Dataset Information

Development of Supervised Learning Predictive Models for Highly Non-linear Biological, Biomedical, and General Datasets.

ABSTRACT: In highly non-linear datasets, attributes or features do not allow readily finding visual patterns for identifying common underlying behaviors. Therefore, it is not possible to achieve classification or regression using linear or mildly non-linear hyperspace partition functions. Hence, supervised learning models based on the application of most existing algorithms are limited, and their performance metrics are low. Linear transformations of variables, such as principal components analysis, cannot avoid the problem, and even models based on artificial neural networks and deep learning are unable to improve the metrics. Sometimes, even when features allow classification or regression in reported cases, performance metrics of supervised learning algorithms remain unsatisfyingly low. This problem is recurrent in many areas of study as, per example, the clinical, biotechnological, and protein engineering areas, where many of the attributes are correlated in an unknown and very non-linear fashion or are categorical and difficult to relate to a target response variable. In such areas, being able to create predictive models would dramatically impact the quality of their outcomes, generating an immediate added value for both the scientific and general public. In this manuscript, we present RV-Clustering, a library of unsupervised learning algorithms, and a new methodology designed to find optimum partitions within highly non-linear datasets that allow deconvoluting variables and notoriously improving performance metrics in supervised learning classification or regression models. The partitions obtained are statistically cross-validated, ensuring correct representativity and no over-fitting. We have successfully tested RV-Clustering in several highly non-linear datasets with different origins. The approach herein proposed has generated classification and regression models with high-performance metrics, which further supports its ability to generate predictive models for highly non-linear datasets. Advantageously, the method does not require significant human input, which guarantees a higher usability in the biological, biomedical, and protein engineering community with no specific knowledge in the machine learning area.

SUBMITTER: Medina-Ortiz D

PROVIDER: S-EPMC7031350 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of Supervised Learning Predictive Models for Highly Non-linear Biological, Biomedical, and General Datasets.

Medina-Ortiz David D Contreras Sebastián S Quiroz Cristofer C Olivera-Nappa Álvaro Á

Frontiers in molecular biosciences 20200213

In highly non-linear datasets, attributes or features do not allow readily finding visual patterns for identifying common underlying behaviors. Therefore, it is not possible to achieve classification or regression using linear or mildly non-linear hyperspace partition functions. Hence, supervised learning models based on the application of most existing algorithms are limited, and their performance metrics are low. Linear transformations of variables, such as principal components analysis, canno ...[more]

PMID: 32118039

Similar Datasets

Project description:BackgroundExogenous short interfering RNAs (siRNAs) induce a gene knockdown effect in cells by interacting with naturally occurring RNA processing machinery. However not all siRNAs induce this effect equally. Several heterogeneous kinds of machine learning techniques and feature sets have been applied to modeling siRNAs and their abilities to induce knockdown. There is some growing agreement to which techniques produce maximally predictive models and yet there is little consensus for methods to compare among predictive models. Also, there are few comparative studies that address what the effect of choosing learning technique, feature set or cross validation approach has on finding and discriminating among predictive models.Principal findingsThree learning techniques were used to develop predictive models for effective siRNA sequences including Artificial Neural Networks (ANNs), General Linear Models (GLMs) and Support Vector Machines (SVMs). Five feature mapping methods were also used to generate models of siRNA activities. The 2 factors of learning technique and feature mapping were evaluated by complete 3x5 factorial ANOVA. Overall, both learning techniques and feature mapping contributed significantly to the observed variance in predictive models, but to differing degrees for precision and accuracy as well as across different kinds and levels of model cross-validation.ConclusionsThe methods presented here provide a robust statistical framework to compare among models developed under distinct learning techniques and feature sets for siRNAs. Further comparisons among current or future modeling approaches should apply these or other suitable statistically equivalent methods to critically evaluate the performance of proposed models. ANN and GLM techniques tend to be more sensitive to the inclusion of noisy features, but the SVM technique is more robust under large numbers of features for measures of model precision and accuracy. Features found to result in maximally predictive models are not consistent across learning techniques, suggesting care should be taken in the interpretation of feature relevance. In the models developed here, there are statistically differentiable combinations of learning techniques and feature mapping methods where the SVM technique under a specific combination of features significantly outperforms all the best combinations of features within the ANN and GLM techniques.

Project description:UnlabelledBackgroundExperimental screening of chemical compounds for biological activity is a time consuming and expensive practice. In silico predictive models permit inexpensive, rapid "virtual screening" to prioritize selection of compounds for experimental testing. Both experimental and in silico screening can be used to test compounds for desirable or undesirable properties. Prior work on prediction of mutagenicity has primarily involved identification of toxicophores rather than whole-molecule predictive models. In this work, we examined a range of in silico predictive classification models for prediction of mutagenic properties of compounds, including methods such as J48 and SMO which have not previously been widely applied in cheminformatics.ResultsThe Bursi mutagenicity data set containing 4337 compounds (Set 1) and a Benchmark data set of 6512 compounds (Set 2) were taken as input data set in this work. A third data set (Set 3) was prepared by joining up the previous two sets. Classification algorithms including Naïve Bayes, Random Forest, J48 and SMO with 10 fold cross-validation and default parameters were used for model generation on these data sets. Models built using the combined performed better than those developed from the Benchmark data set. Significantly, Random Forest outperformed other classifiers for all the data sets, especially for Set 3 with 89.27% accuracy, 89% precision and ROC of 95.3%. To validate the developed models two external data sets, AID1189 and AID1194, with mutagenicity data were tested showing 62% accuracy with 67% precision and 65% ROC area and 91% accuracy, 91% precision with 96.3% ROC area respectively. A Random Forest model was used on approved drugs from DrugBank and metabolites from the Zinc Database with True Positives rate almost 85% showing the robustness of the model.ConclusionWe have created a new mutagenicity benchmark data set with around 8,000 compounds. Our work shows that highly accurate predictive mutagenicity models can be built using machine learning methods based on chemical descriptors and trained using this set, and these models provide a complement to toxicophores based methods. Further, our work supports other recent literature in showing that Random Forest models generally outperform other comparable machine learning methods for this kind of application.

Project description:Proper expression of the genes plays a vital role in the function of an organism. Recent advancements in DNA microarray technology allow for monitoring the expression level of thousands of genes. One of the important tasks in this context is to understand the underlying mechanisms of gene regulation. Recently, researchers have focused on identifying local DNA elements, or motifs to infer the relation between the expression and the nucleotide sequence of the gene. This study proposes a novel data adaptive representation approach for supervised learning to predict the response associated with the biological sequences. Biological sequences such as DNA and protein are a class of categorical sequences. In machine learning, categorical sequences are generally mapped to a lower dimensional representation for learning tasks to avoid problems with high dimensionality. The proposed method, namely SW-RF (sliding window-random forest), is a feature-based approach requiring two main steps to learn a representation for categorical sequences. In the first step, each sequence is represented by overlapping subsequences of constant length. Then a tree-based learner on this representation is trained to obtain a bag-of-words like representation which is the frequency of subsequences on the terminal nodes of the tree for each sequence. After representation learning, any classifier can be trained on the learned representation. A lasso logistic regression is trained on the learned representation to facilitate the identification of important patterns for the classification task. Our experiments show that proposed approach provides significantly better results in terms of accuracy on both synthetic data and DNA promoter sequence data. Moreover, a common problem for microarray datasets, namely missing values, is handled efficiently by the tree learners in SW-RF. Although the focus of this paper is on biological sequences, SW-RF is flexible in handling any categorical sequence data from different applications.

Dataset Information

Development of Supervised Learning Predictive Models for Highly Non-linear Biological, Biomedical, and General Datasets.

Publications

Development of Supervised Learning Predictive Models for Highly Non-linear Biological, Biomedical, and General Datasets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets