The model shows that mRNA abundance can be predicted from promoter sequence alone using deep neural networks. The residuals of these predictions make it easier to infere about the regulatory influence of enhancers, heterochromatic domains, and microRNAs. It is observed that CpG dinucleotide content at core promoters is associated with transcriptional activity. A quantitative model is trained using a genomic sequence to predict mRNA expression levels. When pairwise Spearman correlations of mRNA expression levels among cell types were evaluated it was found that most of the cell types were highly correlated with an average 0.78 correlation between any pair of cell types. Which lead the initial development of a cell-type-agnostic model for median mRNA expression levels prediction. Also it was observed that if training sample is between 4,000 to 6,000 then model gains in performance. To compare the generality and performance of the method across mammalian species, 18,377 and 21,865 genes in human and mouse were studied. The best model for human and mouse achieved gives R-squared value of 0.59 and 0.71 respectively.
Input variables : Genomic sequence
Output Variables : mRNA expression level
| Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
| Business | : | Population at High Risk of Disease | Risk by Geography | Risk by Demographics | Risk by Clinical Parameters | Optimized Hospital Resource Utilization | Decreased Cost of Care | Decreased Patient Visits |
| Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : github.com
Additional links : cell.com
| Model Category | : | Public |
| Date Published | : | June, 2020 |
| Healthcare Domain | : | Life Sciences |
| Code | : | github.com |
| Health Risk Management |
| Health Risk Prediction |