Benchmarking of deep neural networks for predicting personal gene expression from DNA sequence highlights shortcomings.
Ontology highlight
ABSTRACT:
SUBMITTER: Sasse A
PROVIDER: S-EPMC10055057 | biostudies-literature | 2023 Sep
REPOSITORIES: biostudies-literature
Publications
Benchmarking of deep neural networks for predicting personal gene expression from DNA sequence highlights shortcomings.
Sasse Alexander A Ng Bernard B Spiro Anna E AE Tasaki Shinya S Bennett David A DA Gaiteri Christopher C De Jager Philip L PL Chikina Maria M Mostafavi Sara S
bioRxiv : the preprint server for biology 20230928
Deep learning methods have recently become the state-of-the-art in a variety of regulatory genomic tasks<sup>1-6</sup> including the prediction of gene expression from genomic DNA. As such, these methods promise to serve as important tools in interpreting the full spectrum of genetic variation observed in personal genomes. Previous evaluation strategies have assessed their predictions of gene expression across genomic regions, however, systematic benchmarking is lacking to assess their predictio ...[more]
Similar Datasets
Project description:BackgroundIn the human genome, distal enhancers are involved in regulating target genes through proximal promoters by forming enhancer-promoter interactions. Although recently developed high-throughput experimental approaches have allowed us to recognize potential enhancer-promoter interactions genome-wide, it is still largely unclear to what extent the sequence-level information encoded in our genome help guide such interactions.MethodsHere we report a new computational method (named "SPEID") using deep learning models to predict enhancer-promoter interactions based on sequence-based features only, when the locations of putative enhancers and promoters in a particular cell type are given.ResultsOur results across six different cell types demonstrate that SPEID is effective in predicting enhancer-promoter interactions as compared to state-of-the-art methods that only use information from a single cell type. As a proof-of-principle, we also applied SPEID to identify somatic non-coding mutations in melanoma samples that may have reduced enhancer-promoter interactions in tumor genomes.ConclusionsThis work demonstrates that deep learning models can help reveal that sequence-based features alone are sufficient to reliably predict enhancer-promoter interactions genome-wide.
| S-EPMC8188889 | biostudies-literature
Project description:Quality assessment of a protein model is to predict the absolute or relative quality of a protein model using computational methods before the native structure is available. Single-model methods only need one model as input and can predict the absolute residue-specific quality of an individual model. Here, we have developed four novel single-model methods (Wang_deep_1, Wang_deep_2, Wang_deep_3, and Wang_SVM) based on stacked denoising autoencoders (SdAs) and support vector machines (SVMs). We evaluated these four methods along with six other methods participating in CASP11 at the global and local levels using Pearson's correlation coefficients and ROC analysis. As for residue-specific quality assessment, our four methods achieved better performance than most of the six other CASP11 methods in distinguishing the reliably modeled residues from the unreliable measured by ROC analysis; and our SdA-based method Wang_deep_1 has achieved the highest accuracy, 0.77, compared to SVM-based methods and our ensemble of an SVM and SdAs. However, we found that Wang_deep_2 and Wang_deep_3, both based on an ensemble of multiple SdAs and an SVM, performed slightly better than Wang_deep_1 in terms of ROC analysis, indicating that integrating an SVM with deep networks works well in terms of certain measurements.
| S-EPMC4725912 | biostudies-other
Project description:BackgroundWith the rapid development of deep sequencing techniques in the recent years, enhancers have been systematically identified in such projects as FANTOM and ENCODE, forming genome-wide landscapes in a series of human cell lines. Nevertheless, experimental approaches are still costly and time consuming for large scale identification of enhancers across a variety of tissues under different disease status, making computational identification of enhancers indispensable.ResultsTo facilitate the identification of enhancers, we propose a computational framework, named DeepEnhancer, to distinguish enhancers from background genomic sequences. Our method purely relies on DNA sequences to predict enhancers in an end-to-end manner by using a deep convolutional neural network (CNN). We train our deep learning model on permissive enhancers and then adopt a transfer learning strategy to fine-tune the model on enhancers specific to a cell line. Results demonstrate the effectiveness and efficiency of our method in the classification of enhancers against random sequences, exhibiting advantages of deep learning over traditional sequence-based classifiers. We then construct a variety of neural networks with different architectures and show the usefulness of such techniques as max-pooling and batch normalization in our method. To gain the interpretability of our approach, we further visualize convolutional kernels as sequence logos and successfully identify similar motifs in the JASPAR database.ConclusionsDeepEnhancer enables the identification of novel enhancers using only DNA sequences via a highly accurate deep learning model. The proposed computational framework can also be applied to similar problems, thereby prompting the use of machine learning methods in life sciences.
| S-EPMC5773911 | biostudies-literature
Project description:Taxonomic classification, that is, the assignment to biological clades with shared ancestry, is a common task in genetics, mainly based on a genome similarity search of large genome databases. The classification quality depends heavily on the database, since representative relatives must be present. Many genomic sequences cannot be classified at all or only with a high misclassification rate. Here we present BERTax, a deep neural network program based on natural language processing to precisely classify the superkingdom and phylum of DNA sequences taxonomically without the need for a known representative relative from a database. We show BERTax to be at least on par with the state-of-the-art approaches when taxonomically similar species are part of the training data. For novel organisms, however, BERTax clearly outperforms any existing approach. Finally, we show that BERTax can also be combined with database approaches to further increase the prediction quality in almost all cases. Since BERTax is not based on similar entries in databases, it allows precise taxonomic classification of a broader range of genomic sequences, thus increasing the overall information gain.
| S-EPMC9436379 | biostudies-literature
Project description:BackgroundTandem mass spectrometry allows biologists to identify and quantify protein samples in the form of digested peptide sequences. When performing peptide identification, spectral library search is more sensitive than traditional database search but is limited to peptides that have been previously identified. An accurate tandem mass spectrum prediction tool is thus crucial in expanding the peptide space and increasing the coverage of spectral library search.ResultsWe propose MS2CNN, a non-linear regression model based on deep convolutional neural networks, a deep learning algorithm. The features for our model are amino acid composition, predicted secondary structure, and physical-chemical features such as isoelectric point, aromaticity, helicity, hydrophobicity, and basicity. MS2CNN was trained with five-fold cross validation on a three-way data split on the large-scale human HCD MS2 dataset of Orbitrap LC-MS/MS downloaded from the National Institute of Standards and Technology. It was then evaluated on a publicly available independent test dataset of human HeLa cell lysate from LC-MS experiments. On average, our model shows better cosine similarity and Pearson correlation coefficient (0.690 and 0.632) than MS2PIP (0.647 and 0.601) and is comparable with pDeep (0.692 and 0.642). Notably, for the more complex MS2 spectra of 3+ peptides, MS2PIP is significantly better than both MS2PIP and pDeep.ConclusionsWe showed that MS2CNN outperforms MS2PIP for 2+ and 3+ peptides and pDeep for 3+ peptides. This implies that MS2CNN, the proposed convolutional neural network model, generates highly accurate MS2 spectra for LC-MS/MS experiments using Orbitrap machines, which can be of great help in protein and peptide identifications. The results suggest that incorporating more data for deep learning model may improve performance.
| S-EPMC6929458 | biostudies-literature
Project description:Multiple Sclerosis (MS) is a chronic disease developed in the human brain and spinal cord, which can cause permanent damage or deterioration of the nerves. The severity of MS disease is monitored by the Expanded Disability Status Scale, composed of several functional sub-scores. Early and accurate classification of MS disease severity is critical for slowing down or preventing disease progression via applying early therapeutic intervention strategies. Recent advances in deep learning and the wide use of Electronic Health Records (EHR) create opportunities to apply data-driven and predictive modeling tools for this goal. Previous studies focusing on using single-modal machine learning and deep learning algorithms were limited in terms of prediction accuracy due to data insufficiency or model simplicity. In this paper, we proposed the idea of using patients' multimodal longitudinal and longitudinal EHR data to predict multiple sclerosis disease severity in the future. Our contribution has two main facets. First, we describe a pioneering effort to integrate structured EHR data, neuroimaging data and clinical notes to build a multi-modal deep learning framework to predict patient's MS severity. The proposed pipeline demonstrates up to 19% increase in terms of the area under the Area Under the Receiver Operating Characteristic curve (AUROC) compared to models using single-modal data. Second, the study also provides valuable insights regarding the amount useful signal embedded in each data modality with respect to MS disease prediction, which may improve data collection processes.
| S-EPMC10634041 | biostudies-literature
Project description:Early identification of individuals at risk of developing Alzheimer's disease (AD) dementia is important for developing disease-modifying therapies. In this study, given multimodal AD markers and clinical diagnosis of an individual from one or more timepoints, we seek to predict the clinical diagnosis, cognition and ventricular volume of the individual for every month (indefinitely) into the future. We proposed and applied a minimal recurrent neural network (minimalRNN) model to data from The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) challenge, comprising longitudinal data of 1677 participants (Marinescu et al., 2018) from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We compared the performance of the minimalRNN model and four baseline algorithms up to 6 years into the future. Most previous work on predicting AD progression ignore the issue of missing data, which is a prevalent issue in longitudinal data. Here, we explored three different strategies to handle missing data. Two of the strategies treated the missing data as a "preprocessing" issue, by imputing the missing data using the previous timepoint ("forward filling") or linear interpolation ("linear filling). The third strategy utilized the minimalRNN model itself to fill in the missing data both during training and testing ("model filling"). Our analyses suggest that the minimalRNN with "model filling" compared favorably with baseline algorithms, including support vector machine/regression, linear state space (LSS) model, and long short-term memory (LSTM) model. Importantly, although the training procedure utilized longitudinal data, we found that the trained minimalRNN model exhibited similar performance, when using only 1 input timepoint or 4 input timepoints, suggesting that our approach might work well with just cross-sectional data. An earlier version of our approach was ranked 5th (out of 53 entries) in the TADPOLE challenge in 2019. The current approach is ranked 2nd out of 63 entries as of June 3rd, 2020.
| S-EPMC7797176 | biostudies-literature
Project description:The increasing production of genomic data has led to an intensified need for models that can cope efficiently with the lossless compression of DNA sequences. Important applications include long-term storage and compression-based data analysis. In the literature, only a few recent articles propose the use of neural networks for DNA sequence compression. However, they fall short when compared with specific DNA compression tools, such as GeCo2. This limitation is due to the absence of models specifically designed for DNA sequences. In this work, we combine the power of neural networks with specific DNA models. For this purpose, we created GeCo3, a new genomic sequence compressor that uses neural networks for mixing multiple context and substitution-tolerant context models. We benchmark GeCo3 as a reference-free DNA compressor in 5 datasets, including a balanced and comprehensive dataset of DNA sequences, the Y-chromosome and human mitogenome, 2 compilations of archaeal and virus genomes, 4 whole genomes, and 2 collections of FASTQ data of a human virome and ancient DNA. GeCo3 achieves a solid improvement in compression over the previous version (GeCo2) of $2.4\%$, $7.1\%$, $6.1\%$, $5.8\%$, and $6.0\%$, respectively. To test its performance as a reference-based DNA compressor, we benchmark GeCo3 in 4 datasets constituted by the pairwise compression of the chromosomes of the genomes of several primates. GeCo3 improves the compression in $12.4\%$, $11.7\%$, $10.8\%$, and $10.1\%$ over the state of the art. The cost of this compression improvement is some additional computational time (1.7-3 times slower than GeCo2). The RAM use is constant, and the tool scales efficiently, independently of the sequence size. Overall, these values outperform the state of the art. GeCo3 is a genomic sequence compressor with a neural network mixing approach that provides additional gains over top specific genomic compressors. The proposed mixing method is portable, requiring only the probabilities of the models as inputs, providing easy adaptation to other data compressors or compression-based data analysis tools. GeCo3 is released under GPLv3 and is available for free download at https://github.com/cobilab/geco3.
| S-EPMC7657843 | biostudies-literature
Project description:Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.
| S-EPMC5995439 | biostudies-literature
Project description:Most organisms are more closely related to nearby than distant members of their species, creating spatial autocorrelations in genetic data. This allows us to predict the location of origin of a genetic sample by comparing it to a set of samples of known geographic origin. Here, we describe a deep learning method, which we call Locator, to accomplish this task faster and more accurately than existing approaches. In simulations, Locator infers sample location to within 4.1 generations of dispersal and runs at least an order of magnitude faster than a recent model-based approach. We leverage Locator's computational efficiency to predict locations separately in windows across the genome, which allows us to both quantify uncertainty and describe the mosaic ancestry and patterns of geographic mixing that characterize many populations. Applied to whole-genome sequence data from Plasmodium parasites, Anopheles mosquitoes, and global human populations, this approach yields median test errors of 16.9km, 5.7km, and 85km, respectively.
| S-EPMC7324158 | biostudies-literature