Award Abstract # 1827472
SCH: INT: Mining Drug-Drug Interaction Induced Adverse Effects from Health Record Databases

NSF Org: IIS
Division of Information & Intelligent Systems
Recipient: TRUSTEES OF THE UNIVERSITY OF PENNSYLVANIA, THE
Initial Amendment Date: April 11, 2018
Latest Amendment Date: April 11, 2018
Award Number: 1827472
Award Instrument: Standard Grant
Program Manager: Sylvia Spengler
sspengle@nsf.gov
 (703)292-7347
IIS
 Division of Information & Intelligent Systems
CSE
 Directorate for Computer and Information Science and Engineering
Start Date: February 1, 2018
End Date: August 31, 2022 (Estimated)
Total Intended Award Amount: $898,355.00
Total Awarded Amount to Date: $914,354.00
Funds Obligated to Date: FY 2016 = $898,354.00
FY 2017 = $16,000.00
History of Investigator:
  • Li Shen (Principal Investigator)
    li.shen@pennmedicine.upenn.edu
Recipient Sponsored Research Office: University of Pennsylvania
3451 WALNUT ST STE 440A
PHILADELPHIA
PA  US  19104-6205
(215)898-7293
Sponsor Congressional District: 03
Primary Place of Performance: University of Pennsylvania
423 Guardian Drive
Philadelphia
PA  US  19104-4865
Primary Place of Performance
Congressional District:
03
Unique Entity Identifier (UEI): GM1XX56LEP58
Parent UEI: GM1XX56LEP58
NSF Program(s): Smart and Connected Health
Primary Program Source: 01001617DB NSF RESEARCH & RELATED ACTIVIT
01001718DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 8018, 8062
Program Element Code(s): 801800
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.070

ABSTRACT

Recent advances in large-scale electronic health record database techniques provide exciting new opportunities to the study of drug safety. Drug-drug interactions (DDIs), a major cause of adverse drug events (ADEs), are a serious global health concern, and a severe detriment to public health. The scale of DDIs involving three or more drugs (also called high-order DDIs) has posed a prohibitory challenge for its molecular pharmacology and clinical research, which motivates alternative strategies such as mining health record data. This project aims to develop large-scale computational strategies and effective software tools for mining high-order DDI effects from health record databases, in order to yield novel discoveries in drug safety, and ultimately to benefit national health and well being.


To achieve the above goal, this project is designed to complete four specific tasks. Task 1 aims to develop a novel statistical framework to discover high-order DDI signals associated with ADEs from health record databases. Task 2 aims to study a novel drug safety problem for mining directional DDI signals. Task 3 aims to develop an innovative approach for mining directional DDI patterns at the drug-group level. Task 4 is devoted to software development, evaluation and validation. The project applies these methods to analyze three independent databases, packages method implementations into a user-friendly software toolkit, and releases the toolkit to the public. This project not only facilitates the development of novel computational techniques in drug safety research, but also addresses emerging scientific questions in modeling, mining, and visual exploration of complex data such as the health record data. The project's educational activities include course development, student mentoring and advising, and involvement of minority and underrepresented students in research activities.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

(Showing: 1 - 10 of 20)
Bo Peng, Zhiyun Ren, Srinivasan Parthasarathy, and Xia Ning "HAM: Hybrid associations model with pooling for sequential recommendation" IEEE Transactions on Knowledge and Data Engineering , 2021 10.1109/TKDE.2021.3049692
Chasioti D, Yao X, Zhang P, Quinney SK, Ning X, Li L, Shen L "Mining directional drug interaction effects on myopathy using the FAERS database" IEEE Journal of Biomedical and Health Informatics , 2018
Chiang C, Zhang P, Wang X, Wang L, Zhang S, Ning X, Shen L, Quinney S, Li L "Translational high-dimensional drug Interaction discovery and validation using health record databases and pharmacokinetics models" Clinical Pharmacology and Therapeutics , v.103 , 2018 , p.287
Chiang WH, Schleyer T, Shen L, Li L, Ning X "Pattern discovery from high-order drug-drug interaction relations" Journal of Healthcare Informatics Research , v.2 , 2018 , p.272
Chiang W, Shen L, Li L, Ning X "Drug-drug interaction prediction based on co-medication patterns and graph matching" International Journal of Computational Biology and Drug Design , v.13 , 2020 , p.36 10.1504/IJCBDD.2020.105093
Dey, Vishal and Machiraju, Raghu and Ning, Xia "Improving Compound Activity Classification via Deep Transfer and Representation Learning" ACS Omega , v.7 , 2022 , p.9465-9483 10.1021/acsomega.1c06805
He Y, Liu J, Ning X "Drug selection via joint push and learning to rank" IEEE Transactions on Computational Biology and Bioinformatics , 2018 10.1109/TCBB.2018.2848908
Liu J, Ning X "Differential compound prioritization via bi-directional selectivity push with power" Journal of Chemical Information and Modeling , v.57 , 2017 , p.2958
Peng B, Ning X "Deep learning for high-order drug-drug interaction prediction" 10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB) , 2019 , p.197 10.1145/3307339.3342136
Peng, Bo and Ren, Zhiyun and Parthasarathy, Srinivasan and Ning, Xia "HAM: Hybrid Associations Models for Sequential Recommendation" IEEE Transactions on Knowledge and Data Engineering , v.34 , 2022 , p.4838-4853 10.1109/TKDE.2021.3049692
Peng, Bo and Ren, Zhiyun and Parthasarathy, Srinivasan and Ning, Xia "M2: Mixed Models with Preferences, Popularities and Transitions for Next-Basket Recommendation" IEEE Transactions on Knowledge and Data Engineering , 2022 , p.1-1 10.1109/TKDE.2022.3142773
(Showing: 1 - 10 of 20)

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

The investigation of this project produces several important outcomes.

1.     We developed multiple statistical models for identifying high order drug-drug-interaction (DDI) effect on myopathy.

2.     We proposed a novel pharmacovigilance problem for mining directional high order DDI effects on myopathy and developed multiple data mining and visualization methods for revealing directional DDI effects on myopathy.

3.     We developed a hyper-graph-net approach for defining drug similarity. Based on this, we developed machine learning methods for detecting and predicting high-order DDI effects. We developed a method for mining DDIs at the drug group level, and a super-combo-drug test to detect high-order drug interactions and to handle strongly correlated drugs.

4.     We created a web page for visual exploration of directional DDIs and released the code for high-order DDI prediction using deep learning.

5.     We published over 20 full-length papers related to this project in peer-reviewed conference proceedings and journals.

6.     This project supported the following students

a.     University of Pennsylvania (Penn): Three female REU students in Computer and Information Science, one male REU student in Economics and Mathematical Biology, one male REU student in Bioengineering

b.     Ohio State University (OSU):  Seven graduate students.

c.      Indiana University (before PI's transition to Penn): Two female PhD students in Bioinformatics, one PhD student in Computer Science, one PhD student in Genetics, one REU student and two high school students.

7.     This project provided capstone project topics for the following two groups of students

a.     Four senior students in Computer and information Science at Penn

b.     Five senior students in Computer and Information Science at Penn

8.     The research materials produced in this project are used in (1) teaching several graduate courses in Penn and OSU, and (2) giving numerous conference and seminar presentations.

9.     We co-organized two conferences in related fields: International Conference on Intelligent Biology and Medicine (ICIBM 2020 and ICIBM 2021).

 


Last Modified: 12/29/2022
Modified by: Li Shen

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page