

Ayuso-Muñoz,

Rodríguez-González

2023

Enhancing Drug Repurposing Through Graph Neural Networks and Link Prediction

View full text Add to dashboard Cite

The use of computational methods in drug repurposing has become increasingly popular, and innovative artificial intelligence techniques have proven to be valuable tools for predicting new therapeutical opportunities of existing drugs. Within this framework, biomedical data can be represented as graphs, offering a highly expressive way to depict the underlying structure of the information. Integrating these graph-based data structures with deep learning models enhances the prediction of novel connections, such as potential associations between diseases and drugs, which can be regarded as repurposing possibilities.In particular, we have employed the heterogeneous integrated biomedical information from the DISNET project (https://disnet.ctb.upm.es) [1], which compiles a set of different structured and unstructured data that revolve around diseases, and which is based in the concepts of the Human Disease Network (HDN) [2]. This information is represented as a multilayered complex network whose node types, in addition to diseases, include symptoms, genes, proteins, genetic variants, non-coding RNAs, biological pathways, drugs, and so on. And the links represent the connection between diseases and genes, diseases and drugs, the interactions between proteins (Protein-Protein Interactions -PPIs), and the interactions between drugs (Drug-Drug Interactions -DDIs), among others. We consider two derived graphs: a simplified version of the DISNET knowledge base that we name simple and its complete version that we name complex. The simple graph contains a limited set of information: diseases, symptoms, drugs and their relationships. The complex graph uses all the available information. Node types are "phenotype", "drug", "pathway", "protein" and "drug-drug-interaction"; and link types are Disease-Drug (therapeutic) ("dis_dru_the"), Disease-Symptom ("dse_sym"), Disease-Protein ("dis_pro"), Disease-Pathway ("dis_pat"), Drug-Drug ("druA_druB"), Drug-Protein ("dru_pro"), Drug-Symptom (side effect) ("dru_sym_sef"), Drug-Symptom (indication) ("dru_sym_ind"), Protein-Protein ("proA_proB"), Protein-Pathway ("pro_pat"), DDI-Phenotype ("ddi_phe"), and DDI-Drug ("ddi_dru"). From these two different networks, we have developed several models based on Graph Neural Network (GNN) pipelines to embed the information in the network (representing each node as a vector of features) to then decode these embedding vectors optimizing the prediction of new links of the type disease-drug. Firstly, REDIRECTION (dRug rEpurposing Disnet lInk pREdiCTION) was presented [3]. REDIRECTION is a model that was trained on the simple graph, which was developed under this encoder-decoder framework to predict 'dis_dru_the' links. 2/2Afterwards, we presented DMSR (Drug Molecular Structure REDIRECTION), which incorporated drug molecular structures as the initial drug nodes' features in REDIRECTION [4]. This model also used GNNs to embed twodimensional drug molecular structures and obtain the corresponding features. DMSR was originally trained on the simple graph, imp...

show abstract

REDIRECTION: Generating drug repurposing hypotheses using link prediction with DISNET data

Cited by 9 publications

References 36 publications

Machine Learning and Artificial Intelligence in drug repurposing – challenges and perspectives

Machine Learning and Artificial Intelligence in drug repurposing – challenges and perspectives

Comparing neural language models for medical concept representation and patient trajectory prediction

Enhancing drug repurposing through graph neural networks and link prediction

Contact Info

Product

Resources

About