Publications by authors named "Jianxin Wang"

560 Publications

Genetic continuity of Bronze Age ancestry with increased Steppe-related ancestry in Late Iron Age Uzbekistan.

Mol Biol Evol 2021 Jul 28. Epub 2021 Jul 28.

Key Laboratory of Vertebrate Evolution and Human Origins, Institute of Vertebrate Paleontology and Paleoanthropology, Chinese Academy of Sciences, Beijing, 100044, China.

While Uzbekistan and Central Asia are known for the well-studied Bronze Age civilization of Bactria-Margiana Archaeological Complex (BMAC), the lesser-known Iron Age was also a dynamic period that resulted in increased interaction and admixture among different cultures from this region. To broaden our understanding of events which impacted the demography and population structure of this region, we generated 27 genome-wide SNP capture datasets of Late Iron Age individuals around the Historical Kushan time period (∼2100-1500 BP) from three sites in South Uzbekistan. Overall, Bronze Age ancestry persists into the Iron Age in Uzbekistan, with no major replacements of populations with Steppe-related ancestry. However, these individuals suggest diverse ancestries related to Iranian farmers, Anatolian farmers and Steppe herders, with a small amount of West European Hunter Gatherer, East Asian and South Asian Hunter Gatherer ancestry as well. Genetic affinity towards the Late Bronze Age Steppe herders and a higher Steppe-related ancestry than that found in BMAC populations suggest an increased mobility and interaction of individuals from Northern Steppe in a Southward direction. In addition, a decrease of Iranian farmers and an increase of Anatolian farmer-like ancestry in Uzbekistan Iron Age individuals were observed compared to the BMAC populations from Uzbekistan. Thus, despite continuity from the Bronze Age, increased admixture played a major role in the shift from the Bronze to the Iron Age in southern Uzbekistan. This mixed ancestry is also observed in other parts of the Steppe and Central Asia, suggesting more widespread admixture among local populations.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/molbev/msab216DOI Listing
July 2021

Antibody-siRNA conjugates (ARCs) using multifunctional peptide as a tumor enzyme cleavable linker mediated effective intracellular delivery of siRNA.

Int J Pharm 2021 Jul 24;606:120940. Epub 2021 Jul 24.

Tianjin Key Laboratory on Technologies Enabling Development of Clinical Therapeutics and Diagnostics, School of Pharmacy, Tianjin Medical University, Tianjin 300070, China. Electronic address:

The tissue-specific targeted delivery and efficient cellular uptake of siRNAs are the main obstacles to their clinical application. Antibody-siRNA-conjugates (ARCs) can deliver siRNA by exploiting the targeting property of antibodies like antibody-drug conjugates (ADCs). However, the effective conjugation of antibodies and siRNAs and the release of siRNAs specifically at target sites have posed challenges to the development of ARCs. In this study, the successful conjugation of antibodies and siRNAs was achieved using a multifunctional peptide as a linker, composed of a cell-penetrating peptide (CPP) and a substrate peptide (SP), which is highly expressed in solid tumors. The resulting antibody-multifunctional peptide (SP-CPP)-siRNA system delivered the siRNA to target tumor cells by the specific binding of the antibody. Once the enzymes on the tumor cell surface hydrolyzed the substrate peptide linker, siRNA-CPP was released from ARCs. The released siRNA-CPP entered the targeted cells via the cellular penetrating ability of CPP, resulting in improved siRNA-mediated gene silencing efficiency, verified both in vitro and in vivo. After intravenous administration, the designed ARCs achieved approximately 66.7% EGFP (Enhanced Green Fluorescent Protein) downregulation efficiency in nude mice xenografted with the HCT116-EGFP tumor model. The proposed system provides a prospective choice for ARC production and the safe and efficient delivery of siRNAs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijpharm.2021.120940DOI Listing
July 2021

Fascinating MXene nanomaterials: emerging opportunities in the biomedical field.

Biomater Sci 2021 Jul 23. Epub 2021 Jul 23.

Science and Technology Innovation Center, Guangzhou University of Chinese Medicine, Guangzhou 510405, China.

In recent years, there has been rapid progress in MXene research due to its distinctive two-dimensional structure and outstanding properties. Especially in biomedical applications, MXenes have attracted widespread favor with numerous studies on biosafety, bioimaging, therapy, and biosensing, although their development is still in the experimental stage. A comprehensive understanding of the current status of MXenes in biomedicine will promote their use in clinical applications. Here, we review advances in MXene research. First, we introduce the methods of synthesis, surface modification and functionalization of MXenes. Then, we summarize the biosafety and biocompatibility, paving the way for specific biomedical applications. On this basis, MXene nanostructures are described with respect to their use in antibacterial, bioimaging, cancer therapy, tissue regeneration and biosensor applications. Finally, we discuss MXene as a promising candidate material for further applications in biomedicine.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1039/d1bm00526jDOI Listing
July 2021

Exosomal transfer of miR‑25‑3p promotes the proliferation and temozolomide resistance of glioblastoma cells by targeting FBXW7.

Int J Oncol 2021 Aug 19;59(2). Epub 2021 Jul 19.

Department of Neurosurgery, Henan Provincial People's Hospital, Henan Provincial Cerebrovascular Hospital, Zhengzhou University People's Hospital, Henan University People's Hospital, Zhengzhou, Henan 450003, P.R. China.

Intrinsic or acquired resistance to temozolomide (TMZ) is a frequent occurrence in patients with glioblastoma (GBM). Accumulating evidence has indicated that the exosomal transfer of proteins and RNAs may confer TMZ resistance to recipient cells; however, the potential molecular mechanisms are not fully understood. Thus, the aim of the present study was to elucidate the possible role of exosomal microRNAs (miRNAs/miRs) in the acquired resistance to TMZ in GBM. A TMZ‑resistant GBM cell line (A172R) was used, and exosomes derived from A172R cells were extracted. Exosomal miR‑25‑3p was identified as a miRNA associated with TMZ resistance. The potential functions of exosomal miR‑25‑3p were evaluated by reverse transcription‑quantitative PCR, as well as cell viability, colony formation and soft agar assay, flow cytometry, western blot analysis, BrdU incorporation assay, tumor xenograft formation, luciferase reporter assay and RNA immunoprecipitation. It was found that A172R‑derived exosomes promoted the proliferation and TMZ resistance of sensitive GBM cells. Moreover, miR‑25‑3p epxression was upregulated in the exosomes of A172R cells and in serum samples of patients with GBM treated with TMZ. The depletion of exosomal miR‑25‑3p partially abrogated the effects induced by the transfer of exosomes from A172R cells. By contrast, miR‑25‑3p overexpression facilitated the proliferation and TMZ resistance of sensitive GBM cells. F‑box and WD repeat domain‑containing‑7 (FBXW7) was identified as a direct target of miR‑25‑3p. FBXW7 knockdown promoted the proliferation and TMZ resistance of GBM cells. Furthermore, the exosomal transfer of miR‑25‑3p promoted c‑Myc and cyclin E expression by downregulating FBXW7. Our results provided a novel insight into exosomal microRNAs in acquired TMZ resistance of GBM cells. Besides, exosomal miR‑25‑3p might be a potential prognostic marker for GBM patients.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3892/ijo.2021.5244DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8295027PMC
August 2021

Ferrite-encapsulated nanoparticles with stable photothermal performance for multimodal imaging-guided atherosclerotic plaque neovascularization therapy.

Biomater Sci 2021 Jul 13. Epub 2021 Jul 13.

Department of Cardiology, The First Affiliated Hospital, Cardiovascular Institute, Harbin Medical University, Harbin 150001, P. R. China. and Department of Pathophysiology and Key Laboratory of Cardiovascular Pathophysiology, Harbin Medical University, Key Laboratory of Cardiovascular Medicine Research (Harbin Medical University), Ministry of Education, Harbin 150086, P. R. China.

Pathological angiogenesis is a critical contributor to atherosclerotic plaque rupture. However, there are few effective theranostic strategies to stabilize plaques by suppressing neovascularization. In this study, we fabricated a polymeric nanosystem using 3 nm manganese ferrite (MnFe2O4) and perfluorohexane (PFH) stabilized by polylactic acid-glycolic acid (PLGA) shells and conjugated to the surface of an anti-vascular endothelial growth factor receptor 2 (VEGFR2) antibody [ramucirumab (Ram)]. The [email protected]/MnFe2O4-Ram nanoparticles (NPs) were used as atherosclerotic plaque angiogenesis theranostics for multimodal imaging-guided photothermal therapy (PTT). Three-nanometer MnFe2O4 is an excellent magnetic resonance imaging T1 and photoacoustic imaging contrast agent. Upon exposure to near-infrared (NIR) light, MnFe2O4 in the NPs could transform NIR light into thermal energy for the photothermal elimination of plaque angiogenesis. Additionally, optical droplet vaporization of PFH in the NPs triggered by the thermal effect to form gas bubbles enhanced ultrasound imaging. Our in vitro experiments revealed that [email protected]/MnFe2O4-Ram NPs actively accumulated in rabbit aortic endothelial cells, and NP-mediated PTT promoted endothelial cell apoptosis while inhibiting their proliferation, migration, and tubulogenesis. Notably, the [email protected]/MnFe2O4-Ram NPs possessed excellent photostability and biocompatibility. In the rabbit advanced atherosclerotic plaque model, [email protected]/MnFe2O4-Ram NP-guided PTT significantly induced apoptosis of neovascular endothelial cells and improved the hypoxia status in the plaque 3 days after treatment. On day 28, PTT significantly reduced the density of neovessels and subsequently stabilized rabbit plaques by inhibiting plaque hemorrhage and macrophage infiltration. Collectively, these results suggest that [email protected]/MnFe2O4-Ram NP-guided PTT is a safe and effective theranostic strategy for inhibiting atherosclerotic plaque angiogenesis.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1039/d1bm00343gDOI Listing
July 2021

Multimodal Disentangled Variational Autoencoder with Game Theoretic Interpretability for Glioma grading.

IEEE J Biomed Health Inform 2021 Jul 8;PP. Epub 2021 Jul 8.

Effective fusion of multimodal magnetic resonance imaging (MRI) is of great significance to boost the accuracy of glioma grading thanks to the complementary information provided by different imaging modalities. However, how to extract the common and distinctive information from MRI to achieve complementarity is still an open problem in information fusion research. In this study, we propose a deep neural network model termed as multimodal disentangled variational autoencoder (MMD-VAE) for glioma grading based on radiomics features extracted from preoperative multimodal MRI images. Specifically, the radiomics features are quantized and extracted from the region of interest for each modality. Then, the latent representations of variational autoencoder for these features are disentangled into common and distinctive representations to obtain the shared and complementary data among modalities. Afterward, cross-modality reconstruction loss and common-distinctive loss are designed to ensure the effectiveness of the disentangled representations. Finally, the disentangled common and distinctive representations are fused to predict the glioma grades, and SHapley Additive exPlanations (SHAP) is adopted to quantitatively interpret and analyze the contribution of the important features to grading. Experimental results on two benchmark datasets demonstrate that the proposed MMD-VAE model achieves encouraging predictive performance (AUC:0.9939) on a public dataset, and good generalization performance (AUC:0.9611) on a cross-institutional private dataset. These quantitative results and interpretations may help radiologists understand gliomas better and make better treatment decisions for improving clinical outcomes.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/JBHI.2021.3095476DOI Listing
July 2021

Artificial intelligence for prediction of COVID-19 progression using CT imaging and clinical data.

Eur Radiol 2021 Jul 5. Epub 2021 Jul 5.

School of Computer Science and Engineering, Central South University, Changsha, China.

Objectives: Early recognition of coronavirus disease 2019 (COVID-19) severity can guide patient management. However, it is challenging to predict when COVID-19 patients will progress to critical illness. This study aimed to develop an artificial intelligence system to predict future deterioration to critical illness in COVID-19 patients.

Methods: An artificial intelligence (AI) system in a time-to-event analysis framework was developed to integrate chest CT and clinical data for risk prediction of future deterioration to critical illness in patients with COVID-19.

Results: A multi-institutional international cohort of 1,051 patients with RT-PCR confirmed COVID-19 and chest CT was included in this study. Of them, 282 patients developed critical illness, which was defined as requiring ICU admission and/or mechanical ventilation and/or reaching death during their hospital stay. The AI system achieved a C-index of 0.80 for predicting individual COVID-19 patients' to critical illness. The AI system successfully stratified the patients into high-risk and low-risk groups with distinct progression risks (p < 0.0001).

Conclusions: Using CT imaging and clinical data, the AI system successfully predicted time to critical illness for individual patients and identified patients with high risk. AI has the potential to accurately triage patients and facilitate personalized treatment.

Key Point: • AI system can predict time to critical illness for patients with COVID-19 by using CT imaging and clinical data.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00330-021-08049-8DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8256200PMC
July 2021

A sensitive repeat identification framework based on short and long reads.

Nucleic Acids Res 2021 Jul 2. Epub 2021 Jul 2.

Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha 410083, P.R. China.

Numerous studies have shown that repetitive regions in genomes play indispensable roles in the evolution, inheritance and variation of living organisms. However, most existing methods cannot achieve satisfactory performance on identifying repeats in terms of both accuracy and size, since NGS reads are too short to identify long repeats whereas SMS (Single Molecule Sequencing) long reads are with high error rates. In this study, we present a novel identification framework, LongRepMarker, based on the global de novo assembly and k-mer based multiple sequence alignment for precisely marking long repeats in genomes. The major characteristics of LongRepMarker are as follows: (i) by introducing barcode linked reads and SMS long reads to assist the assembly of all short paired-end reads, it can identify the repeats to a greater extent; (ii) by finding the overlap sequences between assemblies or chomosomes, it locates the repeats faster and more accurately; (iii) by using the multi-alignment unique k-mers rather than the high frequency k-mers to identify repeats in overlap sequences, it can obtain the repeats more comprehensively and stably; (iv) by applying the parallel alignment model based on the multi-alignment unique k-mers, the efficiency of data processing can be greatly optimized and (v) by taking the corresponding identification strategies, structural variations that occur between repeats can be identified. Comprehensive experimental results show that LongRepMarker can achieve more satisfactory results than the existing de novo detection methods (https://github.com/BioinformaticsCSU/LongRepMarker).
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/nar/gkab563DOI Listing
July 2021

A novel graph attention model for predicting frequencies of drug-side effects from multi-view data.

Brief Bioinform 2021 Jul 2. Epub 2021 Jul 2.

School of Computer Science and Engineering, Central South University, Changsha 410083, China.

Identifying the frequencies of the drug-side effects is a very important issue in pharmacological studies and drug risk-benefit. However, designing clinical trials to determine the frequencies is usually time consuming and expensive, and most existing methods can only predict the drug-side effect existence or associations, not their frequencies. Inspired by the recent progress of graph neural networks in the recommended system, we develop a novel prediction model for drug-side effect frequencies, using a graph attention network to integrate three different types of features, including the similarity information, known drug-side effect frequency information and word embeddings. In comparison, the few available studies focusing on frequency prediction use only the known drug-side effect frequency scores. One novel approach used in this work first decomposes the feature types in drug-side effect graph to extract different view representation vectors based on three different type features, and then recombines these latent view vectors automatically to obtain unified embeddings for prediction. The proposed method demonstrates high effectiveness in 10-fold cross-validation. The computational results show that the proposed method achieves the best performance in the benchmark dataset, outperforming the state-of-the-art matrix decomposition model. In addition, some ablation experiments and visual analyses are also supplied to illustrate the usefulness of our method for the prediction of the drug-side effect frequencies. The codes of MGPred are available at https://github.com/zhc940702/MGPred and https://zenodo.org/record/4449613.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/bib/bbab239DOI Listing
July 2021

One Stone Four Birds: A Novel Liposomal Delivery System Multi-functionalized with Ginsenoside Rh2 for Tumor Targeting Therapy.

Nanomicro Lett 2020 Jun 16;12(1):129. Epub 2020 Jun 16.

Department of Pharmaceutics, School of Pharmacy, Fudan University & Key Laboratory of Smart Drug Delivery, Ministry of Education, Shanghai, 201203, People's Republic of China.

Liposomes hold great potential in anti-cancer drug delivery and the targeting treatment of tumors. However, the clinical therapeutic efficacy of liposomes is still limited by the complexity of tumor microenvironment (TME) and the insufficient accumulation in tumor sites. Meanwhile, the application of cholesterol and polyethylene glycol (PEG), which are usually used to prolong the blood circulation and stabilize the structure of liposomes respectively, has been questioned due to various disadvantages. Herein, we developed a ginsenoside Rh2-based multifunctional liposome system (Rh2-lipo) to effectively address these challenges once for all. Different with the conventional 'wooden' liposomes, Rh2-lipo is a much more brilliant carrier with multiple functions. In Rh2-lipo, both cholesterol and PEG were substituted by Rh2, which works as membrane stabilizer, long-circulating stealther, active targeting ligand, and chemotherapy adjuvant at the same time. Firstly, Rh2 could keep the stability of liposomes and avoid the shortcomings caused by cholesterol. Secondly, Rh2-lipo showed a specifically prolonged circulation behavior in the blood. Thirdly, the accumulation of the liposomes in the tumor was significantly enhanced by the interaction of glucose transporter of tumor cells with Rh2. Fourth, Rh2-lipo could remodel the structure and reverse the immunosuppressive environment in TME. When tested in a 4T1 breast carcinoma xenograft model, the paclitaxel-loaded Rh2-lipo realized high efficient tumor growth suppression. Therefore, Rh2-lipo not only innovatively challenges the position of cholesterol as a liposome component, but also provides another innovative potential system with multiple functions for anti-cancer drug delivery.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s40820-020-00472-8DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7770862PMC
June 2020

RNPredATC: a deep residual learning-based model with applications to the prediction of drug-ATC code association.

IEEE/ACM Trans Comput Biol Bioinform 2021 Jun 10;PP. Epub 2021 Jun 10.

The ATC (Anatomical Therapeutic Chemical) code of a drug is a classification system designated by the World Health Organization Collaborating Center for Drug Statistics Methodology. Correctly identifying the potential ATC codes for drugs can accelerate drug development and reduce the cost of experiments. Several classifiers have been proposed in this regard. However, they lack of ability to learn basic features from sparsely known drug-ATC code associations. In this paper, we provide a novel end-to-end model, so-called RNPredATC, to predict potential drug-ATC code associations in five ATC classification levels. RNPredATC can extract dense feature vectors from sparsely known drug-ATC code associations and reduce the impact from the degradation problem by a novel deep residual learning. We extensively compare our method with some state-of-the-art methods, including NetPredATC, SPACE, and some multi-label-based methods. Our experimental results show that RNPredATC achieves better performances in five-fold and ten-fold cross validations. Furthermore, the visualization analysis of hidden layers and case studies of predicted associations at the fifth ATC classification level confirm that RNPredATC can effectively identify the potential ATC codes of drugs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCBB.2021.3088256DOI Listing
June 2021

Antifungal Activity of Quinofumelin against and Its Inhibitory Effect on DON Biosynthesis.

Toxins (Basel) 2021 05 12;13(5). Epub 2021 May 12.

Department of Pesticide Science, College of Plant Protection, Nanjing Agricultural University, Nanjing 210095, China.

causal agent of Fusarium head blight (FHB), causes a huge economic loss. No information is available on the activity of quinofumelin, a novel quinoline fungicide, against or other phytopathogens. In this study, we used mycelial growth and spore germination inhibition methods to determine the inhibitory effect of quinofumelin against in vitro. The results indicated that quinofumelin excellently inhibited mycelial growth and spore germination of , with the average EC values of 0.019 ± 0.007 μg/mL and 0.087 ± 0.024 μg/mL, respectively. In addition, we found that quinofumelin could significantly decrease deoxynivalenol (DON) production and inhibit the expression of DON-related gene in . Furthermore, we found that quinofumelin could disrupt the formation of Fusarium toxisome, a structure for producing DON. Western blot analysis demonstrated that the translation level of TRI1, a marker gene for Fusarium toxisome, was suppressed by quinofumelin. The protective and curative assays indicated that quinofumelin had an excellent control efficiency against on wheat coleoptiles. Taken together, quinofumelin exhibits not only an excellent antifungal activity on mycelial growth and spore germination, but also could inhibit DON biosynthesis in . The findings provide a novel candidate for controlling FHB caused by .
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/toxins13050348DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8151098PMC
May 2021

Therapeutic effect of various ginsenosides on rheumatoid arthritis.

BMC Complement Med Ther 2021 May 25;21(1):149. Epub 2021 May 25.

Department of Pharmaceutics, School of Pharmacy, Fudan University & Key Laboratory of Smart Drug Delivery, Ministry of Education, Shanghai, 201203, China.

Background: Rheumatoid arthritis (RA) is an autoimmune disease which causes disability and threatens the health of humans. Therefore, it is of great significance to seek novel effective drugs for RA. It has been reported that various ginsenoside monomers are able to treat RA. However, it is still unclear which ginsenoside is the most effective and has the potential to be developed into an anti-RA drug.

Methods: The ginsenosides, including Rg1, Rg3, Rg5, Rb1, Rh2 and CK, were evaluated and compared for their therapeutic effect on RA. In in vitro cell studies, methotrexate (MTX) and 0.05% dimethyl sulfoxide (DMSO) was set as a positive control group and a negative control group, respectively. LPS-induced RAW264.7 cells and TNF-α-induced HUVEC cells were cultured with MTX, DMSO and six ginsenosides, respectively. Cell proliferation was analyzed by MTT assay and cell apoptosis was carried out by flow cytometry. CIA mice model was developed to evaluate the therapeutic efficacy of ginsenosides. The analysis of histology, immunohistochemistry, flow cytometry and cytokine detections of the joint tissues were performed to elucidate the action mechanisms of ginsenosides.

Results: All six ginsenosides showed good therapeutic effect on acute arthritis compared with the negative control group, Ginsenoside CK provided the most effective treatment ability. It could significantly inhibit the proliferation and promote the apoptosis of RAW 264.7 and HUVEC cells, and substantially reduce the swelling, redness, functional impairment of joints and the pathological changes of CIA mice. Meanwhile, CK could increase CD8 + T cell to down-regulate the immune response, decrease the number of activated CD4 + T cell and proinflammatory M1-macrophages, thus resulting in the inhibition of the secretion of proinflammatory cytokine such as TNF-α and IL-6.

Conclusion: Ginsenoside CK was proved to be a most potential candidate among the tested ginsenosides for the treatment of RA, with a strong anti-inflammation and immune modulating capabilities.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/s12906-021-03302-5DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8145820PMC
May 2021

Predicting the Survival of Cancer Patients with Multimodal Graph Neural Network.

IEEE/ACM Trans Comput Biol Bioinform 2021 May 25;PP. Epub 2021 May 25.

In recent years, cancer patients survival prediction holds important significance for worldwide health problems, and has gained many researchers attention in medical information communities. Cancer patients survival prediction can be seen the classification work which is a meaningful and challenging task. Nevertheless, research in this field is still limited. In this paper, we design a novel Multimodal Graph Neural Network (MGNN) framework for predicting cancer survival, which explores the features of real-world multimodal data such as gene expression, copy number alteration and clinical data in a unified framework. Specifically, we first construct the bipartite graphs between patients and multimodal data to explore the inherent relation. Subsequently, the embedding of each patient on different bipartite graphs is obtained with graph neural network. Finally, a multimodal fusion neural layer is proposed to fuse the medical features from different modality data. Comprehensive experiments have been conducted on real-world datasets, which demonstrate the superiority of our modal with significant improvements against state-of-the-arts. Furthermore, the proposed MGNN is validated to be more robust on other four cancer datasets.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCBB.2021.3083566DOI Listing
May 2021

A Chimeric Cationic Peptide Composed of Human β-Defensin 3 and Human β-Defensin 4 Exhibits Improved Antibacterial Activity and Salt Resistance.

Front Microbiol 2021 7;12:663151. Epub 2021 May 7.

State Key Laboratory of Pathogens and Biosecurity, Beijing Institute of Microbiology and Epidemiology, Beijing, China.

Human beta-defensins (hBDs) play an important role in the host defense against various microbes, showing different levels of antibacterial activity and salt resistance . It is of interest to investigate whether can chimeric hBD analogs enhanced antibacterial activity and salt resistance. In this study, we designed a chimeric human defensin, named H4, by combining sequences of human beta-defensin-3 (hBD-3) and human beta-defensin-4 (hBD-4), then evaluated its antibacterial activity, salt resistance, and cytotoxic effects. The result showed that the antibacterial activity of H4 against most tested strains, including , , , , , , and was significantly improved compared to that of hBD-3 and hBD-4. Notably, H4 exhibited significantly better antibacterial activity against multidrug resistant isolate MDR-ZJ06 than commonly used antibiotics. Chimeric H4 still showed more than 80% antibacterial activity at high salt concentration (150 μM), which proves its good salt tolerance. The cytotoxic effect assay showed that the toxicity of H4 to Hela, Vero, A549 cells and erythrocytes at a low dose (<10 μg/ml) was similar to that of hBD-3 and hBD-4. In conclusion, given its broad spectrum of antibacterial activity and high salt resistance, chimeric H4 could serve as a promising template for new therapeutic antimicrobial agents.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fmicb.2021.663151DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8137984PMC
May 2021

A survey on predicting microbe-disease associations: biological data and computational methods.

Brief Bioinform 2021 May;22(3)

Hunan Provincial Key Lab of Bioinformatics, School of Computer Science and Engineering at Central South University, Hunan, China.

Various microbes have proved to be closely related to the pathogenesis of human diseases. While many computational methods for predicting human microbe-disease associations (MDAs) have been developed, few systematic reviews on these methods have been reported. In this study, we provide a comprehensive overview of the existing methods. Firstly, we introduce the data used in existing MDA prediction methods. Secondly, we classify those methods into different categories by their nature and describe their algorithms and strategies in detail. Next, experimental evaluations are conducted on representative methods using different similarity data and calculation methods to compare their prediction performances. Based on the principles of computational methods and experimental results, we discuss the advantages and disadvantages of those methods and propose suggestions for the improvement of prediction performances. Considering the problems of the MDA prediction at present stage, we discuss future work from three perspectives including data, methods and formulations at the end.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/bib/bbaa157DOI Listing
May 2021

Characteristics of bone metabolism in postmenopausal women with newly diagnosed type 2 diabetes mellitus.

Clin Endocrinol (Oxf) 2021 May 18. Epub 2021 May 18.

Department of Endocrinology, Tongji Hospital, Tongji University School of Medicine, Shanghai, China.

Objective: The characteristics of bone metabolism in T2DM are still controversial. This study aims to recognize bone turnover features in patients with newly diagnosed T2DM who have never been treated with anti-diabetic drugs and further explore the possible factors contributing to their impaired bone turnover.

Materials And Methods: An analytic sample of 88 patients with newly diagnosed T2DM and 152 non-diabetic control individuals were studied. All the participants were postmenopausal women. Demographics variables and clinical history were recorded. We measured lipid profile, glucose metabolism, bone turnover markers indices as well as their related hormones, serum calcium and phosphorus. Bone mineral density was detected by dual-energy X-ray absorptiometry. We compared the differences in bone turnover markers and their regulating hormones between two groups and further analysed the factors related to bone turnover in T2DM.

Results: Compared with the control group, patients with T2DM had a higher level of bone alkaline phosphatase (BALP), lower levels of procollagen type I intact N-terminal (P1NP), osteocalcin (OC) and parathyroid hormone (PTH). Multiple linear regression analysis showed that in patients with T2DM, HbA1c was negatively correlated with P1NP and OC. For patients without diabetes, HbA1c was negatively related to BALP and OC.

Conclusions: Patients with newly diagnosed T2DM may have impaired osteoblastic maturation and bone formation, which may be mainly attributed to hyperglycaemia.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/cen.14501DOI Listing
May 2021

Phosphatidylserine-exposing tumor-derived microparticles exacerbate coagulation and cancer cell transendothelial migration in triple-negative breast cancer.

Theranostics 2021 19;11(13):6445-6460. Epub 2021 Apr 19.

Department of Ultrasound, The First Hospital, Harbin Medical University, Harbin, China.

Neoadjuvant chemotherapy is relevant to the formation of thromboembolism and secondary neoplasms in triple-negative breast cancer (TNBC). Chemotherapy-induced breast cancer cell-derived microparticles (BCMPs) may have important thrombogenic and pro-metastatic effects on platelets and endothelium, which may be related to the expression and distribution of phosphatidylserine (PS). However, investigating these interactions is challenging due to technical limitations. A study was conducted in 20 healthy individuals and 18 patients who had been recently diagnosed with TNBC and were undergoing neoadjuvant chemotherapy with doxorubicin and cyclophosphamide. BCMPs were isolated from patient blood samples and doxorubicin-treated breast cancer cell lines. Their structure and morphology were studied by electron microscopy and antigen levels were measured by fluorescence-activated cell sorting. In an inhibition assay, isolated BCMPs were pretreated with lactadherin or tissue factor antibodies. Platelets isolated from healthy subjects were treated with BCMPs and coagulation time, fibrin formation, and expression of intrinsic/extrinsic factor Xase (FXa) and thrombin were evaluated. The effects of BCMPs on endothelial thrombogenicity and integrity were assessed by confocal microscopy, electron microscopy, measurement of intrinsic/extrinsic FXa, prothrombinase assay, and transwell permeability assay. Neoadjuvant chemotherapy significantly increased the expression of PS+ BCMPs in patient plasma. Its expression was associated with a rapid increase in procoagulant activity. Treatment with lactadherin, a PS-binding scavenging molecule, markedly reduced the adhesion of BCMPs and abolished their procoagulant activity, but this was not observed with tissue factor antibody treatment. Intravenous injection of BCMPs in mice induced a significant hypercoagulable state, reducing the extent of plasma fibrinogen and promoting the appearance of new thrombus. Cancer cells incubated with doxorubicin released large numbers of PS+ BCMPs, which stimulated and transformed endothelial cells into a procoagulant phenotype and increased the aggregation and activation of platelets. Moreover, cancer cells exploited this BCMP-induced endothelial leakiness and showed promoted metastasis. Pretreatment with lactadherin increased uptake of both PS+ BCMPs and cancer cells by endothelial cells and limited the transendothelial migration of cancer cells. Lactadherin, a biosensor that we developed, was used to study the extracellular vesicle distribution of PS, which revealed a novel PS+ BCMPs administrative axis that initiated a local coagulation cascade and facilitated metastatic colonization of circulating cancer cells.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.7150/thno.53637DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8120203PMC
July 2021

Temporal characterization of heating in femtosecond laser filamentation with planar Rayleigh scattering.

Opt Express 2021 May;29(10):14883-14893

Temporal and spatial evolution of temperature in femtosecond laser filamentation is investigated using planar Rayleigh scattering combined with optical flow algorithm, the corresponding mechanism is analyzed. The temperature increases sharply with a characteristic time of 4.53μs and reach a maximum value of 418 K within 1∼10μs, then decreases slowly to around 300 K with a characteristic time of 136μs. While the temperature first diffuses rapidly in the radial direction and then diffuses very slowly, an obvious step is observed around 2μs. The mechanism of heat transfer is the result of energy exchange between electron and heavy particles and heat conduction. Within 1 ns to 10μs, molecules obtain energy continuously due to collision with electrons, which is much larger than the energy loss due to thermal conduction, leading to rise of gas temperature and the high-speed movement of the filament edges. After 10μs, thermal conduction becomes the dominant factor, resulting gas temperature decreasing and slower movement of the filament edges.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1364/OE.418654DOI Listing
May 2021

NeuralPolish: a novel Nanopore polishing method based on alignment matrix construction and orthogonal Bi-GRU Networks.

Bioinformatics 2021 May 11. Epub 2021 May 11.

School of Computer Science and Engineering, Central South University, Changsha, 410083, China.

Motivation: Oxford Nanopore sequencing producing long reads at low cost has made many breakthroughs in genomics studies. However, the large number of errors in Nanopore genome assembly affect the accuracy of genome analysis. Polishing is a procedure to correct the errors in genome assembly and can improve the reliability of the downstream analysis. However, the performances of the existing polishing methods are still not satisfactory.

Results: We developed a novel polishing method, NeuralPolish, to correct the errors in assemblies based on alignment matrix construction and orthogonal Bi-GRU networks. In this method, we designed an alignment feature matrix for representing read-to-assembly alignment. Each row of the matrix represents a read, and each column represents the aligned bases at each position of the contig. In the network architecture, a bi-directional GRU network is used to extract the sequence information inside each read by processing the alignment matrix row by row. After that, the feature matrix is processed by another bi-directional GRU network column by column to calculate the probability distribution. Finally, a CTC decoder generates a polished sequence with a greedy algorithm. We used five real data sets and three assembly tools including Wtdbg2, Flye and Canu for testing, and compared the results of different polishing methods including NeuralPolish, Racon, MarginPolish, HELEN and Medaka. Comprehensive experiments demonstrate that NeuralPolish achieves more accurate assembly with fewer errors than other polishing methods and can improve the accuracy of assembly obtained by different assemblers.

Availability: https://github.com/huangnengCSU/NeuralPolish.git.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/bioinformatics/btab354DOI Listing
May 2021

A 1,8-naphthalimide-based lysosome-targeting dual-analyte fluorescent probe for the detection of pH and palladium in biological samples.

Talanta 2021 Aug 29;231:122365. Epub 2021 Mar 29.

Institute of Natural Medicine and Health Products, School of Life Science, Taizhou University, Taizhou, 318000, PR China; Department of Pharmaceutics, School of Pharmacy & Key Laboratory of Smart Drug Delivery, Fudan University, Shanghai, 200433, PR China. Electronic address:

Fluorescent probes containing 1,8-naphthalimide dyes have been used to detect biomolecules in the environmental and biological fields. However, most of the probes only exhibit single fluorescent output to one analyte, making them insufficient for detection of more analytes. Herein, we developed a novel 1,8-naphthalimide-based lysosome-targeting dual-analyte sensitive fluorescent probe (DPPP) for the detection of pH and palladium (Pd) using two different emissive channels. The probe showed high selectivity, large Stokes shifts (Δλ ≥ 100 nm) and enhanced response to pH, with blue emission at 485 nm via a morpholine group, and responsive to Pd concentration, with yellow emission at 545 nm via an allylcarbamate group. The effect of DPPP was successfully observed for sensitive visualizing pH and Pd concentration in the lysosome of HeLa cells and zebrafish using fluorescence microscopy. This work provides guidance for the design of dual-analyte fluorescent probes.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.talanta.2021.122365DOI Listing
August 2021

Real-World Effectiveness of Mepolizumab in Severe Eosinophilic Asthma: A Systematic Review and Meta-analysis.

Clin Ther 2021 May 4. Epub 2021 May 4.

Department of Pulmonary and Critical Care Medicine, China-Japan Friendship Hospital, Beijing, China. Electronic address:

Purpose: Mepolizumab is a human monoclonal antibody against interleukin 5 (IL-5) used to treat severe eosinophilic asthma. Several studies have evaluated the effectiveness of mepolizumab in the real world. We conducted a systematic review and meta-analysis in the context of heterogeneity among patients, clinicians, and treatment regimens to study the effectiveness of mepolizumab in the real world.

Methods: We searched the PubMed and Embase databases for real-world studies on severe asthma treatment with mepolizumab as of June 30, 2020. Exacerbations, asthma-related hospitalizations, forced expiratory volume in 1 second (FEV), Asthma Control Questionnaire (ACQ) or Asthma Control Test (ACT), corticosteroid use, peripheral blood eosinophil counts, and the fraction of exhaled nitric oxide were selected as indicators to evaluate the effectiveness. Standardized mean differences by the Cohen method and mean differences were chosen as indicators of effect size. Cohen d values of 0.2, 0.5, and 0.8 are considered as small, medium, and large effects, respectively. We used the Dersimonian-Laird random-effect model to quantify pooled effectiveness estimates.

Findings: A total of 1457 patients from 13 studies were included in this review. At all time points, mepolizumab was associated with reductions in exacerbations (2.92 and 2.73 events per patient per year fewer at 6 and 12 months, respectively) and hospitalizations (0.36 events per patient per year fewer at 12 months); improvements in asthma control (ACQ scores reductions of 1.32 and 1.03 at 6 and 12 months, respectively; ACT scores increase of 6.52 at 6-12 months); slight improvements in pulmonary function (FEV increase of 0.23 L at 1-3 months and 6-12 months, respectively); reductions in oral corticosteroid use (9.02- and 7.68-mg decrease at 6 and 12 months, respectively); and reductions in peripheral blood eosinophil counts (decreases of 559.11 cells/μL and 599.17 cells/μL at 1-3 months and 6-12 months, respectively) and fraction of exhaled nitric oxide (13-ppb reduction at 6-12 months).

Implications: Our study suggests that mepolizumab is associated with improvements in several clinically meaningful real-world outcomes. This study is a supplement to and extension of the efficacy of randomized controlled trials of mepolizumab. (Clin Ther. 2021;XX:XXX-XXX) © 2021 Elsevier HS Journals, Inc.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.clinthera.2021.03.023DOI Listing
May 2021

Drug-target interaction prediction using multi-head self-attention and graph attention network.

IEEE/ACM Trans Comput Biol Bioinform 2021 May 6;PP. Epub 2021 May 6.

Identifying drug-target interactions (DTIs) is an important step in the process of new drug discovery and drug repositioning. Accurate predictions for DTIs can improve efficiency in drug discovery and development. Although rapid advances in deep learning technologies have generated various computational methods, it is still appealing to further investigate how to design efficient networks for predicting DTIs. In this study, we propose an end-to-end deep learning method (called MHSADTI) to predict DTIs based on the graph attention network and multi-head self-attention mechanism models. First, the characteristics of drugs and proteins are extracted by the graph attention network model and multi-head self-attention mechanism, respectively. Then, the attention scores are used to consider which amino acid subsequence in a protein is more important for the drug to predict its interactions. Finally, we predict DTIs by a fully connected layer network after obtaining the feature vectors of drugs and proteins. The experiments in four datasets, human, C.elegans, DUD-E and DrugBank show our method outperforms the state-of-the-art method in terms of AUC, Precision, Recall, Recall, AUPR and F1-score. In addition, the case studies further demonstrate that our method can provide effective visualization to interpret the prediction results from biological insights.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCBB.2021.3077905DOI Listing
May 2021

Pharmaceutical care program for ischemic stroke patients: a randomized controlled trial.

Int J Clin Pharm 2021 Apr 28. Epub 2021 Apr 28.

College of Pharmacy and Health Sciences, Western New England University, Springfield, MA, 01119, USA.

Background Effective secondary prevention is essential for reducing stroke recurrence. Objective This parallel randomized-controlled study aimed to evaluate the impact of a pharmaceutical care program on risk factor control (blood pressure, blood glucose, lipid profile, and medication adherence) and hospital readmissions in post-stroke care. Setting The First Hospital of Hebei Medical University, China. Method Ischemic stroke patients were enrolled in the study. Upon hospital discharge, patients were randomly allocated either to a control group (CG, no pharmaceutical care) or to an intervention group (IG, monthly pharmaceutical care follow-up for 6 months). The interventions aimed to increase medication adherence and improve risk factor control through education and counseling. Medication adherence and surrogate laboratory markers of risk factors were assessed and compared between the two groups. Main outcome measures Blood pressure, blood glucose, lipid profile, and medication adherence. Results A total of 184 patients with ischemic strokes were randomly assigned, and 84 patients in IG and 82 in CG were analyzed. There were no significant differences (P > 0.05) in both groups concerning demographic and clinical characteristics. Compared to CG, at the 6-month follow-up, medication adherence rates significantly increased regarding antihypertensive drugs (92.86% versus 78.57%, P = 0.031), anti-diabetic drugs (91.67% versus 69.7%, P = 0.02), and lipid-lowering drugs (77.38% versus 60.98%, P = 0.022) in IG. Compared to CG, more patients in IG attained the goal surrogate risk factor control markers of hemoglobin A1c (87.88% vs. 52.78%, P = 0.038) and low-density lipoprotein-C (66.67% vs. 48.78%, P = 0.02). Significantly fewer patients were re-admitted to the hospital in IG than CG (7.14% vs. 18.3%, P = 0.03). Conclusion Pharmaceutical care programs can improve risk factor control for the secondary prevention of stroke recurrence in ischemic stroke patients.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11096-021-01272-9DOI Listing
April 2021

Clinical significance of T lymphocyte subsets, immunoglobulin and complement expression in peripheral blood of children with steroid-dependent nephrotic syndrome/frequently relapsing nephrotic syndrome.

Am J Transl Res 2021 15;13(3):1890-1895. Epub 2021 Mar 15.

Department of Pediatrics, Quanzhou First Hospital Affiliated to Fujian Medical University Quanzhou, Fujian Province, China.

Objective: To investigate the clinical significance of T lymphocyte subsets, immunoglobulin and complement expression in the peripheral blood of children with steroid-dependent nephrotic syndrome/frequently relapsing nephrotic syndrome (SDNS/FRNS).

Methods: A prospective study was conducted on 285 children with nephrotic syndrome (NS). Among the 285 patients, 187 children had steroid-sensitive nephrotic syndrome (SSNS) and 98 children had SDNS/FRNS according to their sensitivity to hormones. Meanwhile, 50 healthy children in the same period were selected as the control group. Serum albumin (ALB), blood urea nitrogen (BUN), serum creatinine (SCr), estimated glomerular filtration rate (eGFR), high-sensitivity C-reactive protein (hs-CRP), interleukin-6 (IL-6), CD3+, CD4+, CD8+, immunoglobulin IgA, IgG, IgM and complement C3 and C4 were measured upon admission, and the content of urinary CD80 was also determined.

Results: Compared with the control group, BUN, SCr, hs-CRP and IL-6 levels, urinary CD80, IgA, IgM and C3 in the SDNS/FRNS and SSNS groups were significantly higher, while ALB, eGFR, CD3+, CD4+, CD4+/CD8+, IgG and IgG/IgM were significantly lower (all P<0.05). Compared with the SSNS group, BUN, SCr, hs-CRP and IL-6 levels in the SDNS/FRNS group were significantly higher, while ALB and eGFR levels were significantly lower (all P<0.05). Compared with the SDNS/FRNS group, IgM in the SSNS group was significantly lower, while CD4+/CD8+, urinary CD80 and IgG/IgM were significantly higher (all P<0.001).

Conclusion: Renal function decline and inflammatory response existed in children with NS. CD3+, CD4+, CD4+/CD8+ and IgG/IgM in peripheral blood were decreased, while IgA, IgM, C3 and urinary CD80 were increased. Moreover, renal function decline, increase of inflammatory factors, decrease of IgG/IgM and CD4+/CD8+ were more obvious in the SDNS/FRNS group.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8014369PMC
March 2021

Parallel computing for genome sequence processing.

Brief Bioinform 2021 Apr 5. Epub 2021 Apr 5.

School of Computer Science and Engineering at Central South University, Changsha, Hunan, China.

The rapid increase of genome data brought by gene sequencing technologies poses a massive challenge to data processing. To solve the problems caused by enormous data and complex computing requirements, researchers have proposed many methods and tools which can be divided into three types: big data storage, efficient algorithm design and parallel computing. The purpose of this review is to investigate popular parallel programming technologies for genome sequence processing. Three common parallel computing models are introduced according to their hardware architectures, and each of which is classified into two or three types and is further analyzed with their features. Then, the parallel computing for genome sequence processing is discussed with four common applications: genome sequence alignment, single nucleotide polymorphism calling, genome sequence preprocessing, and pattern detection and searching. For each kind of application, its background is firstly introduced, and then a list of tools or algorithms are summarized in the aspects of principle, hardware platform and computing efficiency. The programming model of each hardware and application provides a reference for researchers to choose high-performance computing tools. Finally, we discuss the limitations and future trends of parallel computing technologies.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/bib/bbab070DOI Listing
April 2021

Prognostication of patients with COVID-19 using artificial intelligence based on chest x-rays and clinical data: a retrospective study.

Lancet Digit Health 2021 05 24;3(5):e286-e294. Epub 2021 Mar 24.

Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA. Electronic address:

Background: Chest x-ray is a relatively accessible, inexpensive, fast imaging modality that might be valuable in the prognostication of patients with COVID-19. We aimed to develop and evaluate an artificial intelligence system using chest x-rays and clinical data to predict disease severity and progression in patients with COVID-19.

Methods: We did a retrospective study in multiple hospitals in the University of Pennsylvania Health System in Philadelphia, PA, USA, and Brown University affiliated hospitals in Providence, RI, USA. Patients who presented to a hospital in the University of Pennsylvania Health System via the emergency department, with a diagnosis of COVID-19 confirmed by RT-PCR and with an available chest x-ray from their initial presentation or admission, were retrospectively identified and randomly divided into training, validation, and test sets (7:1:2). Using the chest x-rays as input to an EfficientNet deep neural network and clinical data, models were trained to predict the binary outcome of disease severity (ie, critical or non-critical). The deep-learning features extracted from the model and clinical data were used to build time-to-event models to predict the risk of disease progression. The models were externally tested on patients who presented to an independent multicentre institution, Brown University affiliated hospitals, and compared with severity scores provided by radiologists.

Findings: 1834 patients who presented via the University of Pennsylvania Health System between March 9 and July 20, 2020, were identified and assigned to the model training (n=1285), validation (n=183), or testing (n=366) sets. 475 patients who presented via the Brown University affiliated hospitals between March 1 and July 18, 2020, were identified for external testing of the models. When chest x-rays were added to clinical data for severity prediction, area under the receiver operating characteristic curve (ROC-AUC) increased from 0·821 (95% CI 0·796-0·828) to 0·846 (0·815-0·852; p<0·0001) on internal testing and 0·731 (0·712-0·738) to 0·792 (0·780-0 ·803; p<0·0001) on external testing. When deep-learning features were added to clinical data for progression prediction, the concordance index (C-index) increased from 0·769 (0·755-0·786) to 0·805 (0·800-0·820; p<0·0001) on internal testing and 0·707 (0·695-0·729) to 0·752 (0·739-0·764; p<0·0001) on external testing. The image and clinical data combined model had significantly better prognostic performance than combined severity scores and clinical data on internal testing (C-index 0·805 vs 0·781; p=0·0002) and external testing (C-index 0·752 vs 0·715; p<0·0001).

Interpretation: In patients with COVID-19, artificial intelligence based on chest x-rays had better prognostic performance than clinical data or radiologist-derived severity scores. Using artificial intelligence, chest x-rays can augment clinical data in predicting the risk of progression to critical illness in patients with COVID-19.

Funding: Brown University, Amazon Web Services Diagnostic Development Initiative, Radiological Society of North America, National Cancer Institute and National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/S2589-7500(21)00039-XDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7990487PMC
May 2021

Biomedical data and deep learning computational models for predicting compound-protein relations.

IEEE/ACM Trans Comput Biol Bioinform 2021 Mar 26;PP. Epub 2021 Mar 26.

Researchers have developed a computational field called virtual screening (VS) to aid experimental drug development. These methods utilize experimentally validated biological interaction information to generate datasets and use the physicochemical and structural properties of compounds and target proteins as input information to train computational prediction models. At present, deep learning has been used in the field of biomedicine widely, and the prediction of CPRs based on deep learning has developed rapidly and has achieved good results. The purpose of this study is to investigate and discuss the latest applications of deep learning techniques in CPR prediction. First, we describe the datasets and feature engineering (i.e., compound and protein representations and descriptors) commonly used in CPR prediction methods. Then, we review and classify recent deep learning approaches in CPR prediction. Next, a comprehensive comparison is performed to demonstrate the prediction performance of representative methods on classical datasets. Finally, we discuss the current state of the field, including the existing challenges and our proposed future directions. We believe that this investigation will provide sufficient references and insight for researchers to understand and develop new deep learning methods to enhance CPR predictions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCBB.2021.3069040DOI Listing
March 2021

A Convolutional Neural Network and Graph Convolutional Network Based Method for Predicting the Classification of Anatomical Therapeutic Chemicals.

Bioinformatics 2021 Mar 26. Epub 2021 Mar 26.

Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, 410083, China.

Motivation: The Anatomical Therapeutic Chemical (ATC) system is an official classification system established by the World Health Organization for medicines. Correctly assigning ATC classes to given compounds is an important research problem in drug discovery, which can not only discover the possible active ingredients of the compounds, but also infer theirs therapeutic, pharmacological, and chemical properties.

Results: In this paper, we develop an end-to-end multi-label classifier called CGATCPred to predict 14 main ATC classes for given compounds. In order to extract rich features of each compound, we use the deep Convolutional Neural Network (CNN) and shortcut connections to represent and learn the seven association scores between the given compound and others. Moreover, we construct the correlation graph of ATC classes and then apply graph convolutional network (GCN) on the graph for label embedding abstraction. We use all label embedding to guide the learning process of compound representation. As a result, by using the Jackknife test, CGATCPred obtain reliable Aiming of 81.94%, Coverage of 82.88%, Accuracy 80.81%, Absolute True 76.58% and Absolute False 2.75%, yielding significantly improvements compared to exiting multi-label classifiers.

Availability: The codes of CGATCPred are available at https://github.com/zhc940702/CGATCPred and https://zenodo.org/record/4552917.

Supplementary Information: Supplementary data are available at Bioinformatics online.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/bioinformatics/btab204DOI Listing
March 2021
-->