GenNet framework: interpretable deep learning for predicting phenotypes from genetic data.
Ontology highlight
ABSTRACT:
SUBMITTER: van Hilten A
PROVIDER: S-EPMC8448759 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BACKGROUND:Adverse drug reactions (ADRs) are unintended and harmful reactions caused by normal uses of drugs. Predicting and preventing ADRs in the early stage of the drug development pipeline can help to enhance drug safety and reduce financial costs. METHODS:In this paper, we developed machine learning models including a deep learning framework which can simultaneously predict ADRs and identify the molecular substructures associated with those ADRs without defining the substructures a-priori. RESULTS:We evaluated the performance of our model with ten different state-of-the-art fingerprint models and found that neural fingerprints from the deep learning model outperformed all other methods in predicting ADRs. Via feature analysis on drug structures, we identified important molecular substructures that are associated with specific ADRs and assessed their associations via statistical analysis. CONCLUSIONS:The deep learning model with feature analysis, substructure identification, and statistical assessment provides a promising solution for identifying risky components within molecular structures and can potentially help to improve drug safety evaluation.
| S-EPMC6300887 | biostudies-other
Project description:BackgroundPredicting outcome of breast cancer is important for selecting appropriate treatments and prolonging the survival periods of patients. Recently, different deep learning-based methods have been carefully designed for cancer outcome prediction. However, the application of these methods is still challenged by interpretability. In this study, we proposed a novel multitask deep neural network called UISNet to predict the outcome of breast cancer. The UISNet is able to interpret the importance of features for the prediction model via an uncertainty-based integrated gradients algorithm. UISNet improved the prediction by introducing prior biological pathway knowledge and utilizing patient heterogeneity information.ResultsThe model was tested in seven public datasets of breast cancer, and showed better performance (average C-index = 0.691) than the state-of-the-art methods (average C-index = 0.650, ranged from 0.619 to 0.677). Importantly, the UISNet identified 20 genes as associated with breast cancer, among which 11 have been proven to be associated with breast cancer by previous studies, and others are novel findings of this study.ConclusionsOur proposed method is accurate and robust in predicting breast cancer outcomes, and it is an effective way to identify breast cancer-associated genes. The method codes are available at: https://github.com/chh171/UISNet .
| S-EPMC10902951 | biostudies-literature
Project description:Accurate prognosis for cancer patients can provide critical information for optimizing treatment plans and improving life quality. Combining omics data and demographic/clinical information can offer a more comprehensive view of cancer prognosis than using omics or clinical data alone and can reveal the underlying disease mechanisms at the molecular level. In this study, we developed a novel deep learning framework to extract information from high-dimensional gene expression and miRNA expression data and conduct prognosis prediction for breast cancer and ovarian cancer patients. Our model achieved significantly better prognosis prediction than the conventional Cox Proportional Hazard model and other competitive deep learning approaches in various settings. Moreover, an interpretation approach was applied to tackle the "black-box" nature of deep neural networks and we identified features (i.e., genes, miRNA, demographic/clinical variables) that made important contributions to distinguishing predicted high- and low-risk patients. The identified associations were partially supported by previous studies.
| S-EPMC10441464 | biostudies-literature
Project description:Automating retrosynthesis with artificial intelligence expedites organic chemistry research in digital laboratories. However, most existing deep-learning approaches are hard to explain, like a "black box" with few insights. Here, we propose RetroExplainer, formulizing the retrosynthesis task into a molecular assembly process, containing several retrosynthetic actions guided by deep learning. To guarantee a robust performance of our model, we propose three units: a multi-sense and multi-scale Graph Transformer, structure-aware contrastive learning, and dynamic adaptive multi-task learning. The results on 12 large-scale benchmark datasets demonstrate the effectiveness of RetroExplainer, which outperforms the state-of-the-art single-step retrosynthesis approaches. In addition, the molecular assembly process renders our model with good interpretability, allowing for transparent decision-making and quantitative attribution. When extended to multi-step retrosynthesis planning, RetroExplainer has identified 101 pathways, in which 86.9% of the single reactions correspond to those already reported in the literature. As a result, RetroExplainer is expected to offer valuable insights for reliable, high-throughput, and high-quality organic synthesis in drug development.
| S-EPMC10547708 | biostudies-literature
Project description:Alzheimer's disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer's disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer's disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer's disease and cognitively normal subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n = 417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n = 382), the Framingham Heart Study (n = 102), and the National Alzheimer's Coordinating Center (NACC) (n = 582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n = 11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer's disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.
| S-EPMC7296847 | biostudies-literature
Project description:Genomic selection (GS) models use single nucleotide polymorphism (SNP) markers to predict phenotypes. However, these predictive models face challenges due to the high dimensionality of genome-wide SNP marker data. Thanks to recent breakthroughs in DNA sequencing and decreased sequencing cost, the study of novel genomic variants such as structural variations (SVs) and transposable elements (TEs) become increasingly prevalent. In this article, we develop a deep convolutional neural network model, NovGMDeep, to predict phenotypes using SVs and TEs markers for GS. The proposed model is trained and tested on samples of Arabidopsis thaliana and Oryza sativa using k-fold cross-validation. The prediction accuracy is evaluated using Pearson's Correlation Coefficient (PCC), mean absolute error (MAE) and SD of MAE. The predicted results showed higher correlation when the model is trained with SVs and TEs than with SNPs. NovGMDeep also has higher prediction accuracy when comparing with conventional statistical models. This work sheds light on the unappreciated function of SVs and TEs in genotype-to-phenotype associations, as well as their extensive significance and value in crop development.
| S-EPMC10132579 | biostudies-literature
Project description:Explainable artificial intelligence holds a great promise for neuroscience and plays an important role in the hypothesis generation process. We follow-up a recent machine learning-oriented study that constructed a deep convolutional neural network to automatically identify biological sex from EEG recordings in healthy individuals and highlighted the discriminative role of beta-band power. If generalizing, this finding would be relevant not only theoretically by pointing to some specific neurobiological sexual dimorphisms, but potentially also as a relevant confound in quantitative EEG diagnostic practice. To put this finding to test, we assess whether the automatic identification of biological sex generalizes to another dataset, particularly in the presence of a psychiatric disease, by testing the hypothesis of higher beta power in women compared to men on 134 patients suffering from Major Depressive Disorder. Moreover, we construct ROC curves and compare the performance of the classifiers in determining sex both before and after the antidepressant treatment. We replicate the observation of a significant difference in beta-band power between men and women, providing classification accuracy of nearly 77%. The difference was consistent across the majority of electrodes, however multivariate classification models did not generally improve the performance. Similar results were observed also after the antidepressant treatment (classification accuracy above 70%), further supporting the robustness of the initial finding.
| S-EPMC7652844 | biostudies-literature
Project description:BackgroundMachine learning involves strategies and algorithms that may assist bioinformatics analyses in terms of data mining and knowledge discovery. In several applications, viz. in Life Sciences, it is often more important to understand how a prediction was obtained rather than knowing what prediction was made. To this end so-called interpretable machine learning has been recently advocated. In this study, we implemented an interpretable machine learning package based on the rough set theory. An important aim of our work was provision of statistical properties of the models and their components.ResultsWe present the R.ROSETTA package, which is an R wrapper of ROSETTA framework. The original ROSETTA functions have been improved and adapted to the R programming environment. The package allows for building and analyzing non-linear interpretable machine learning models. R.ROSETTA gathers combinatorial statistics via rule-based modelling for accessible and transparent results, well-suited for adoption within the greater scientific community. The package also provides statistics and visualization tools that facilitate minimization of analysis bias and noise. The R.ROSETTA package is freely available at https://github.com/komorowskilab/R.ROSETTA . To illustrate the usage of the package, we applied it to a transcriptome dataset from an autism case-control study. Our tool provided hypotheses for potential co-predictive mechanisms among features that discerned phenotype classes. These co-predictors represented neurodevelopmental and autism-related genes.ConclusionsR.ROSETTA provides new insights for interpretable machine learning analyses and knowledge-based systems. We demonstrated that our package facilitated detection of dependencies for autism-related genes. Although the sample application of R.ROSETTA illustrates transcriptome data analysis, the package can be used to analyze any data organized in decision tables.
| S-EPMC7937228 | biostudies-literature
Project description:Most prior studies focused on developing models for the severity or mortality prediction of COVID-19 patients. However, effective models for recovery-time prediction are still lacking. Here, we present a deep learning solution named iCOVID that can successfully predict the recovery-time of COVID-19 patients based on predefined treatment schemes and heterogeneous multimodal patient information collected within 48 hours after admission. Meanwhile, an interpretable mechanism termed FSR is integrated into iCOVID to reveal the features greatly affecting the prediction of each patient. Data from a total of 3008 patients were collected from three hospitals in Wuhan, China, for large-scale verification. The experiments demonstrate that iCOVID can achieve a time-dependent concordance index of 74.9% (95% CI: 73.6-76.3%) and an average day error of 4.4 days (95% CI: 4.2-4.6 days). Our study reveals that treatment schemes, age, symptoms, comorbidities, and biomarkers are highly related to recovery-time predictions.
| S-EPMC8367981 | biostudies-literature
Project description:BackgroundThe ability to accurately predict essential genes intolerant to loss-of-function (LOF) mutations can dramatically improve the identification of disease-associated genes. Recently, there have been numerous computational methods developed to predict human essential genes from population genomic data. While the existing methods are highly predictive of essential genes of long length, they have limited power in pinpointing short essential genes due to the sparsity of polymorphisms in the human genome.ResultsMotivated by the premise that population and functional genomic data may provide complementary evidence for gene essentiality, here we present an evolution-based deep learning model, DeepLOF, to predict essential genes in an unsupervised manner. Unlike previous population genetic methods, DeepLOF utilizes a novel deep learning framework to integrate both population and functional genomic data, allowing us to pinpoint short essential genes that can hardly be predicted from population genomic data alone. Compared with previous methods, DeepLOF shows unmatched performance in predicting ClinGen haploinsufficient genes, mouse essential genes, and essential genes in human cell lines. Notably, at a false positive rate of 5%, DeepLOF detects 50% more ClinGen haploinsufficient genes than previous methods. Furthermore, DeepLOF discovers 109 novel essential genes that are too short to be identified by previous methods.ConclusionThe predictive power of DeepLOF shows that it is a compelling computational method to aid in the discovery of essential genes.
| S-EPMC10506225 | biostudies-literature