Limits...
The Marker State Space (MSS) method for classifying clinical samples.

Fallon BP, Curnutte B, Maupin KA, Partyka K, Choi S, Brand RE, Langmead CJ, Tembe W, Haab BB - PLoS ONE (2013)

Bottom Line: Marker State Space (MSS) defines "marker states" based on all possible patterns of high and low values among a panel of markers.Each marker state is defined as either a case state or a control state, and a sample is classified as case or control based on the state it occupies.MSS provides a straightforward approach for modeling highly divergent subclasses of patients, which may be adaptable for diverse applications.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Cancer Immunodiagnostics, Van Andel Institute, Grand Rapids, Michigan, USA.

ABSTRACT
The development of accurate clinical biomarkers has been challenging in part due to the diversity between patients and diseases. One approach to account for the diversity is to use multiple markers to classify patients, based on the concept that each individual marker contributes information from its respective subclass of patients. Here we present a new strategy for developing biomarker panels that accounts for completely distinct patient subclasses. Marker State Space (MSS) defines "marker states" based on all possible patterns of high and low values among a panel of markers. Each marker state is defined as either a case state or a control state, and a sample is classified as case or control based on the state it occupies. MSS was used to define multi-marker panels that were robust in cross validation and training-set/test-set analyses and that yielded similar classification accuracy to several other classification algorithms. A three-marker panel for discriminating pancreatic cancer patients from control subjects revealed subclasses of patients based on distinct marker states. MSS provides a straightforward approach for modeling highly divergent subclasses of patients, which may be adaptable for diverse applications.

Show MeSH

Related in: MedlinePlus

Training set marker states and patient classifications.(A) Training set marker states. The eight possible marker states for the three indicated markers are shown, followed by the numbers of case and control samples in each state and the categorization of each state. *State 2 was unoccupied by categorized as a control state because of similarity to other control states. The lower panel shows condensed marker states, in which X indicates either 0 or 1. (B) Individual sample classifications. Each column represents an individual patient sample, and the first three rows indicate results from the indicated markers. A yellow square indicates the sample was above the threshold for that marker, and black indicates below. The blue lines indicate the state in which each sample was classified.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3672150&req=5

pone-0065905-g003: Training set marker states and patient classifications.(A) Training set marker states. The eight possible marker states for the three indicated markers are shown, followed by the numbers of case and control samples in each state and the categorization of each state. *State 2 was unoccupied by categorized as a control state because of similarity to other control states. The lower panel shows condensed marker states, in which X indicates either 0 or 1. (B) Individual sample classifications. Each column represents an individual patient sample, and the first three rows indicate results from the indicated markers. A yellow square indicates the sample was above the threshold for that marker, and black indicates below. The blue lines indicate the state in which each sample was classified.

Mentions: Before applying this panel to the test set, we used the entire training set data to find the thresholds and state rules that gave the best performance. The panel achieved 88.9% sensitivity, 86.0% specificity, and 87.8% accuracy (Table 1). State 4 (0,1,1), state 6 (1,0,1), state 7 (1,1,0), and state 8 (1,1,1) were mainly occupied by case samples and therefore were classified as case states (Fig. 3A). State 1, state 3, and state 5 were classified as control states. State 2 (0,0,1) was not occupied by any sample but was classified as a control state due to its similarity to the other control states. These state rules can be condensed into a simplified rule that if a sample is elevated in any two or more of the markers, it is called a “case” (Fig. 3A).


The Marker State Space (MSS) method for classifying clinical samples.

Fallon BP, Curnutte B, Maupin KA, Partyka K, Choi S, Brand RE, Langmead CJ, Tembe W, Haab BB - PLoS ONE (2013)

Training set marker states and patient classifications.(A) Training set marker states. The eight possible marker states for the three indicated markers are shown, followed by the numbers of case and control samples in each state and the categorization of each state. *State 2 was unoccupied by categorized as a control state because of similarity to other control states. The lower panel shows condensed marker states, in which X indicates either 0 or 1. (B) Individual sample classifications. Each column represents an individual patient sample, and the first three rows indicate results from the indicated markers. A yellow square indicates the sample was above the threshold for that marker, and black indicates below. The blue lines indicate the state in which each sample was classified.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3672150&req=5

pone-0065905-g003: Training set marker states and patient classifications.(A) Training set marker states. The eight possible marker states for the three indicated markers are shown, followed by the numbers of case and control samples in each state and the categorization of each state. *State 2 was unoccupied by categorized as a control state because of similarity to other control states. The lower panel shows condensed marker states, in which X indicates either 0 or 1. (B) Individual sample classifications. Each column represents an individual patient sample, and the first three rows indicate results from the indicated markers. A yellow square indicates the sample was above the threshold for that marker, and black indicates below. The blue lines indicate the state in which each sample was classified.
Mentions: Before applying this panel to the test set, we used the entire training set data to find the thresholds and state rules that gave the best performance. The panel achieved 88.9% sensitivity, 86.0% specificity, and 87.8% accuracy (Table 1). State 4 (0,1,1), state 6 (1,0,1), state 7 (1,1,0), and state 8 (1,1,1) were mainly occupied by case samples and therefore were classified as case states (Fig. 3A). State 1, state 3, and state 5 were classified as control states. State 2 (0,0,1) was not occupied by any sample but was classified as a control state due to its similarity to the other control states. These state rules can be condensed into a simplified rule that if a sample is elevated in any two or more of the markers, it is called a “case” (Fig. 3A).

Bottom Line: Marker State Space (MSS) defines "marker states" based on all possible patterns of high and low values among a panel of markers.Each marker state is defined as either a case state or a control state, and a sample is classified as case or control based on the state it occupies.MSS provides a straightforward approach for modeling highly divergent subclasses of patients, which may be adaptable for diverse applications.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Cancer Immunodiagnostics, Van Andel Institute, Grand Rapids, Michigan, USA.

ABSTRACT
The development of accurate clinical biomarkers has been challenging in part due to the diversity between patients and diseases. One approach to account for the diversity is to use multiple markers to classify patients, based on the concept that each individual marker contributes information from its respective subclass of patients. Here we present a new strategy for developing biomarker panels that accounts for completely distinct patient subclasses. Marker State Space (MSS) defines "marker states" based on all possible patterns of high and low values among a panel of markers. Each marker state is defined as either a case state or a control state, and a sample is classified as case or control based on the state it occupies. MSS was used to define multi-marker panels that were robust in cross validation and training-set/test-set analyses and that yielded similar classification accuracy to several other classification algorithms. A three-marker panel for discriminating pancreatic cancer patients from control subjects revealed subclasses of patients based on distinct marker states. MSS provides a straightforward approach for modeling highly divergent subclasses of patients, which may be adaptable for diverse applications.

Show MeSH
Related in: MedlinePlus