Search

Motivation Detecting synthetic lethality (SL) is a promising strategy for identifying anti-cancer drug targets. Targeting SL partners of a primary gene mutated in cancer is selectively lethal to cancer cells. Due to high cost of wet-lab experiments and availability of gold standard SL data, supervised machine learning for SL prediction has been popular. However, most of the methods are based on binary classification and thus limited by the lack of reliable negative data. Contrastive learning can train models without any negative sample and is thus promising for finding novel SLs. Results We propose NSF4SL, a negative-sample-free SL prediction model based on a contrastive learning framework. It captures the characteristics of positive SL samples by using two branches of neural networks that interact with each other to learn SL-related gene representations. Moreover, a feature-wise data augmentation strategy is used to mitigate the sparsity of SL data. NSF4SL significantly outperforms all baselines which require negative samples, even in challenging experimental settings. To the best of our knowledge, this is the first time that SL prediction is formulated as a gene ranking problem, which is more practical than the current formulation as binary classification. NSF4SL is the first contrastive learning method for SL prediction and its success points to a new direction of machine-learning methods for identifying novel SLs. Availability and implementation Our source code is available at https://github.com/JieZheng-ShanghaiTech/NSF4SL. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Periodontal ligament stem cells (PDLSCs) are promising stem cells sources for regenerative medicine, particularly clinical periodontal ligament repair. It is critical to maintain high quality and a large quantity of PDLSCs for clinical usage. However, how PDLSCs respond to environmental stimuli, including reactive oxygen species (ROS), is poorly understood. The aim of the present study was to investigate how PDLSCs react to oxidative stress and the underlying mechanisms. Hydrogen peroxide-induced oxidative stress was used to mimic a ROS increase in rat PDLSCs. The expression levels of Creb were detected under oxidative stress to examine the role that Creb serves in PDLSCs under oxidative stress. The present results demonstrated that the expression of Creb was reduced in a dose-dependent manner in response to the H2O2 stimulus. Overexpressing Creb significantly reduced the ROS levels and protein expression levels of apoptotic genes in PDLSCs. The phosphorylation of the ERK pathway is indispensable in the activation of Creb-induced protection. Our results revealed a protective role of Creb in ROS-induced apoptosis, and validated the ERK/Creb/apoptosis regulator Bcl-2 pathway works as an anti-apoptotic signaling in PDLSCs. These findings will facilitate the in vitro culturing of PDLSCs for clinical usage and promote stem cell based therapy for periodontal tissue regeneration. [ABSTRACT FROM AUTHOR]

Highlights • Fbxw7 is upregulated in PDLSCs under oxidative stress. • Overexpression of Fbxw7 protects PDLSCs from H 2 O 2 -induced cytotoxicity. • Overexpression of Fbxw7 deactivates the Notch signaling pathway. • Inhibition of the Notch pathway attenuates H 2 O 2 -induced apoptosis in Fbxw7-knockout cells. Abstract Objective To investigate the protective role of F-box/WD repeat domain-containing 7 in rat periodontal ligament stem cells under oxidative stress. Materials and methods The apoptosis of rat periodontal ligament stem cells was induced by exposure to various concentrations of hydrogen peroxide for 24 h, after which cell viability and the cleaved caspase-3 and -9 levels were determined. The levels of proteins in the Notch signaling pathway were determined by western blotting. Results The overexpression of F-box/WD repeat domain-containing 7 increased cell viability following hydrogen peroxide administration and suppressed the activation of caspases-3 and -9. The overexpression of F-box/WD repeat domain-containing 7 inhibited Notch signaling. Furthermore, the protective effect of F-box/WD repeat domain-containing 7 could be resumed by PF-03084014, a Notch-specific inhibitor. Conclusions These observations suggest a protective role of F-box/WD repeat domain-containing 7 against hydrogen peroxide-induced oxidative stress in rat periodontal ligament stem cells. These findings will facilitate the in vitro culturing of periodontal ligament stem cell for clinical usage and promote stem cell-based therapy for periodontal tissue regeneration. [ABSTRACT FROM AUTHOR]

Small cell lung cancer (SCLC) originates from pulmonary neuroendocrine cells and accounts for approximately 15% of lung cancer incidents. Patients with SCLC have a very low survival rate due to fast progression and early metastasis. Despite the recent approval of immune checkpoint blockade for treatment of SCLC by US FDA, conventional platinum chemotherapy remains the first‐line treatment which always develops quick drug resistance. To define targets for diagnosis and treatment, SCLC has been categorized by different molecular markers. The most popular markers include genomic mutations in tumour suppressor genes such as TP53 and RB1 and expression of lineage‐specific transcription factors (TFs), that is ASCL1, NEUROD1, POU2F3 and YAP1. As DNA methylation is an important hallmark of cancer, efforts were made to investigate the mechanisms of DNA methylation involved in SCLC progression. Indeed, SCLC has distinct pattern of DNA methylation due to its different features compared to non‐SCLC and other tumours. In this review, we summarized the mechanisms of DNA methylation in SCLC which are associated with lineage‐specific TFs, cell proliferation, anti‐apoptosis, drug resistance, immune evasion and metastasis. We foresaw the challenges of applying DNA methylation in clinical diagnosis and treatment and discussed new approaches and technologies to overcome them. Combined with other gene regulatory information such as transcription and histone modification, DNA methylation/hydroxymethylation in SCLC will be resolved at single‐cell resolution to dissect the tumour microenvironment. The huge multiomics data will be processed and integrated with clinical data such as clinical images and pathological histochemistry by artificial intelligence and cloud computing. Circulating cell‐free DNA methylation will greatly enhance early diagnosis and prognosis prediction. New organoid and organ chip models will break through the obstacles of sampling limitation, faithfully simulate the physiology of human tissues and enable examining spatiotemporal DNA methylation during SCLC progression. [ABSTRACT FROM AUTHOR]

Motivation Synthetic lethality (SL) is a promising strategy for anticancer therapy, as inhibiting SL partners of genes with cancer-specific mutations can selectively kill the cancer cells without harming the normal cells. Wet-lab techniques for SL screening have issues like high cost and off-target effects. Computational methods can help address these issues. Previous machine learning methods leverage known SL pairs, and the use of knowledge graphs (KGs) can significantly enhance the prediction performance. However, the subgraph structures of KG have not been fully explored. Besides, most machine learning methods lack interpretability, which is an obstacle for wide applications of machine learning to SL identification. Results We present a model named KR4SL to predict SL partners for a given primary gene. It captures the structural semantics of a KG by efficiently constructing and learning from relational digraphs in the KG. To encode the semantic information of the relational digraphs, we fuse textual semantics of entities into propagated messages and enhance the sequential semantics of paths using a recurrent neural network. Moreover, we design an attentive aggregator to identify critical subgraph structures that contribute the most to the SL prediction as explanations. Extensive experiments under different settings show that KR4SL significantly outperforms all the baselines. The explanatory subgraphs for the predicted gene pairs can unveil prediction process and mechanisms underlying synthetic lethality. The improved predictive power and interpretability indicate that deep learning is practically useful for SL-based cancer drug target discovery. Availability and implementation The source code is freely available at https://github.com/JieZheng-ShanghaiTech/KR4SL. [ABSTRACT FROM AUTHOR]