Lymphocyte detection for cancer analysis using a novel fusion block based channel boosted CNN.

Tumor-infiltrating lymphocytes, specialized immune cells, are considered an important biomarker in cancer analysis. Automated lymphocyte detection is challenging due to its heterogeneous morphology, variable distribution, and presence of artifacts. In this work, we propose a novel Boosted Channels Fusion-based CNN "BCF-Lym-Detector" for lymphocyte detection in multiple cancer histology images. The proposed network initially selects candidate lymphocytic regions at the tissue level and then detects lymphocytes at the cellular level. The proposed "BCF-Lym-Detector" generates diverse boosted channels by utilizing the feature learning capability of different CNN architectures. In this connection, a new adaptive fusion block is developed to combine and select the most relevant lymphocyte-specific features from the generated enriched feature space. Multi-level feature learning is used to retain lymphocytic spatial information and detect lymphocytes with variable appearances. The assessment of the proposed "BCF-Lym-Detector" show substantial improvement in terms of F-score (0.93 and 0.84 on LYSTO and NuClick, respectively), which suggests that the diverse feature extraction and dynamic feature selection enhanced the feature learning capacity of the proposed network. Moreover, the proposed technique's generalization on unseen test sets with a good recall (0.75) and F-score (0.73) shows its potential use for pathologists' assistance.

In Vitro Analysis of Cytotoxic Activities of Monotheca buxifolia Targeting WNT/ß-Catenin Genes in Breast Cancer Cells.

Breast cancer (BC) is known to be the most common malignancy among women throughout the world. Plant-derived natural products have been recognized as a great source of anticancer drugs. In this study, the efficacy and anticancer potential of the methanolic extract of Monotheca buxifolia leaves using human breast cancer cells targeting WNT/ß-catenin signaling was evaluated. We used methanolic and other (chloroform, ethyl acetate, butanol, and aqueous) extracts to discover their potential cytotoxicity on breast cancer cells (MCF-7). Among these, the methanol showed significant activity in the inhibition of the proliferation of cancer cells because of the presence of bioactive compounds, including phenols and flavonoids, detected by a Fourier transform infrared spectrophotometer and by gas chromatography mass spectrometry. The cytotoxic effect of the plant extract on the MCF-7 cells was examined by MTT and acid phosphatase assays. Real-time PCR analysis was performed to measure the mRNA expression of WNT-3a and ß-catenin, along with Caspase-1,-3,-7, and -9 in MCF-7 cells. The IC50 value of the extract was found to be 232 µg/mL and 173 µg/mL in the MTT and acid phosphatase assays, respectively. Dose selection (100 and 300 µg/mL) was performed for real-time PCR, Annexin V/PI analysis, and Western blotting using Doxorubicin as a positive control. The extract at 100 µg/mL significantly upregulated caspases and downregulated the WNT-3a and ß-catenin gene in MCF-7 cells. Western blot analysis further confirmed the dysregulations of the WNT signaling component (*** p< 0.0001). The results showed an increase in the number of dead cells in methanolic extract-treated cells in the Annexin V/PI analysis. Our study concludes that M. buxifolia may serve as an effective anticancer mediator through gene modulation that targets WNT/ß-catenin signaling, and it can be further characterized using more powerful experimental and computational tools.

Structural Consequences of IRS-2 nsSNPs and Implication for Insulin Receptor Substrate-2 Protein Stability.

Single-Nucleotide Polymorphisms (SNPs) are common genetic variations implicated in human diseases. The non-synonymous SNPs (nsSNPs) affect the proteins' structures and their molecular interactions with other interacting proteins during the accomplishment of biochemical processes. This ultimately causes proteins functional perturbation and disease phenotypes. The Insulin receptor substrate-2 (IRS-2) protein promotes glucose absorption and participates in the biological regulation of glucose metabolism and energy production. Several IRS-2 SNPs are reported in association with type 2 diabetes and obesity in human populations. However, there are no comprehensive reports about the protein structural consequences of these nsSNPs. Keeping in view the pathophysiological consequences of the IRS-2 nsSNPs, we designed the current study to understand their possible structural impact on coding protein. The prioritized list of the deleterious IRS-2 nsSNPs was acquired from multiple bioinformatics resources, including VEP (SIFT, PolyPhen, and Condel), PROVEAN, SNPs&GO, PMut, and SNAP2. The protein structure stability assessment of these nsSNPs was performed by MuPro and I-Mutant-3.0 servers via structural modeling approaches. The atomic-level structural and molecular dynamics (MD) impact of these nsSNPs were examined using GROMACS 2019.2 software package. The analyses initially predicted 8 high-risk nsSNPs located in the highly conserved regions of IRS-2. The MD simulation analysis eventually prioritized the N232Y, R218C, and R104H nsSNPs that predicted to significantly compromise the structure stability and may affect the biological function of IRS-2. These nsSNPs are predicted as high-risk candidates for diabetes and obesity. The validation of protein structural impact of these shortlisted nsSNPs may provide biochemical insight into the IRS-2-mediated type-2 diabetes.

Attention-guided multi-scale deep object detection framework for lymphocyte analysis in IHC histological images.

Tumor-infiltrating lymphocytes are specialized lymphocytes that can detect and kill cancerous cells. Their detection poses many challenges due to significant morphological variations, overlapping occurrence, artifact regions and high-class resemblance between clustered areas and artifacts. In this regard, a Lymphocyte Analysis Framework based on Deep Convolutional neural network (DC-Lym-AF) is proposed to analyze lymphocytes in immunohistochemistry images. The proposed framework comprises (i) pre-processing, (ii) screening phase, (iii) localization phase and (iv) post-processing. In the screening phase, a custom convolutional neural network architecture (lymphocyte dilated network) is developed to screen lymphocytic regions by performing a patch-level classification. This proposed architecture uses dilated convolutions and shortcut connections to capture multi-level variations and ensure reference-based learning. In contrast, the localization phase utilizes an attention-guided multi-scale lymphocyte detector to detect lymphocytes. The proposed detector extracts refined and multi-scale features by exploiting dilated convolutions, attention mechanism and feature pyramid network (FPN) using its custom attention-aware backbone. The proposed DC-Lym-AF shows exemplary performance on the NuClick dataset compared with the existing detection models, with an F-score and precision of 0.84 and 0.83, respectively. We verified the generalizability of our proposed framework by participating in a publically open LYON'19 challenge. Results in terms of detection rate (0.76) and F-score (0.73) suggest that the proposed DC-Lym-AF can effectively detect lymphocytes in immunohistochemistry-stained images collected from different laboratories. In addition, its promising generalization on several datasets implies that it can be turned into a medical diagnostic tool to investigate various histopathological problems. Graphical Abstract.

A New Deep Hybrid Boosted and Ensemble Learning-Based Brain Tumor Analysis Using MRI.

Brain tumor analysis is essential to the timely diagnosis and effective treatment of patients. Tumor analysis is challenging because of tumor morphology factors like size, location, texture, and heteromorphic appearance in medical images. In this regard, a novel two-phase deep learning-based framework is proposed to detect and categorize brain tumors in magnetic resonance images (MRIs). In the first phase, a novel deep-boosted features space and ensemble classifiers (DBFS-EC) scheme is proposed to effectively detect tumor MRI images from healthy individuals. The deep-boosted feature space is achieved through customized and well-performing deep convolutional neural networks (CNNs), and consequently, fed into the ensemble of machine learning (ML) classifiers. While in the second phase, a new hybrid features fusion-based brain-tumor classification approach is proposed, comprised of both static and dynamic features with an ML classifier to categorize different tumor types. The dynamic features are extracted from the proposed brain region-edge net (BRAIN-RENet) CNN, which is able to learn the heteromorphic and inconsistent behavior of various tumors. In contrast, the static features are extracted by using a histogram of gradients (HOG) feature descriptor. The effectiveness of the proposed two-phase brain tumor analysis framework is validated on two standard benchmark datasets, which were collected from Kaggle and Figshare and contain different types of tumors, including glioma, meningioma, pituitary, and normal images. Experimental results suggest that the proposed DBFS-EC detection scheme outperforms the standard and achieved accuracy (99.56%), precision (0.9991), recall (0.9899), F1-Score (0.9945), MCC (0.9892), and AUC-PR (0.9990). The classification scheme, based on the fusion of feature spaces of proposed BRAIN-RENet and HOG, outperform state-of-the-art methods significantly in terms of recall (0.9913), precision (0.9906), accuracy (99.20%), and F1-Score (0.9909) in the CE-MRI dataset.

Cross-continental admixture in the Kho population from northwest Pakistan.

Northern Pakistan is home to many diverse ethnicities and languages. The region acted as a prime corridor for ancient invasions and population migrations between Western Eurasia and South Asia. Kho, one of the major ethnic groups living in this region, resides in the remote and isolated mountainous region in the Chitral Valley of the Hindu Kush Mountain range. They are culturally and linguistically distinct from the rest of the Pakistani population groups and their genetic ancestry is still unknown. In this study, we generated genome-wide genotype data of ~1 M loci (Illumina WeGene array) for 116 unrelated Kho individuals and carried out comprehensive analyses in the context of worldwide extant and ancient anatomically modern human populations across Eurasia. The results inferred that the Kho can trace a large proportion of their ancestry to the population who migrated south from the Southern Siberian steppes during the second millennium BCE ~110 generations ago. An additional wave of gene flow from a population carrying East Asian ancestry was also identified in the Kho that occurred ~60 generations ago and may possibly be linked to the expansion of the Tibetan Empire during 7th to 9th centuries CE (current era) in the northwestern regions of the Indian sub-continent. We identified several candidate regions suggestive of positive selection in the Kho, that included genes mainly involved in pigmentation, immune responses, muscular development, DNA repair, and tumor suppression.

Detection of tumour infiltrating lymphocytes in CD3 and CD8 stained histopathological images using a two-phase deep CNN.

BACKGROUND: Immuno-score, a prognostic measure for cancer, employed in determining tumor grade and type, is generated by counting the number of Tumour-Infiltrating Lymphocytes (TILs) in CD3 and CD8 stained histopathological tissue samples. Significant stain variations and heterogeneity in lymphocytes' spatial distribution and density make automated counting of TILs' a challenging task. METHODS: This work addresses the aforementioned challenges by developing a pipeline "Two-Phase Deep Convolutional Neural Network based Lymphocyte Counter (TDC-LC)" to detect lymphocytes in CD3 and CD8 stained histology images. The proposed pipeline sequentially works by removing hard negative examples (artifacts) in the first phase using a custom CNN "LSATM-Net" that exploits the idea of a split, asymmetric transform, and merge. Whereas, in the second phase, instance segmentation is performed to detect and generate a lymphocyte count against the remaining samples. Furthermore, the effectiveness of the proposed pipeline is measured by comparing it with the state-of-the-art single- and two-stage detectors. The inference code is available at GitHub Repository https://github.com/m-mohsin-zafar/tdc-lc. RESULTS: The empirical evaluation on samples from LYSTO dataset shows that the proposed LSTAM-Net can learn variations in the images and precisely remove the hard negative stain artifacts with an F-score of 0.74. The detection analysis shows that the proposed TDC-LC outperforms the existing models in identifying and counting lymphocytes with high Recall (0.87) and F-score (0.89). Moreover, the commendable performance of the proposed TDC-LC in different organs suggests a good generalization. CONCLUSION: The promising performance of the proposed pipeline suggests that it can serve as an automated system for detecting and counting lymphocytes from patches of tissue samples thereby reducing the burden on pathologists.

Bcl-2 Modulation in p53 Signaling Pathway by Flavonoids: A Potential Strategy towards the Treatment of Cancer.

Cancer is a major cause of death, affecting human life in both developed and developing countries. Numerous antitumor agents exist but their toxicity and low efficacy limits their utility. Furthermore, the complex pathophysiological mechanisms of cancer, serious side effects and poor prognosis restrict the administration of available cancer therapies. Thus, developing novel therapeutic agents are required towards a simultaneous targeting of major dysregulated signaling mediators in cancer etiology, while possessing lower side effects. In this line, the plant kingdom is introduced as a rich source of active phytochemicals. The secondary metabolites produced by plants could potentially regulate several dysregulated pathways in cancer. Among the secondary metabolites, flavonoids are hopeful phytochemicals with established biological activities and minimal side effects. Flavonoids inhibit B-cell lymphoma 2 (Bcl-2) via the p53 signaling pathway, which is a significant apoptotic target in many cancer types, hence suppressing a major dysregulated pathway in cancer. To date, there have been no studies reported which extensively highlight the role of flavonoids and especially the different classes of flavonoids in the modulation of Bcl-2 in the P53 signaling pathway. Herein, we discuss the modulation of Bcl-2 in the p53 signaling pathway by different classes of flavonoids and highlight different mechanisms through which this modulation can occur. This study will provide a rationale for the use of flavonoids against different cancers paving a new mechanistic-based approach to cancer therapy.

Coronavirus disease analysis using chest X-ray images and a novel deep convolutional neural network.

BACKGROUND: The recent emergence of a highly infectious and contagious respiratory viral disease known as COVID-19 has vastly impacted human lives and overloaded the health care system. Therefore, it is crucial to develop a fast and accurate diagnostic system for the timely identification of COVID-19 infected patients and thus to help control its spread. METHODS: This work proposes a new deep CNN based technique for COVID-19 classification in X-ray images. In this regard, two novel custom CNN architectures, namely COVID-RENet-1 and COVID-RENet-2, are developed for COVID-19 specific pneumonia analysis. The proposed technique systematically employs Region and Edge-based operations along with convolution operations. The advantage of the proposed idea is validated by performing series of experimentation and comparing results with two baseline CNNs that exploited either a single type of pooling operation or strided convolution down the architecture. Additionally, the discrimination capacity of the proposed technique is assessed by benchmarking it against the state-of-the-art CNNs on radiologist's authenticated chest X-ray dataset. Implementation is available at https://github.com/PRLAB21/Coronavirus-Disease-Analysis-using-Chest-X-Ray-Images. RESULTS: The proposed classification technique shows good generalization as compared to existing CNNs by achieving promising MCC (0.96), F-score (0.98) and Accuracy (98%). This suggests that the idea of synergistically using Region and Edge-based operations aid in better exploiting the region homogeneity, textural variations, and region boundary-related information in an image, which helps to capture the pneumonia specific pattern. CONCLUSIONS: The encouraging results of the proposed classification technique on the test set with high sensitivity (0.98) and precision (0.98) suggest the effectiveness of the proposed technique. Thus, it suggests the potential use of the proposed technique in other X-ray imagery-based infectious disease analysis.

Mitotic nuclei analysis in breast cancer histopathology images using deep ensemble classifier.

Mitotic nuclei estimation in breast tumour samples has a prognostic significance in analysing tumour aggressiveness and grading system. The automated assessment of mitotic nuclei is challenging because of their high similarity with non-mitotic nuclei and heteromorphic appearance. In this work, we have proposed a new Deep Convolutional Neural Network (CNN) based Heterogeneous Ensemble technique "DHE-Mit-Classifier" for analysis of mitotic nuclei in breast histopathology images. The proposed technique in the first step detects candidate mitotic patches from the histopathological biopsy regions, whereas, in the second step, these patches are classified into mitotic and non-mitotic nuclei using the proposed DHE-Mit-Classifier. For the development of a heterogeneous ensemble, five different deep CNNs are designed and used as base-classifiers. These deep CNNs have varying architectural designs to capture the structural, textural, and morphological properties of the mitotic nuclei. The developed base-classifiers exploit different ideas, including (i) region homogeneity and feature invariance, (ii) asymmetric split-transform-merge, (iii) dilated convolution based multi-scale transformation, (iv) spatial and channel attention, and (v) residual learning. Multi-layer-perceptron is used as a meta-classifier to develop a robust and accurate classifier for providing the final decision. The performance of the proposed ensemble "DHE-Mit-Classifier" is evaluated against state-of-the-art CNNs. The performance evaluation on the test set suggests the superiority of the proposed ensemble with an F-score (0.77), recall (0.71), precision (0.83), and area under the precision-recall curve (0.80). The good generalisation of the proposed ensemble with a considerably high F-score and precision suggests its potential use in the development of an assistance tool for pathologists.

Deep convolutional neural network and emotional learning based breast cancer detection using digital mammography.

Breast cancer is one of the deadly diseases among women. However, the chances of death are highly reduced if it gets diagnosed and treated at its early stage. Mammography is one of the reliable methods used by the radiologist to detect breast cancer at its initial stage. Therefore, an automatic and secure breast cancer detection system that accurately detects abnormalities not only increases the radiologist's diagnostic confidence but also provides more objective evidence. In this work, an automatic Diverse Features based Breast Cancer Detection (DFeBCD) system is proposed to classify a mammogram as normal or abnormal. Four sets of distinct feature types are used. Among them, features based on taxonomic indexes, statistical measures and local binary patterns are static. The proposed DFeBCD dynamically extracts the fourth set of features from mammogram images using a highway-network based deep convolution neural network (CNN). Two classifiers, Support Vector Machine (SVM) and Emotional Learning inspired Ensemble Classifier (ELiEC), are trained on these distinct features using a standard IRMA mammogram dataset. The reliability of the system performance is ensured by applying 5-folds cross-validation. Through experiments, we have observed that the performance of the DFeBCD system on dynamically generated features through highway network-based CNN is better than that of all the three individual sets of ad-hoc features. Furthermore, the hybridization of all four types of features improves the system's performance by nearly 2-3%. The performance of both the classifiers is comparable using the individual sets of ad-hoc features. However, the ELiEC classifier's performance is better than SVM using both hybrid and dynamic features.

A multi-phase deep CNN based mitosis detection framework for breast cancer histopathological images.

The mitotic activity index is a key prognostic measure in tumour grading. Microscopy based detection of mitotic nuclei is a significant overhead and necessitates automation. This work proposes deep CNN based multi-phase mitosis detection framework "MP-MitDet" for mitotic nuclei identification in breast cancer histopathological images. The workflow constitutes: (1) label-refiner, (2) tissue-level mitotic region selection, (3) blob analysis, and (4) cell-level refinement. We developed an automatic label-refiner to represent weak labels with semi-sematic information for training of deep CNNs. A deep instance-based detection and segmentation model is used to explore probable mitotic regions on tissue patches. More probable regions are screened based on blob area and then analysed at cell-level by developing a custom CNN classifier "MitosRes-CNN" to filter false mitoses. The performance of the proposed "MitosRes-CNN" is compared with the state-of-the-art CNNs that are adapted to cell-level discrimination through cross-domain transfer learning and by adding task-specific layers. The performance of the proposed framework shows good discrimination ability in terms of F-score (0.75), recall (0.76), precision (0.71) and area under the precision-recall curve (0.78) on challenging TUPAC16 dataset. Promising results suggest good generalization of the proposed framework that can learn characteristic features from heterogenous mitotic nuclei.

Mitosis detection in breast cancer histopathology images using hybrid feature space.

Breast Cancer grading is a challenging task as regards image analysis, which is normally based on mitosis count rate. The mitotic count provides an estimate of aggressiveness of the tumor. The detection of mitosis is a challenging task because in a frame of slides at X40 magnification, there are hundreds of nuclei containing few mitotic nuclei. However, manual counting of mitosis by pathologists is a difficult and time intensive job, moreover conventional method rely mainly on the shape, color, and/or texture features as well as pathologist experience. The objective of this study is to accept the atypaia-2014 mitosis detection challenge, automate the process of mitosis detection and a proposal of a hybrid feature space that provides better discrimination of mitotic and non-mitotic nuclei by combining color features with morphological and texture features. To exploit color channels, they were first selected, and then normalized and cumulative histograms were computed in wavelet domain. A detailed analysis presented on these features in different color channels of respective color spaces using Random Forest (RF) and Support Vector Machine (SVM) classifiers. The proposed hybrid feature space when used with SVM classifier achieved a detection rate of 78.88% and F-measure of 72.07%. Our results, especially high detection rate, indicate that proposed hybrid feature space model contains discriminant information for mitotic nuclei, being therefore a very capable are for exploration to improve the quality of the diagnostic assistance in histopathology.

Cancer nanomedicine: focus on recent developments and self-assembled peptide nanocarriers.

The applications of nanoparticulate drug delivery have received abundant interest in the field of cancer diagnosis and treatment. By virtue of their unique features and design, nanomedicines have made remarkable progress in eliminating dreadful tumors. Research in cancer nanomedicine has spanned multitudes of drug delivery systems that possess high tumor targeting ability, sensitivity towards tumor microenvironments and improved efficacy. Various nanocarriers have been developed and approved for anti-tumor drug targeting. These nanocarriers, i.e., liposomes, micelles, nanotubes, dendrimers and peptides, offer a wide range of advantages, such as high selectivity, multi-functionality, specificity, biocompatibility and precise control of drug release. Nanomedicines based on self-assembled peptide carrier systems have been developed in recent years for cancer targeting. Self-assembled peptides have tremendous properties of forming targeted drug delivery vehicles such as nanohydrogels with unique features and functionality. In this review article, we discuss some developments in cancer nanomedicine. We present a diverse range of nanotargeted drug-delivery systems.

Synergism of cisplatin-oleanolic acid co-loaded calcium carbonate nanoparticles on hepatocellular carcinoma cells for enhanced apoptosis and reduced hepatotoxicity.

Background: Cisplatin (CDDP), a widely used chemotherapeutic agent against hepatocellular carcinoma (HCC), faces severe resistance and hepatotoxicity problems which can be alleviated through combination therapy. Purpose: The objective of this study was to develop a pH-dependent calcium carbonate nano-delivery system for the combination therapy of CDDP with oleanolic acid (OA). Methods: A microemulsion method was employed to generate lipid coated cisplatin/oleanolic acid calcium carbonate nanoparticles (CDDP/OA-LCC NPs), and the loading concentration of CDDP and OA was measured by atomic absorption spectroscopy and HPLC respectively.Transmission electron microscopy (TEM) was used to examine the nanoparticles morphology while its pH dependent release characteristics were investigated through in vitro release study. Cellular uptake was examined through a fluorescence microscopy. Apoptotic assays and western blot analysis were conducted to explore the synergistic apoptotic effect of OA on CDDP against HCC cells. The hepatoprotective of OA for CDDP was evaluated through H&E staining. Results: TEM analysis revealed nanoparticles spherical shape with an average particle size of 206±15 nm, and the overall entrapment efficiency was 63.70%±3.9%. In vitro drug release study confirmed the pH-dependent property of the formulation, with the maximum CDDP release of 70%±4.6% at pH 5.5, in contrast to 28%±4.1% CDDP release at pH 7.4. Annexin V-FITC/PI assay and cell cycle analysis confirmed that CDDP and OA synergistically promoted greater HepG2 cells apoptosis for the CDDP/OA-LCC NPs as compared to their individual free drug solutions and NPs-treated groups. Western blot analysis also proved that CDDP/OA-LCC NPs induced the apoptosis by enhancing the proapoptotic protein expressions through downregulating P13K/AKT/mTOR pathway and upregulating p53 proapoptotic pathway. OA helped CDDP to overcome the resistance by downregulating the expression of proteins like XIAP, Bcl-2 via NF-κB pathway. OA also significantly alleviated CDDP-induced hepatotoxicity as evident from the decreased alanine transaminase, aspartate transaminase levels and histochemical evaluation. The possible mechanism may be related to the Nrf-2 induction via its antioxidant mechanism to maintain the redox balance and reduction in CYP2E1 activity which can lead to ROS-mediated oxidative stress. Conclusion: These results suggest that CDDP/OA-LCC NPs have promising applications for co-delivering CDDP and OA to synergize their anti-tumor activity against HCC and to utilize OA's protective effect against CDDP-induced hepatotoxicity.

Paclitaxel-loaded pH responsive hydrogel based on self-assembled peptides for tumor targeting.

Intratumoral delivery of chemotherapeutic agents may permit the localization of drugs in tumors, decrease nonspecific targeting and increase efficacy. The pH-responsive peptide hydrogel is considered a suitable carrier for chemotherapeutics via intratumoral injection. Thus, a study was carried out to develop a paclitaxel (PTX) drug delivery system using a pH-responsive FER-8 peptide hydrogel for tumor targeting. The pH-sensitive hydrogel system was characterized for loading capacity, acid sensitivity, structure, rheology, morphology, drug release, in vitro cytotoxicity and in vivo efficacy in H22 tumor-bearing mice. The stable FER-8 peptide hydrogel with high drug-loading capacity was formed at pH 7.4 by the self-assembly of peptide, whereas higher degradation was observed at an acidic pH. Circular dichroism and rheology confirmed the suitable meshwork structure and enhanced mechanical properties of the hydrogel. The FER-8 peptide hydrogel fibers were found to have an average size less than 500 nm at pH 7.4, which was confirmed by TEM and DLS analysis. Sustained release of PTX at pH 5.5 was observed for the FER-8 peptide hydrogel (HG-PTX) for almost 1 week. In vitro cytotoxicity studies indicated that the FER-8 peptide hydrogel increased the drug accumulation in HepG2 cells and effectively inhibited the growth of HepG2 tumor cells compared with free drugs. Furthermore, in vivo studies using H22-bearing mice indicated that the paclitaxel-loaded FER-8 peptide hydrogel significantly increased the amount of drugs in tumor tissues and showed prolonged retention (96 hours) at the tumor site by intratumoral injection. The in vivo anti-tumor studies confirmed the pH-sensitive properties of HG-PTX, which allowed the drug to be triggered by the acidic pH environment at tumor sites, provided sustained delivery of the drug and enhanced tumor inhibition. In conclusion, HG-PTX provides an attractive strategy and potential vehicle for efficient anti-cancer drug delivery. The carrier can enhance tumor targeting, prolong retention, reduce systemic side effects and increase the accumulation of drugs at the tumor site.

Transfer learning based deep CNN for segmentation and detection of mitoses in breast cancer histopathological images.

Segmentation and detection of mitotic nuclei is a challenging task. To address this problem, a Transfer Learning based fast and accurate system is proposed. To give the classifier a balanced dataset, this work exploits the concept of Transfer Learning by first using a pre-trained convolutional neural network (CNN) for segmentation, and then another Hybrid-CNN (with Weights Transfer and custom layers) for classification of mitoses. First, mitotic nuclei are automatically annotated, based on the ground truth centroids. The segmentation module then segments mitotic nuclei and also produces some false positives. Finally, the detection module is trained on the patches from the segmentation module and performs the final detection. Fine-tuning based Transfer Learning reduced training time, provided good initial weights, and improved the detection rate with F-measure of 0.713 and 76% area under the precision-recall curve for the challenging task of mitosis detection.

Reverse vaccinology and subtractive genomics-based putative vaccine targets identification for Burkholderia pseudomallei Bp1651.

The Burkholderia pseudomallei is a unique bio-threat and causative agent of melioidosis. The B. pseudomallei Bp1651 strain has been isolated from a chronic cystic fibrosis patient. The genome-level DNA sequences information of this strain has recently been published. Unfortunately, there is no commercial vaccine available till date to combat B. pseudomallei infection. The genome-wide prioritization approaches are widely used for the identification of potential therapeutic candidates against pathogens. In the present study, we utilized the recently available annotated genomic information of B. pseudomallei Bp1651 through subtractive genomics and reverse-vaccinology strategies to identify its potential vaccine targets. The analyses identified more than 60 pathogen-specific, human host non-homologous proteins that may prioritize in future studies to investigate therapeutic targets for B. pseudomallei Bp1651. The potential B and T-cells antigenic determinant peptides from these pathogen-specific proteins were cataloged using antigenicity and epitope prediction tools. The analyses unveiled a promising antigenic peptide "FQWEFSLSV" from protein-export membrane protein (SecF) of Bp1651 strain, which was predicted to interact with multiple class I and class II MHC alleles with IC50 value < 100 nM. The molecular docking analysis verified favorable molecular interaction of this lead antigenic peptide with the ligand-binding pocket residues of HLA A*02:06 human host immune cell surface receptor. This peptide is predicted to be a suitable epitope capable to elicit the cell-mediated immune response against the B. pseudomallei pathogen. The putative epitopes and proteins identified in this study may be promising vaccine targets against Bp1651 as well as other pathogenic strains of B. pseudomallei.

Two-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detection.

Different types of breast cancer are affecting lives of women across the world. Common types include Ductal carcinoma in situ (DCIS), Invasive ductal carcinoma (IDC), Tubular carcinoma, Medullary carcinoma, and Invasive lobular carcinoma (ILC). While detecting cancer, one important factor is mitotic count - showing how rapidly the cells are dividing. But the class imbalance problem, due to the small number of mitotic nuclei in comparison to the overwhelming number of non-mitotic nuclei, affects the performance of classification models. This work presents a two-phase model to mitigate the class biasness issue while classifying mitotic and non-mitotic nuclei in breast cancer histopathology images through a deep convolutional neural network (CNN). First, nuclei are segmented out using blue ratio and global binary thresholding. In Phase-1 a CNN is then trained on the segmented out 80×80 pixel patches based on a standard dataset. Hard non-mitotic examples are identified and augmented; mitotic examples are oversampled by rotation and flipping; whereas non-mitotic examples are undersampled by blue ratio histogram based k-means clustering. Based on this information from Phase-1, the dataset is modified for Phase-2 in order to reduce the effects of class imbalance. The proposed CNN architecture and data balancing technique yielded an F-measure of 0.79, and outperformed all the methods relying on specific handcrafted features, as well as those using a combination of handcrafted and CNN-generated features.

The in silico identification of small molecules for protein-protein interaction inhibition in AKAP-Lbc-RhoA signaling complex.

The rational design of small molecules that mimic key residues at the interface of interacting proteins can be a successful approach to target certain biological signaling cascades causing pathophysiological outcome. The A-Kinase Anchoring Protein, i.e. AKAP-Lbc, catalyses nucleotide exchange on RhoA and is involved in cardiac repolarization. The oncogenic AKAP-Lbc induces the RhoA GTPase hyperactivity and aberrantly amplifies the signaling pathway leading to hypertrophic cardiomyocytes. We took advantage of the AKAP-Lbc-RhoA complex crystal structure to design in silico small molecules predicted to inhibit the associated pathological signaling cascade. We adopted the strategies of pharmacophore building, virtual screening and molecular docking to identify the small molecules capable to target AKAP-Lbc and RhoA interactions. The pharmacophore model based virtual screening unveils two lead compounds from the TIMBAL database of small molecules modulating the targeted protein-protein interactions. The molecular docking analysis revealed the lead compounds' potentialities to establish the essential chemical interactions with the key interactive residues of the complex. These features provided a road map for designing additional potent chemical derivatives and fragments of the original lead compounds to perturb the AKAP-Lbc and RhoA interactions. Experimental validations may elucidate the therapeutic potential of these lead chemical scaffolds to deal with aberrant AKAP-Lbc signaling based cardiac hypertrophy.