Breast Cancer Survival Prognosis With Biological Network Algorithms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting breast tumor aggressiveness and survival prognosis are limited in scope and accuracy due to the consideration of a reduced number of genes and lack of interaction between genes, making them ineffective for a wide range of tumor sub-types.
Innovation Solution
A method using gene expression data and biological networks to calculate an aggressiveness score through binarization and thresholding, allowing for the classification of patients into high or low risk groups based on personalized reports.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a reduced number of genes are considered for prediction, then the method is simpler to implement, but the prediction accuracy and scope are limited
Solution Approach 1:
The patent segments the complex biological system into modular functional pathways and gene networks. Instead of analyzing all genes simultaneously, the method divides them into functional modules (e.g., cell cycle, apoptosis, metabolism pathways) that can be analyzed independently and then integrated. This segmentation reduces computational complexity while maintaining comprehensive coverage of relevant biological processes, thereby improving both implementability and prediction accuracy.
Solution Approach 2:
The patent transforms gene expression data from continuous values to standardized scores through parameter changes. Gene expression levels are converted into normalized expression scores, and pathway activities are calculated as aggregated scores from multiple genes. This parameter transformation simplifies the data structure and enables more efficient computational analysis while preserving the essential biological information needed for accurate prediction.
2Device complexity
If gene interactions are not taken into account, then the calculation is simpler, but the predictive reliability is reduced
Solution Approach 1:
The patent merges individual gene expression data with pathway-level information to create an integrated analysis framework. Gene expression values are combined with pathway membership information, and pathway activities are merged from multiple contributing genes. This merging approach captures gene interactions at the pathway level without requiring complex pairwise interaction analysis, thereby improving predictive reliability while keeping the computational model manageable.
Solution Approach 2:
The patent introduces pathway activity scores as intermediary variables between individual gene expressions and final prediction outcomes. Instead of directly modeling complex gene-gene interactions, the method uses pathway activities as mediators that aggregate and summarize the collective behavior of gene groups. This intermediary layer simplifies the interaction modeling while preserving the essential cooperative and competitive relationships among genes within functional pathways.
3Ease of manufacture
If limited gene sets are used, then the method is easier to implement, but the applicability to different tumor sub-types is restricted
Solution Approach 1:
The patent creates a universal prediction framework that can be applied across different breast cancer sub-types through multi-functionality. The methodology uses standardized pathway analysis that can accommodate various gene sets and expression platforms. The same analytical pipeline can process data from different tumor types by simply updating the input gene expression matrices, making the method universally applicable while maintaining ease of implementation through a consistent workflow.
Solution Approach 2:
The patent implements a dynamic and flexible gene set configuration that adapts to different tumor sub-types. Rather than using a fixed gene panel, the method allows the input gene set to be dynamically adjusted based on the specific tumor type being analyzed. The pathway analysis framework automatically adapts to different gene compositions, enabling the same computational methodology to effectively handle luminal, HER2-enriched, and basal-like sub-types with their distinct molecular profiles.
Data Source
AI summary
A method is described for determining a survival prognosis of a patient suffering from a breast tumor, using processing carried out by electronic processing and/or calculation means. The method first comprises step (a) of defining a biological network representative of a particular biological process associated with the breast tumor. The biological network comprises a plurality of nodes, a set of directional relationships between these nodes and a set of genes associated with these nodes. The method also includes step (b) of accessing a data set related to the patient, comprising gene expressions in a biological sample of the tumor isolated from the patient; and step (c) of calculating a continuous expression value for the aforesaid nodes of the biological network. If the node is associated with only one gene and it is found that the gene is present in the biological sample, the continuous expression value of the node is calculated as the expression of the associated gene detected in the biological sample. If the node is associated with multiple genes, and it is found that at least one of the aforesaid genes is present in the biological sample, the continuous expression value of the node is calculated based on the expressions of the associated genes, present in the biological sample. If the node is not associated with any gene, or the associated gene is not found in the biological sample, the node is marked as a node not associated with a continuous expression value. The method then comprises the following steps, carried out by the electronic processing and/or calculation means: (d) binarizing the data set of continuous expression values calculated for each node of the biological network to which a continuous expression value is associated, based on a comparison of the continuous expression value with a respective threshold, to thus obtain a first binarized data set of the nodes, obtained based on the detections made; (e) calculating an aggressiveness score based on the aforesaid first binarized data set of the nodes; and finally (f) determining a survival prognosis result based on the aforesaid aggressiveness score calculated.