A review of drug knowledge discovery using BioNLP and tensor or matrix decomposition

Drug knowledge discovery via multi-task learning and pre-trained models

Background

Drug repurposing is to find new indications of approved drugs, which is essential for investigating new uses for approved or investigational drug efficiency. The active gene annotation corpus (named AGAC) is annotated by human experts, which was developed to support knowledge discovery for drug repurposing. The AGAC track of the BioNLP Open Shared Tasks using this corpus is organized by EMNLP-BioNLP 2019, where the “Selective annotation” attribution makes AGAC track more challenging than other traditional sequence labeling tasks. In this work, we show our methods for trigger word detection (Task 1) and its thematic role identification (Task 2) in the AGAC track. As a step forward to drug repurposing research, our work can also be applied to large-scale automatic extraction of medical text knowledge.

Methods

To meet the challenges of the two tasks, we consider Task 1 as the medical name entity recognition (NER), which cultivates molecular phenomena related to gene mutation. And we regard Task 2 as a relation extraction task, which captures the thematic roles between entities. In this work, we exploit pre-trained biomedical language representation models (e.g., BioBERT) in the information extraction pipeline for mutation-disease knowledge collection from PubMed. Moreover, we design the fine-tuning framework by using a multi-task learning technique and extra features. We further investigate different approaches to consolidate and transfer the knowledge from varying sources and illustrate the performance of our model on the AGAC corpus. Our approach is based on fine-tuned BERT, BioBERT, NCBI BERT, and ClinicalBERT using multi-task learning. Further experiments show the effectiveness of knowledge transformation and the ensemble integration of models of two tasks. We conduct a performance comparison of various algorithms. We also do an ablation study on the development set of Task 1 to examine the effectiveness of each component of our method.

Results

Compared with competitor methods, our model obtained the highest Precision (0.63), Recall (0.56), and F-score value (0.60) in Task 1, which ranks first place. It outperformed the baseline method provided by the organizers by 0.10 in F-score. The model shared the same encoding layers for the named entity recognition and relation extraction parts. And we obtained a second high F-score (0.25) in Task 2 with a simple but effective framework.

Conclusions

Experimental results on the benchmark annotation of genes with active mutation-centric function changes corpus show that integrating pre-trained biomedical language representation models (i.e., BERT, NCBI BERT, ClinicalBERT, BioBERT) into a pipe of information extraction methods with multi-task learning can improve the ability to collect mutation-disease knowledge from PubMed.

A Novel Metric to Quantify the Effect of Pathway Enrichment Evaluation With Respect to Biomedical Text-Mined Terms: Development and Feasibility Study

BACKGROUND

Natural language processing has long been applied in various applications for biomedical knowledge inference and discovery. Enrichment analysis based on named entity recognition is a classic application for inferring enriched associations in terms of specific biomedical entities such as gene, chemical, and mutation.

OBJECTIVE

The aim of this study was to investigate the effect of pathway enrichment evaluation with respect to biomedical text-mining results and to develop a novel metric to quantify the effect.

METHODS

Four biomedical text mining methods were selected to represent natural language processing methods on drug-related gene mining. Subsequently, a pathway enrichment experiment was performed by using the mined genes, and a series of inverse pathway frequency (IPF) metrics was proposed accordingly to evaluate the effect of pathway enrichment. Thereafter, 7 IPF metrics and traditional P value metrics were compared in simulation experiments to test the robustness of the proposed metrics.

RESULTS

IPF metrics were evaluated in a case study of rapamycin-related gene set. By applying the best IPF metrics in a pathway enrichment simulation test, a novel discovery of drug efficacy of rapamycin for breast cancer was replicated from the data chosen prior to the year 2000. Our findings show the effectiveness of the best IPF metric in support of knowledge discovery in new drug use. Further, the mechanism underlying the drug-disease association was visualized by Cytoscape.

CONCLUSIONS

The results of this study suggest the effectiveness of the proposed IPF metrics in pathway enrichment evaluation as well as its application in drug use discovery.

A semantic relationship mining method among disorders, genes, and drugs from different biomedical datasets

BACKGROUND

Semantic web technology has been applied widely in the biomedical informatics field. Large numbers of biomedical datasets are available online in the resource description framework (RDF) format. Semantic relationship mining among genes, disorders, and drugs is widely used in, for example, precision medicine and drug repositioning. However, most of the existing studies focused on a single dataset. It is not easy to find the most current relationships among disorder-gene-drug relationships since the relationships are distributed in heterogeneous datasets. How to mine their semantic relationships from different biomedical datasets is an important issue.

METHODS

First, a variety of biomedical datasets were converted into RDF triple data; then, multisource biomedical datasets were integrated into a storage system using a data integration algorithm. Second, nine query patterns among genes, disorders, and drugs from different biomedical datasets were designed. Third, the gene-disorder-drug semantic relationship mining algorithm is presented. This algorithm can query the relationships among various entities from different datasets.

RESULTS AND CONCLUSIONS

We focused on mining the putative and the most current disorder-gene-drug relationships about Parkinson's disease (PD). The results demonstrate that our method has significant advantages in mining and integrating multisource heterogeneous biomedical datasets. Twenty-five new relationships among the genes, disorders, and drugs were mined from four different datasets. The query results showed that most of them came from different datasets. The precision of the method increased by 2.51% compared to that of the multisource linked open data fusion method presented in the 4th International Workshop on Semantics-Powered Data Mining and Analytics (SEPDA 2019). Moreover, the number of query results increased by 7.7%, and the number of correct queries increased by 9.5%.

Hybrid phenotype mining method for investigating off-target protein and underlying side effects of anti-tumor immunotherapy

BACKGROUND

It is of utmost importance to investigate novel therapies for cancer, as it is a major cause of death. In recent years, immunotherapies, especially those against immune checkpoints, have been developed and brought significant improvement in cancer management. However, on the other hand, immune checkpoints blockade (ICB) by monoclonal antiboties may cause common and severe adverse reactions (ADRs), the cause of which remains largely undetermined. We hypothesize that ICB-agents may induce adverse reactions through off-target protein interactions, similar to the ADR-causing off-target effects of small molecules. In this study, we propose a hybrid phenotype mining approach which integrates molecular level information and provides new mechanistic insights for ICB-associated ADRs.

METHODS

We trained a conditional random fields model on the TAC 2017 benchmark training data, then used it to extract all drug-centric phenotypes for the five anti-PD-1/PD-L1 drugs from the drug labels of the DailyMed database. Proteins with structure similar to the drugs were obtained by using BlastP, and the gene targets of drugs were obtained from the STRING database. The target-centric phenotypes were extracted from the human phenotype ontology database. Finally, a screening module was designed to investigate off-target proteins, by making use of gene ontology analysis and pathway analysis.

RESULTS

Eventually, through the cross-analysis of the drug and target gene phenotypes, the off-target effect caused by the mutation of gene BTK was found, and the candidate side-effect off-target site was analyzed.

CONCLUSIONS

This research provided a hybrid method of biomedical natural language processing and bioinformatics to investigate the off-target-based mechanism of ICB treatment. The method can also be applied for the investigation of ADRs related to other large molecule drugs.

HPO-Shuffle: an associated gene prioritization strategy and its application in drug repurposing for the treatment of canine epilepsy

Epilepsy is a common neurological disorder that affects mammalian species including human beings and dogs. In order to discover novel drugs for the treatment of canine epilepsy, multiomics data were analyzed to identify epilepsy associated genes. In this research, the original ranking of associated genes was obtained by two high-throughput bioinformatics experiments: Genome Wide Association Study (GWAS) and microarray analysis. The association ranking of genes was enhanced by a re-ranking system, HPO-Shuffle, which integrated information from GWAS, microarray analysis and Human Phenotype Ontology database for further downstream analysis. After applying HPO-Shuffle, the association ranking of epilepsy genes were improved. Afterward, a weighted gene coexpression network analysis (WGCNA) led to a set of gene modules, which hinted a clear relevance between the high ranked genes and the target disease. Finally, WGCNA and connectivity map (CMap) analysis were performed on the integrated dataset to discover a potential drug list, in which a well-known anticonvulsant phensuximide was included.