A Multi-Task Group Bi-LSTM Networks Application on Electrocardiogram Classification.

BACKGROUND: Cardiovascular diseases (CVD) are the leading cause of death globally. Electrocardiogram (ECG) analysis can provide thoroughly assessment for different CVDs efficiently. We propose a multi-task group bidirectional long short-term memory (MTGBi-LSTM) framework to intelligent recognize multiple CVDs based on multi-lead ECG signals. METHODS: This model employs a Group Bi-LSTM (GBi-LSTM) and Residual Group Convolutional Neural Network (Res-GCNN) to learn the dual feature representation of ECG space and time series. GBi-LSTM is divided into Global Bi-LSTM and Intra-Group Bi-LSTM, which can learn the features of each ECG lead and the relationship between leads. Then, through attention mechanism, the different lead information of ECG is integrated to make the model to possess the powerful feature discriminability. Through multi-task learning, the model can fully mine the association information between diseases and obtain more accurate diagnostic results. In addition, we propose a dynamic weighted loss function to better quantify the loss to overcome the imbalance between classes. RESULTS: Based on more than 170,000 clinical 12-lead ECG analysis, the MTGBi-LSTM method achieved accuracy, precision, recall and F1 of 88.86%, 90.67%, 94.19% and 92.39%, respectively. The experimental results show that the proposed MTGBi-LSTM method can reliably realize ECG analysis and provide an effective tool for computer-aided diagnosis of CVD.

Artificial Intelligence Approach To Investigate the Longevity Drug.

Longevity is a very important and interesting topic, and Klotho has been demonstrated to be related to longevity. We combined network pharmacology, machine learning, deep learning, and molecular dynamics (MD) simulation to investigate potent lead drugs. Related protein insulin-like growth factor 1 receptor (IGF1R) and insulin receptor (IR) were docked with the traditional Chinese medicine (TCM) database to screen out several novel candidates. Besides, nine different machine learning algorithms were performed to build reliable and accurate predicted models. Moreover, we used the novel deep learning algorithm to build predicted models. All of these models obtained significant R2, which are all greater than 0.87 on the training set and higher than 0.88 for the test set, respectively. The long time 500 ns molecular dynamics simulation was also performed to verify protein-ligand properties and stability. Finally, we obtained Antifebrile Dichroa, Holarrhena antidysenterica, and Gelsemium sempervirens, which might be potent TCMs for two targets.

Artificial Intelligence Approach to Find Lead Compounds for Treating Tumors.

It has been demonstrated that MMP13 enzyme is related to most cancer cell tumors. The world's largest traditional Chinese medicine database was applied to screen for structure-based drug design and ligand-based drug design. To predict drug activity, machine learning models (Random Forest (RF), AdaBoost Regressor (ABR), Gradient Boosting Regressor (GBR)), and Deep Learning models were utilized to validate the Docking results, and we obtained an R2 of 0.922 on the training set and 0.804 on the test set in the RF algorithm. For the Deep Learning algorithm, R2 of the training set is 0.90, and R2 of the test set is 0.810. However, these TCM compounds fly away during the molecular dynamics (MD) simulation. We seek another method: peptide design. All peptide database were screened by the Docking process. Modification peptides were optimized the interaction modes, and the affinities were assessed with ZDOCK protocol and Refine Docked protein protocol. The 300 ns MD simulation evaluated the stability of receptor-peptide complexes. The double-site effect appeared on S2, a designed peptide based on a known inhibitor, when complexed with BCL2. S3, a designed peptide referred from endogenous inhibitor P16, competed against cyclin when binding with CDK6. The MDM2 inhibitors S5 and S6 were derived from the P53 structure and stable binding with MDM2. A flexible region of peptides S5 and S6 may enhance the binding ability by changing its own conformation, which was unforeseen. These peptides (S2, S3, S5, and S6) are potentially interesting to treat cancer; however, these findings need to be affirmed by biological testing, which will be conducted in the near future.