Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Current application of conformal prediction in drug discovery
Ahlberg E., Hammar O., Bendtsen C., Carlsson L. Annals of Mathematics and Artificial Intelligence81 (1-2):145-154,2017.Type:Article
Date Reviewed: Dec 15 2017

Conformal prediction (CP) is a general method widely applied in machine learning. In general, it uses previous experience/data to predict unknown data to a prescribed confidence level. In this paper, the authors describe how the CP method is applied in the medical industry, especially in the drug discovery process.

The paper first provides a brief introduction to the pharmaceutical research and lists the disadvantages of the traditional methods for developing drugs. This section helps readers gain a general understanding of current pharmaceutical development by giving specific examples (such as the hERG gene), and also raises the problem of how to overcome the challenges of traditional methods.

In the next section, the authors describe the whole pipeline of the drug discovery process in detail. Basically, there are two major stages: drug discovery and drug development. In the first stage, the focus is to locate the druggable biological target that can be treated by a new drug. To better explain the procedure, the in vitro assay is introduced. After the target is locked, the next stage is drug development. This is the key stage to the success of the drug. According to the authors, “to support the process, models are built to predict the outcome of tests and decisions at different stages.” Among different prediction methods that are applied, the authors focused on the “application and interpretation of conformal prediction in a drug discovery setting.” Next, conformal prediction is introduced, and how it can be applied in the drug development process is carefully described.

In Section 2, the authors explain how the interpretation of prediction works in drug development. Several examples are demonstrated in this section to provide a more straightforward description of the procedure. As a major advantage of the conformal prediction method, it can reduce experimental testing; this is explained at the end of the section.

Recently, machine learning has become a hot topic in computer science and has been widely applied in various fields. In this paper, the authors introduce how conformal prediction has been utilized in modern pharmaceutical research. The applications mentioned in the paper provide a convincing signal that this method indeed has a positive influence on medical research and could become a promising research direction for new drug discovery and development.

Reviewer:  Jun Ma Review #: CR145711 (1802-0108)
Bookmark and Share
 
Learning (I.2.6 )
 
 
Medicine And Science (I.2.1 ... )
 
Would you recommend this review?
yes
no
Other reviews under "Learning": Date
Learning in parallel networks: simulating learning in a probabilistic system
Hinton G. (ed) BYTE 10(4): 265-273, 1985. Type: Article
Nov 1 1985
Macro-operators: a weak method for learning
Korf R. Artificial Intelligence 26(1): 35-77, 1985. Type: Article
Feb 1 1986
Inferring (mal) rules from pupils’ protocols
Sleeman D.  Progress in artificial intelligence (, Orsay, France,391985. Type: Proceedings
Dec 1 1985
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy