Genome-Scale Variant Interpretation

Automated Radiation Dose Estimation

Mission Statement

MutationForecaster® ( is Cytognomix’s patented web-portal for analysis of all types of mutations – coding and non-coding- including interpretation, comparison and management of genetic variant data. It’s a fully automated genome interpretation solution for research, translational and clinical labs.

Run our world-leading genome interpretation software on your exome, gene panel, or complete genome (Shannon transcription factor and splicing pipelines, ASSEDA, Veridical) with the Cytognomix User Variation Database and  Variant Effect Predictor.  With our integrated suite of software products, analyze coding, non-coding, and copy number variants, and compare new results with existing or your own database.  Select predicted mutations  by phenotype using articles with CytoVisualization Analytics.  With Workflows,  automatically perform end-to-end analysis with all of our software products.  Download an 1 page overview of MutationForecaster® (link)

Subscribe and analyze your own data via the cloud or… Don’t want to run your own analyses on MutationForecaster®? Let us do it for you with our Bespoke Analysis Service.

Experience our suite of genome interpretation products through a free trial of MutationForecaster®. Once you register, we provide datasets from our peer-reviewed publications to evaluate these software tools.

Automated radiation biodosimetry

Ionizing radiation produces characteristic chromosome changes. The altered chromosomes  are known as dicentric chromosomes [DCs]). DC biodosimetry is approved by the IAEA for occupational radiation exposure, radiation emergencies, or monitoring long term exposures.  The DC assay can also monitor effects of interventional radiation therapies.

Cytognomix has developed  a novel approach to find DCs (TBME).  The Automated Dicentric Chromosome Identifier and Dose Estimator (ADCI) software  works on multiple platforms and uses images produced by any of the existing automated metaphase capture systems found in most cytogenetic laboratories. ADCI is now available for for trial or  purchase (link).  Or contact us for details (pricing).

ADCI* uses machine learning to distinguish monocentric and dicentric chromosomes (Try the Dicentric Chromosome Identifier web app). With novel image segmentation, ADCI has become a fully functional cytogenetic biodosimetry system. ADCI takes images from metaphase scanning systems,  selects high quality cells, identifies dicentric chromosomes, builds biodosimetry calibration curves, and estimates exposures.  ADCI fulfills the criteria established by the IAEA for accurate triage biodosimetry of a sample in less than an hour. The accuracy is comparable to an experienced cytogeneticist. Check out our online user manual: wiki.

We find and validate mutations and gene signatures that others cannot with advanced,  patented genomic bioinformatic technologies. Cytognomix continues our  long track record of creating technologies for genomic medicine. We anticipate and implement the needs of the molecular medicine and genomics communities.

Predict chemotherapy outcomes

Pharmacogenomic responses to chemotherapy drugs can be predicted by supervised machine learning of expression and copy number of relevant gene combinations. Since 2015,  CytoGnomix has used biochemical evidence to derive gene signatures from changes in gene expression in cell lines, which can subsequently be examined in patients that have been treated with the same drugs. We have derived signatures for 30 different commonly used drugs.  Try out out our online predictor: 

Quantifying responses to ionizing radiation with gene expression signatures.

Gene signatures derived by machine learning have low error rates in externally validated, independent radiation exposed data. They exhibit high specificity and granularity for dose estimation in humans and mice.  These signatures can be designed to avoid the effects of confounding, comorbidities which can reduce specificity for detecting radiation exposures. See:

Single copy genomic technologies

Latest Posts

July 31, 2015. Chemotherapy resistance in breast cancer manuscript accepted for publication

Genomic signatures for paclitaxel and gemcitabine resistance in breast cancer derived by machine learning Authors:  Stephanie N. Dormana, Katherina Baranovaa, Joan H.M. Knollb,c,d, Brad L. Urquharte, Gabriella Marianif, Maria Luisa Carcangiuf, Peter K. Rogana,d,g,h* aDepartment of Biochemistry, Schulich School of Medicine and Dentistry, University of Western Ontario, London, ON, Canada, bDepartment of Pathology and Laboratory Medicine, […]

July 8, 2015. New paper using Cytognomix’s single copy FISH probes

Khan WA, Rogan PK, Knoll JH. Reversing chromatin accessibility differences that distinguish homologous mitotic metaphase chromosomes. Molecular Cytogenetics, in press. Stay tuned for posts providing details and links to the manuscript once it is available online at the journal website.

July 3, 2015. New publication on breast cancer gene mutation

FANCM c.5791C>T nonsense mutation (rs144567652) induces exon skipping, affects DNA repair activity, and is a familial breast cancer risk factor. Peterlongo et al. Hum Mol Genet. 2015 Jun 30. pii: ddv251. In this paper, we use information theory to demonstrate a new mechanism for disease mutations. It turns out that this a fairly common type […]

April 18, 2015. New software distribution agreement for MutationForecaster

Today, Cytognomix Inc. and Illumina  signed a distribution agreement to make MutationForecaster software available through the BaseSpace ecosystem. Work is underway to enable Illumina users to analyze data processed in BaseSpace to be interpreted with Cytognomix’s software.  The BaseSpace environment enables MiSeq users to carry out sequence analyses with requiring an  onsite computing infrastructure, with […]

May 21, 2015. Platform presentation at Compute Ontario Research Day

Dr. Peter Rogan’s laboratory at the University of Western Ontario will present:  Discovery of Primary, Cofactor, and Novel Transcription Factor Binding Site Motifs by Recursive, Thresholded Entropy Minimization by Ruipeng Lu 1, Eliseos Mucaki 2, and Peter Rogan 1,2,3.    Departments of (1) Computer Science and (2)Biochemistry, University of Western Ontario, and (3)Cytognomix Inc., London ON at Compute Ontario […]