Overexpressing Bcl-2 enhances murine chimeric antigen receptor T cell therapy against solid tumor.

Chimeric antigen receptor T (CART) cell therapy has demonstrated promising potential in the treatment of hematologic malignancies. However, its application to solid tumors is limited due to the restrictive nature of the tumor microenvironment, resulting in functional failure and poor persistence of CART cells. Overexpression of Bcl-2 in human CART cells (hCART) has been found to significantly enhance their anti-apoptotic effects both in vitro and in vivo. Nevertheless, the evaluation of hCART cells in preclinical studies has predominantly relied on immunodeficient mice xenograft tumor models, making it challenging to assess the impact of hCART cells on normal tissues and the immune system. We established a murine CART (mCART) that overexpresses Bcl-2 and targets the epidermal growth factor receptor variant III (EGFRvIII), named EGFRvIII·mCART-Bcl2. It demonstrated superior proliferation, cytotoxicity, and anti-apoptotic capabilities in vitro. In an immunocompetent mouse model of abdominal metastasis of colorectal cancer, EGFRvIII·mCART-Bcl2 exhibited improved survival of CART in the abdomen, increased tumor clearance, and significantly prolonged overall mouse survival. In summary, our study provides evidence that the introduction of Bcl-2 into mCART cells can enhance their therapeutic efficacy against solid tumors while ensuring safety.

Bioactive components and potential mechanisms of Biqi Capsule in the treatment of osteoarthritis: based on chondroprotective and anti-inflammatory activity.

Cartilage damage and synovial inflammation are vital pathological changes in osteoarthritis (OA). Biqi Capsule, a traditional Chinese medicine formula used for the clinical treatment of arthritis in China, yields advantages in attenuating OA progression. The drawback here is that the bioactive components and pharmacological mechanisms by which Biqi Capsule exerts its anti-inflammatory and chondroprotective effects have yet to be fully clarified. For in vivo studies, a papain-induced OA rat model was established to explore the pharmacological effects and potential mechanisms of Biqi Capsule against OA. Biqi Capsule alleviated articular cartilage degeneration and chondrocyte damage in OA rats and inhibited the phosphorylation of NF-κB and the expression of pro-inflammatory cytokines in synovial tissue. Network pharmacology analysis suggested that the primary biological processes regulated by Biqi Capsule are inflammation and oxidative stress, and the critical pathway regulated is the PI3K/AKT signaling pathway. The result of this analysis was later verified on SW1353 cells. The in vitro studies demonstrated that Glycyrrhizic Acid and Liquiritin in Biqi Capsule attenuated H2O2-stimulated SW1353 chondrocyte damage via activation of PI3K/AKT/mTOR pathway. Moreover, Biqi Capsule alleviated inflammatory responses in LPS-stimulated RAW264.7 macrophages via the NF-κB/IL-6 pathway. These observations were suggested to have been facilitated by Brucine, Liquiritin, Salvianolic Acid B, Glycyrrhizic Acid, Cryptotanshinone, and Tanshinone ⅡA. Put together, this study partially clarifies the pharmacological mechanisms and the bioactive components of Biqi capsules against OA and suggests that it is a promising therapeutic option for the treatment of OA. Chemical compounds studied in this article. Strychnine (Pubchem CID:441071); Brucine (Pubchem CID:442021); Liquiritin (Pubchem CID:503737); Salvianolic Acid B (Pubchem CID:6451084); Glycyrrhizic Acid (Pubchem CID:14982); Cryptotanshinone (Pubchem CID:160254); Tanshinone ⅡA (Pubchem CID:164676).

Enhanced ApcMin/+ adenoma formation after epithelial CUL4B deletion by recruitment of myeloid-derived suppressor cells.

Colorectal cancer (CRC) stands as a prevalent malignancy globally. A pivotal event in CRC pathogenesis involves the loss-of-function mutation in the APC gene, leading to the formation of benign polyps. Despite the well-established role of APC, the contribution of CUL4B to CRC initiation in the pre-tumorous stage remains poorly understood. In this investigation, we generated a murine model by crossing ApcMin/+ mice with Cul4bΔIEC mice to achieve specific deletion of Cul4b in the gut epithelium against an ApcMin/+ background. By employing histological methods, RNA-sequencing (RNA-seq), and flow cytometry, we assessed alterations and characterized the immune microenvironment. Our results unveiled that CUL4B deficiency in gut epithelium expedited ApcMin/+ adenoma formation. Notably, CUL4B in adenomas restrained the accumulation of tumor-infiltrating myeloid-derived suppressor cells (MDSCs). In vivo inhibition of MDSCs significantly delayed the growth of CUL4B deleted ApcMin/+ adenomas. Furthermore, the addition of MDSCs to in vitro cultured ApcMin/+; Cul4bΔIEC adenoma organoids mitigated their alterations. Mechanistically, CUL4B directly interacted with the promoter of Csf3, the gene encoding granulocyte-colony stimulating factor (G-CSF) by coordinating with PRC2. Inhibiting CUL4B epigenetically activated the expression of G-CSF, promoting the recruitment of MDSCs. These findings offer novel insights into the tumor suppressor-like roles of CUL4B in regulating ApcMin/+ adenomas, suggesting a potential therapeutic strategy for CRC initiation and progression in the context of activated Wnt signaling.

Rho kinase inhibitor Y-27632 downregulates IL-1ß expression in mice with experimental autoimmune myocarditis.

Autoimmune myocarditis is the limited or diffuse inflammation of the myocardium due to dysfunctional cellular and humoral immunity mechanisms. We constructed mouse models of experimental autoimmune myocarditis (EAM) using peptide MyHC-α614-629. On the day after secondary immunization, the mice were intraperitoneally injected with Rho kinase (ROCK) inhibitor Y-27632. On day 21, the cardiac tissues were harvested and weighed. The hearts of EAM mice were significantly enlarged and whitened. Furthermore, body weight (BW) slowly increased during the treatment period, the heart weight (HW) and the ratio of HW/eventual BW were increased, and inflammatory infiltration and fibrosis were aggravated in the myocardial tissue. Y-27632 treatment improved the aforementioned phenotypic and pathological features of EAM mice. Mechanistic analysis revealed a significant increase in Notch1, Hes1, Jag2, Dil1, Toll-like receptor (Tlr) 2, and interleukin (IL)-1ß expression in the myocardial tissue of EAM mice. Notably, IL-1ß expression was correlated with that of Notch1 and Tlr2. Following Y-27632 treatment, the expression of key target genes of the Notch signaling pathway (Notch1, Hes1, Dil1, and Jag2) and Tlr2 were obviously decreased. Y-27632 treatment also decreased the number of monocytes in the spleen of EAM mice. Thus, ROCK inhibitor Y-27632 exerted a protective effect in EAM mice by downregulating IL-1ß expression. This study aimed to provide a reference point for the future treatment of myocarditis in clinical settings.

Comparison of intestinal toxicity in enhancing intestinal permeability and in causing ROS production of six PPD quinones in Caenorhabditis elegans.

As the derivatives of p-phenylenediamines (PPDs), PPD quinones (PPDQs) have received increasing attention due to their possible exposure risk. We compared the intestinal toxicity of six PPDQs (6-PPDQ, 77PDQ, CPPDQ, DPPDQ, DTPDQ and IPPDQ) in Caenorhabditis elegans. In the range of 0.01-10 µg/L, only 77PDQ (10 µg/L) moderately induced the lethality. All the examined PPDQs at 0.01-10 µg/L did not affect intestinal morphology. Different from this, exposure to 6-PPDQ (1-10 µg/L), 77PDQ (0.1-10 µg/L), CPPDQ (1-10 µg/L), DPPDQ (1-10 µg/L), DTPDQ (1-10 µg/L), and IPPDQ (10 µg/L) enhanced intestinal permeability to different degrees. Meanwhile, exposure to 6-PPDQ (0.1-10 µg/L), 77PDQ (0.01-10 µg/L), CPPDQ (0.1-10 µg/L), DPPDQ (0.1-10 µg/L), DTPDQ (1-10 µg/L), and IPPDQ (1-10 µg/L) resulted in intestinal reactive oxygen species (ROS) production and activation of both SOD-3::GFP and GST-4::GFP. In 6-PPDQ, 77PDQ, CPPDQ, DPPDQ, DTPDQ, and/or IPPDQ exposed nematodes, the ROS production was strengthened by RNAi of genes (acs-22, erm-1, hmp-2, and pkc-3) governing functional state of intestinal barrier. Additionally, expressions of acs-22, erm-1, hmp-2, and pkc-3 were negatively correlated with intestinal ROS production in nematodes exposed to 6-PPDQ, 77PDQ, CPPDQ, DPPDQ, DTPDQ, and/or IPPDQ. Therefore, exposure to different PPDQs differentially induced the intestinal toxicity on nematodes. Our data highlighted potential exposure risk of PPDQs at low concentrations to organisms by inducing intestinal toxicity.

Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography.

We demonstrate an adaptation of deep learning for label-free imaging of the micro-scale lymphatic vessels and aqueous veins in the eye using optical coherence tomography (OCT). The proposed deep learning-based OCT lymphangiography (DL-OCTL) method was trained, validated and tested, using OCT scans (23 volumetric scans comprising 19,736 B-scans) from 11 fresh ex vivo porcine eyes with the corresponding vessel labels generated by a conventional OCT lymphangiography (OCTL) method based on thresholding with attenuation compensation. Compared to conventional OCTL, the DL-OCTL method demonstrates comparable results for imaging lymphatics and aqueous veins in the eye, with an Intersection over Union value of 0.79 ± 0.071 (mean ± standard deviation). In addition, DL-OCTL mitigates the imaging artifacts in conventional OCTL where the OCT signal modelling was corrupted by the tissue heterogeneity, provides ~ 10 times faster processing based on a rough comparison and does not require OCT-related knowledge for correct implementation as in conventional OCTL. With these favorable features, DL-OCTL promises to improve the practicality of OCTL for label-free imaging of lymphatics and aqueous veins for preclinical and clinical imaging applications.

Human emissions of size-resolved fluorescent bioaerosols in control situations.

Human bioaerosols contribute significantly to indoor air quality. This study used a Wideband Integrated Bioaerosol Sensor (WIBS-4A) instrument for real-time measurement of particle size distribution and count to differentiate fluorescent bioaerosols from non-fluorescent aerosols. Through an experiment involving 12 subjects (six men and six women) wearing standard cotton clothing in a 2 m × 2 m × 2 m environmental chamber, we established a quantitative method to obtain the bioaerosol emission rate of a single subject, aiming to explore the effects of masks and sex on bioaerosol emissions from different individuals. The mean emission rates of fluorescent bioaerosols in the particle size ranges of 0.5-2.5 µm and 2.5-10 µm were 3.192±2.11×104 counts/(person·h) and 13.98±9.34×104 counts/(person·h), respectively. A comparison between those wearing and not wearing masks revealed no significant differences in the emissions of fluorescent bioaerosols. This suggests respiratory sources may not significantly impact the emissions of fluorescent bioaerosols from individuals under seated breathing conditions. Significant disparities in the fluorescent bioaerosol emission rates of different biological sexes were observed through independent sample analysis. Males exhibited 41 % and 15 % higher emission rates than females for particle size ranges of 0.5-2.5 µm and 2.5-10 µm, respectively, possibly because of different metabolic rates. A significant correlation between metabolic rates and fluorescent bioaerosols (sig = 0.044 < 0.05) was observed in all the subjects. These findings underscore the individual variations that affect bioaerosol emission rates. The data provided by this study will facilitate further analysis of the on-site measured data and source analysis.

Cancer-Alterome: a literature-mined resource for regulatory events caused by genetic alterations in cancer.

It is vital to investigate the complex mechanisms underlying tumors to better understand cancer and develop effective treatments. Metabolic abnormalities and clinical phenotypes can serve as essential biomarkers for diagnosing this challenging disease. Additionally, genetic alterations provide profound insights into the fundamental aspects of cancer. This study introduces Cancer-Alterome, a literature-mined dataset that focuses on the regulatory events of an organism's biological processes or clinical phenotypes caused by genetic alterations. By proposing and leveraging a text-mining pipeline, we identify 16,681 thousand of regulatory events records encompassing 21K genes, 157K genetic alterations and 154K downstream bio-concepts, extracted from 4,354K pan-cancer literature. The resulting dataset empowers a multifaceted investigation of cancer pathology, enabling the meticulous tracking of relevant literature support. Its potential applications extend to evidence-based medicine and precision medicine, yielding valuable insights for further advancements in cancer research.

A systematic evaluation of computation methods for cell segmentation.

Cell segmentation is a fundamental task in analyzing biomedical images. Many computational methods have been developed for cell segmentation, but their performances are not well understood in various scenarios. We systematically evaluated the performance of 18 segmentation methods to perform cell nuclei and whole cell segmentation using light microscopy and fluorescence staining images. We found that general-purpose methods incorporating the attention mechanism exhibit the best overall performance. We identified various factors influencing segmentation performances, including training data and cell morphology, and evaluated the generalizability of methods across image modalities. We also provide guidelines for choosing the optimal segmentation methods in various real application scenarios. We developed Seggal, an online resource for downloading segmentation models already pre-trained with various tissue and cell types, which substantially reduces the time and effort for training cell segmentation models.

Combined-task deep network based on LassoNet feature selection for predicting the comorbidities of acute coronary syndrome.

Acute coronary syndrome (ACS) is a multifaceted cardiovascular condition frequently accompanied by multiple comorbidities, which can have significant implications for patient outcomes and treatment approaches. Precisely predicting these comorbidities is crucial for providing personalized care and making well-informed clinical decisions. However, there is a shortage of research investigating the identification of risk factors associated with ACS comorbidities and accurately predicting their likelihood of occurrence beyond heart failure. In this study, an approach called Combined-task Deep Network based on LassoNet feature selection (CDNL) is presented for predicting ACS comorbidities, including hypertension, diabetes, hyperlipidemia, and heart failure. In order to identify crucial biomarkers associated with ACS comorbidities, the proposed framework first incorporates LassoNet, which extends Lasso regression to the deep network by adding a skip (residual) layer. Additionally, a correlation score calculation method across tasks is introduced based on measuring the overlap of identified biomarkers and their assigned importance. This method enables the development of an optimal combined-task prediction model for each ACS comorbidity, addressing the challenge of limited representations in traditional multi-task learning. Our evaluation, conducted through a meticulous cross-sectional study at a tertiary hospital in China, involved a dataset of 2941 samples with 42 clinical features. The results demonstrate that CDNL facilitates the identification of significant biomarkers and achieves an average improvement in AUC of 4.93% and 8.58% compared to deep learning multi-layer neural network (DNN) and SVM, respectively. Additionally, it shows an average improvement of 2.64% and 1.92% compared to two state-of-the-art multi-task models.

Synthesis, characterization and discovery of multiple anticancer mechanisms of dibutyltin complexes based on salen-like ligands.

A series of novel dibutyltin complexes based on salen-like ligands (S01-S03) were synthesized and characterized using ultraviolet-visible spectra，infrared spectra, 1H, 13C, and 119Sn nuclear magnetic resonance, high-resolution mass spectrometry, X-ray crystallography, and thermogravimetric analysis. Complex S03 had excellent anticancer activity in vitro (IC50 = 1.5 ± 0.2 µM in CAL-27 cell lines), which highly activated ROS expression levels and induced apoptosis and cell cycle arrest at the G2/M phase. Interestingly, complex S03 induced cancer cell death through multiple mechanisms (mitochondrial pathway, ER-stress pathway, and DNA damage pathway). This study reveals new mechanisms of organotin complexes and provides new insights into the development of organotin metal complexes as anticancer drugs in the future, and compounds with multiple anticancer mechanisms may be a new strategy for delaying or overcoming drug resistance to chemotherapy and target therapy.

The association between chronic sinonasal inflammation and nasopharyngeal carcinoma - A systematic review and meta-analysis.

PURPOSE: There has been mounting evidence that inflammation is a key risk factor towards the development of certain cancers. Past studies have shown associations between nasopharyngeal carcinoma (NPC) and sinonasal tract inflammation. We aim to conduct a review and meta-analysis on the association between NPC and chronic sinus inflammation. MATERIALS AND METHODS: We conducted a meta-analysis, searching 4 international databases from 1 January 1973 to 28 March 2022 for studies reporting on sinonasal inflammation and NPC in adult patients (>18 years old). We included cohort, case-control or cross-sectional studies. These studies must examine the association between a prior history of sinonasal inflammation and the risk of developing NPC. The outcome is the incidence of NPC in patients who had prior sinonasal inflammation. RESULTS: 8 studies (8245 NPC; 1,036,087 non-NPC) were included. The overall odds ratio (OR) of patients having NPC after reporting sinonasal inflammation was 1.81 (95 % CI 1.73-1.89). Of note, chronic rhinosinusitis (CRS) (OR of 1.78 (95 %-CI: 1.68-1.90)) was more closely associated with an increased risk of NPC, as compared to allergic rhinitis (AR) (OR of 1.60 (95 %-CI: 1.52-1.68)). CONCLUSION: Chronic sinonasal inflammation is significantly associated with NPC in this systemic review and meta-analysis. The true cause-effect relationship and the potential effects of targeted screening need to be explored thoroughly with large scale prospective studies.

TNFAIP3 Derived from Skeletal Stem Cells Alleviated Rat Osteoarthritis by Inhibiting the Necroptosis of Subchondral Osteoblasts.

Recent investigations have shown that the necroptosis of tissue cells in joints is important in the development of osteoarthritis (OA). This study aimed to investigate the potential effects of exogenous skeletal stem cells (SSCs) on the necroptosis of subchondral osteoblasts in OA. Human SSCs and subchondral osteoblasts isolated from human tibia plateaus were used for Western blotting, real-time PCR, RNA sequencing, gene editing, and necroptosis detection assays. In addition, the rat anterior cruciate ligament transection OA model was used to evaluate the effects of SSCs on osteoblast necroptosis in vivo. The micro-CT and pathological data showed that intra-articular injections of SSCs significantly improved the microarchitecture of subchondral trabecular bones in OA rats. Additionally, SSCs inhibited the necroptosis of subchondral osteoblasts in OA rats and necroptotic cell models. The results of bulk RNA sequencing of SSCs stimulated or not by tumor necrosis factor α suggested a correlation of SSCs-derived tumor necrosis factor α-induced protein 3 (TNFAIP3) and cell necroptosis. Furthermore, TNFAIP3-derived from SSCs contributed to the inhibition of the subchondral osteoblast necroptosis in vivo and in vitro. Moreover, the intra-articular injections of TNFAIP3-overexpressing SSCs further improved the subchondral trabecular bone remodeling of OA rats. Thus, we report that TNFAIP3 from SSCs contributed to the suppression of the subchondral osteoblast necroptosis, which suggests that necroptotic subchondral osteoblasts in joints may be possible targets to treat OA by stem cell therapy.

The neutrophil percentage-to-albumin ratio is associated with all-cause mortality in patients with chronic heart failure.

BACKGROUND: In this study, we evaluated the predictive utility of neutrophil percentage-to-albumin ratio (NPAR) for all-cause mortality in patients with chronic heart failure (CHF). METHODS: Patients diagnosed as CHF enrolled in this retrospective cohort study were from Beijing Chaoyang Hospital, capital medical university. Admission NPAR was calculated as neutrophil percentage divided by serum albumin. The endpoints of this study were defined as 90-day, 1-year and 2-year all-cause mortality. Multivariable Cox proportional hazard regression model was performed to confirm the association between NPAR and all-cause mortality. Receiver operating characteristics (ROC) curves were used to evaluate the ability for NPAR to predict all-cause mortality. RESULTS: The 90-day (P = 0.009), 1-year (P < 0.001) and 2-year (P < 0.001) all-cause mortality in 622 patients with CHF were increased as admission NPAR increased. Multivariable Cox regression analysis found the higher NPAR value was still independently associated with increased risk of 90-day (Group III versus Group I: HR, 95% CI: 2.21, 1.01-4.86, P trend = 0.038), 1-year (Group III versus Group I: HR, 95% CI:2.13, 1.30-3.49, P trend = 0.003), and 2-year all-cause mortality (Group III versus Group I: HR, 95% CI:2.06, 1.37-3.09, P trend = 0.001), after adjustments for several confounders. ROC curves revealed that NPAR had a better ability to predict all-cause mortality in patients with CHF, than either albumin or the neutrophil percentage alone. CONCLUSIONS: NPAR was independently correlated with 90-day, 1-year, and 2-year all-cause mortality in patients with CHF.

GeneSegNet: a deep learning framework for cell segmentation by integrating gene expression and imaging.

When analyzing data from in situ RNA detection technologies, cell segmentation is an essential step in identifying cell boundaries, assigning RNA reads to cells, and studying the gene expression and morphological features of cells. We developed a deep-learning-based method, GeneSegNet, that integrates both gene expression and imaging information to perform cell segmentation. GeneSegNet also employs a recursive training strategy to deal with noisy training labels. We show that GeneSegNet significantly improves cell segmentation performances over existing methods that either ignore gene expression information or underutilize imaging information.

Feasibility of deep learning-based polarization-sensitive optical coherence tomography angiography for imaging cutaneous microvasculature.

Polarization-sensitive optical coherence tomography (PS-OCT) measures the polarization states of the backscattered light from tissue that can improve angiography based on conventional optical coherence tomography (OCT). We present a feasibility study on PS-OCT integrated with deep learning for PS-OCT angiography (PS-OCTA) imaging of human cutaneous microvasculature. Two neural networks were assessed for PS-OCTA, including the residual dense network (RDN), which previously showed superior performance for angiography with conventional OCT and the upgraded grouped RDN (GRDN). We also investigated different protocols to process the multiple signal channels provided by the Jones matrices from the PS-OCT system to achieve optimal PS-OCTA performance. The training and testing of the deep learning-based PS-OCTA were performed using PS-OCT scans collected from 18 skin locations comprising 16,600 B-scan pairs. The results demonstrated a moderately improved performance of GRDN over RDN, and of the use of the combined signal from the Jones matrix elements over the separate use of the elements, as well as a similar image quality to that provided by speckle decorrelation angiography. GRDN-based PS-OCTA also showed ∼2-3 times faster processing and improved mitigation of tissue motion as compared to speckle decorrelation angiography, and enabled fully automatic processing. Deep learning-based PS-OCTA can be used for imaging cutaneous microvasculature, which may enable easy adoption of PS-OCTA for preclinical and clinical applications.

Human osteoarthritic articular cartilage stem cells suppress osteoclasts and improve subchondral bone remodeling in experimental knee osteoarthritis partially by releasing TNFAIP3.

BACKGROUND: Though articular cartilage stem cell (ACSC)-based therapies have been demonstrated to be a promising option in the treatment of diseased joints, the wide variety of cell isolation, the unknown therapeutic targets, and the incomplete understanding of the interactions of ACSCs with diseased microenvironments have limited the applications of ACSCs. METHODS: In this study, the human ACSCs have been isolated from osteoarthritic articular cartilage by advantage of selection of anatomical location, the migratory property of the cells, and the combination of traumatic injury, mechanical stimuli and enzymatic digestion. The protective effects of ACSC infusion into osteoarthritis (OA) rat knees on osteochondral tissues were evaluated using micro-CT and pathological analyses. Moreover, the regulation of ACSCs on osteoarthritic osteoclasts and the underlying mechanisms in vivo and in vitro were explored by RNA-sequencing, pathological analyses and functional gain and loss experiments. The one-way ANOVA was used in multiple group data analysis. RESULTS: The ACSCs showed typical stem cell-like characteristics including colony formation and committed osteo-chondrogenic capacity. In addition, intra-articular injection into knee joints yielded significant improvement on the abnormal subchondral bone remodeling of osteoarthritic rats. Bioinformatic and functional analysis showed that ACSCs suppressed osteoarthritic osteoclasts formation, and inflammatory joint microenvironment augmented the inhibitory effects. Further explorations demonstrated that ACSC-derived tumor necrosis factor alpha-induced protein 3 (TNFAIP3) remarkably contributed to the inhibition on osteoarhtritic osteoclasts and the improvement of abnormal subchondral bone remodeling. CONCLUSION: In summary, we have reported an easy and reproducible human ACSC isolation strategy and revealed their effects on subchondral bone remodeling in OA rats by releasing TNFAIP3 and suppressing osteoclasts in a diseased microenvironment responsive manner.

Gene based message passing for drug repurposing.

The medicinal effect of a drug acts through a series of genes, and the pathological mechanism of a disease is also related to genes with certain biological functions. However, the complex information between drug or disease and a series of genes is neglected by traditional message passing methods. In this study, we proposed a new framework using two different strategies for gene-drug/disease and drug-disease networks, respectively. We employ long short-term memory (LSTM) network to extract the flow of message from series of genes (gene path) to drug/disease. Incorporating the resulting information of gene paths into drug-disease network, we utilize graph convolutional network (GCN) to predict drug-disease associations. Experimental results showed that our method GeneDR (gene-based drug repurposing) makes better use of the information in gene paths, and performs better in predicting drug-disease associations.

Marker-Free Isoelectric Focusing Patterns for Identification of Meat Samples via Deep Learning.

Isoelectric focusing (IEF) is a powerful tool for resolving complex protein samples, which generates IEF patterns consisting of multiplex analyte bands. However, the interpretation of IEF patterns requires the careful selection of isoelectric point (pI) markers for profiling the pH gradient and a trivial process of pI labeling, resulting in low IEF efficiency. Here, we for the first time proposed a marker-free IEF method for the efficient and accurate classification of IEF patterns by using a convolutional neural network (CNN) model. To verify our method, we identified 21 meat samples whose IEF patterns comprised different bands of meat hemoglobin, myoglobin, and their oxygen-binding variants but no pI marker. Thanks to the high throughput and short assay time of the microstrip IEF, we efficiently collected 1449 IEF patterns to construct the data set for model training. Despite the absence of pI markers, we experimentally introduced the severe pH gradient drift into 189 IEF patterns in the data set, thereby omitting the need for profiling the pH gradient. To enhance the model robustness, we further employed data augmentation during the model training to mimic pH gradient drift. With the advantages of simple preprocessing, a rapid inference of 50 ms, and a high accuracy of 97.1%, the CNN model outperformed the traditional algorithm for simultaneously identifying meat species and cuts of meat of 105 IEF patterns, suggesting its great potential of being combined with microstrip IEF for large-scale IEF analyses of complicated protein samples.