iPlexus™ is now powered by Google Cloud platform
Founded in 2011 and headquartered in Germany, with offices in US and India, Innoplexus AG offers Data as a Service (DaaS) and Continuous Analytics as a Service (CAaS) products. These products leverage Artificial Intelligence (AI) and advanced analytics to significantly reduce drug development time, from synthesis to approval. Crawling, aggregating, analysing and visualising millions of webpage every day is Innoplexus core business. The core product iPlexusTM has more than 300 terabytes of indexed scientific data across 25 million publications, 365k clinical trial databases, 200 biological databases, all major patent offices (20 million patents), regulatory agencies, patient forums, and so on. This is growing in numbers as we get additional tera-bytes of data is crawled each day. Soon, we will have a 360-degree access to the data, when we will enable searching through all five types of data sources viz. Published data, Unpublished data, Restricted data, Enterprise Data and Third party data.
“Key Google Cloud Platform services like BigQuery analytics based data warehouse help our product in managing an enormous amount of data that the product generates on a daily basis. This expedited the training of information extraction models by 20x and scalability by 8x. Further, architectural enhancements led to increase in number of pages crawled per second from 1,000 to 20,000”, says Gaurav Tripathi, Co-founder and CTO, Innoplexus. This resulted in cost savings by a whopping 80% and increased content capture and processing capability by 20x.”
iPlexus crawls, aggregates and analyses data from a range of formats and structures from multiple regions and providers. All ‘crawled’ data is passed through an information extraction pipeline that converts semi-structured and unstructured sources to a structured format. This is achieved through leveraging of various AI based techniques like natural language programming, computer vision, machine learning and deep learning. All the information extraction models are implemented using TensorFlow and the Keras open source neural network library. These models are then trained using Google Cloud Machine Learning Engine before being deployed. Google Cloud Dataflow is used for batch processing and Google Kubernetes Engine API to run iPlexus applications in containers.
Innoplexus is really looking forward to Google Cloud to take iPlexus platform to the next level in terms of scalability, security and performance.