Dataset Information

The influence of the inactives subset generation on the performance of machine learning methods.

ABSTRACT:

Background

A growing popularity of machine learning methods application in virtual screening, in both classification and regression tasks, can be observed in the past few years. However, their effectiveness is strongly dependent on many different factors.

Results

In this study, the influence of the way of forming the set of inactives on the classification process was examined: random and diverse selection from the ZINC database, MDDR database and libraries generated according to the DUD methodology. All learning methods were tested in two modes: using one test set, the same for each method of inactive molecules generation and using test sets with inactives prepared in an analogous way as for training. The experiments were carried out for 5 different protein targets, 3 fingerprints for molecules representation and 7 classification algorithms with varying parameters. It appeared that the process of inactive set formation had a substantial impact on the machine learning methods performance.

Conclusions

The level of chemical space limitation determined the ability of tested classifiers to select potentially active molecules in virtual screening tasks, as for example DUDs (widely applied in docking experiments) did not provide proper selection of active molecules from databases with diverse structures. The study clearly showed that inactive compounds forming training set should be representative to the highest possible extent for libraries that undergo screening.

SUBMITTER: Smusz S

PROVIDER: S-EPMC3626618 | biostudies-literature | 2013 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The influence of the inactives subset generation on the performance of machine learning methods.

Smusz Sabina S Kurczab Rafał R Bojarski Andrzej J AJ

Journal of cheminformatics 20130405 1

<h4>Background</h4>A growing popularity of machine learning methods application in virtual screening, in both classification and regression tasks, can be observed in the past few years. However, their effectiveness is strongly dependent on many different factors.<h4>Results</h4>In this study, the influence of the way of forming the set of inactives on the classification process was examined: random and diverse selection from the ZINC database, MDDR database and libraries generated according to t ...[more]

PMID: 23561266

Similar Datasets

Project description:Human movements are characterized by highly non-linear and multi-dimensional interactions within the motor system. Therefore, the future of human movement analysis requires procedures that enhance the classification of movement patterns into relevant groups and support practitioners in their decisions. In this regard, the use of data-driven techniques seems to be particularly suitable to generate classification models. Recently, an increasing emphasis on machine-learning applications has led to a significant contribution, e.g., in increasing the classification performance. In order to ensure the generalizability of the machine-learning models, different data preprocessing steps are usually carried out to process the measured raw data before the classifications. In the past, various methods have been used for each of these preprocessing steps. However, there are hardly any standard procedures or rather systematic comparisons of these different methods and their impact on the classification performance. Therefore, the aim of this analysis is to compare different combinations of commonly applied data preprocessing steps and test their effects on the classification performance of gait patterns. A publicly available dataset on intra-individual changes of gait patterns was used for this analysis. Forty-two healthy participants performed 6 sessions of 15 gait trials for 1 day. For each trial, two force plates recorded the three-dimensional ground reaction forces (GRFs). The data was preprocessed with the following steps: GRF filtering, time derivative, time normalization, data reduction, weight normalization and data scaling. Subsequently, combinations of all methods from each preprocessing step were analyzed by comparing their prediction performance in a six-session classification using Support Vector Machines, Random Forest Classifiers, Multi-Layer Perceptrons, and Convolutional Neural Networks. The results indicate that filtering GRF data and a supervised data reduction (e.g., using Principal Components Analysis) lead to increased prediction performance of the machine-learning classifiers. Interestingly, the weight normalization and the number of data points (above a certain minimum) in the time normalization does not have a substantial effect. In conclusion, the present results provide first domain-specific recommendations for commonly applied data preprocessing methods and might help to build more comparable and more robust classification models based on machine learning that are suitable for a practical application.

Project description:The analysis of large genomic data is hampered by issues such as a small number of observations and a large number of predictive variables (commonly known as "large P small N"), high dimensionality or highly correlated data structures. Machine learning methods are renowned for dealing with these problems. To date machine learning methods have been applied in Genome-Wide Association Studies for identification of candidate genes, epistasis detection, gene network pathway analyses and genomic prediction of phenotypic values. However, the utility of two machine learning methods, Gradient Boosting Machine (GBM) and Extreme Gradient Boosting Method (XgBoost), in identifying a subset of SNP makers for genomic prediction of breeding values has never been explored before. In this study, using 38,082 SNP markers and body weight phenotypes from 2,093 Brahman cattle (1,097 bulls as a discovery population and 996 cows as a validation population), we examined the efficiency of three machine learning methods, namely Random Forests (RF), GBM and XgBoost, in (a) the identification of top 400, 1,000, and 3,000 ranked SNPs; (b) using the subsets of SNPs to construct genomic relationship matrices (GRMs) for the estimation of genomic breeding values (GEBVs). For comparison purposes, we also calculated the GEBVs from (1) 400, 1,000, and 3,000 SNPs that were randomly selected and evenly spaced across the genome, and (2) from all the SNPs. We found that RF and especially GBM are efficient methods in identifying a subset of SNPs with direct links to candidate genes affecting the growth trait. In comparison to the estimate of prediction accuracy of GEBVs from using all SNPs (0.43), the 3,000 top SNPs identified by RF (0.42) and GBM (0.46) had similar values to those of the whole SNP panel. The performance of the subsets of SNPs from RF and GBM was substantially better than that of evenly spaced subsets across the genome (0.18-0.29). Of the three methods, RF and GBM consistently outperformed the XgBoost in genomic prediction accuracy.

Project description:Background: Microglia plays complex and crucial roles in multiple sclerosis (MS). This study aimed to explore the biological significance of microglia-associated genes in experimental autoimmune encephalomyelitis (EAE) . Methods: Differentially expressed genes (DEGs) were screened with six machine learning (ML) methods, which were also utilized to validate the microglia-associated DEGs in three public databases. ceRNA and Protein–protein interaction (PPI) network analyses were utilized to identify the interaction of the 6 novel biomarkers with other molecules. Then, CIBERSORT and single-sample gene set enrichment analysis (ssGSEA) were employed to quantify the relative abundance of each immune cell infiltration, respectively. qRT-PCR was performed to test the expression of key DEGs in murine models. Results: A total of 247 DEmRNA, 499 DElncRNAs and 269 DEcircRNAs were identified. With screening strategy of five ML algorithms, 6 DEmRNAs were obtained including NGP, HIST1H2BJ, PBLD1, MBLN3, CD180 and F10. Then the 6 DEmRNAs were used as a multigene signature to construct models to differentiate EAE from normal microglia, and AUC value for each model was greater than 0.8. The diagnostic value of these 6 DEmRNAs were identified and further verified by qRT-PCR. Then, differential expression for five out of these 6 DEmRNAs, namely NGP, HIST1H2BJ, PBLD1, MBLN3, and F10 were confirmed. Using PPI analysis, DEmRNAs frequently interacting with transcription factors (TFs), potential drugs and RBPs were identified. With immune cell infiltration analyses, we found EAE microglia presented high levels of immune infiltration, especially Nature Killer (NK) cells and CD8+ T cells. We also reported circRNA (circRNA_00638) was predicted to bind to 76 RBPs. Conclusions: We identified and validated 6 novel microglia related genes and developed a multigene signature with ML methods to confirm their ability to accurately diagnose and characterize biological alterations in EAE microglia. The six key DEmRNAs might also be latent targets for immunoregulatory therapy.

Dataset Information

The influence of the inactives subset generation on the performance of machine learning methods.

Background

Results

Conclusions

Publications

The influence of the inactives subset generation on the performance of machine learning methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets