As well as taking time and costing money, only a small proportion of drugs are successful, with the figure sometimes being as low as 5 percent. Drug development includes the need for pre-clinical research on microorganisms and animals, plus filing for regulatory status, and it may also include the processes of obtaining regulatory approval with a new drug application to market the drug. Often there is unfamiliarity and other stumbling blocks linked with the regulatory process.
Other challenges include the issue of unknown pathophysiology for many nervous system disorders which means that drug target identification is challenging. Furthermore, many animal models often cannot recapitulate an entire disorder or disease. To add to this, there are problems linked to heterogeneity of the patient population.
According to Dr. Omar Gadir, of Iteru Systems, artificial intelligence offers a means to streamline drug development and to reduce the time it takes for a new drug to come to the market.
The main focus of the Iteru Systems review is with cancer drug discovery. While there have been advances with targeted small molecules the success rate remains haphazard. This is where artificial intelligence has the potential of assisting.
Drug development is partially dependent upon biomedical data. Such data is invariably highly complex, plus there are complex interactions between hundreds of biological entities. Iteru Systems develops platforms to assist with examining biomedical data.
Given there is no open source software available for the types of analysis required, proprietary algorithms are required. For this, mechanisms to extract data based on the objective of analysis are required together with the selection of the necessary biological entities and features related to the objective of analysis.
From this, AI can assist the user with interrogating the data to clarify ambiguity or verify the relevance of entities, helping the scientists on a faster path towards drug discovery.
