↓ Skip to main content

Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set

Overview of attention for article published in Journal of Cheminformatics, August 2017
Altmetric Badge

About this Attention Score

  • In the top 5% of all research outputs scored by Altmetric
  • Among the highest-scoring outputs from this source (#28 of 604)
  • High Attention Score compared to outputs of the same age (92nd percentile)

Mentioned by

blogs
2 blogs
twitter
34 tweeters

Citations

dimensions_citation
65 Dimensions

Readers on

mendeley
232 Mendeley
citeulike
2 CiteULike
You are seeing a free-to-access but limited selection of the activity Altmetric has collected about this research output. Click here to find out more.
Title
Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set
Published in
Journal of Cheminformatics, August 2017
DOI 10.1186/s13321-017-0232-0
Pubmed ID
Authors

Eelke B. Lenselink, Niels ten Dijke, Brandon Bongers, George Papadatos, Herman W. T. van Vlijmen, Wojtek Kowalczyk, Adriaan P. IJzerman, Gerard J. P. van Westen

Abstract

The increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics. In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naïve Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution. Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method ('DNN_PCM') performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi-task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized 'DNN_PCM'). Here, a standardized set to test and evaluate different machine learning algorithms in the context of multi-task learning is offered by providing the data and the protocols. Graphical Abstract .

Twitter Demographics

The data shown below were collected from the profiles of 34 tweeters who shared this research output. Click here to find out more about how the information was compiled.

Mendeley readers

The data shown below were compiled from readership statistics for 232 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Unknown 232 100%

Demographic breakdown

Readers by professional status Count As %
Researcher 57 25%
Student > Ph. D. Student 51 22%
Student > Master 33 14%
Student > Bachelor 23 10%
Other 14 6%
Other 26 11%
Unknown 28 12%
Readers by discipline Count As %
Chemistry 58 25%
Computer Science 38 16%
Biochemistry, Genetics and Molecular Biology 27 12%
Pharmacology, Toxicology and Pharmaceutical Science 25 11%
Agricultural and Biological Sciences 19 8%
Other 31 13%
Unknown 34 15%

Attention Score in Context

This research output has an Altmetric Attention Score of 33. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 14 May 2019.
All research outputs
#606,928
of 15,050,853 outputs
Outputs from Journal of Cheminformatics
#28
of 604 outputs
Outputs of similar age
#19,697
of 270,296 outputs
Outputs of similar age from Journal of Cheminformatics
#1
of 1 outputs
Altmetric has tracked 15,050,853 research outputs across all sources so far. Compared to these this one has done particularly well and is in the 95th percentile: it's in the top 5% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 604 research outputs from this source. They typically receive more attention than average, with a mean Attention Score of 9.6. This one has done particularly well, scoring higher than 95% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 270,296 tracked outputs that were published within six weeks on either side of this one in any source. This one has done particularly well, scoring higher than 92% of its contemporaries.
We're also able to compare this research output to 1 others from the same source and published within six weeks on either side of this one. This one has scored higher than all of them