Search: onr:"swepub:oai:research.chalmers.se:fe2406fc-145d-47be-9691-26c7eb358cda" >
Blinded Predictions...
Blinded Predictions and Post Hoc Analysis of the Second Solubility Challenge Data: Exploring Training Data and Feature Set Selection for Machine and Deep Learning Models
-
- Conn, Jonathan G.M. (author)
- University of Strathclyde
-
- Carter, James W. (author)
- University of Strathclyde
-
- Conn, Justin J.A. (author)
- University of Strathclyde
-
show more...
-
- Subramanian, Vigneshwari (author)
- AstraZeneca AB
-
- Baxter, Andrew (author)
- GlaxoSmithKline
-
- Engkvist, Ola, 1967 (author)
- Chalmers tekniska högskola,Chalmers University of Technology,AstraZeneca AB
-
- Llinas, Antonio (author)
- AstraZeneca AB
-
- Ratkova, Ekaterina L. (author)
- AstraZeneca AB
-
- Pickett, Stephen D. (author)
- GlaxoSmithKline
-
Mcdonagh, James L. (author)
-
- Palmer, David S. (author)
- University of Strathclyde
-
show less...
-
(creator_code:org_t)
- 2023-02-09
- 2023
- English.
-
In: Journal of Chemical Information and Modeling. - : American Chemical Society (ACS). - 1549-960X .- 1549-9596. ; 63:4, s. 1099-1113
- Related links:
-
https://research.cha... (primary) (free)
-
show more...
-
https://research.cha...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Accurate methods to predict solubility from molecular structure are highly sought after in the chemical sciences. To assess the state of the art, the American Chemical Society organized a "Second Solubility Challenge"in 2019, in which competitors were invited to submit blinded predictions of the solubilities of 132 drug-like molecules. In the first part of this article, we describe the development of two models that were submitted to the Blind Challenge in 2019 but which have not previously been reported. These models were based on computationally inexpensive molecular descriptors and traditional machine learning algorithms and were trained on a relatively small data set of 300 molecules. In the second part of the article, to test the hypothesis that predictions would improve with more advanced algorithms and higher volumes of training data, we compare these original predictions with those made after the deadline using deep learning models trained on larger solubility data sets consisting of 2999 and 5697 molecules. The results show that there are several algorithms that are able to obtain near state-of-the-art performance on the solubility challenge data sets, with the best model, a graph convolutional neural network, resulting in an RMSE of 0.86 log units. Critical analysis of the models reveals systematic differences between the performance of models using certain feature sets and training data sets. The results suggest that careful selection of high quality training data from relevant regions of chemical space is critical for prediction accuracy but that other methodological issues remain problematic for machine learning solubility models, such as the difficulty in modeling complex chemical spaces from sparse training data sets.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Annan data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Other Computer and Information Science (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Bioinformatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Bioinformatics (hsv//eng)
- NATURVETENSKAP -- Biologi -- Bioinformatik och systembiologi (hsv//swe)
- NATURAL SCIENCES -- Biological Sciences -- Bioinformatics and Systems Biology (hsv//eng)
Keyword
- Learning algorithms
- Convolutional neural networks
- Deep learning
- Solubility prediction
- Molecules
Publication and Content Type
- art (subject category)
- ref (subject category)
Find in a library
To the university's database
- By the author/editor
-
Conn, Jonathan G ...
-
Carter, James W.
-
Conn, Justin J.A ...
-
Subramanian, Vig ...
-
Baxter, Andrew
-
Engkvist, Ola, 1 ...
-
show more...
-
Llinas, Antonio
-
Ratkova, Ekateri ...
-
Pickett, Stephen ...
-
Mcdonagh, James ...
-
Palmer, David S.
-
show less...
- About the subject
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Computer and Inf ...
-
and Other Computer a ...
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Computer and Inf ...
-
and Bioinformatics
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Biological Scien ...
-
and Bioinformatics a ...
- Articles in the publication
-
Journal of Chemi ...
- By the university
-
Chalmers University of Technology