NeuralLasso: Neural Networks Meet Lasso in Genomic Prediction.
Ontology highlight
ABSTRACT:
SUBMITTER: Mathew B
PROVIDER: S-EPMC9100816 | biostudies-literature | 2022
REPOSITORIES: biostudies-literature
Publications
NeuralLasso: Neural Networks Meet Lasso in Genomic Prediction.
Mathew Boby B Hauptmann Andreas A Léon Jens J Sillanpää Mikko J MJ
Frontiers in plant science 20220429
Prediction of complex traits based on genome-wide marker information is of central importance for both animal and plant breeding. Numerous models have been proposed for the prediction of complex traits and still considerable effort has been given to improve the prediction accuracy of these models, because various genetics factors like additive, dominance and epistasis effects can influence of the prediction accuracy of such models. Recently machine learning (ML) methods have been widely applied ...[more]
Similar Datasets
Project description:The prediction of breeding values and phenotypes is of central importance for both livestock and crop breeding. In this study, we analyze the use of artificial neural networks (ANN) and, in particular, local convolutional neural networks (LCNN) for genomic prediction, as a region-specific filter corresponds much better with our prior genetic knowledge on the genetic architecture of traits than traditional convolutional neural networks. Model performances are evaluated on a simulated maize data panel (n = 10,000; p = 34,595) and real Arabidopsis data (n = 2,039; p = 180,000) for a variety of traits based on their predictive ability. The baseline LCNN, containing one local convolutional layer (kernel size: 10) and two fully connected layers with 64 nodes each, is outperforming commonly proposed ANNs (multi layer perceptrons and convolutional neural networks) for basically all considered traits. For traits with high heritability and large training population as present in the simulated data, LCNN are even outperforming state-of-the-art methods like genomic best linear unbiased prediction (GBLUP), Bayesian models and extended GBLUP, indicated by an increase in predictive ability of up to 24%. However, for small training populations, these state-of-the-art methods outperform all considered ANNs. Nevertheless, the LCNN still outperforms all other considered ANNs by around 10%. Minor improvements to the tested baseline network architecture of the LCNN were obtained by increasing the kernel size and of reducing the stride, whereas the number of subsequent fully connected layers and their node sizes had neglectable impact. Although gains in predictive ability were obtained for large scale data sets by using LCNNs, the practical use of ANNs comes with additional problems, such as the need of genotyping all considered individuals, the lack of estimation of heritability and reliability. Furthermore, breeding values are additive by design, whereas ANN-based estimates are not. However, ANNs also comes with new opportunities, as networks can easily be extended to account for additional inputs (omics, weather etc.) and outputs (multi-trait models), and computing time increases linearly with the number of individuals. With advances in high-throughput phenotyping and cheaper genotyping, ANNs can become a valid alternative for genomic prediction.
| S-EPMC7689358 | biostudies-literature
Project description:In genomics, use of deep learning (DL) is rapidly growing and DL has successfully demonstrated its ability to uncover complex relationships in large biological and biomedical data sets. With the development of high-throughput sequencing techniques, genomic markers can now be allocated to large sections of a genome. By analyzing allele sharing between individuals, one may calculate realized genomic relationships from single-nucleotide polymorphisms (SNPs) data rather than relying on known pedigree relationships under polygenic model. The traditional approaches in genome-wide prediction (GWP) of quantitative phenotypes utilize genomic relationships in fixed global covariance modeling, possibly with some nonlinear kernel mapping (for example Gaussian processes). On the other hand, the DL approaches proposed so far for GWP fail to take into account the non-Euclidean graph structure of relationships between individuals over several generations. In this paper, we propose one global convolutional neural network (GCN) and one local sub-sampling architecture (GCN-RS) that are specifically designed to perform regression analysis based on genomic relationship information. A GCN is tailored to non-Euclidean spaces and consists of several layers of graph convolutions. The GCN-RS architecture is designed to further improve the GCN's performance by sub-sampling the graph to reduce the dimensionality of the input data. Through these graph convolutional layers, the GCN maps input genomic markers to their quantitative phenotype values. The graphs are constructed using an iterative nearest neighbor approach. Comparisons show that the GCN-RS outperforms the popular Genomic Best Linear Unbiased Predictor method on one simulated and three real datasets from wheat, mice and pig with a predictive improvement of 4.4% to 49.4% in terms of test mean squared error. This indicates that GCN-RS is a promising tool for genomic predictions in plants and animals. Furthermore, GCN-RS is computationally efficient, making it a viable option for large-scale applications.
| S-EPMC11540326 | biostudies-literature
Project description:Genomic wide selection (GWS) is one contributions of molecular genetics to breeding. Machine learning (ML) and artificial neural networks (ANN) methods are non-parameterized and can develop more accurate and parsimonious models for GWS analysis. Multivariate Adaptive Regression Splines (MARS) is considered one of the most flexible ML methods, automatically modeling nonlinearities and interactions of the predictor variables. This study aimed to evaluate and compare methods based on ANN, ML, including MARS, and G-BLUP through GWS. An F2 population formed by 1000 individuals and genotyped for 4010 SNP markers and twelve traits from a model considering epistatic effect, with QTL numbers ranging from eight to 480 and heritability ( h2 ) of 0.3, 0.5 or 0.8 were simulated. Variation in heritability and number of QTL impacts the performance of methods. About quantitative traits (40, 80, 120, 240, and 480 QTLs) was observed highest R2 to Radial Base Network (RBF) and G-BLUP, followed by Random Forest (RF), Bagging (BA), and Boosting (BO). RF and BA also showed better results for traits to h2 of 0.3 with R2 values 16.51% and 16.30%, respectively, while MARS methods showed better results for oligogenic traits with R2 values ranging from 39,12 % to 43,20 % in h2 of 0.5 and from 59.92% to 78,56% in h2 of 0.8. Non-additive MARS methods also showed high R2 for traits with high heritability and 240 QTLs or more. ANN and ML methods are powerful tools to predict genetic values in traits with epistatic effect, for different degrees of heritability and QTL numbers.
| S-EPMC9547190 | biostudies-literature
Project description:Alzheimer's disease (AD) is an illness that affects the nervous system, leading to a loss in cognitive and logical abilities. Gene regulatory expressions, which are the complex language exhibited by DNA, serve several functionalities, including the physical and biological life cycle processes in the human body. The gene expression sequence affects the pathology experienced by an individual, its longevity, and potential for a cure. The transcription factors, from DNA to RNA conversion, and the binding process determine the gene expression, which varies for every human organ and disease. This study proposes Deep convolutional neural network model that reads the gene regulatory expression sequence through various convolutional layers encoded to detect positive spikes in transcription factors. This results in the prediction of disease conversion probability from mild cognitive impairment to AD which is the key-requisite for affected geriatric cohorts.
| S-EPMC10977432 | biostudies-literature
Project description:Prediction of long-term survival in patients with invasive intraductal papillary mucinous neoplasm (IPMN) of the pancreas may aid in patient assessment, risk stratification and personalization of treatment. This study aimed to investigate the predictive ability of artificial neural networks (ANN) and LASSO regression in terms of 5-year disease-specific survival. ANN work in a non-linear fashion, having a potential advantage in analysis of variables with complex correlations compared to regression models. LASSO is a type of regression analysis facilitating variable selection and regularization. A total of 440 patients undergoing surgical treatment for invasive IPMN of the pancreas registered in the Surveillance, Epidemiology and End Results (SEER) database between 2004 and 2016 were analyzed. The dataset was prior to analysis randomly split into a modelling and test set (7:3). The accuracy, precision and F1 score for predicting mortality were 0.82, 0.83 and 0.89, respectively for ANN with variable selection compared to 0.79, 0.85 and 0.87, respectively for the LASSO-model. ANN using all variables showed similar accuracy, precision and F1 score of 0.81, 0.85 and 0.88, respectively compared to a logistic regression analysis. McNemar´s test showed no statistical difference between the models. The models showed high and similar performance with regard to accuracy and precision for predicting 5-year survival status.
| S-EPMC7993879 | biostudies-literature
Project description:BackgroundBiologically annotated neural networks (BANNs) are feedforward Bayesian neural network models that utilize partially connected architectures based on SNP-set annotations. As an interpretable neural network, BANNs model SNP and SNP-set effects in their input and hidden layers, respectively. Furthermore, the weights and connections of the network are regarded as random variables with prior distributions reflecting the manifestation of genetic effects at various genomic scales. However, its application in genomic prediction has yet to be explored.ResultsThis study extended the BANNs framework to the area of genomic selection and explored the optimal SNP-set partitioning strategies by using dairy cattle datasets. The SNP-sets were partitioned based on two strategies-gene annotations and 100 kb windows, denoted as BANN_gene and BANN_100kb, respectively. The BANNs model was compared with GBLUP, random forest (RF), BayesB and BayesCπ through five replicates of five-fold cross-validation using genotypic and phenotypic data on milk production traits, type traits, and one health trait of 6,558, 6,210 and 5,962 Chinese Holsteins, respectively. Results showed that the BANNs framework achieves higher genomic prediction accuracy compared to GBLUP, RF and Bayesian methods. Specifically, the BANN_100kb demonstrated superior accuracy and the BANN_gene exhibited generally suboptimal accuracy compared to GBLUP, RF, BayesB and BayesCπ across all traits. The average accuracy improvements of BANN_100kb over GBLUP, RF, BayesB and BayesCπ were 4.86%, 3.95%, 3.84% and 1.92%, and the accuracy of BANN_gene was improved by 3.75%, 2.86%, 2.73% and 0.85% compared to GBLUP, RF, BayesB and BayesCπ, respectively across all seven traits. Meanwhile, both BANN_100kb and BANN_gene yielded lower overall mean square error values than GBLUP, RF and Bayesian methods.ConclusionOur findings demonstrated that the BANNs framework performed better than traditional genomic prediction methods in our tested scenarios, and might serve as a promising alternative approach for genomic prediction in dairy cattle.
| S-EPMC11215832 | biostudies-literature
Project description:BackgroundThe accurate identification of the exon/intron boundaries is critical for the correct annotation of genes with multiple exons. Donor and acceptor splice sites (SS) demarcate these boundaries. Therefore, deriving accurate computational models to predict the SS are useful for functional annotation of genes and genomes, and for finding alternative SS associated with different diseases. Although various models have been proposed for the in silico prediction of SS, improving their accuracy is required for reliable annotation. Moreover, models are often derived and tested using the same genome, providing no evidence of broad application, i.e. to other poorly studied genomes.ResultsWith this in mind, we developed the Splice2Deep models for SS detection. Each model is an ensemble of deep convolutional neural networks. We evaluated the performance of the models based on the ability to detect SS in Homo sapiens, Oryza sativa japonica, Arabidopsis thaliana, Drosophila melanogaster, and Caenorhabditis elegans. Results demonstrate that the models efficiently detect SS in other organisms not considered during the training of the models. Compared to the state-of-the-art tools, Splice2Deep models achieved significantly reduced average error rates of 41.97% and 28.51% for acceptor and donor SS, respectively. Moreover, the Splice2Deep cross-organism validation demonstrates that models correctly identify conserved genomic elements enabling annotation of SS in new genomes by choosing the taxonomically closest model.ConclusionsThe results of our study demonstrated that Splice2Deep both achieved a considerably reduced error rate compared to other state-of-the-art models and the ability to accurately recognize SS in other organisms for which the model was not trained, enabling annotation of poorly studied or newly sequenced genomes. Splice2Deep models are implemented in Python using Keras API; the models and the data are available at https://github.com/SomayahAlbaradei/Splice_Deep.git.
| S-EPMC7285987 | biostudies-literature
Project description:BackgroundThe experimental determination of a bacteriophage host is a laborious procedure. Thus, there is a pressing need for reliable computational predictions of bacteriophage hosts.Materials and methodsWe developed the program vHULK for phage host prediction based on 9504 phage genome features, which consider alignment significance scores between predicted proteins and a curated database of viral protein families. The features were fed to a neural network, and two models were trained to predict 77 host genera and 118 host species.ResultsIn controlled random test sets with 90% redundancy reduction in terms of protein similarity, vHULK obtained on average 83% precision and 79% recall at the genus level, and 71% precision and 67% recall at the species level. The performance of vHULK was compared against three other tools on a test data set with 2153 phage genomes. On this data set, vHULK achieved better performance at both the genus and the species levels than the other tools.ConclusionsOur results suggest that vHULK represents an advance on the state of art in phage host prediction.
| S-EPMC9917316 | biostudies-literature
Project description:A significant amount of attention has been given to the design and synthesis of co-crystals by both industry and academia because of its potential to change a molecule's physicochemical properties. Yet, difficulties arise when searching for adequate combinations of molecules (or coformers) to form co-crystals, hampering the efficient exploration of the target's solid-state landscape. This paper reports on the application of a data-driven co-crystal prediction method based on two types of artificial neural network models and co-crystal data present in the Cambridge Structural Database. The models accept pairs of coformers and predict whether a co-crystal is likely to form. By combining the output of multiple models of both types, our approach shows to have excellent performance on the proposed co-crystal training and validation sets, and has an estimated accuracy of 80 % for molecules for which previous co-crystallization data is unavailable.
| S-EPMC7756866 | biostudies-literature
Project description:Predictive modeling of toxicity is a crucial step in the drug discovery pipeline. It can help filter out molecules with a high probability of failing in the early stages of de novo drug design. Thus, several machine learning (ML) models have been developed to predict the toxicity of molecules by combining classical ML techniques or deep neural networks with well-known molecular representations such as fingerprints or 2D graphs. But the more natural, accurate representation of molecules is expected to be defined in physical 3D space like in ab initio methods. Recent studies successfully used equivariant graph neural networks (EGNNs) for representation learning based on 3D structures to predict quantum-mechanical properties of molecules. Inspired by this, we investigated the performance of EGNNs to construct reliable ML models for toxicity prediction. We used the equivariant transformer (ET) model in TorchMD-NET for this. Eleven toxicity data sets taken from MoleculeNet, TDCommons, and ToxBenchmark have been considered to evaluate the capability of ET for toxicity prediction. Our results show that ET adequately learns 3D representations of molecules that can successfully correlate with toxicity activity, achieving good accuracies on most data sets comparable to state-of-the-art models. We also test a physicochemical property, namely, the total energy of a molecule, to inform the toxicity prediction with a physical prior. However, our work suggests that these two properties can not be related. We also provide an attention weight analysis for helping to understand the toxicity prediction in 3D space and thus increase the explainability of the ML model. In summary, our findings offer promising insights considering 3D geometry information via EGNNs and provide a straightforward way to integrate molecular conformers into ML-based pipelines for predicting and investigating toxicity prediction in physical space. We expect that in the future, especially for larger, more diverse data sets, EGNNs will be an essential tool in this domain.
| S-EPMC10583285 | biostudies-literature