Multi-objective deep learning framework for COVID-19 dataset problems.

Background: It has been reported that a deadly virus known as COVID-19 has arisen in China and has spread rapidly throughout the country. The globe was shattered, and a large number of people on the planet died. It quickly became an epidemic due to the absence of apparent symptoms and causes for patients, confusion appears due to the lack of sufficient laboratory results, and its intelligent algorithms were used to make decisions on clinical outcomes. Methods: This study developed a new framework for medical datasets with high missing values based on deep-learning optimization models. The robustness of our model is achieved by combining: Data Missing Care (DMC) Framework to overcome the problem of high missing data in medical datasets, and Grid-Search optimization used to develop an improved deep predictive training model for patients with COVID-19 by setting multiple hyperparameters and tuning assessments on three deep learning algorithms: ANN (Artificial Neural Network), CNN (Convolutional Neural Network), and Recurrent Neural Networks (RNN). Results: The experiment results conducted on three medical datasets showed the effectiveness of our hybrid approach and an improvement in accuracy and efficiency since all the evaluation metrics were close to ideal for all deep learning classifiers. We got the best evaluation in terms of accuracy 98%, precession 98.5%, F1-score 98.6%, and ROC Curve (95% to 99%) for the COVID-19 dataset provided by GitHub. The second dataset is also Covid-19 provided by Albert Einstein Hospital with high missing data after applying our approach the accuracy reached more than 91%. Third dataset for Cervical Cancer provided by Kaggle all the evaluation metrics reached more than 95%. Conclusions: The proposed formula for processing this type of data can replace the traditional formats in optimization while providing high accuracy and less time to classify patients. Whereas, the experimental results of our approach, supported by comprehensive statistical analysis, can improve the overall evaluation performance of the problem of classifying medical data sets with high missing values. Therefore, this approach can be used in many areas such as energy management, environment, and medicine.

Using Fomitopsis pinicola for bioinspired synthesis of titanium dioxide and silver nanoparticles, targeting biomedical applications.

The current study proposes a bio-directed approach for the formation of titanium oxide and silver nanoparticles (TiO2 and Ag NPs), using a wild mushroom, Fomitopsis pinicola, identified by 18S ribosomal RNA gene sequencing (gene accession no. MK635350) and phenotypic examination. NP synthesis was confirmed by X-ray diffraction (XRD), Fourier transform infrared spectroscopy (FT-IR), diffuse reflectance UV-visible spectroscopy (DR-UV), and scanning and transmission electron microscopy (SEM/TEM). Furthermore, the impact of NPs on Escherichia coli and Staphylococcus aureus and a human colon cancer cell line (HCT) were evaluated by MIC/MBC and MTT assays, respectively, along with structural morphogenesis by different microscopy methods. The results obtained showed that TiO2 and Ag NPs were found to be significantly active, however, slightly enhanced antibacterial and anticancer action was seen with Ag NPs (10-30 nm). Such NPs can be utilized to control and treat infectious diseases and colon cancer and therefore have potential in a range of biomedical applications.

Synthesis of magnetic iron oxide nanoparticles using pulp and seed aqueous extract of Citrullus colocynth and evaluation of their antimicrobial activity.

OBJECTIVES: Citrullus colocynth (CTC) is a wild medicinal plant with proven antimicrobial activity. The aim of this study is to investigate the use of its aqueous extract in producing magnetic iron oxide nanoparticles (MNPs) with improved antimicrobial activity. The cold and hot aqueous extract of seed and pulp parts of CTC, respectively, were used to produce MNPs. The particles were characterized by transmission electron microscope, energy dispersion x-ray, FTIR and their surface charge were measured. The antimicrobial activity of the produced particles was assessed against two Gram positive (Bacillus subtillis and Staphylococcus aureus) and two Gram negative (Escherichia coli and Pseudomonas aeruginosa) bacteria and well as against Candida albicans. RESULTS: MNPs synthesized using cold seed extract (S-MNP) and pulp extract (P-MNP) were spherical in shape. The size distribution was more uniform in the S-MNP (6-15 nm) compared to the P-MNP (12-45 nm). Both particles showed comparable anti-microbial potential against the tested microorganisms. At a concentration range of 0.48-1000 µg/mL, S-MNP inhibited bacterial growth by 16.0-99.0% and 10.0-91.0%; while P-MNP inhibition was 11.0-100.0% and 11.0-99.0% for Gram positive and negative bacteria; respectively. Candida albicans was the least affected microorganism with maximum inhibition of 63-88% after treatment with S-MNP and P-MNP (1 mg/mL), respectively. CONCLUSIONS: The aqueous extract of CTC can be used for synthesis of MNPs with antimicrobial activity. The described procedures are simple and can be modified for large scale green synthesis of MNPs.

Evaluation of Polyphenolic Compounds and Pharmacological Activities in Hairy Root Cultures of Ligularia fischeri Turcz. f. spiciformis (Nakai).

A considerable amount of bioactive compounds have been used for the biopharmaceutical engineering to help human health and nutrition. Hairy root culture (HRC) or transgenic root is a favourable alternative technique for phytochemical production. Ligularia fischeri is a significant source of pharmaceutically important active compounds with an enormous range of health care applications. HRC of L. fischeri was developed using Agrobacterium rhizogenes for the production of polyphenolic compounds with antioxidant, antimicrobial, antidiabetic, anticancer and anti-inflammatory pharmaceutical activities. Hairy roots (HRs) were selected by morphological assessment, genetic and molecular analyses. The maximum accumulation of fresh mass (94.15 g/L) and dry mass (9.45 g/L) was recorded in MS liquid medium supplemented with 30 g/L sucrose at 28 days. Furthermore, HRs successfully produced numerous polyphenolic compounds, including six hydroxycinnamic acids, seven flavonols, seven hydroxybenzoic acids, vanillin, resveratrol, pyrogallol, homogentisic, and veratric acids, which were identified by UHPLC analysis. HRs produced higher total phenolic (185.65 mg/g), and flavonoid (5.25 mg/g) contents than non-transformed roots (125.55 mg/g and 3.75 mg/g). As a result of these metabolic changes, pharmaceutical activities were found higher in HRs than non-transformed roots (NTRs). The present study indicates that HRC has the potential to increase the content of beneficial polyphenolic compounds with higher potential pharmaceutical activities. To the best of our knowledge, the present study is the first report on enhancing the production of polyphenolic compounds with pharmaceutical activities from the HRCs of L. fischeri.