ABOUT THE CUSTOMER

Biotech company

Revenue (20B$ +)

CHALLENGE

– We took the challenge of predicting optimal parameters for a device used in medical research.

– The device has many parameters which are determined experimentally.

– Lot of manual effort has to be involved to set the proper parameters to get results.

– In some cases the samples they use might be rare or it takes much time for sample preparation, and cannot afford to test so many times with different sets of parameters.

– So, there should be some automated process to find the correct parameters, which Machine learning or Deep learning can solve.

WHERE THEY WERE

The parameter  values are tried and tested manually. Testing will continue till the optimal parameters are found. Incase of rare samples, sample will get wasted when tested with so many values.

CLIENT BENEFIT

– The model developed will increase the range of research and experimentation, while reducing the time and effort  taken in sample preparation and other steps for scientists. 

– Increased selectivity of parametres results in low cost and improved ease of operation.

PREDERA CAPABILITY

– AI approach to solve the problem

– Built a deep learning models to predict ideal parameters.

– Use predera’s AIQ platform to easily build, deploy and monitor the Deep learning model

– Schedule to train the model at regular intervals to improve accuracy

PAIN POINT

The sample used could be rare, valuable and costly, as the sample is rare there can only limited experiments that can be done. Time, a lot of effort and cost spent for each experiment is high.

SOLUTION

The required work is feature extraction and deep learning models  to optimize the parameters.

MODEL

Fig: Architecture

Deep Learning

This is a deep learning problem as there is non-linearity, which deep learning can do well. Neural networks can identify hidden patterns in the data without exclusive feature engineering.

The traditional algorithms cannot perform well or separate out the signals  when their is non-linearity, which “Artificial Neural Networks” also called deep learning can do. Traditional algorithms need most of the features to identified by an expert and then hand-coded as per domain and data type.

The performance of the most of machine learning algorithms depends on how accurately the features are identified and extracted.

Deep learning algorithms try to learn high-level features from data which is a major step ahead of machine learning. Deep learning reduces the task of developing new feature extractor for every problem.

An Artificial neural network is developed to predict the ideal parameters. The network takes protein data as input and the input is passed through hidden layers of neural network and finally to output layer which gives the predicted optimal parameters. 

RESULTS

The Predera team experimented different algorithms with different representation of input features and developed a model to predict optimal parameters which reduce the window size of the parameter values to be experimented.

The client was able to easily run predictions and explore more.

The model achieved 95% accuracy(no.of correct predictions) with error rate of 20 volts, 75% for error rate 10 volts and 50% for error rate 5 volts.