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 Concept Videos

Classification of Systems-I01:26

Classification of Systems-I

169
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
169
Classification of Systems-II01:31

Classification of Systems-II

134
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
134
Aggregates Classification01:29

Aggregates Classification

303
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
303
Classification of Signals01:30

Classification of Signals

401
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
401
How Data are Classified: Categorical Data01:11

How Data are Classified: Categorical Data

31.6K
A variable, usually notated by capital letters such as X and Y, is a characteristic or measurement that can be determined for each member of a population. Data are the actual values of variables. They may be numbers, or they may be words. Datum is a single value.
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
31.6K
Functional Classification of Joints01:09

Functional Classification of Joints

3.8K
Functional Classification of Joints
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses  or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An...
3.8K

You might also read

Related Articles

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

Sort by
Same author

Microbial named entity recognition and normalisation for AI-assisted literature review and meta-analysis.

Bioinformatics (Oxford, England)·2026
Same author

Erratum: Intestinal microbiome changes in response to amino acid and micronutrient supplementation: secondary analysis of the AMAZE trial - CORRIGENDUM.

Gut microbiome (Cambridge, England)·2026
Same author

AI-Assisted Pneumonia Detection, Localisation and Report Generation from Chest X-rays.

medRxiv : the preprint server for health sciences·2026
Same author

End-to-end integrative segmentation and radiomics prognostic models for risk stratification of high-grade serous ovarian cancer: a retrospective multicohort study.

The Lancet. Digital health·2026
Same author

From description to implementation: key takeaways from the 3rd African Microbiome Symposium.

mSphere·2025
Same author

Strengths and limitations of urinary sugar testing: an observational study of intestinal permeability and absorption in adults and children in Zambia and Tanzania with reference to mucosal biopsies.

The American journal of clinical nutrition·2025

Related Experiment Video

Updated: Jun 6, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K

Topological embedding and directional feature importance in ensemble classifiers for multi-class classification.

Eloisa Rocha Liedl1,2, Shabeer Mohamed Yassin1,3, Melpomeni Kasapi1,4

  • 1Section of Bioinformatics, Department of Metabolism, Digestion and Reproduction, Faculty of Medicine, Hammersmith Hospital Campus, Imperial College London, London, W12 0NN, United Kingdom.

Computational and Structural Biotechnology Journal
|December 3, 2024
PubMed
Summary
This summary is machine-generated.

We developed a new Class-Based Directional Feature Importance (CLIFI) metric to improve machine learning interpretability in cancer biomarker discovery. This method enhances understanding of protein expression patterns across various cancer types.

Keywords:
Decision treesFeature importanceMachine learningMulti-class classificationTopological information

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

979
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

468

Related Experiment Videos

Last Updated: Jun 6, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

979
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

468

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning in Oncology

Background:

  • Cancer remains a leading cause of death globally, necessitating advancements in early detection and treatment.
  • Machine learning (ML) offers potential for identifying novel cancer biomarkers from high-dimensional data.
  • Interpreting ML models is challenging but crucial for biological insight and clinical application.

Purpose of the Study:

  • To develop and evaluate a novel Class-Based Directional Feature Importance (CLIFI) metric for decision tree-based ML models.
  • To enhance the interpretability of ML models used for cancer biomarker identification.
  • To assess the performance of CLIFI-integrated models on The Cancer Genome Atlas (TCGA) proteomics data for cancer classification.

Main Methods:

  • Developed the CLIFI metric for decision tree methods, integrating it into Random Forest (RF), LAtent VAriable Stochastic Ensemble of Trees (LAVASET), Gradient Boosted Decision Trees (GBDTs), and a novel LAVABOOST extension.
  • Incorporated protein-protein interaction network topology into LAVASET and LAVABOOST models.
  • Applied the models to TCGA proteomics data for classifying 28 cancer types.

Main Results:

  • The CLIFI metric facilitated visualization of ML model decision-making processes.
  • Models achieved high F1-scores: RF (92.6%), LAVASET (92.0%), LAVABOOST (89.3%), and GBDTs (85.7%), with no single model superior across all cancers.
  • CLIFI analysis revealed heterogeneous expression patterns for proteins like MYH11, ERα, and BCL2 across diverse cancer types (e.g., brain, breast, kidney, prostate).

Conclusions:

  • The CLIFI metric provides an integrated approach for interpretable feature importance assessment in multi-class classification.
  • Combining CLIFI with topological information introduces inductive bias, enhancing model interpretability.
  • This approach aids in understanding complex protein expression heterogeneity in cancer, supporting biomarker discovery.