Stance detection for unseen targets is designed to automatically identify the user's stance or attitude towards various new targets that are constantly appearing with no labels. Inspired by work in cognitive science, we distinguish functions between systems for syntactic and semantic to enhance stance detection. First, we construct a dual-view graph and utilize unsupervised graph contrastive learning to capture target-invariant features influencing stance expression from a syntactic structure perspective. Second, we use an attention mechanism to learn the relationship between syntactic pattern features and a given target, and fuse the two parts to enhance the model's ability to predict unseen targets. Meanwhile, we employ the interactive GCN to maintain the global semantics of the dual-view graph fusion and ensure the stability and validity of the learned syntactic representations. Comprehensive experiments on stance detection of unseen targets verify the effectiveness and superiority of our proposed method.

Angiotensin converting enzyme 2 (ACE2) is a key receptor present on cell surfaces that directly interacts with the viral spike (S) protein of the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2). It is proposed that inhibiting this interaction can be promising in treating COVID-19. Here, the presence of ACE2 in extracellular vesicles (EVs) is reported and the EV-ACE2 levels are determined by protein palmitoylation. The Cys141 and Cys498 residues on ACE2 are S-palmitoylated by zinc finger DHHC-Type Palmitoyltransferase 3 (ZDHHC3) and de-palmitoylated by acyl protein thioesterase 1 (LYPLA1), which is critical for the membrane-targeting of ACE2 and their EV secretion. Importantly, by fusing the S-palmitoylation-dependent plasma membrane (PM) targeting sequence with ACE2, EVs enriched with ACE2 on their surface (referred to as PM-ACE2-EVs) are engineered. It is shown that PM-ACE2-EVs can bind to the SARS-CoV-2 S-RBD with high affinity and block its interaction with cell surface ACE2 in vitro. PM-ACE2-EVs show neutralization potency against pseudotyped and authentic SARS-CoV-2 in human ACE2 (hACE2) transgenic mice, efficiently block viral load of authentic SARS-CoV-2, and thus protect host against SARS-CoV-2-induced lung inflammation. The study provides an efficient engineering protocol for constructing a promising, novel biomaterial for application in prophylactic and therapeutic treatments against COVID-19.

Global climatic transitions and Tibetan Plateau uplifts are hypothesized to have profoundly impacted biodiversity in southeastern Asia. To further test the hypotheses related to the impacts of these incidents, we investigated the diversification patterns of the newt genus Tylototriton sensu lato, distributed across the mountain ranges of southeastern Asia. Gene-tree and species-tree analyses of two mitochondrial genes and two nuclear genes revealed five major clades in the genus, and suggested several cryptic species. Dating estimates suggested that the genus originated in the early-to-middle Miocene. Under different species delimitating scenarios, diversification analyses with birth-death likelihood tests indicated that the genus held a higher diversification rate in the late Miocene-to-Pliocene era than that in the Pleistocene. Ancestral area reconstructions indicated that the genus originated from the northern Indochina Peninsula. Accordingly, we hypothesized that the Miocene Climatic Transition triggered the diversification of the genus, and the reinforcement of East Asian monsoons associated with the stepwise uplifts of the Tibetan Plateau promoted the radiation of the genus in southeastern Asia during the Miocene-to-Pliocene period. Quaternary glacial cycles likely had limited effects on speciation events in the genus, but mainly had contributions on their intraspecific differentiations.

Purpose

Tumor genomic features have been of particular interest because of their potential impact on the tumor immune microenvironment and response to immunotherapy. Due to the substantial heterogeneity, an integrative approach incorporating diverse molecular features is needed to characterize immunologic features underlying primary resistance to immunotherapy and for the establishment of novel predictive biomarkers.

Experimental design

We developed a pan-cancer deep machine learning model integrating tumor mutation burden, microsatellite instability, and somatic copy-number alterations to classify tumors of different types into different genomic clusters, and assessed the immune microenvironment in each genomic cluster and the association of each genomic cluster with response to immunotherapy.

Results

Our model grouped 8,646 tumors of 29 cancer types from The Cancer Genome Atlas into four genomic clusters. Analysis of RNA-sequencing data revealed distinct immune microenvironment in tumors of each genomic class. Furthermore, applying this model to tumors from two melanoma immunotherapy clinical cohorts demonstrated that patients with melanoma of different genomic classes achieved different benefit from immunotherapy. Interestingly, tumors in cluster 4 demonstrated a cold immune microenvironment and lack of benefit from immunotherapy despite high microsatellite instability burden.

Conclusions

Our study provides a proof for principle that deep learning modeling may have the potential to discover intrinsic statistical cross-modality correlations of multifactorial input data to dissect the molecular mechanisms underlying primary resistance to immunotherapy, which likely involves multiple factors from both the tumor and host at different molecular levels.