Chemical and Textual Embeddings for Drug Repurposing

Nordon, Galia; Gottlieb, Levi; Radinsky, Kira

doi:10.1609/aaai.v34i08.7046

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a vast, and still growing, literature on integrating and using forms of computable biomedical knowledge. For example, related work has been done in defining ontologies for representing knowledge for neurodegenerative diseases 146 , identifying erroneous information by applying transitive closure over causal predicates 146 , modeling argument structure 147 , detecting contradictions in statements extracted from the literature 148, 149 , drug repurposing pipelines 31, 32, 34, 150, 151 , and elucidating mechanisms in systems and molecular biology 39 . Simply put, the vast body of tangentially related work would be impossible to condense here.…”

Section: Discussionmentioning

confidence: 99%

Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: a use case studying depression as a risk factor for Alzheimer's disease

Malec

Taneja

Albert

et al. 2022

Preprint

View full text Add to dashboard Cite

IntroductionCausal feature selection entails identifying confounders that eliminate confounding bias when estimating effects from observational data. Traditionally, researchers employ expertise and literature review to identify confounders. Uncontrolled confounding from unidentified confounders threatens validity while conditioning on intermediate variables (mediators) weakens estimates, and conditioning on common effects (colliders) induces bias. Additionally, erroneously conditioning on variables playing multiple roles introduces bias. In a use case studying depression as a potential independent risk factor for Alzheimer’s disease (AD), we introduce a novel knowledge graph application enabling causal feature selection from computable literature-derived knowledge and biomedical ontologies to address these challenges.MethodsUsing the output from three machine reading systems, we harmonized the computable knowledge extracted from a scoped literature corpus. Next, we applied logical closure operations to infer missing knowledge and mapped the outputs to target terminologies. We then combined the outputs with ontology-grounded resources using a robust KG framework developed by computational biologists. Next, we translated epidemiological definitions of confounder, collider, and mediator into queries for searching the KG and summarized the roles played by the variables identified. Finally, we analyzed a selection of variables and reasoning paths in the search results.ResultsConfounder search yielded 128 confounders, including 58 phenotypes, 47 drugs, and 35 genes. Search also identified 23 collider and 16 mediator phenotypes. Only 31 of the 58 confounder phenotypes were found to behave exclusively as confounders. The remaining 27 phenotypes also play other roles, and 7 of the 21 confounders identified by both the KG and the literature were identified as being exclusively confounders. Stroke was an example of a variable playing all three roles.DiscussionOur findings suggest that our KG application could augment human expertise while confirming the complexity of selecting potential confounders for depression with AD. Imperfect concept mapping introduced errors, and the small literature corpus limited the scope of search results.ConclusionOur results suggest that our method may widely apply to causal feature selection. However, the search results need to be reviewed by human experts and tested empirically, and further work is required to optimize KG output for human consumption.Highlights•Knowledge of causal variables and their roles is essential for causal inference.•We show how to search a knowledge graph (KG) for causal variables and their roles.•The KG combines literature-derived knowledge with ontology-grounded knowledge.•We design queries to search the KG for confounder, collider, and mediator roles.•KG search reveals variables in these roles for depression and Alzheimer’s disease.Graphical abstract

show abstract

Section: Discussionmentioning

confidence: 99%

Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: a use case studying depression as a risk factor for Alzheimer's disease

Malec

Taneja

Albert

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

MPCD: A Multitask Graph Transformer for Molecular Property Prediction by Integrating Common and Domain Knowledge

Yang,

Duan,

Cheng

et al. 2024

J. Med. Chem.

View full text Add to dashboard Cite

Molecular property prediction with deep learning often employs self-supervised learning techniques to learn common knowledge through masked atom prediction. However, the common knowledge gained by masked atom prediction dramatically differs from the graph-level optimization objective of downstream tasks, which results in suboptimal problems. Particularly for properties with limited data, the failure to consider domain knowledge results in a direct search in an immense common space, rendering it infeasible to identify the global optimum. To address this, we propose MPCD, which enhances pretraining transferability by aligning the optimization objectives between pretraining and fine-tuning with domain knowledge. MPCD also leverages multitask learning to improve data utilization and model robustness. Technically, MPCD employs a relation-aware self-attention mechanism to capture molecules' local and global structures comprehensively. Extensive validation demonstrates that MPCD outperforms state-of-the-art methods for absorption, distribution, metabolism, excretion, and toxicity (ADMET) and physicochemical prediction across various data sizes.

show abstract

Enhancing drug repurposing on graphs by integrating drug molecular structure as feature

Ayuso-Muñoz

Santamaría

Pérez

et al. 2023

Preprint

View full text Add to dashboard Cite

Drug repurposing has become increasingly important, particularly in light of the COVID-19 pandemic. This process involves identifying new therapeutic uses for existing drugs, which can significantly reduce the cost, risk, and time associated with developing new drugs, de novo development. A previous conducted study proved that Deep Learning can be used to streamline this process by identifying drug repurposing hypotheses. The study presented a model called REDIRECTION, which utilized the rich biomedical information available in graph form and combined it with Geometric Deep Learning to find new indications for existing drugs. The reported metrics for this model were 0.87 for AUROC and 0.83 for AUPRC. In this current study, the importance of node features in GNNs is explored. Specifically, the study used GNNs to embed two-dimensional drug molecular structures and obtain corresponding features. These features were incorporated into the drug repurposing graph, along with some other enhancements, resulting in an improved model called DMSR. Performance score for the reported metrics values raised by 0.0448 in AUROC and 0.0919 in AUPRC. Based on these findings, we believe that the method used for embedding drug molecular structures is interesting and captures valuable information about drugs. Its incorporation in the graph for drug repurposing can significantly benefit the process, leading to improved performance evaluation metrics.

show abstract

Chemical and Textual Embeddings for Drug Repurposing

Cited by 4 publications

References 15 publications

Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: a use case studying depression as a risk factor for Alzheimer's disease

Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: a use case studying depression as a risk factor for Alzheimer's disease

MPCD: A Multitask Graph Transformer for Molecular Property Prediction by Integrating Common and Domain Knowledge

Enhancing drug repurposing on graphs by integrating drug molecular structure as feature

Contact Info

Product

Resources

About