AWS Helps Pfizer Accelerate Drug Development and Clinical Manufacturing - Seite 2

AWS is working with Pfizer to develop a prototype solution for detecting abnormal data points in its drug product continuous clinical manufacturing platform for solid, oral-dose medicines. The prototype solution uses Amazon SageMaker (AWS’s service for building, training, and deploying machine learning models quickly in the cloud and at the edge), Amazon Lookout for Equipment, Amazon Lookout for Metrics (AWS’s service for automatically detecting anomalies in metrics and identifying their root cause), and Amazon QuickSight (AWS’s scalable machine learning-powered business intelligence service for the cloud). The machine learning models used in the prototype were able to provide early warnings for alarms with minimal false positives and direct users to the relevant signals. As a result, Pfizer can process data from the equipment and sensors involved in Portable Continuous Miniature and Modular (PCMM) manufacturing to detect anomalies as they occur, predict maintenance needs, and reduce potential equipment downtime.

Pfizer scientists will also collaborate with AWS healthcare and life sciences professionals to explore how researchers in Pfizer’s Pharmaceutical Sciences Small Molecules teams can extract and mine information from legacy documents by leveraging AWS analytics and machine learning services. Pfizer has an extensive collection of documents that contain valuable data from a variety of drug development processes. The documents include data related to synthetic chemistry routes, recipes, analytical tests, method development, formulation composition, clinical manufacturing campaigns, batch records, technology transfer, and many other types of work. Housed within these documents are potentially powerful insights that could point Pfizer researchers in the right direction for developing new drugs or repurposing existing ones—if the researchers can identify and link the right information efficiently. To gain quick, secure access to the right information at the right time, Pfizer’s Pharmaceutical Sciences Small Molecules teams are working with AWS to develop a prototype system that can automatically extract, ingest, and process data from this documentation to help in the design of lab experiments. The prototype system is powered by Amazon Comprehend Medical (AWS’s HIPAA-eligible natural language processing (NLP) service to extract information from unstructured medical text accurately and quickly) and Amazon SageMaker, and uses Amazon Cognito to deliver secure user access control.