MultiScale-CNN-4mCPred: a multi-scale CNN and adaptive embedding-based method for mouse genome DNA N4-methylcytosine prediction.

N4-methylcytosine (4mC) is an important epigenetic mechanism, which regulates many cellular processes such as cell differentiation and gene expression. The knowledge about the 4mC sites is a key foundation to exploring its roles. Due to the limitation of techniques, precise detection of 4mC is still a challenging task. In this paper, we presented a multi-scale convolution neural network (CNN) and adaptive embedding-based computational method for predicting 4mC sites in mouse genome, which was referred to as MultiScale-CNN-4mCPred. The MultiScale-CNN-4mCPred used adaptive embedding to encode nucleotides, and then utilized multi-scale CNNs as well as long short-term memory to extract more in-depth local properties and contextual semantics in the sequences. The MultiScale-CNN-4mCPred is an end-to-end learning method, which requires no sophisticated feature design. The MultiScale-CNN-4mCPred reached an accuracy of 81.66% in the 10-fold cross-validation, and an accuracy of 84.69% in the independent test, outperforming state-of-the-art methods. We implemented the proposed method into a user-friendly web application which is freely available at: http://www.biolscience.cn/MultiScale-CNN-4mCPred/ .

DeepHLAPred: a deep learning-based method for non-classical HLA binder prediction.

Human leukocyte antigen (HLA) is closely involved in regulating the human immune system. Despite great advance in detecting classical HLA Class I binders, there are few methods or toolkits for recognizing non-classical HLA Class I binders. To fill in this gap, we have developed a deep learning-based tool called DeepHLAPred. The DeepHLAPred used electron-ion interaction pseudo potential, integer numerical mapping and accumulated amino acid frequency as initial representation of non-classical HLA binder sequence. The deep learning module was used to further refine high-level representations. The deep learning module comprised two parallel convolutional neural networks, each followed by maximum pooling layer, dropout layer, and bi-directional long short-term memory network. The experimental results showed that the DeepHLAPred reached the state-of-the-art performanceson the cross-validation test and the independent test. The extensive test demonstrated the rationality of the DeepHLAPred. We further analyzed sequence pattern of non-classical HLA class I binders by information entropy. The information entropy of non-classical HLA binder sequence implied sequence pattern to a certain extent. In addition, we have developed a user-friendly webserver for convenient use, which is available at http://www.biolscience.cn/DeepHLApred/ . The tool and the analysis is helpful to detect non-classical HLA Class I binder. The source code and data is available at https://github.com/tangxingyu0/DeepHLApred .

Deep6mAPred: A CNN and Bi-LSTM-based deep learning method for predicting DNA N6-methyladenosine sites across plant species.

DNA N6-methyladenine (6mA) is a key DNA modification, which plays versatile roles in the cellular processes, including regulation of gene expression, DNA repair, and DNA replication. DNA 6mA is closely associated with many diseases in the mammals and with growth as well as development of plants. Precisely detecting DNA 6mA sites is of great importance to exploration of 6mA functions. Although many computational methods have been presented for DNA 6mA prediction, there is still a wide gap in the practical application. We presented a convolution neural network (CNN) and bi-directional long-short term memory (Bi-LSTM)-based deep learning method (Deep6mAPred) for predicting DNA 6mA sites across plant species. The Deep6mAPred stacked the CNNs and the Bi-LSTMs in a paralleling manner instead of a series-connection manner. The Deep6mAPred also employed the attention mechanism for improving the representations of sequences. The Deep6mAPred reached an accuracy of 0.9556 over the independent rice dataset, far outperforming the state-of-the-art methods. The tests across plant species showed that the Deep6mAPred is of a remarkable advantage over the state of the art methods. We developed a user-friendly web application for DNA 6mA prediction, which is freely available at http://106.13.196.152:7001/ for all the scientific researchers. The Deep6mAPred would enrich tools to predict DNA 6mA sites and speed up the exploration of DNA modification.

DeepLBCEPred: A Bi-LSTM and multi-scale CNN-based deep learning method for predicting linear B-cell epitopes.

The epitope is the site where antigens and antibodies interact and is vital to understanding the immune system. Experimental identification of linear B-cell epitopes (BCEs) is expensive, is labor-consuming, and has a low throughput. Although a few computational methods have been proposed to address this challenge, there is still a long way to go for practical applications. We proposed a deep learning method called DeepLBCEPred for predicting linear BCEs, which consists of bi-directional long short-term memory (Bi-LSTM), feed-forward attention, and multi-scale convolutional neural networks (CNNs). We extensively tested the performance of DeepLBCEPred through cross-validation and independent tests on training and two testing datasets. The empirical results showed that the DeepLBCEPred obtained state-of-the-art performance. We also investigated the contribution of different deep learning elements to recognize linear BCEs. In addition, we have developed a user-friendly web application for linear BCEs prediction, which is freely available for all scientific researchers at: http://www.biolscience.cn/DeepLBCEPred/.

Disulfidptosis: a new target for metabolic cancer therapy.

Altered metabolism is a hallmark of cancer and presents a vulnerability that can be exploited in cancer treatment. Regulated cell death (RCD) plays a crucial role in cancer metabolic therapy. A recent study has identified a new metabolic-related RCD known as disulfidptosis. Preclinical findings suggest that metabolic therapy using glucose transporter (GLUT) inhibitors can trigger disulfidptosis and inhibit cancer growth. In this review, we summarize the specific mechanisms underlying disulfidptosis and outline potential future research directions. We also discuss the challenges that may arise in the clinical translation of disulfidptosis research.

Targeting the dynamics of cancer metabolism in the era of precision oncology.

Cancer metabolic reprogramming is a promising target for cancer therapy. The progression of tumors, including their growth, development, metastasis, and spread, is a dynamic process that varies over time and location. This means that the metabolic state of tumors also fluctuates. A recent study found that energy production efficiency is lower in solid tumors but increases significantly in tumor metastasis. Despite its importance for targeted tumor metabolism therapy, few studies have described the dynamic metabolic changes of tumors. In this commentary, we discuss the limitations of past targeted tumor metabolism therapy and the key findings of this study. We also summarize its immediate clinical implications for dietary intervention and explore future research directions for understanding the dynamic changes in tumor metabolic reprogramming.

LangMoDHS: A deep learning language model for predicting DNase I hypersensitive sites in mouse genome.

DNase I hypersensitive sites (DHSs) are a specific genomic region, which is critical to detect or understand cis-regulatory elements. Although there are many methods developed to detect DHSs, there is a big gap in practice. We presented a deep learning-based language model for predicting DHSs, named LangMoDHS. The LangMoDHS mainly comprised the convolutional neural network (CNN), the bi-directional long short-term memory (Bi-LSTM) and the feed-forward attention. The CNN and the Bi-LSTM were stacked in a parallel manner, which was helpful to accumulate multiple-view representations from primary DNA sequences. We conducted 5-fold cross-validations and independent tests over 14 tissues and 4 developmental stages. The empirical experiments showed that the LangMoDHS is competitive with or slightly better than the iDHS-Deep, which is the latest method for predicting DHSs. The empirical experiments also implied substantial contribution of the CNN, Bi-LSTM, and attention to DHSs prediction. We implemented the LangMoDHS as a user-friendly web server which is accessible at http:/www.biolscience.cn/LangMoDHS/. We used indices related to information entropy to explore the sequence motif of DHSs. The analysis provided a certain insight into the DHSs.

Nanopore sequencing technology and its applications.

Since the development of Sanger sequencing in 1977, sequencing technology has played a pivotal role in molecular biology research by enabling the interpretation of biological genetic codes. Today, nanopore sequencing is one of the leading third-generation sequencing technologies. With its long reads, portability, and low cost, nanopore sequencing is widely used in various scientific fields including epidemic prevention and control, disease diagnosis, and animal and plant breeding. Despite initial concerns about high error rates, continuous innovation in sequencing platforms and algorithm analysis technology has effectively addressed its accuracy. During the coronavirus disease (COVID-19) pandemic, nanopore sequencing played a critical role in detecting the severe acute respiratory syndrome coronavirus-2 virus genome and containing the pandemic. However, a lack of understanding of this technology may limit its popularization and application. Nanopore sequencing is poised to become the mainstream choice for preventing and controlling COVID-19 and future epidemics while creating value in other fields such as oncology and botany. This work introduces the contributions of nanopore sequencing during the COVID-19 pandemic to promote public understanding and its use in emerging outbreaks worldwide. We discuss its application in microbial detection, cancer genomes, and plant genomes and summarize strategies to improve its accuracy.

Contribution of Nischarin/IRAS in CNS development, injury and diseases.

BACKGROUND: Murine Nischarin and its human homolog IRAS are scaffold proteins highly expressed in the central nervous system (CNS). Nischarin was initially discovered as a tumor suppressor protein, and recent studies have also explored its potential value in the CNS. Research on IRAS has largely focused on its effect on opioid dependence. Although the role of Nischarin/IRAS in the physiological function and pathological process of the CNS has gradually attracted attention and the related research results are expected to be applied in clinical practice, there is no systematic review of the role and mechanisms of Nischarin/IRAS in the CNS so far. AIM OF REVIEW: This review will systematically analyze the role and mechanism of Nischarin/IRAS in the CNS, and provide necessary references and possible targets for the treatment of neurological diseases, thereby broadening the direction of Nischarin/IRAS research and facilitating clinical translation. KEY SCIENTIFIC CONCEPTS OF REVIEW: The pathophysiological processes affected by dysregulation of Nischarin/IRAS expression in the CNS are mainly introduced, including spinal cord injury (SCI), opioid dependence, anxiety, depression, and autism. The molecular mechanisms such as factors regulating Nischarin/IRAS expression and signal transduction pathways regulated by Nischarin/IRAS are systematically summarized. Finally, the clinical application of Nischarin/IRAS has been prospected.

Elesclomol: a copper ionophore targeting mitochondrial metabolism for cancer therapy.

Elesclomol is an anticancer drug that targets mitochondrial metabolism. In the past, elesclomol was recognized as an inducer of oxidative stress, but now it has also been found to suppress cancer by inducing cuproptosis. Elesclomol's anticancer activity is determined by the dependence of cancer on mitochondrial metabolism. The mitochondrial metabolism of cancer stem cells, cancer cells resistant to platinum drugs, proteasome inhibitors, molecularly targeted drugs, and cancer cells with inhibited glycolysis was significantly enhanced. Elesclomol exhibited tremendous toxicity to all three kinds of cells. Elesclomol's toxicity to cells is highly dependent on its transport of extracellular copper ions, a process involved in cuproptosis. The discovery of cuproptosis has perfected the specific cancer suppressor mechanism of elesclomol. For some time, elesclomol failed to yield favorable results in oncology clinical trials, but its safety in clinical application was confirmed. Research progress on the relationship between elesclomol, mitochondrial metabolism and cuproptosis provides a possibility to explore the reapplication of elesclomol in the clinic. New clinical trials should selectively target cancer types with high mitochondrial metabolism and attempt to combine elesclomol with platinum, proteasome inhibitors, molecularly targeted drugs, or glycolysis inhibitors. Herein, the particular anticancer mechanism of elesclomol and its relationship with mitochondrial metabolism and cuproptosis will be presented, which may shed light on the better application of elesclomol in clinical tumor treatment.

A capsule network-based method for identifying transcription factors.

Transcription factors (TFs) are typical regulators for gene expression and play versatile roles in cellular processes. Since it is time-consuming, costly, and labor-intensive to detect it by using physical methods, it is desired to develop a computational method to detect TFs. Here, we presented a capsule network-based method for identifying TFs. This method is an end-to-end deep learning method, consisting mainly of an embedding layer, bidirectional long short-term memory (LSTM) layer, capsule network layer, and three fully connected layers. The presented method obtained an accuracy of 0.8820, being superior to the state-of-the-art methods. These empirical experiments showed that the inclusion of the capsule network promoted great performances and that the capsule network-based representation was superior to the property-based representation for distinguishing between TFs and non-TFs. We also implemented the presented method into a user-friendly web server, which is freely available at http://www.biolscience.cn/Capsule_TF/ for all scientific researchers.

Enhancer-LSTMAtt: A Bi-LSTM and Attention-Based Deep Learning Method for Enhancer Recognition.

Enhancers are short DNA segments that play a key role in biological processes, such as accelerating transcription of target genes. Since the enhancer resides anywhere in a genome sequence, it is difficult to precisely identify enhancers. We presented a bi-directional long-short term memory (Bi-LSTM) and attention-based deep learning method (Enhancer-LSTMAtt) for enhancer recognition. Enhancer-LSTMAtt is an end-to-end deep learning model that consists mainly of deep residual neural network, Bi-LSTM, and feed-forward attention. We extensively compared the Enhancer-LSTMAtt with 19 state-of-the-art methods by 5-fold cross validation, 10-fold cross validation and independent test. Enhancer-LSTMAtt achieved competitive performances, especially in the independent test. We realized Enhancer-LSTMAtt into a user-friendly web application. Enhancer-LSTMAtt is applicable not only to recognizing enhancers, but also to distinguishing strong enhancer from weak enhancers. Enhancer-LSTMAtt is believed to become a promising tool for identifying enhancers.

Controllable gelation of methylcellulose by a salt mixture.

The effects of a salt mixture consisting of a salt-out salt (NaCl) and a salt-in salt (NaI) on the sol-gel transition of methylcellulose (MC) in aqueous solution have been studied by means of micro differential scanning calorimetry and rheometry. The salt mixture was found to have a combined effect from the salt-out and salt-in salts in the mixture, and the salt effect was dependent on the water hydration abilities of the component ions and ion concentration. At a fixed total salt concentration, the sol-gel transition temperature nicely followed a rule of mixing: Tp = m1Tp1 + m2Tp2 where Tp, Tp1, and Tp2 are the gelation peak temperatures for the MC solutions with a salt mixture, NaCl, and NaI, respectively, and mi is the molar fraction of the salt component i in the salt mixture. The linear rule of mixing proved that the effects of NaCl and NaI on the sol-gel transition of MC are completely independent. In addition, the presence of a single salt or a salt mixture in a MC solution does not change the essential mechanism of MC gelation. Therefore, the sol-gel transition of MC can be simply controlled by a salt mixture consisting of a salt-out salt and a salt-in salt. The rheological results supported the micro thermal results excellently. But the gel strength of MC containing salts was influenced by both salt type and salt concentration.