Related Experiment Video
Updated: Feb 2, 2026
05:47
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
1.6K
BLASSO: integration of biological knowledge into a regularized linear model
Daniel Urda1, Francisco Aragón2, Rocío Bautista3
1Universidad de Cádiz, Departamento de Ingeniería Informática, Avda. de la Universidad de Cádiz n°10, Puerto Real, Cádiz, 11519, Spain. daniel.urda@uca.es.
BMC Systems Biology
|November 22, 2018
Summary
BLASSO, a new model integrating biological knowledge, improves breast cancer outcome prediction and biomarker stability over standard LASSO. It identifies novel cancer-related genes, enhancing RNA-Seq analysis for complex traits.
Area of Science:
- Computational biology and bioinformatics
- Genomics and transcriptomics
- Biomedical data analysis
Background:
- Identifying genetic signatures for complex human traits from RNA-Seq data is challenging due to high gene correlation and instability in biomarker selection.
- Existing methods often yield low overlap rates for genetic signatures across different studies.
- Predictive models for complex traits require robust and stable biomarker identification.
Purpose of the Study:
- To propose BLASSO, a linear model with L1-regularization, incorporating prior biological knowledge for predicting breast cancer outcomes.
- To evaluate two distinct approaches (Gene-specific and Gene-disease) for integrating biological knowledge within BLASSO.
- To assess the predictive performance and biomarker stability of BLASSO compared to a baseline LASSO model using RNA-Seq data.
Main Methods:
- Development of BLASSO, a linear model with L1-regularization, enhanced with two strategies for biological knowledge integration.
- Utilized a public RNA-Seq gene expression dataset for breast cancer.
- Employed 10-fold cross-validation with 100 repetitions for model assessment and calculated the robustness index (RI) for biomarker stability.
Main Results:
- BLASSO achieved higher average AUC values (0.7 for Gene-specific, 0.69 for Gene-disease) compared to LASSO (0.65).
- BLASSO demonstrated superior biomarker stability, with the Gene-specific approach showing a 66% increase in robustness (RI of 0.15±0.03 vs. 0.09±0.03 for LASSO).
- Functional analysis of BLASSO-derived signatures revealed known cancer-related genes and identified novel candidates like IFNK and PCNAP1.
Conclusions:
- BLASSO is an effective choice for breast cancer outcome prediction, offering improved efficacy and biomarker stability over traditional methods.
- The integration of biological knowledge into BLASSO enhances the interpretability and robustness of identified genetic signatures.
- BLASSO facilitates the discovery of both established and potentially novel genes involved in cancer pathogenesis.
Related Concept Videos
01:27Growth Models with Integration: Problem Solving
56
In population modeling, integration provides a systematic way to determine accumulated quantities from known rates of change. One such application arises in ecology, where the total weight of a fish population in a body of water is referred to as its biomass. When the rate of growth of this biomass is known as a function of time, calculus can be used to determine the total biomass at a future date.Growth Rate and Biomass FunctionLet the growth rate of the fish population be represented by a...
56
01:17Linear Circuits
872
A linear circuit is characterized by its output having a direct proportionality to its input, adhering to the linearity property, which encompasses the principles of homogeneity (scaling) and additivity. Homogeneity dictates that when the input, also referred to as the excitation, is multiplied by a constant factor, the output, known as the response, is correspondingly scaled by the same constant factor. For instance, if the current is multiplied by a constant 'k,' the voltage likewise...
872
01:27Linear Equations
480
Linear equations form the foundation of many algebraic and real-world applications, characterized by their simplicity and utility. A linear equation is an algebraic statement in which each term is either a constant or a product of a constant and a single variable. These equations represent straight lines when plotted on a Cartesian coordinate plane, reflecting a constant rate of change between two quantities.A typical linear equation in one variable has the form: ax + b = c, where a, b, and c...
480
00:55Linear Momentum
18.2K
The term momentum is used in various ways in everyday language, most of which are consistent with the precise scientific definition. Generally, momentum implies a tendency to continue on course—to move in the same direction; we tend to speak of sports teams or politicians gaining and maintaining the momentum to win. Momentum is also associated with great mass and speed and is often considered when talking about collisions. For example, when rugby players collide and fall to the...
18.2K
01:26Linearization and Approximation
62
Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...
62
01:57What is Conservation Biology?
24.3K
Conservation biology is a scientific field that focuses on the preservation of biodiversity in order to protect ecosystems while meeting the needs of the human population. Humans require properly functioning ecosystems to maintain our supply of natural resources, including food, medicines, and building materials.
24.3K