The pathogenic mechanism of syndactyly type V identified in aHoxd13Q50R knock-in mice

Syndactyly type V (SDTY5) is an autosomal dominant extremity malformation characterized by fusion of the fourth and fifthmetacarpals. In the previous publication, we first identified a heterozygous missense mutation Q50R in homeobox domain (HD) ofHOXD13 in a large Chinese family with SDTY5. In order to substantiate the pathogenicity of the variant and elucidate the underlyingpathogenic mechanism causing limb malformation, transcription-activator-like effector nucleases (TALEN) was employed togenerate a Hoxd13Q50R mutant mouse. The mutant mice exhibited obvious limb malformations including slight brachydactyly andpartial syndactyly between digits 2-4 in the heterozygotes, and severe syndactyly, brachydactyly and polydactyly in homozygotes.Focusing on BMP2 and SHH/GREM1/AER-FGF epithelial mesenchymal (e-m) feedback, a crucial signal pathway for limbdevelopment, we found the ectopically expressed Shh, Grem1 and Fgf8 and down-regulated Bmp2 in the embryonic limb bud atE10.5 to E12.5. A transcriptome sequencing analysis was conducted on limb buds (LBs) at E11.5, revealing 31 genes that exhibitednotable disparities in mRNA level between the Hoxd13Q50R homozygotes and the wild-type. These genes are known to be involvedin various processes such as limb development, cell proliferation, migration, and apoptosis. Our findings indicate that the ectopicexpression of Shh and Fgf8, in conjunction with the down-regulation of Bmp2, results in a failure of patterning along both theanterior-posterior and proximal-distal axes, as well as a decrease in interdigital programmed cell death (PCD). This cascadeultimately leads to the development of syndactyly and brachydactyly in heterozygous mice, and severe limb malformations inhomozygous mice. These findings suggest that abnormal expression of SHH, FGF8, and BMP2 induced by HOXD13Q50R may beresponsible for the manifestation of human SDTY5.

Nested relation extraction with iterative neural network

Most existing researches on relation extraction focus on binary flat relations like Bomln relation between a Person and a Location.But a large portion of objective facts de-scribed in natural language are complex,especially in professional documents in fields such as finance and biomedicine that require precise expressions.For example,“the GDP of the United States in 2018 grew 2.9%compared with 2017”describes a growth rate relation between two other relations about the economic index,which is beyond the expressive power of binary flat relations.Thus,we propose the nested relation extraction problem and formulate it as a directed acyclic graph(DAG)structure extraction problem.Then,we propose a solution using the Iterative Neural Network which extracts relations layer by layer.The proposed solution achieves 78.98 and 97.89 FI scores on two nested relation extraction tasks,namely semantic cause-and-efFect relation extraction and formula extraction.Furthermore,we observe that nested relations are usually expressed in long sentences where entities are mentioned repetitively,which makes the annotation difficult and error-prone.Hence,we extend our model to incorporate a mention-insensitive mode that only requires annotations of relations on entity concepts(instead of exact mentions)while preserving most of its performance.Our mention-insensitive model performs better than the mention sensitive model when the random level in mention selection is higher than 0.3.

Rich-text document styling restoration via reinforcement learning

Richly formatted documents,such as financial disclosures,scientific articles,government regulations,widely exist on Web.However,since most of these documents are only for public reading,the styling information inside them is usually missing,making them improper or even burdensome to be displayed and edited in different formats and platforms.In this study we formulate the task of document styling restoration as an optimization problem,which aims to identify the styling settings on the document elements,e.g.,lines,table cells,text,so that rendering with the output styling settings results in a document,where each element inside it holds the(closely)exact position with the one in the original document.Considering that each styling setting is a decision,this problem can be transformed as a multi-step decision-making task over all the document elements,and then be solved by reinforcement learning.Specifically,Monte-Carlo Tree Search(MCTS)is leveraged to explore the different styling settings,and the policy function is learnt under the supervision of the delayed rewards.As a case study,we restore the styling information inside tables,where structural and functional data in the documents are usually presented.Experiment shows that,our best reinforcement method successfully restores the stylings in 87.65%of the tables,with 25.75%absolute improvement over the greedymethod.We also discuss the tradeoff between the inference time and restoration success rate,and argue that although the reinforcement methods cannot be used in real-time scenarios,it is suitable for the offline tasks with high-quality requirement.Finally,this model has been applied in a PDF parser to support cross-format display.