Performance of models highly depend not only on the used algorithm but also the data set it was applied to. This makes the comparison of newly developed tools to previously published approaches difficult. Either researchers need to implement others' algorithms first, to establish an adequate benchmark on their data, or a direct comparison of new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims to address this problem of comparability. ISLES 2016 and 2017 focused on lesion outcome prediction after ischemic stroke: By providing a uniformly pre-processed data set, researchers from all over the world could apply their algorithm directly. A total of nine teams participated in ISLES 2015, and 15 teams participated in ISLES 2016. Their performance was evaluated in a fair and transparent way to identify the state-of-the-art among all submissions. Top ranked teams almost always employed deep learning tools, which were predominately convolutional neural networks (CNNs). Despite the great efforts, lesion outcome prediction persists challenging. The annotated data set remains publicly available and new approaches can be compared directly via the online evaluation system, serving as a continuing benchmark (www.isles-challenge.org).

Hypoxia induces a vast array of long noncoding RNAs (lncRNA) in breast cancer cells, but their biological functions remain largely unknown. Here, we identified a hitherto uncharacterized hypoxiainduced lncRNA RAB11B-AS1 in breast cancer cells. RAB11B-AS1 is a natural lncRNA upregulated in human breast cancer and its expression is induced by hypoxia-inducible factor 2 (HIF2), but not HIF1, in response to hypoxia. RAB11B-AS1 enhanced the expression of angiogenic factors including VEGFA and ANGPTL4 in hypoxic breast cancer cells by increasing recruitment of RNA polymerase II. In line with increased angiogenic factors, conditioned media from RAB11B-AS1-overexpressing breast cancer cells promoted tube formation of human umbilical vein endothelial cells in vitro. Gain-and loss-of-function studies revealed that RAB11B-AS1 increased breast cancer cell migration and invasion in vitro and promoted tumor angiogenesis and breast cancer distant metastasis without affecting primary tumor growth in mice. Taken together, these findings uncover a fundamental mechanism of hypoxia-induced tumor angiogenesis and breast cancer metastasis.Significance: This study reveals the molecular mechanism by which the lncRNA RAB11B-AS1 regulates hypoxia-induced

Sememes are minimum semantic units of word meanings, and the meaning of each word sense is typically composed by several sememes. Since sememes are not explicit for each word, people manually annotate word sememes and form linguistic common-sense knowledge bases. In this paper, we present that, word sememe information can improve word representation learning (WRL), which maps words into a low-dimensional semantic space and serves as a fundamental step for many NLP tasks. The key idea is to utilize word sememes to capture exact meanings of a word within specific contexts accurately. More specifically, we follow the framework of Skip-gram and present three sememe-encoded models to learn representations of sememes, senses and words, where we apply the attention scheme to detect word senses in various contexts. We conduct experiments on two tasks including word similarity and word analogy, and our models significantly outperform baselines. The results indicate that WRL can benefit from sememes via the attention scheme, and also confirm our models being capable of correctly modeling sememe information.

Set2-mediated H3K36 methylation ubiquitously functions in coding regions in all eukaryotes. It has been linked to the regulation of acetylation states, histone exchange, alternative splicing, DNA repair and recombination. Set2 is recruited to transcribed chromatin through its SRI domain's direct association with phosphorylated Pol II. However, regulatory mechanisms for histone modifying enzymes like Set2 that travel with elongating Pol II remain largely unknown beyond their initial recruitment events. Here, by fusing Set2 to RNA Pol II, we found that the SRI domain can also recognize linker DNA of chromatin, thereby controlling Set2 substrate specificity. We also discovered that an auto-inhibitory domain (AID) of Set2 primarily restricts Set2 activity to transcribed chromatin and fine-tunes several functions of SRI. Finally, we demonstrated that AID mutations caused hyperactive Set2 in vivo and displayed a synthetic interaction with the histone chaperone FACT. Our data suggest that Set2 is intrinsically regulated through multiple mechanisms and emphasize the importance of a precise temporal control of H3K36 methylation during the dynamic transcription elongation process.

Background:The origin of eukaryotic histone modification enzymes still remains obscure. Results: Prototypic KMT4/Dot1 from Archaea targets chromatin proteins (Sul7d and Cren7) and shows increased activity on Sul7d, but not Cren7, in the presence of DNA. Conclusion: Promiscuous aKMT4 could be regulated by chromatin environment. Significance: This study supports the prokaryotic origin model of eukaryotic histone methyltransferases and sheds light on chromatin dynamics in Archaea.