|
Artificial intelligence (AI) and machine learning (ML) have been helping biopharmaceutical companies overcome some of the challenges associated with drug research and development. This is through streamlining and accelerating the process of identifying the most promising drug candidates for specific target illnesses, according to experts.
It has also been learnt that AI has been enabling the process of enhancement in the R&D procedure by examining the patterns of various illnesses. Besides this, it also ascertains which composite formulations are most appropriate for treating disease symptoms.
According to Nandakumar Kalathil, director, Strategy and Enterprise Business: India LSS, Agilent Technologies, “Today, AI and ML are being used to efficiently clean, aggregate, and organize large amounts of data. Data-driven approaches are helping support research into additional uses of existing drugs or those in development. This also brings hope to rare disease early detection. These developments are also likely to change the way biopharma marketers would approach their work, incorporating AI into the development process to bring integrated solutions that help to accelerate breakthrough innovations.”
Agilent recently announced a strategic partnership with PathAI to deliver innovative AI-powered assay development solutions. Agilent Technologies is a global company that provides innovative scientific instruments, software, and services in areas of life sciences, diagnostics, and chemical analysis among others.
Kalathil further informed that Generative AI can potentially speed up various processes involved in the pharma sector, including accelerating the drug discovery cycle. AI is being increasingly explored in pharmaceutical manufacturing to improve efficiency, productivity, and quality control. Some key areas that can benefit from AI in pharma manufacturing are Process optimization, Predictive maintenance, Supply chain optimization, QC, Regulatory compliance, and Batch size optimization.
“Another highly promising area is ‘Continuous manufacturing’ in Pharma. Continuous manufacturing includes adopting analytical control strategies with off-line, at-line and in-line testing. FDA has cited lower process scale-up risk and heightened material and process understanding as a major reason for continuous manufacturing/s faster times to market and regulatory approval vs. conventional batch submissions. This trend will continue as more filings are submitted to the agency,” Kalathil explained.
One use case of Generative AI could be linked to recommendations for trend analysis in USP<1220>. USP General chapter <1220> is the latest guidelines on Analytical Lifecycle Management; that has been made official May 2022 onwards.
In stage-3 ‘Ongoing Procedure Performance Verification’; this includes both routine monitoring of data linked to the performance of the analytical procedure, and evaluation of the procedure's performance after changes to determine if the analytical procedure continues to be fit for purpose. The use of control charts is a recommended practice for monitoring of procedure performance attributes and control sample results.
The major thrust and implication of AI in India would be cancer diagnosis and its treatment, which is primarily based on biotherapeutics. NITI Aayog is in the advanced stage of launching a programme to develop a national repository of annotated and curated pathology images.
“The lab of the future is a concept built on the foundation of digitized labs. It encompasses smart technological workflow systems that are connected and capable of handling vast amounts of data. Agilent is a leader in digital lab solutions and pivotal in the integration of technology that transforms the way we operate internally and with our customers. CrossLab Connect is one such tool that leverages data-intelligence technologies to increase operational efficiency. It uses advances in IoT and analytical capabilities to enable optimization through lab-wide asset monitoring and business intelligence,” Kalathil informed.
|