He is a last year graduate in Bioinformatics currently employed as a data scientist at Lorentus Ltd.
As a data scientist at Lorentus Ltd., He research and develop attribution models for marketing,
which are based on markov chains. In order to efficiently store and process large volumes of data, he
work on Hadoop-based server and utilise Hive and Pyspark.
In his previous job at Amplyfi, he had a chance to work on text mining methods for meaning
extraction from large volumes of text documents, based on statistical NLP methods.
In his PhD research, he was investigating and developing supervised and unsupervised machine
learning methods to predict context specific enhancer-promoter interactions using evidence from
changes in genomic protein occupancy over time. The model provided highly accurate predictions
as validated using data from genome-wide chromatin conformation capture experiments.