AttentiveChrome is an attention-based deep learning model that uses histone modification signals covering the gene’s neighboring DNA region of Transcription start site as input to predict gene expression in different cell types. It models and interprets dependencies between chromatin factors to regulate gene expression. For each gene, 10 kb of DNA region around the transcription start site is divided into bins having 100bp each. Histone modification marks are fed into LSTM network in order to encode spatial dependencies among the bin signals followed by another LSTM to model how different factors work to predict gene expression. The model is composed of 5 LSTM modules: Bin-level LSTM encoder for each HM mark; Bin-level Attention on each HM mark; HM-level LSTM encoder encoding all HM marks; HM-level Attention over all the HM marks; and the final classification module. This model provides better interpretations and more accurate predictions than the state-of-the-art baselines.
Input variables : histone modification signals covering the gene’s neighboring DNA region of Transcription start site
Output Variables : gene expression: +1 (high) or -1 (low)
| 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 : biorxiv.org
| Model Category | : | Public |
| Date Published | : | May, 2018 |
| Healthcare Domain | : | Life Sciences |
| Code | : | github.com |
| Health Risk Management |
| Health Risk Prediction |