Multi-Level Attention Graph Neural Network Based on Co-expression Gene Modules for Disease Diagnosis and Prognosis.

MOTIVATION: Advanced deep learning techniques have been widely applied in disease diagnosis and prognosis with clinical omics, especially gene expression data. In the regulation of biological processes and disease progression, genes often work interactively rather than individually. Therefore, investigating gene association information and co-functional gene modules can facilitate disease state prediction. RESULTS: To explore the gene modules and inter-gene relational information contained in the omics data, we propose a novel multi-level attention graph neural network (MLA-GNN) for disease diagnosis and prognosis. Specifically, we format omics data into co-expression graphs via weighted correlation network analysis (WGCNA), and then construct multi-level graph features, finally fuse them through a well-designed multi-level graph feature fully fusion (MGFFF) module to conduct predictions. For model interpretation, a novel full-gradient graph saliency (FGS) mechanism is developed to identify the disease-relevant genes. MLA-GNN achieves state-of-the-art performance on transcriptomic data from TCGA-LGG/TCGA-GBM and proteomic data from COVID-19/non-COVID-19 patient sera. More importantly, the relevant genes selected by our model are interpretable and are consistent with the clinical understanding. AVAILABILITY: The codes are available at https://github.com/TencentAILabHealthcare/MLA-GNN.

Early triage of critically ill COVID-19 patients using deep learning.

The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.

MolAICal: a soft tool for 3D drug design of protein targets by artificial intelligence and classical algorithm.

Deep learning is an important branch of artificial intelligence that has been successfully applied into medicine and two-dimensional ligand design. The three-dimensional (3D) ligand generation in the 3D pocket of protein target is an interesting and challenging issue for drug design by deep learning. Here, the MolAICal software is introduced to supply a way for generating 3D drugs in the 3D pocket of protein targets by combining with merits of deep learning model and classical algorithm. The MolAICal software mainly contains two modules for 3D drug design. In the first module of MolAICal, it employs the genetic algorithm, deep learning model trained by FDA-approved drug fragments and Vinardo score fitting on the basis of PDBbind database for drug design. In the second module, it uses deep learning generative model trained by drug-like molecules of ZINC database and molecular docking invoked by Autodock Vina automatically. Besides, the Lipinski's rule of five, Pan-assay interference compounds (PAINS), synthetic accessibility (SA) and other user-defined rules are introduced for filtering out unwanted ligands in MolAICal. To show the drug design modules of MolAICal, the membrane protein glucagon receptor and non-membrane protein SARS-CoV-2 main protease are chosen as the investigative drug targets. The results show MolAICal can generate the various and novel ligands with good binding scores and appropriate XLOGP values. We believe that MolAICal can use the advantages of deep learning model and classical programming for designing 3D drugs in protein pocket. MolAICal is freely for any nonprofit purpose and accessible at https://molaical.github.io.

Structure of human steroid 5α-reductase 2 with anti-androgen drug finasteride.

Human steroid 5α-reductase 2 (SRD5α2) as a critical integral membrane enzyme in steroid metabolism catalyzes testosterone to dihydrotestosterone. Mutations on its gene have been linked to 5α-reductase deficiency and prostate cancer. Finasteride and dutasteride as SRD5α2 inhibitors are widely used anti-androgen drugs for benign prostate hyperplasia, which have recently been indicated in the treatment of COVID-19. The molecular mechanisms underlying enzyme catalysis and inhibition remained elusive for SRD5α2 and other eukaryotic integral membrane steroid reductases due to a lack of structural information. Here, we report a crystal structure of human SRD5α2 at 2.8 Å revealing a unique 7-TM structural topology and an intermediate adduct of finasteride and NADPH as NADP-dihydrofinasteride in a largely enclosed binding cavity inside the membrane. Structural analysis together with computational and mutagenesis studies reveals molecular mechanisms for the 5α-reduction of testosterone and the finasteride inhibition involving residues E57 and Y91. Molecular dynamics simulation results indicate high conformational dynamics of the cytosolic region regulating the NADPH/NADP + exchange. Mapping disease-causing mutations of SRD5α2 to our structure suggests molecular mechanisms for their pathological effects. Our results offer critical structural insights into the function of integral membrane steroid reductases and will facilitate drug development.