|
Artificial intelligence (AI)- based solutions are being increasingly implemented in drug discovery and development to speed up go-to-market for efficacious drugs and vaccines besides optimising costs, stated Chaith Kondragunta, CEO, Aira Matrix.
In pharma manufacturing, AI solutions are finding increasing acceptance in optimizing yields and in meeting regulatory requirements, he added.
Now AI has the potential to provide fast answers to several critical decision points for a pharma company. In almost all cases, judicious application of AI helps companies speed up time to market improve outcomes at different steps in the drug discovery development process or to save investments by providing better measures of risk, he said.
In the early drug discovery phase, deep learning and in-silico modelling methods can help expedite the discovery of new molecules. AI-based image analysis solutions can help improve efficacy and safety assessment studies as well as clinical trials. However, these networks have not been adequately exploited in the pre-clinical drug development phase. This is the space that AIRA Matrix has expertise and solutions, Kondragunta told Pharmabiz.
A suite of deep learning-based solutions are developed and being used global pharma, throughout the drug development process to help improve productivity, and profit across the workflow. These solutions comprise modules for predictive toxicology, in-vivo disease model quantification, tissue triaging and abnormality detection.
Specifically for drug manufacturing processes there is a need to abide by stringent clean room regulations, to avoid contamination. We aid this process by providing deep learning-based solutions for the monitoring and quantification of contaminants, in a traceable, customisable workflow with auditable results and records, imperative for regulated settings. This helps organisations abide with regulatory requirements, resulting in optimised approval processes, said Kondragunta.
In R&D, the risk road map and failure point predictions call to reduce the time and resources needed in this early phase of drug development. Here the Aira Matrix models analyse data from multiple modalities to help with the crucial go/no-go decisions in the selection of the safest drug molecule and predict potential toxicity. In addition, it reduces need for animal testing.
The Mumbai-based company’s in-vivo Disease Model Quantification improves the evaluation of histopathological parameters developed to assess efficacy of a drug molecule against a disease process, with significant reduction in the turn-around time. For instance, in pulmonary fibrosis disease models, it quantifies multiple histopathological parameters in the diseased lung and control lung tissues for the accurate assessment and comparison of features between these two groups.
In the case of Tissue Triaging and Abnormality Detection module, it improves the efficiency of workflows in pre-clinical toxicologic pathology studies, crucial to evaluate the toxic effects of new drug molecules. Pathologists can screen and analyse thousands of tissue images fast with evidence based, and reproducible study assessment results. This reduced the study reporting cycle from a few months to a few weeks, said Kondragunta.
|