Search

Heterogeneous graph embedding aims at learning low-dimensional representations from a graph featuring nodes and edges of diverse natures, and meanwhile preserving the underlying topology. Existing approaches along this line have largely relied on meta-paths, which are by nature hand-crafted and pre-defined transition rules, so as to explore the semantics of a graph. Despite the promising results, defining meta-paths requires domain knowledge, and thus when the test distribution deviates from the priors, such methods are prone to errors. In this paper, we propose a self-learning scheme for heterogeneous graph embedding, termed as self-guided walk (SILK), that bypasses meta-paths and learns adaptive attentions for node walking. SILK assumes no prior knowledge or annotation is provided, and conducts a customized random walk to encode the contexts of the heterogeneous graph of interest. Specifically, this is achieved via maintaining a dynamically-updated guidance matrix that records the node-conditioned transition potentials. Experimental results on four real-world datasets demonstrate that SILK significantly outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Video highlight detection (VHD) has emerged as a pressing task due to the unprecedentedly increasing amount of video data, such as those from e-commerce live-broadcasting platforms. Many approaches focus on exploiting text data, in the form of video description or time-sync comments, to facilitate the VHD task. Despite the promising results, they have largely overlooked the noises inherent in the text data and have mostly relied on isolating the feature of text and video. In this paper, we introduce a novel model to handle VHD, termed Coevolution Network (CoEvo-Net), that allows us to account for joint learning of the language and video features explicitly via a coevolution paradigm, in which features from the two data modalities progressively refine each other. This is achieved by a dedicated CoEvo-Cell that takes language and video together as inputs, extracts cross-modality, and filters the undesired parts of the input, such as words in a sentence. Furthermore, we release a large-scale dataset of e-commerce for VHD, in which each video is coupled with a sentence for description, to benchmark the sentence-based VHD approaches. Extensive experiments on the released dataset demonstrate that CoEvo-Net achieves state-of-the-art performance. Our dataset and code will be made publicly available. [ABSTRACT FROM AUTHOR]

Aims: To compare the fibroinflammatory diseases Kimura's disease (KD) and immunoglobulin (Ig)G4‐related disease (IgG4RD) and to explore their possible relationship. Methods and results: Forty‐six cases of KD and 29 IgG4RD from our institution diagnosed from 2011 to 2020 were studied. They were compared with each other on clinical, pathological and immunohistological features. There were similar clinical features, except that IgG4RD affected an older patient population, with more frequent salivary gland involvement and KD affected head and neck lymph nodes, and showed blood eosinophilia more frequently than IgG4RD. IgG4RD exhibited frequent storiform fibrosis and obliterative phlebitis, while KD showed more frequent tissue eosinophilia, eosinophilic abscess, germinal centre eosinophilic deposit and vascularisation. Twenty to 30% of KD had more than 50 IgG4+ plasma cells (PC) per high‐power field (HPF) and IgG4/IgG+PC ratio exceeding 40%. These parameters, however, occurred in 100% of IgG4RD. Significantly more KD had >10 IgE+PC/HPF and lymphoid germinal centre IgE reticular staining compared to IgG4RD. All these histological and immunohistological features are overlapping in the two diseases, although they differed with statistical significance. Conclusion: Our study confirmed that there is significant overlap in clinical, pathological and immunohistological features between KD and IgG4RD. It is important to recognise these overlapping features, and correlation with a clinicopathological picture is required in differential diagnoses. The overlapping features also suggest a possible close relationship between KD and IgG4RD, which could represent different facets of a continuous fibroinflammatory disease spectrum. [ABSTRACT FROM AUTHOR]

Background: Malignant gastrointestinal neuroectodermal tumor (GNET) is a rare malignant mesenchymal neoplasm that commonly arises in the small bowel, stomach or colon. Meanwhile, SMARCA4-deficient undifferentiated carcinoma is a rarely reported entity with highly aggressive behavior that may involve the ovary, lung, gastrointestinal (GI) tract, endometrium and other organs. To our knowledge, we describe for the first time, an extremely rare case of synchronous GNET and SMARCA4-deficient undifferentiated carcinoma with independent origins in the small intestine. Case Presentation: A 46-year-old woman presented with multiple small intestine masses and underwent surgical resection. Two distinct entities, GNET and SMARCA4-deficient undifferentiated carcinoma, were identified. GNET was composed of epithelioid and spindle cells with clear or eosinophilic cytoplasm arranged in sheets, nest, papillary, fascicular, palisade, rosette like or pseudoalveolar pattern. The neoplastic cells were positive for S-100 and SOX-10. Ewing sarcoma breakpoint region 1 gene (EWSR1) rearrangement was confirmed by fluorescence in situ hybridization (FISH), and EWSR1-CREB1 fusion was revealed by next-generation sequencing (NGS). SMARCA4-deficient undifferentiated carcinoma was composed mainly of poorly adhesive rhabdoid cells with eosinophilic cytoplasm arranged in a diffuse pattern. Multifocal necrosis, brisk mitotic figures as well as multinucleated tumor cells were observed. The neoplastic cells diffusely expressed pancytokeratin and vimentin, and was negative for SMARCA4(BRG1). Frame shift mutation of SMARCA4 was detected by NGS. Conclusions: This is the first report that GNET and SMARCA4-deficient undifferentiated carcinoma occurred simultaneously in the small intestine, with the latter showing multiple involvement of the jejunum and ileum. The potential mechanism underlying co-existence of these two rare malignancies is unknown and need further investigations and concern. [ABSTRACT FROM AUTHOR]

Proline, glutamate, and leucine-rich protein 1 (PELP1) are involved in several cancers, but little is known about PELP1 in lung cancer. In this study, PELP1 expression was evaluated in 305 lung cancer (NSCLC) specimens to explore the role of PELP1 in lung cancer. After silencing PELP1, the proliferation, migration, invasion of tumor cells, PELP1 in relation to cell cycle and signaling pathways were evaluated, and whole-genome exons were analyzed. PELP1 is overexpressed in lung cancer, PELP1 expression correlated with squamous carcinoma, smoking, and wild-type EGFR status (all Ps<0.001) but associated with lung cancer-specific survival (P > 0.05). Silencing significantly inhibited lung cancer cell proliferation, migration, and invasion (P < 0.05) and promoted high sensitivity of lung cancer cells to tyrosine kinase inhibitor (TKI) gefitinib. PELP1-silenced cells showed downregulated phosphorylated MAPK, cyclinD1, CDK2, and upregulated RB (P < 0.05) but no change in AKT. In PELP1-silenced lung cancer cells, 140 genes were upregulated, and 143 genes were downregulated. Furthermore, the number of T regulatory cell was higher in lung adenocarcinoma with pelp1 high-expression and pelp1 expression was negatively correlated with CD274 (PDL-1) and CTLA4. Therefore, PELP1 plays an important role in the malignant behavior of NSCLC and could be a potential therapeutic target. [ABSTRACT FROM AUTHOR]

Researchers of temporal networks (e.g., social networks and transaction networks) have been interested in mining dynamic patterns of nodes from their diverse interactions. Inspired by recently powerful graph mining methods like skip-gram models and graph neural networks (GNNs), existing approaches focus on generating temporal node embeddings sequentially with nodes' sequential interactions. However, the sequential modeling of previous approaches cannot handles the transition structure between nodes' neighbors with limited memorization capacity. In detail, an effective method for the transition structures is required to both model nodes' personalized patterns adaptively and capture node dynamics accordingly. In this article, we propose a method, namely t ransition p ropagation g raph n eural n etworks (TIP-GNN), to tackle the challenges of encoding nodes' transition structures. The proposed TIP-GNN focuses on the bilevel graph structure in temporal networks: besides the explicit interaction graph, a node's sequential interactions can also be constructed as a transition graph. Based on the bilevel graph, TIP-GNN further encodes transition structures by multistep transition propagation and distills information from neighborhoods by a bilevel graph convolution. Experimental results over various temporal networks reveal the efficiency of our TIP-GNN, with at most 7.2% improvements of accuracy on temporal link prediction. Extensive ablation studies further verify the effectiveness and limitations of the transition propagation module. Our code is available at https://github.com/doujiang-zheng/TIP-GNN.

Purpose: Proline, glutamic acid, and leucine-rich protein 1 (PELP1), a novel nuclear receptor (NR) co-regulator, is highly expressed in breast cancer. We investigated its expression in breast cancer subtypes, in comparison with other breast markers as well as cancers from different sites. Its prognostic relevance with different subtypes and other NR expression was also examined in breast cancers., Methods: Immunohistochemical analysis was performed on totally 1,944 cancers from six different organs., Results: PELP1 expression rate was the highest in breast cancers (70.5%) among different cancers. Compared to GATA3, mammaglobin and gross cystic disease fluid protein 15, PELP1 was less sensitive than GATA3 for luminal cancers, but was the most sensitive for non-luminal cancers. PELP1 has low expression rate (<20%) in colorectal cancers, gastric cancers and renal cell carcinomas, but higher in lung cancers (49.1%) and ovarian cancers (42.3%). In breast cancer, PELP1 expression was an independent adverse prognostic factor for non-luminal cancers (disease-free survival [DFS]: hazard ratio [HR], 1.403; p=0.012 and breast cancer specific survival [BCSS]: HR, 1.443; p=0.015). Interestingly, its expression affected the prognostication of androgen receptor (AR). ARposPELP1lo luminal cancer showed the best DFS (log-rank=8.563, p=0.036) while ARnegPELP1hi non-luminal cancers showed the worst DFS (log-rank=9.536, p=0.023)., Conclusion: PELP1 is a sensitive marker for breast cancer, particularly non-luminal cases. However, its considerable expression in lung and ovarian cancers may limit its utility in differential diagnosis in some scenarios. PELP1 expression was associated with poor outcome in non-luminal cancers and modified the prognostic effects of AR, suggesting the potential significance of NR co-regulator in prognostication.

Background: Indolent T-cell proliferative disorder of the GIT is a rare and provisional entity in the revised WHO 2016 classification. The patients usually have prolonged survival with persistent disease even without any treatment., Case Presentation: The 46 years old male patient has been followed up for more than 6 years without chemotherapy. Repeated gastrointestinal biopsies showed expansion of the lamina propria extending to the submucosa by small to medium sized lymphocytes with minimal cytologic atypia. The lymphoid cells were positive for CD3, CD43, TIA-1, CD2, CD7 and the B-cell marker CD20; but negative for CD4, CD8, PAX5, CD56, cyclinD1, granzyme (GraB) and Epstein Barr virus-encoded RNA (EBER). Ki-67(MIB1) index was less than 10%. Molecular tests demonstrated a clonal rearrangement for T-cell receptor γ (TCR γ) gene but immunoglobulin chain (IgH, IgK, IgL) gene remained germline. Recognition of possible aberrant CD20 expression in indolent T-cell LPD is important to avoid potential diagnostic pitfall and improper treatment., Conclusions: We present an unusual case of indolent T-cell lymphoproliferative disorder with aberrant CD20 expression, Recognition of this unusual immunophenotype of indolent T-cell LPD of GI helps to eschew misdiagnosis of B-cell and other high grade lymphomas and inappropriate aggressive treatment.

Dendritic fibromyxolipoma is an uncommon benign soft tissue tumor. Here, we report a case in a 53-year-old man presenting a painless mass located deep in the latissimus dorsi of the right back. Microscopically, the tumor was mainly consisted of small spindle and stellate cells, abundant myxoid stroma, collagen bundles and mature adipose tissue. Immunohistochemical study showed the spindle and stellate cells were positive for CD34, Bcl-2 and Vimentim, but not for Keratin, EMA, SMA and Desmin. To date, one year after operation, the patient is well without evidence of recurrence or metastasis. The implication of this report is to provide insights into further understanding of this rare tumor with review of the literature.

Abdominal leiomyomas are extremely rare intraabdominal tumors, especially in male patient. Here, we report a case of a 22 years-old male with a huge abdominal leiomyoma. The patient presented with a chief complaint of abdominal distension for three months, no others significant symptom were found. CT-scan showed a cystic-solid huge mass in the middle and lower abdominal peritoneal cavity with uneven density. An exploratory laparotomy was performed and the tumor was completely resected. Microscopically, Tumor cells have a spindled shape, eosinophilic cytoplasm, and cigar-like nuclei, arranged in bundles or intersecting fascicles. Immunohistochemistry, the tumor cells were SMA, desmin diffuse positive and CD117, S-100 negative, interestingly, ER, PR were positive. The characteristics of a few of the male abdominal leiomyoma reported in the literature were generalized.