IEPAPI: a method for immune epitope prediction by incorporating antigen presentation and immunogenicity.

CD8+ T cells can recognize peptides presented by class I human leukocyte antigen (HLA-I) of nucleated cells. Exploring this immune mechanism is essential for identifying T-cell vaccine targets in cancer immunotherapy. Over the past decade, the wealth of data generated by experiments has spawned many computational approaches for predicting HLA-I binding, antigen presentation and T-cell immune responses. Nevertheless, existing HLA-I binding and antigen presentation prediction approaches suffer from low precision due to the absence of T-cell receptor (TCR) recognition. Direct modeling of T-cell immune responses is less effective as TCR recognition's mechanism still remains underexplored. Therefore, directly applying these existing methods to screen cancer neoantigens is still challenging. Here, we propose a novel immune epitope prediction method termed IEPAPI by effectively incorporating antigen presentation and immunogenicity. First, IEPAPI employs a transformer-based feature extraction block to acquire representations of peptides and HLA-I proteins. Second, IEPAPI integrates the prediction of antigen presentation prediction into the input of immunogenicity prediction branch to simulate the connection between the biological processes in the T-cell immune response. Quantitative comparison results on an independent antigen presentation test dataset exhibit that IEPAPI outperformed the current state-of-the-art approaches NetMHCpan4.1 and mhcflurry2.0 on 100 (25/25) and 76% (19/25) of the HLA subtypes, respectively. Furthermore, IEPAPI demonstrates the best precision on two independent neoantigen datasets when compared with existing approaches, suggesting that IEPAPI provides a vital tool for T-cell vaccine design.

Identifying the Branch of Kiwifruit Based on Unmanned Aerial Vehicle (UAV) Images Using Deep Learning Method.

It is important to obtain accurate information about kiwifruit vines to monitoring their physiological states and undertake precise orchard operations. However, because vines are small and cling to trellises, and have branches laying on the ground, numerous challenges exist in the acquisition of accurate data for kiwifruit vines. In this paper, a kiwifruit canopy distribution prediction model is proposed on the basis of low-altitude unmanned aerial vehicle (UAV) images and deep learning techniques. First, the location of the kiwifruit plants and vine distribution are extracted from high-precision images collected by UAV. The canopy gradient distribution maps with different noise reduction and distribution effects are generated by modifying the threshold and sampling size using the resampling normalization method. The results showed that the accuracies of the vine segmentation using PSPnet, support vector machine, and random forest classification were 71.2%, 85.8%, and 75.26%, respectively. However, the segmentation image obtained using depth semantic segmentation had a higher signal-to-noise ratio and was closer to the real situation. The average intersection over union of the deep semantic segmentation was more than or equal to 80% in distribution maps, whereas, in traditional machine learning, the average intersection was between 20% and 60%. This indicates the proposed model can quickly extract the vine distribution and plant position, and is thus able to perform dynamic monitoring of orchards to provide real-time operation guidance.

Novel drug delivery nanosystems based on out-inside bifunctionalized mesoporous silica yolk-shell magnetic nanostars used as nanocarriers for curcumin.

Mesoporous silica has aroused lots of interest in biomedical fields, in which novel kinds of mesoporous silica with tunable mesoporosity and size have attracted much attention, but functionalization or multi-functionalization inside the mesopores of these structures is still rarely detected. Among all the functionalized molecules, beta cyclodextrin hydrate (ß-CD), a kind of hydrophilic non-toxic carrier for hydrophobic drugs, can increase the solubility and bioavailability of drugs, acting as a pH responsive "gate" when functionalized on the surface of mesoporous silica. Herein, we functionalized ß-CD inside novel kinds of mesoporous silica or magnetic mesoporous silica as the physical binding sites for the model drug curcumin through an out-inside two step bifunctionalization process including a vacuum pumping recrystallization drug loading process. According to the physical characterization with XRD, FT-IR, XPS, solid state NMR, BET, TG, DTA, TEM and DLS, the drug delivery nanosystems were successfully fabricated and contained nano-formulations of curcumin. In vitro cell testing, including Cell Counting Kit-8, Hoechst 33342 staining, hemolysis experiments and cell apoptosis, indicated that through the bifunctionalization, the biocompatibility of the mesoporous silica with cells could be improved, and the toxicity of the drug delivery nano-formulations towards two kinds of cancer cells, SK-HEP1 and HepG2, was significantly increased compared with free curcumin. In vitro release studies revealed that the nano-formulations contained more suspended curcumin molecules as described by the Higuchi models and showed enhanced pH responsive release properties, and that the magnetic nano-formulations exhibited alternating magnetically controlled release properties. The confocal microscopy analysis results revealed the obviously increasing intercellular release and uptake of both nano-formulations of curcumin by SK-HEP1 cells and the "on" and "off" stages of the alternating magnetism responsive intercellular release properties of the fabricated magnetic nano-formulations. The bifunctionalization process combined with the nanostar structure has immense potential in the drug delivery field, especially for hydrophobic drugs.

Outside-in stepwise functionalization of mesoporous silica nanocarriers for matrix type sustained release of fluoroquinolone drugs.

In this study, we propose outside-in stepwise functionalization of MCM-41-type mesoporous silica for use as a high-efficiency matrix drug delivery nanosystem aimed at the insoluble antibacterial agent fluoroquinolone. Thiol (-SH) modification on the surface of the nanocarrier and aminopropyl groups (-NH2) in the channels give the system a framework for sustained drug release for 72 h with drug loading capacity of 58.64% as a result of the completely opposite electrostatic interaction between drug molecules of thiol and amino. Unusually, abundant crystals of drug molecules were observed by transmission electron microscopy (TEM) in channels of the nanocarriers, caused by self-organization under the electrostatic attraction of the grafting groups. The elevated crystallinity of drug molecules loaded in the functional mesoporous MCM-41 nanoparticles was proved also through wide-angle XRD. Analysis of the release profiles highlighted the low cytotoxicity and excellent biocompatibility of the modified nanocarriers in vitro. Compared with single functionalization, the outside-in stepwise process can completely modify the deep inner of the channel and achieve effective internal drug loading of mesoporous materials. We believe that this method is not only of use for framework sustained-release tablets, but also other clinical medicine and chemical engineering.