Deciphering COVID-19 host transcriptomic complexity and variations for therapeutic discovery against new variants.

The molecular manifestations of host cells responding to SARS-CoV-2 and its evolving variants of infection are vastly different across the studied models and conditions, imposing challenges for host-based antiviral drug discovery. Based on the postulation that antiviral drugs tend to reverse the global host gene expression induced by viral infection, we retrospectively evaluated hundreds of signatures derived from 1,700 published host transcriptomic profiles of SARS/MERS/SARS-CoV-2 infection using an iterative data-driven approach. A few of these signatures could be reversed by known anti-SARS-CoV-2 inhibitors, suggesting the potential of extrapolating the biology for new variant research. We discovered IMD-0354 as a promising candidate to reverse the signatures globally with nanomolar IC50 against SARS-CoV-2 and its five variants. IMD-0354 stimulated type I interferon antiviral response, inhibited viral entry, and down-regulated hijacked proteins. This study demonstrates that the conserved coronavirus signatures and the transcriptomic reversal approach that leverages polypharmacological effects could guide new variant therapeutic discovery.

Drug target inference by mining transcriptional data using a novel graph convolutional network framework

A fundamental challenge that arises in biomedicine is the need to characterize compounds in a relevant cellular context in order to reveal potential on-target or off-target effects. Recently, the fast accumulation of gene transcriptional profiling data provides us an unprecedented opportunity to explore the protein targets of chemical compounds from the perspective of cell transcriptomics and RNA biology. Here, we propose a novel Siamese spectral-based graph convolutional network (SSGCN) model for inferring the protein targets of chemical compounds from gene transcriptional profiles. Although the gene signature of a compound perturbation only provides indirect clues of the interacting targets, and the biological networks under different experiment conditions further complicate the situation, the SSGCN model was successfully trained to learn from known compound-target pairs by uncovering the hidden correlations between compound perturbation profiles and gene knockdown profiles. On a benchmark set and a large time-split validation dataset, the model achieved higher target inference accuracy as compared to previous methods such as Connectivity Map. Further experimental validations of prediction results highlight the practical usefulness of SSGCN in either inferring the interacting targets of compound, or reversely, in finding novel inhibitors of a given target of interest. Supplementary Information The online version contains supplementary material available at 10.1007/s13238-021-00885-0.