A Natural Language Processing System for Extracting Evidence of Drug Repurposing from Scientific Publications

Subramanian, Shivashankar; Baldini, Ioana; Ravichandran, Sushma; Katz-Rogozhnikov, Dmitriy A.; Ramamurthy, Karthikeyan Natesan; Sattigeri, Prasanna; Varshney, Kush R.; Wang, Annmarie; Mangalath, Pradeep; Kleiman, Laura B.

doi:10.1609/aaai.v34i08.7052

Cited by 10 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, scoring so many records using the methods we employed would have required us to review tens of thousands of primary references. Machine learning methods such as natural language processing (NLP) [ 113 ] and neural joint models [ 114 ] might be used to help automate this process. Data similar to what we present might be useful for parameterizing models based on the text passages used to score drivers of outbreaks.…”

Section: Implications For Future Workmentioning

confidence: 99%

Characteristics of the 100 largest modern zoonotic disease outbreaks

Stephens

Gottdenker

Schatz

et al. 2021

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

Zoonotic disease outbreaks are an important threat to human health and numerous drivers have been recognized as contributing to their increasing frequency. Identifying and quantifying relationships between drivers of zoonotic disease outbreaks and outbreak severity is critical to developing targeted zoonotic disease surveillance and outbreak prevention strategies. However, quantitative studies of outbreak drivers on a global scale are lacking. Attributes of countries such as press freedom, surveillance capabilities and latitude also bias global outbreak data. To illustrate these issues, we review the characteristics of the 100 largest outbreaks in a global dataset ( n = 4463 bacterial and viral zoonotic outbreaks), and compare them with 200 randomly chosen background controls. Large outbreaks tended to have more drivers than background outbreaks and were related to large-scale environmental and demographic factors such as changes in vector abundance, human population density, unusual weather conditions and water contamination. Pathogens of large outbreaks were more likely to be viral and vector-borne than background outbreaks. Overall, our case study shows that the characteristics of large zoonotic outbreaks with thousands to millions of cases differ consistently from those of more typical outbreaks. We also discuss the limitations of our work, hoping to pave the way for more comprehensive future studies. This article is part of the theme issue ‘Infectious disease macroecology: parasite diversity and dynamics across the globe’.

show abstract

Section: Implications For Future Workmentioning

confidence: 99%

Characteristics of the 100 largest modern zoonotic disease outbreaks

Stephens

Gottdenker

Schatz

et al. 2021

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

show abstract

“…We propose a natural language processing (NLP) pipeline that identifies the type of information in scientific publications relevant to our drug repurposing goal (Subramanian et al 2020). A schematic view of the pipeline is presented in Figure 1.…”

Section: Nlp Pipeline For Drug-cancer Discoverymentioning

confidence: 99%

Exploring the Efficacy of Generic Drugs in Treating Cancer

Baldini¹,

Bernagozzi²,

Aggarwal

et al. 2021

AAAI

Self Cite

View full text Add to dashboard Cite

Thousands of scientific publications discuss evidence on the efficacy of non-cancer generic drugs being tested for cancer. However, trying to manually identify and extract such evidence is intractable at scale. We introduce a natural language processing pipeline to automate the identification of relevant studies and facilitate the extraction of therapeutic associations between generic drugs and cancers from PubMed abstracts. We annotate datasets of drug-cancer evidence and use them to train models to identify and characterize such evidence at scale. To make this evidence readily consumable, we incorporate the results of the models in a web application that allows users to browse documents and their extracted evidence. Users can provide feedback on the quality of the evidence extracted by our models. This feedback is used to improve our datasets and the corresponding models in a continuous integration system. We describe the natural language processing pipeline in our application and the steps required to deploy services based on the machine learning models.

show abstract

“…To better and easily search for the high-quality public sports resource allocation strategy documents, government officials can enter a more comprehensive text description (i.e., paragraphs or sentences or phrases). Next, we will analyze the government officials' query inputs and mine the information of the text description; Meanwhile, we convert each text phrase or sentence or paragraph into a vector according to the existing natural language processing techniques [27][28].…”

Section: A Step 1: Converting the Query Contents Of Government Officmentioning

confidence: 99%

Fuzzy Keywords-Driven Public Sports Resource Allocation Strategies Retrieval With Privacy-Preservation

Sang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Currently, the government proposes various public sports resource allocation strategies to promote the construction of public sports in the local. Thus, searching for the document database becomes an economic and efficient way for government officials to understand the contents of various public sports resource allocation strategies. As the government officials lack background knowledge of public sports resource allocation, the government officials are hard to retrieve appropriate documents. What's more, the document database is generally unwilling to share all text document information with the government official as some documents contain sensitive data information. Considering the above drawbacks, we put forward a fuzzy keywords-driven public sports resource allocation strategies retrieval approach based on the Simhash (named PSRASk+S) in the paper. The retrieval approach can accurately recommend appropriate documents to the government officials, by using the text description mining of documents and the fuzzy keywords search technology. Furthermore, the retrieval process is not revealing the sensitive data information of the irrelevant public sports resource allocation strategy document to the government officials, so the retrieval process can achieve local information protection mechanism. Finally, a case study explains the feasibility and effectiveness of our retrieval approach step by step.

show abstract

A Natural Language Processing System for Extracting Evidence of Drug Repurposing from Scientific Publications

Cited by 10 publications

References 17 publications

Characteristics of the 100 largest modern zoonotic disease outbreaks

Characteristics of the 100 largest modern zoonotic disease outbreaks

Exploring the Efficacy of Generic Drugs in Treating Cancer

Fuzzy Keywords-Driven Public Sports Resource Allocation Strategies Retrieval With Privacy-Preservation

Contact Info

Product

Resources

About