A genome-scale deep learning model to predict gene expression changes of genetic perturbations from multiplex biological networks.

Systematic characterization of biological effects to genetic perturbation is essential to the application of molecular biology and biomedicine. However, the experimental exhaustion of genetic perturbations on the genome-wide scale is challenging. Here, we show TranscriptionNet, a deep learning model that integrates multiple biological networks to systematically predict transcriptional profiles to three types of genetic perturbations based on transcriptional profiles induced by genetic perturbations in the L1000 project: RNA interference, clustered regularly interspaced short palindromic repeat, and overexpression. TranscriptionNet performs better than existing approaches in predicting inducible gene expression changes for all three types of genetic perturbations. TranscriptionNet can predict transcriptional profiles for all genes in existing biological networks and increases perturbational gene expression changes for each type of genetic perturbation from a few thousand to 26 945 genes. TranscriptionNet demonstrates strong generalization ability when comparing predicted and true gene expression changes on different external tasks. Overall, TranscriptionNet can systemically predict transcriptional consequences induced by perturbing genes on a genome-wide scale and thus holds promise to systemically detect gene function and enhance drug development and target discovery.

A Natural Glucan from Black Bean Inhibits Cancer Cell Proliferation via PI3K-Akt and MAPK Pathway.

A natural α-1,6-glucan named BBWPW was identified from black beans. Cell viability assay showed that BBWPW inhibited the proliferation of different cancer cells, especially HeLa cells. Flow cytometry analysis indicated that BBWPW suppressed the HeLa cell cycle in the G2/M phase. Consistently, RT-PCR experiments displayed that BBWPW significantly impacts the expression of four marker genes related to the G2/M phase, including p21, CDK1, Cyclin B1, and Survivin. To explore the molecular mechanism of BBWPW to induce cell cycle arrest, a transcriptome-based target inference approach was utilized to predict the potential upstream pathways of BBWPW and it was found that the PI3K-Akt and MAPK signal pathways had the potential to mediate the effects of BBWPW on the cell cycle. Further experimental tests confirmed that BBWPW increased the expression of BAD and AKT and decreased the expression of mTOR and MKK3. These results suggested that BBWPW could regulate the PI3K-Akt and MAPK pathways to induce cell cycle arrest and ultimately inhibit the proliferation of HeLa cells, providing the potential of the black bean glucan to be a natural anticancer drug.

Specific gene module pair-based target identification and drug discovery.

Identification of the biological targets of a compound is of paramount importance for the exploration of the mechanism of action of drugs and for the development of novel drugs. A concept of the Connectivity Map (CMap) was previously proposed to connect genes, drugs, and disease states based on the common gene-expression signatures. For a new query compound, the CMap-based method can infer its potential targets by searching similar drugs with known targets (reference drugs) and measuring the similarities into their specific transcriptional responses between the query compound and those reference drugs. However, the available methods are often inefficient due to the requirement of the reference drugs as a medium to link the query agent and targets. Here, we developed a general procedure to extract target-induced consensus gene modules from the transcriptional profiles induced by the treatment of perturbagens of a target. A specific transcriptional gene module pair (GMP) was automatically identified for each target and could be used as a direct target signature. Based on the GMPs, we built the target network and identified some target gene clusters with similar biological mechanisms. Moreover, a gene module pair-based target identification (GMPTI) approach was proposed to predict novel compound-target interactions. Using this method, we have discovered novel inhibitors for three PI3K pathway proteins PI3Kα/ß/δ, including PU-H71, alvespimycin, reversine, astemizole, raloxifene HCl, and tamoxifen.

TMNP: a transcriptome-based multi-scale network pharmacology platform for herbal medicine.

One of the most difficult problems that hinder the development and application of herbal medicine is how to illuminate the global effects of herbs on the human body. Currently, the chemo-centric network pharmacology methodology regards herbs as a mixture of chemical ingredients and constructs the 'herb-compound-target-disease' connections based on bioinformatics methods, to explore the pharmacological effects of herbal medicine. However, this approach is severely affected by the complexity of the herbal composition. Alternatively, gene-expression profiles induced by herbal treatment reflect the overall biological effects of herbs and are suitable for studying the global effects of herbal medicine. Here, we develop an online transcriptome-based multi-scale network pharmacology platform (TMNP) for exploring the global effects of herbal medicine. Firstly, we build specific functional gene signatures for different biological scales from molecular to higher tissue levels. Then, specific algorithms are designed to measure the correlations of transcriptional profiles and types of gene signatures. Finally, TMNP uses pharmacotranscriptomics of herbal medicine as input and builds associations between herbs and different biological scales to explore the multi-scale effects of herb medicine. We applied TMNP to a single herb Astragalus membranaceus and Xuesaitong injection to demonstrate the power to reveal the multi-scale effects of herbal medicine. TMNP integrating herbal medicine and multiple biological scales into the same framework, will greatly extend the conventional network pharmacology model centering on the chemical components, and provide a window for systematically observing the complex interactions between herbal medicine and the human body. TMNP is available at http://www.bcxnfz.top/TMNP.