Predicting Successes and Failures of Clinical Trials With Outer Product-Based Convolutional Neural Network.

Despite several improvements in the drug development pipeline over the past decade, drug failures due to unexpected adverse effects have rapidly increased at all stages of clinical trials. To improve the success rate of clinical trials, it is necessary to identify potential loser drug candidates that may fail at clinical trials. Therefore, we need to develop reliable models for predicting the outcomes of clinical trials of drug candidates, which have the potential to guide the drug discovery process. In this study, we propose an outer product-based convolutional neural network (OPCNN) model which integrates effectively chemical features of drugs and target-based features. The validation results via 10-fold cross-validations on the dataset used for a data-driven approach PrOCTOR proved that our OPCNN model performs quite well in terms of accuracy, F1-score, Matthews correlation coefficient (MCC), precision, recall, area under the curve (AUC) of the receiver operating characteristic, and area under the precision-recall curve (AUPRC). In particular, the proposed OPCNN model showed the best performance in terms of MCC, which is widely used in biomedicine as a performance metric and is a more reliable statistical measure. Through 10-fold cross-validation experiments, the accuracy of the OPCNN model is as high as 0.9758, F1 score is as high as 0.9868, the MCC reaches 0.8451, the precision is as high as 0.9889, the recall is as high as 0.9893, the AUC is as high as 0.9824, and the AUPRC is as high as 0.9979. The results proved that our OPCNN model shows significantly good prediction performance on outcomes of clinical trials and it can be quite helpful in early drug discovery.

Prediction of drug-target binding affinity using similarity-based convolutional neural network.

Identifying novel drug-target interactions (DTIs) plays an important role in drug discovery. Most of the computational methods developed for predicting DTIs use binary classification, whose goal is to determine whether or not a drug-target (DT) pair interacts. However, it is more meaningful but also more challenging to predict the binding affinity that describes the strength of the interaction between a DT pair. If the binding affinity is not sufficiently large, such drug may not be useful. Therefore, the methods for predicting DT binding affinities are very valuable. The increase in novel public affinity data available in the DT-related databases enables advanced deep learning techniques to be used to predict binding affinities. In this paper, we propose a similarity-based model that applies 2-dimensional (2D) convolutional neural network (CNN) to the outer products between column vectors of two similarity matrices for the drugs and targets to predict DT binding affinities. To our best knowledge, this is the first application of 2D CNN in similarity-based DT binding affinity prediction. The validation results on multiple public datasets show that the proposed model is an effective approach for DT binding affinity prediction and can be quite helpful in drug development process.

Tantalum-coated polylactic acid fibrous membranes for guided bone regeneration.

Guided bone regeneration (GBR) membrane is necessary to reconstruct the defect bone tissue by defending penetration of soft tissues. Polylactic acid (PLA) attracts much attention to utilize as a GBR membrane because it has relatively high mechanical strength and biodegradability. However, the poor osteoconductivity of PLA is a major concern. The aim of this study is to improve the osteoconductivity of fibrous, electrospun, PLA guided bone regeneration membranes by coating the fiber surface with highly biocompatible tantalum (Ta). Ta coating of electrospun PLA membrane was created through sputtered Ta ions surrounding the PLA fibers. The Ta-coated PLA (Ta-PLA) membranes remain a randomly aligned fibrous structure with no defects caused by sputtering. The chemical composition of Ta-PLA membrane indicates Ta coating was well deposited on PLA fibers. Although the mechanical strength of Ta-PLA was reduced compared with bare PLA membrane, the Ta coating layer does not readily delaminate from the single PLA fiber surface due to its cladded structure which indicates that the Ta coating has high mechanical stability on PLA fibers. In vitro cell tests demonstrate that the attachment, proliferation, and differentiation of preosteoblasts are significantly promoted on the Ta-PLA membranes compared to bare PLA. In an in vivo animal test, most calvarial defects in the Ta-PLA group are covered with newly formed bone within six weeks, while the defects in the bare PLA group are rarely covered. Furthermore, the degree of bone healing in the Ta-PLA group is comparable to healing observed on collagen membranes, which are highly bioactive materials. These results indicate the superior osteoconductivity of Ta-PLA will make it particularly useful as a guided bone regeneration membrane.

Tantalum - Poly (L-lactic acid) nerve conduit for peripheral nerve regeneration.

Recently, Tantalum (Ta) has been re-explored and used with bone implants to promote bone regeneration. It has previously been extensively used as a nerve suture material; however, its use was abandoned because of the formation of scar tissue. In this study, we constructed a nerve conduit made of poly (L-lactic acid) PLA (outer layer) and tantalum Ta (inner layer) to evaluate its efficiency in the promotion of peripheral nerve regeneration. MATERIALS AND METHODS: First, we conducted an in vitro study to evaluate the viability and proliferation of Schwann cells and rat pheocromocytoma (PC-12) cells on Ta-PLA sheets using Enhanced Cell Viability Assay Kit (EZ-CYTOX). An in vivo study was then performed using Sprague Dawley rats that were randomly divided into the following three groups: sham, PLA, and Ta-PLA nerve conduits. The nerve conduit was placed over a 10-mm gap of the rat sciatic nerve to promote nerve regeneration. The rats were observed over 12 wk with weekly sciatic functional index functional assessment. At the end of 12 wk, the nerve regeneration outcome was assessed through dorsal root ganglions (DRG) retrograde neurons labeling, histomorphometric analysis, and histological analysis. RESULTS: The in vitro study showed significant viability and proliferation of Schwann cells in the Ta-PLA group than in the other groups. In the in vivo study, the gross findings revealed well-regenerated neural tissue in both the experimental groups with no scarring. The histological analysis showed that about 50 % of the conduits were filled with axons with a higher tendency for peripheral growth in the PLA group than for central growth within the Ta-PLA group conduits. The retrograde labeled neurons were significantly higher in Ta-PLA group than in the PLA group. Ta-PLA showed non-significant difference in the total fibers compared to the sham group. CONCLUSION: Tantalum proved favorable for the growth of Schwann cells.In vivo, Ta-PLA nerve conduit induced peripheral nerve regeneration without scar tissue formation.

Enhanced biolubrication on biomedical devices using hyaluronic acid-silica nanohybrid hydrogels.

In this work, highly lubricous hyaluronic acid-silica (HA-SiO2) nanohybrid coatings were fabricated through a sequential process consisting of a sol-gel followed by electrophoretic deposition (EPD). SiO2 nanoparticles were uniformly distributed in the coating layers, and the coating thickness was identified as approximately 1-2 µm regardless of the amount of SiO2. Incorporation of SiO2 into the HA polymer matrix enhanced the mechanical stability of the nanohybrid coatings, indicating greater interfacial bonding strength compared to HA coating layers alone. In addition, due to improved stability, the nanohybrid coatings showed excellent biolubrication properties, which were evaluated with a tribological experiment. These results indicate that the nanohybrid coatings have great potential to be used in biomedical applications that require superior biolubrication properties.

Detection of chromosome structural variation by targeted next-generation sequencing and a deep learning application.

Molecular testing is increasingly important in cancer diagnosis. Targeted next generation sequencing (NGS) is widely accepted method but structural variation (SV) detection by targeted NGS remains challenging. In the brain tumor, identification of molecular alterations, including 1p/19q co-deletion, is essential for accurate glial tumor classification. Hence, we used targeted NGS to detect 1p/19q co-deletion using a newly developed deep learning (DL) model in 61 tumors, including 19 oligodendroglial tumors. An ensemble 1-dimentional convolution neural network was developed and used to detect the 1p/19q co-deletion. External validation was performed using 427 low-grade glial tumors from The Cancer Genome Atlas (TCGA). Manual review of the copy number plot from the targeted NGS identified the 1p/19q co-deletion in all 19 oligodendroglial tumors. Our DL model also perfectly detected the 1p/19q co-deletion (area under the curve, AUC = 1) in the testing set, and yielded reproducible results (AUC = 0.9652) in the validation set (n = 427), although the validation data were generated on a completely different platform (SNP Array 6.0 platform). In conclusion, targeted NGS using a cancer gene panel is a promising approach for classifying glial tumors, and DL can be successfully integrated for the SV detection in NGS data.

Kernel-based geographically and temporally weighted autoregressive model for house price estimation.

Spatiotemporal nonstationarity and autocorrelation are two crucial points in modeling geographical data. Previous studies have demonstrated that geographically and temporally weighted autoregressive (GTWAR) model accounts for both spatiotemporal nonstationarity and autocorrelation simultaneously to estimate house prices. Therefore, this paper proposes a kernel-based GTWAR (KBGTWAR) model by incorporating the basic principle of support vector machine regression into spatially and temporally varying coefficients model. The efficacy of KBGTWAR model is demonstrated through a case study on housing prices in the city of Shenzhen, China, from year 2004 to 2008. Comparing the existing models, KBGTWAR model obtains the lowest value for the residual sum of squares (RSS) and the highest value for the coefficient of determination R2. Moreover, KBGTWAR model improves the goodness of fit of the existing GTWAR model from 12.0 to 4.5 in terms of RSS, from 0.914 to 0.968 in terms of R2 and from 3.84 to 4.45 in terms of F-statistic. The results show that KBGTWAR model provides a comparatively high goodness of fit and sufficient explanatory power for both spatiotemporal nonstationarity and autocorrelation. The results of this study demonstrate that the proposed KBGTWAR model can be used to effectively formulate polices for real estate management.

Enhancement of bio-stability and mechanical properties of hyaluronic acid hydrogels by tannic acid treatment.

Hyaluronic acid (HA) has been widely investigated because of its excellent biocompatibility and its ability to form hydrogels with various chemical modifications. However, HA hydrogels undergo rapid degradation and exhibit poor mechanical stability under physiological conditions. Tannic acid (TA), a naturally occurring polyphenol found in plants and fruits, has recently attracted interest as a crosslinking agent because of its abundant hydroxyl groups. In this study, we prepared HA hydrogels chemically crosslinked by polyethylene glycol diglycidyl ether (PEGDE) and treated with TA in an attempt to enhance the physical properties of HA hydrogels. TA acts as a physical crosslinker owing to the strong hydrogen bonding between TA and PEGDE, resulting in improved mechanical properties that support both cell attachment and proliferation without any sign of cytotoxicity. The enzymatic stability of the HA-TA hydrogels was significantly enhanced with the addition of TA, which was attributed to the hyaluronidase inhibition activity of TA. Additionally, the antioxidant potential of TA resulted in good resistance to degradation by reactive oxygen species, which can be generated in human tissues.