HNetGO: protein function prediction via heterogeneous network transformer.

Protein function annotation is one of the most important research topics for revealing the essence of life at molecular level in the post-genome era. Current research shows that integrating multisource data can effectively improve the performance of protein function prediction models. However, the heavy reliance on complex feature engineering and model integration methods limits the development of existing methods. Besides, models based on deep learning only use labeled data in a certain dataset to extract sequence features, thus ignoring a large amount of existing unlabeled sequence data. Here, we propose an end-to-end protein function annotation model named HNetGO, which innovatively uses heterogeneous network to integrate protein sequence similarity and protein-protein interaction network information and combines the pretraining model to extract the semantic features of the protein sequence. In addition, we design an attention-based graph neural network model, which can effectively extract node-level features from heterogeneous networks and predict protein function by measuring the similarity between protein nodes and gene ontology term nodes. Comparative experiments on the human dataset show that HNetGO achieves state-of-the-art performance on cellular component and molecular function branches.

Pan-cancer molecular analysis of EGFR large fragment deletion in the Asian population.

BACKGROUND: Large fragment deletion (LFD) of EGFR was associated with carcinogenesis in many types of cancers. However, the molecular features of EGFR-LFD have not been studied in the Asian cancer population. METHOD: Here we retrospectively analyzed the targeted sequencing data from a large cancer database. RESULTS: EGFR-LFD was detected at a frequency of 0.03% with EGFRvIII being the most frequently observed LFD. TERTp variants were identified in 60% of the cases. TP53 alterations (33%) were mutually exclusive with TERTp variants and coexisted with EGFR-LFD in lung cancer and colorectal cancer. EGFR amplification (67%) and chromosome 10p deletion (53%) were the most focal-level and arm-level CNV in this cohort. EGFR exon2-17 skipping was found in the tumor tissue of one patient after progressing on osimertinib. CONCLUSION: Our study provided valuable insights into the distribution and molecular characteristics of EGFR-LFD, hoping to shed light on the treatment management for EGFR-LFD carriers.

iTTCA-RF: a random forest predictor for tumor T cell antigens.

BACKGROUND: Cancer is one of the most serious diseases threatening human health. Cancer immunotherapy represents the most promising treatment strategy due to its high efficacy and selectivity and lower side effects compared with traditional treatment. The identification of tumor T cell antigens is one of the most important tasks for antitumor vaccines development and molecular function investigation. Although several machine learning predictors have been developed to identify tumor T cell antigen, more accurate tumor T cell antigen identification by existing methodology is still challenging. METHODS: In this study, we used a non-redundant dataset of 592 tumor T cell antigens (positive samples) and 393 tumor T cell antigens (negative samples). Four types feature encoding methods have been studied to build an efficient predictor, including amino acid composition, global protein sequence descriptors and grouped amino acid and peptide composition. To improve the feature representation ability of the hybrid features, we further employed a two-step feature selection technique to search for the optimal feature subset. The final prediction model was constructed using random forest algorithm. RESULTS: Finally, the top 263 informative features were selected to train the random forest classifier for detecting tumor T cell antigen peptides. iTTCA-RF provides satisfactory performance, with balanced accuracy, specificity and sensitivity values of 83.71%, 78.73% and 88.69% over tenfold cross-validation as well as 73.14%, 62.67% and 83.61% over independent tests, respectively. The online prediction server was freely accessible at http://lab.malab.cn/~acy/iTTCA . CONCLUSIONS: We have proven that the proposed predictor iTTCA-RF is superior to the other latest models, and will hopefully become an effective and useful tool for identifying tumor T cell antigens presented in the context of major histocompatibility complex class I.

LOXL1-AS1 Contributes to Non-Small Cell Lung Cancer Progression by Regulating miR-3128/RHOXF2 Axis.

PURPOSE: The purpose of this study was to investigate the molecular mechanism of LncRNA LOXL1-AS1 in non-small cell lung cancer (NSCLC). METHODS: Lung cancer cell lines (H1299, A549, H520 and H596) and human normal lung epithelial cell line (BEAS-2B) were used in this study. Gene expression was measured by qRT-PCR (quantitative real-time PCR). The bioinformatics databases (miRDB and TargetScan7) were used to predict target genes. Luciferase assay and pull-down assay were processed for verifying the binding sites. CCK8 assay was used for detecting proliferation, and transwell assay was undertaken for migration and invasion. RESULTS: LncRNA LOXL1-AS1 was higher expressed in lung cancer tissues and cells. Moreover, LOXL1-AS1 expression was upregulated in tumor tissues with advanced stages and metastasis. After knocking down LOXL1-AS1, proliferation, invasion and migration of H1299 and A549 cells were inhibited. Interestingly, miR-3128 was negatively regulated by LncRNA LOXL1-AS1, which inhibited the expression of RHOXF2. Rescue assay also confirmed that miR-3128 inhibitor and oeRHOXF2 could rescue the effect of down-regulated LOXL1-AS1 on proliferation, invasion and migration progression. CONCLUSION: LOXL1-AS1 promotes the progression of NSCLC by regulating miR-3128/RHOXF2 axis, which might be a new potential target for the diagnosis and treatment of NSCLC.

Apatinib, combined with chemotherapy or alone is effective in treating angiosarcoma: a case report.

Angiosarcomas are rare but aggressive tumors with poor prognosis. The treatment of angiosarcomas with vascular endothelial growth factor receptor inhibitors is still in the stage of clinical exploration. Herein we reported a patient of skin angiosarcoma with multiple organ metastasis. She was resistance to multiline chemotherapy and pazopanib but achieved remarkable shrinkage of the lesion after apatinib treatment combined with chemotherapy or alone. The progression-free survival of the primary lesion with KRAS V14I and RBM10 E119D mutations (10 months) was shorter than that of the brain without the mutation ( ≥ 12 months). Although it is not clear whether the KRAS V14I and RBM10 E119D mutations are the main factors that impact the effect of apatinib treatment or not, the results of this study will provide valuable clues for relevant follow-up basic and clinical studies.