Computational analysis of biological data using manifold and a hyperplane
Inventors
Eden, Eran • Oved, Kfir • NAVON, Roy • COHEN-DOTAN, Assaf • BOICO, Olga
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11776658-B2
Publication Date
2023-10-03
Expiration Date
Abstract
A method of analyzing biological data containing expression values of a plurality of polypeptides in the blood of a subject. The method comprises: calculating a distance between a segment of a curved line and an axis defined by a direction, the distance being calculated at a point over the curved line defined by a coordinate along the direction. The method further comprises correlating the distance to the presence of, absence of, or likelihood that the subject has, a bacterial infection. The coordinate is defined by a combination of the expression values, wherein at least 90% of the segment is between a lower bound line and an upper bound line.
Core Innovation
The invention provides a computer-implemented method for analyzing biological data by receiving values of biomarkers in the blood of a subject and displaying a graphical user interface (GUI) having a calculation activation control. When a user activates the control, the method automatically calculates a score based on the received blood biomarker values and generates on the GUI a graphical scale indicative of likelihoods for bacterial infections and a mark on the scale at a location corresponding to the calculated score.
The disclosure further validates a prospective multi-center observational host-proteome signature that distinguishes bacterial infections versus viral infections, and also distinguishes non-infectious/healthy from bacterial infections, using blood biomarker levels. The approach uses a composite blinded physician reference standard with majority, unanimous, and clear-diagnosis cohorts to ground the classification labels, and feature selection identifies TRAIL, IP-10, and CRP for a probabilistic diagnostic score.
Graphical user interface embodiments include receiving and presenting biomarker-based analysis results, including calculating and displaying scores and marks on a viral-to-bacterial scale and displaying visual indicators of likelihoods such as a color index. Biomarker panels and polypeptide examples include CRP, IP-10, TRAIL, IL1ra, PCT, and SAA, with validation context using a multi-center observational study and signature performance examples including AUC, sensitivity, specificity, and LR+ / LR- metrics.
Claims Coverage
The partial content provides two independent claims covering a GUI-based method and a system. The inventive features across the independent claims include GUI activation, automatic scoring from blood biomarker values, and graphical scale and mark generation tied to infection-likelihood directions.
Graphical user interface with calculation activation control
Displaying on a display device a graphical user interface (GUI) having a calculation activation control.
Receiving blood biomarker values and automatically calculating a score upon activation
Receiving values of biomarkers in the blood of a subject; and responsively to an activation of said control by a user, automatically calculating a score based on said values.
Graphical scale indicative of likelihoods for infection type and a mark at a corresponding location
Generating on said GUI a graphical scale indicative of likelihoods for bacterial infections; and generating a mark on said scale at a location corresponding to said score.
Viral-to-bacterial GUI scale endpoints identified as viral and bacterial infections
Generating on said GUI a graphical scale having a first end identified as corresponding to a viral infection of said subject, and a second end identified as corresponding to a bacterial infection of said subject.
Across the independent claims, the core claim coverage centers on a GUI-driven workflow where user activation triggers automatic score calculation from blood biomarker values, followed by generation of a graphical scale that indicates infection likelihoods and placement of a mark corresponding to the calculated score.
Stated Advantages
Distinguishes bacterial infections versus viral infections and distinguishes non-infectious/healthy from bacterial infections using blood biomarker levels.
Provides high discrimination between bacterial and viral infections, characterized by high AUC values.
Robust performance across subgroups and despite potential bacterial colonization.
Compares favorably or is evaluated against clinical/lab parameters and established biomarkers such as procalcitonin (PCT) and CRP.
Supports probabilistic diagnostic scoring and graphical visualization of likelihoods, including embodiments with probability surfaces.
Documented Applications
Prospective multi-center observational host-proteome signature validation to distinguish bacterial versus viral infections using blood biomarker levels in blood of a subject, including differentiation from non-infectious/healthy.
GUI-based analysis of biological data where a user activates calculation, biomarker values are received, a probabilistic diagnostic score is calculated, and likelihoods are displayed on a graphical scale for infection classification.
Interested in licensing this patent?