A recent paper published in the journal “Intelligent Medicine” article discusses various aspects of using AI and machine learning in the pharmaceutical industry for drug discovery and development.
Table of Contents
Results
The results section of the article presents specific findings related to the application of AI and machine learning in drug discovery and development. Two notable results are as follows:
1. Drug Screening: The article discusses the use of a machine learning approach to find an inhibitor molecule for a specific protein called DDR1. This application involves the use of neural networks and is described as accurate.
2. Drug Design: Another application discussed is the use of artificial neural networks and deep learning to predict interactions between drugs and their targets. This approach is highly accurate. Additionally, the article mentions the integration of neural networks into a neural computer for designing new small organic molecules, and this method is also highly accurate.
Challenges
Despite the progress made in implementing AI and machine learning algorithms in the pharmaceutical industry, the article highlights several challenges related to their integration into the drug discovery process and the broader pharmaceutical field. One major challenge is inefficient data integration caused by the diversity that exists between datasets. These datasets can include raw data, processed data, metadata, or candidate data, and collating them for efficient analysis currently lacks a standardized method. The challenges of data integration are likely impeding the full potential of AI and machine learning in drug discovery.
