Machine learning solutions

Microarray Analysis

The scale and complexity of genomic data sets is increasing exponentially with the recent revolution in DNA sequencing and related technologies.

Machine learning enables us to bear on these data sets, letting us shed light on key interactions involved in complex disease.

Functional genomics involves the analysis of large datasets of information derived from various biological experiments.

One such type of large-scale experiment involves monitoring the expression levels of thousands of genes simultaneously under a particular condition, called gene expression analysis.

Microarray technology makes this possible and the quantity of data generated from each experiment is enormous.

Data mining can give a feeling for what the data actually represents, derive meaningful results from such experiments.

The main challenge for artificial intelligence is to analyze clinical data to take up new models of care and new technologies promoting health and wellbeing.

DESCRIPTIVE ANALYTICS

Analyze the changes in the genes to find patterns and determine if the are in the normal or disease state.

DIAGNOSTIC ANALYTICS

Determine the conditions that make a gene change from normal to disease state.

PREDICTIVE ANALYTICS

Develop a model that can recognize the changes in the genes and predict the state of them.

PRESCRIPTIVE ANALYTICS

Use the predictive model for preventive medicine and early diagnosis.

It is important that all of the information about a microarray experiment is recorded systematically, so that meaningful data sets can be generated.

In addition, it is important to apply the correct analysis techniques to obtain the best possible results.

Neural Designer is a software that implements neural networks, a machine learning technique capable of analyzing large amount of data and find complex relationships between them.

The user interface of Neural Designer provides you with different methods to analyze relations between the state of the genes and the environmental conditions, model selection algorithms for the best design of the neural network and a set of testing methods to check the correct functioning of the predictive model.

The next image shows a summary of the process that would be followed to obtain a predictive model for this case.

Activity diagram

First, the data about DNA are arranged into a data set. This data is analyzed by Neural Designer to find patterns. As a result, we obtain a predictive model capable of detecting diseases from this information.

Related solutions:

Related examples: