Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Kernel approaches for genic interaction extraction.

Seonho Kim1, Juntae Yoon, Jihoon Yang

  • 1Department of Computer Science, Sogang University and Daumsoft Inc., Se-Ah Venture Tower, Seoul, Korea. shkim@lex.yonsei.ac.kr

Bioinformatics (Oxford, England)
|November 16, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Ultrasound Microvascular Imaging Using Deep Knowledge Distillation.

Ultrasonic imaging·2026
Same author

Associations of Body Mass Index and Waist Circumference With Falls Among Community-dwelling Older Adults in Korea.

Journal of preventive medicine and public health = Yebang Uihakhoe chi·2026
Same author

On-Chip Direct Synthesis of 2D Semimetals for van der Waals Metal-Semiconductor Junction Transistor Arrays.

ACS nano·2026
Same author

Spinal Mincle activation as a new model of neuroinflammation-associated neuropathic pain: comparison with spinal nerve ligation.

The Korean journal of pain·2025
Same author

Single-Crystalline Si Stacked AlGaN/GaN High-Electron-Mobility Transistors with Enhanced Two-Dimensional Electron Gas Density.

Micromachines·2025
Same author

Sucrose supplementation mitigates heat stress-induced alterations in rumen metabolism and immunity in dairy cows.

Scientific reports·2025
Same journal

Biomedical Concept Recognition with Error-aware Negative-enhanced Ranking Framework.

Bioinformatics (Oxford, England)·2026
Same journal

TEDLH: Domain HMMs for sensitive detection of remote homologues.

Bioinformatics (Oxford, England)·2026
Same journal

PLNFGL: Joint Estimation of Multi-Condition Gene Networks from Single-cell RNA-seq Data.

Bioinformatics (Oxford, England)·2026
Same journal

MCFST: Spatial domain identification method based on multi-view graph convolutional network and graph fusion network.

Bioinformatics (Oxford, England)·2026
Same journal

SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers.

Bioinformatics (Oxford, England)·2026
Same journal

EDEL: Enhancing Dense Retrievers for Curation of Biomedical Knowledge Bases.

Bioinformatics (Oxford, England)·2026
See all related articles

This study introduces novel kernel methods for biomedical relation extraction, achieving a 77.5 F-score using the walk kernel for improved named entity recognition and information access.

Area of Science:

  • Biomedical informatics
  • Computational linguistics
  • Bioinformatics

Background:

  • Biomedical literature analysis faces challenges in named entity recognition and relation extraction due to complex sentence structures.
  • Traditional pattern-based methods struggle with long-range dependencies and semantic variations in biomedical text.

Purpose of the Study:

  • To develop advanced kernel construction methods for biomedical relation extraction.
  • To improve the accuracy of identifying relationships between entities in complex biomedical sentences.

Main Methods:

  • Proposed four novel kernels: predicate, walk, dependency, and hybrid kernels.
  • Represented sentence dependency structures as graphs to find shortest paths between entities.
  • Gradually augmented kernels from flat features to structural descriptions of shortest paths.

Related Experiment Videos

Main Results:

  • Achieved a 77.5 F-score using the walk kernel on the Language Learning in Logic (LLL) 05 genic interaction shared task.
  • Demonstrated the effectiveness of structural kernel methods over pattern-based approaches.

Conclusions:

  • Kernel construction offers a promising direction for enhancing biomedical relation extraction.
  • The proposed methods effectively capture complex syntactic and semantic information for improved entity relation prediction.