Involvement of Bayesiannetwork models inpredicting various typesof hematologicalmalignanciesAn Academic presentation by

Dr. Nancy Agnes, Head, Technical Operations, Statswork Group  www.statswork.comEmail: info@statswork.com

Outline

TODAY'S DISCUSSION

INTRODUCTION

SIGNIFICANCE OF NETWORK ANALYSIS:

CONCLUSION

Acute Myeloid Leukemia (AML) is a kind of myeloid blood malignancy in whichthe bone marrow produces aberrant white blood cells, red blood cells, orplatelets.

It is the most prevalent acute leukaemia in adults, and it predominantly affectsthe elderly.

It is a deadly kind of blood cancer that causes around 1.2 % of all cancerfatalities in the United States.

Myelodysplastic Syndrome (MDS) is bone marrow and a blood disorder thatdamages myeloid cells.

Abnormal hematopoiesis, or the inefficient generation of blood cells andplatelets in the bone marrow, is a hallmark of MDS. MDS, unlike AML, isgenerally benign and has a low mortality risk, but it can advance over time,with 30% of MDS patients progressing to AML.

As a result, it's critical to compare these two illnesses and give scientificinsights into their molecular parallels and variances.

INTRODUCTION

For detecting small but coordinated changes in expression of an interacting and linked group of genes, networkanalysis is the best method.

The AML and MDS were classified using a new technique based on coexpression networks and Bayesian networks.

The approach is depicted schematically in Figure 1.

Figure 1.Schematic view

of themethodology

In AML, WGCNA was used to organise related genes into gene modules (clusters) based on their coexpressionpatterns. WGCNA uses the average linkage hierarchical method to cluster the genes6.

WGCNA calculates one eigen gene for each gene module, which summarises the biological information in thatmodule into a single value per sample.

These eigen genes were used to train a Bayesian network (BN) with nodes (random variables) representinggene modules and directed edges (arcs) representing conditional dependencies between the eigen genes.

Gene expression data and gene regulatory networks have both been modelled using Bayesian networks.

A directed acyclic graph (DAG) and its accompanying conditional probability density functions make up a BN.

Biological activities in cells frequently need the cooperation of several genes.

Network analysis can discover small but coordinated changes in a group ofgenes that connect and have similar functions. As a result, network analysisoutperforms traditional techniques based on a list of differentially expressedgenes.

A coexpression network, in particular, stimulates the interaction betweenseveral genes based on their coexpression pattern.

The eigen genes that arise, which summarise the biological information ofmodules, are noise and profiling platform resistant.

This was proven by comparing eigengenes efficacy and differentially expressedgenes in support vector machine learning.

We coupled coexpression network analysis with Bayesian networks to describethe interactions between hundreds of genes in one network.

SIGNIFICANCEOF NETWORKANALYSIS

The use of network analysis to derive relevant biomarkers (features) from geneexpression patterns is beneficial.

Eigengenes, in particular, have more predictive potential than individual genes.These data may be used to construct a Bayesian network to describe therelationship between the gene modules and the biological or clinical state ofinterest. (SVM), demonstrating that the power of our method is based on howwe use eigengenes as biological fingerprints (i.e., features).

When individual genes are used as features, the SVM performs poorly, butwhen eigengenes are used as features, it performs similarly to the Bayesiannetwork.

Nonetheless, unlike SVM, which is more of a black box classifier, our Bayesiannetwork technique is beneficial since it quickly delineates the most relatedcharacteristics with the illness type.

CONCLUSION

Contact Us+44-1143520021

UNITED KINGDOM

+91-4448137070

EMAIL

INDIA

info@statswork.com