Dataset Information

Random Forests Are Able to Identify Differences in Clotting Dynamics from Kinetic Models of Thrombin Generation.

ABSTRACT: Current methods for distinguishing acute coronary syndromes such as heart attack from stable coronary artery disease, based on the kinetics of thrombin formation, have been limited to evaluating sensitivity of well-established chemical species (e.g., thrombin) using simple quantifiers of their concentration profiles (e.g., maximum level of thrombin concentration, area under the thrombin concentration versus time curve). In order to get an improved classifier, we use a 34-protein factor clotting cascade model and convert the simulation data into a high-dimensional representation (about 19000 features) using a piecewise cubic polynomial fit. Then, we systematically find plausible assays to effectively gauge changes in acute coronary syndrome/coronary artery disease populations by introducing a statistical learning technique called Random Forests. We find that differences associated with acute coronary syndromes emerge in combinations of a handful of features. For instance, concentrations of 3 chemical species, namely, active alpha-thrombin, tissue factor-factor VIIa-factor Xa ternary complex, and intrinsic tenase complex with factor X, at specific time windows, could be used to classify acute coronary syndromes to an accuracy of about 87.2%. Such a combination could be used to efficiently assay the coagulation system.

SUBMITTER: Arumugam J

PROVIDER: S-EPMC4865224 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Random Forests Are Able to Identify Differences in Clotting Dynamics from Kinetic Models of Thrombin Generation.

Arumugam Jayavel J Bukkapatnam Satish T S ST Narayanan Krishna R KR Srinivasa Arun R AR

PloS one 20160512 5

Current methods for distinguishing acute coronary syndromes such as heart attack from stable coronary artery disease, based on the kinetics of thrombin formation, have been limited to evaluating sensitivity of well-established chemical species (e.g., thrombin) using simple quantifiers of their concentration profiles (e.g., maximum level of thrombin concentration, area under the thrombin concentration versus time curve). In order to get an improved classifier, we use a 34-protein factor clotting ...[more]

PMID: 27171403

Similar Datasets

Project description:BackgroundThe haemostatic balance is an equilibrium of pro- and anticoagulant factors that work synergistically to prevent bleeding and thrombosis. As thrombin is the central enzyme in the coagulation pathway, it is desirable to measure thrombin generation (TG) in order to detect possible bleeding or thrombotic phenotypes, as well as to investigate the capacity of drugs affecting the formation of thrombin. By investigating the underlying processes of TG (i.e., prothrombin conversion and inactivation), additional information is collected about the dynamics of thrombin formation.ObjectivesTo obtain reference values for thrombin dynamics (TD) analysis in 112 healthy donors using an automated system for TG.MethodsTG was measured on the ST Genesia, fibrinogen on the Start, anti-thrombin (AT) on the STA R Max and α2Macroglobulin (α2M) with an in-house chromogenic assay.ResultsTG was measured using STG-BleedScreen, STG-ThromboScreen and STG-DrugScreen. The TG data was used as an input for TD analysis, in combination with plasma levels of AT, α2M and fibrinogen that were 113% (108-118%), 2.6 μM (2.2 μM-3.1 μM) and 2.9 g/L (2.6-3.2 g/L), respectively. The maximum rate of the prothrombinase complex (PCmax) and the total amount of prothrombin converted (PCtot) increased with increasing tissue factor (TF) concentration. PCtot increased from 902 to 988 nM, whereas PCmax increased from 172 to 508 nM/min. Thrombin (T)-AT and T-α2M complexes also increased with increasing TF concentration (i.e., from 860 to 955 nM and from 28 to 33 nm, respectively). PCtot, T-AT and T-α2M complex formation were strongly inhibited by addition of thrombomodulin (-44%, -43%, and -48%, respectively), whereas PCmax was affected less (-24%). PCtot, PCmax, T-AT, and T-α2M were higher in women using oral contraceptives (OC) compared to men/women without OC, and inhibition by thrombomodulin was also significantly less in women on OC (p < 0.05).ConclusionsTG measured on the ST Genesia can be used as an input for TD analysis. The data obtained can be used as reference values for future clinical studies as the balance between prothrombin conversion and thrombin inactivation has shown to be useful in several clinical settings.

Dataset Information

Random Forests Are Able to Identify Differences in Clotting Dynamics from Kinetic Models of Thrombin Generation.

Publications

Random Forests Are Able to Identify Differences in Clotting Dynamics from Kinetic Models of Thrombin Generation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets