Tag Archives: machine learning

Platform presentation at ConRad 2021 on radiation gene signatures

Posted on by
On May 10, 2021, Dr. Rogan is giving a platform presentation at ConRad 2021 (www.radiation-medicine.de) titled
“Radiation biodosimetry exposure assessment from gene expression signatures can be confounded by other underlying disease pathologies.”

Misclassification of patients with underlying disorders by otherwise accurate radiation gene signatures compromises their utility for population-scale radiation exposure assessment. Underlying conditions modify the normal baseline values of biomarkers used for diagnostic analysis of radiation exposure. The collective frequency of these conditions would confound efforts to assess radiation exposures in a mass casualty event, affecting determination of eligibility for radiation-mitigating therapies.

#radiation #misdiagnosis #geneexpression #signature #medicine

Dec. 10, 2020. New article on chemotherapy response prediction

Posted on by
We have published:
Pathway‐extended gene expression signatures integrate novel biomarkers that improve predictions of patient responses to kinase inhibitors.

Ashis J. Bagchee‐Clark , Eliseos J. Mucaki, Tyson Whitehead, and Peter K. Rogan

MedComm (Wiley) 1(3): 311-327, 2020.  (https://doi.org/10.1002/mco2.46)

Abstract:
Cancer chemotherapy responses have been related to multiple pharmacogenetic biomarkers, often for the same drug. This study utilizes machine learning to derive multi‐gene expression signatures that predict individual patient responses to specific tyrosine kinase inhibitors, including erlotinib, gefitinib, sorafenib, sunitinib, lapatinib and imatinib. Support vector machine (SVM) learning was used to train mathematical models that distinguished sensitivity from resistance to these drugs using a novel systems biology‐based approach. This began with expression of genes previously implicated in specific drug responses, then expanded to evaluate genes whose products were related through biochemical pathways and interactions. Optimal pathway‐extended SVMs predicted responses in patients at accuracies of 70% (imatinib), 71% (lapatinib), 83% (sunitinib), 83% (erlotinib), 88% (sorafenib) and 91% (gefitinib). These best performing pathway‐extended models demonstrated improved balance predicting both sensitive and resistant patient categories, with many of these genes having a known role in cancer aetiology. Ensemble machine learning‐based averaging of multiple pathway‐extended models derived for an individual drug increased accuracy to >70% for erlotinib, gefitinib, lapatinib and sorafenib. Through incorporation of novel cancer biomarkers, machine learning‐based pathway‐extended signatures display strong efficacy predicting both sensitive and resistant patient responses to chemotherapy.

July 4, 2019. Presentations describing interlaboratory comparison of radiation exposure determination by automated cytogenetic biodosimetry

Posted on by

We will be presenting:

Determination of radiation exposure levels by fully automated
dicentric chromosome analysis: Results from IAEA MEDBIODOSE
(CRP E35010) interlaboratory comparison

at both the 19th International Congress of Radiation Research (Aug. 25-29, 2019) and the 12th International Symposium on Chromosome Aberrations (Aug. 27, 2019)  in Manchester, UK. This study compared the performance of our Automated Dicentric Chromosome Identifier and Dose Estimator (ADCI) using data from 6 different laboratories.  Each of these members of the  IAEA-sponsored Cooperative Research Project E35010, submitted images for calibration curve construction and at least 2 samples of unknown exposure to CytoGnomix for analysis with ADCI. We will report the results of this analysis during this presentation.

This poster presentation is now available on the Zenodo website (http://doi.org/10.5281/zenodo.4012749)

doi:  DOI 10.5281/zenodo.4012748

Authors:

Rogan P , Shirley B , Li Y , Guogyte K , Sevriukova O , Ngoc Duy P , Moquet J ,
Ainsbury E , Sudprasert W , Wilkins R , Norton F , Knoll J

Department of Biochemistry , University of Western Ontario, London Ontario, Canada
Department of Pathology and Laboratory Medicine, University of Western Ontario, London
Ontario, Canada
Radiation Protection Centre, Ministry of Health (L T -RPC), Vilnius, Lithuania
Dalat Nuclear Research Institute (VN-DNRI), Dalat, Vietnam
Public Health England (PHE), Oxford, Great Britain
Thai Biodosimetry Network, Kasetsart University (THA), Bangkok, Thailand
Health Canada, Ottawa Ontario, Canada
Canadian Nuclear Laboratories, Chalk River Ontario, Canada
Cytognomix, London Ontario, Canada