Innovative Artificial-Intelligence- Based Approach for the Biodegradation of Feather Keratin by Bacillus paramycoides, and Cytotoxicity of the Resulting Amino Acids

Abstract

The current study reported a new keratinolytic bacterium, which was characterized as Bacillus paramycoides and identified by 16S rRNA, and the sequence was then deposited in the GenBank (MW876249). The bacterium was able to degrade the insoluble chicken feather keratin (CFK) into amino acids (AA) through the keratinase system. The statistical optimization of the biodegradation process into AA was performed based on the Plackett–Burman design and rotatable central composite design (RCCD) on a simple solid-state fermentation medium. The optimum conditions were temperature, 37°C, 0.547 mg KH2PO4, 1.438 mg NH4Cl, and 11.61 days of incubation. Innovatively, the degradation of the CFK process was modeled using the artificial neural network (ANN), which was better than RCCD in modeling the biodegradation process. Differentiation of the AA by high-performance liquid chromatography (HPLC) revealed the presence of 14 AA including essential and non-essential ones; proline and aspartic acids were the most dominant. The toxicity test of AA on the HepG2 cell line did not show any negative effect either on the cell line or on the morphological alteration. B. paramycoides ZW-5 is a new eco-friendly tool for CFK degradation that could be optimized by ANN. However, additional nutritional trials are encouraged on animal models.

Innovative biosynthesis, artificial intelligence-based optimization, and characterization of chitosan nanoparticles by Streptomyces microflavus and their inhibitory potential against Pectobacterium carotovorum

“…The ANN platform employs an algorithm for machine learning that predicts response variables utilizing a supple function. The activation function helps the ANN learn weights and maps the complex nonlinear relationship, even if there is no apparent relation between input(s) and output(s) variables, that is why ANN can predict and fit data very well by modeling different response surfaces using the suitable architecture, and capable of learning any nonlinear function in flexibility and accuracy way 20 , 21 , 69 .…”

Innovative binary sorption of Cobalt(II) and methylene blue by Sargassum latifolium using Taguchi and hybrid artificial neural network paradigms

“…The ANN approach of artificial intelligence has found its way into the optimization of biological processes and has emerged as an alternative genius tool for non-linear multivariate modeling 6 , 40 , 41 . The prettiness of ANNs as empirical modeling is owing to their capability to accurately extract trends between input and output variables, regardless of the degree of nonlinearity 56 .…”

“…The prettiness of ANNs as empirical modeling is owing to their capability to accurately extract trends between input and output variables, regardless of the degree of nonlinearity 56 . ANN has the aptitude to acquire knowledge from data, without a previous description of the suitable fitting function, and ANN has entire estimate capability i.e., guessing almost all sorts of non-linear functions including quadratic ones 40 , 41 . Generally, the ANN required a much greater number of experimental trials to assemble an efficient model.…”

“…Such a network starts learning and training processes until understands the data pattern. Finally, validation and verification of the resulting ANN model take place before approving the predictive model 40 , 41 . The learning mechanism of ANN is based on diagnosing the diverse designs in the data to detect any differences and decide which pattern achieves the target, this process is controlled through intelligent backpropagation that generates the desired model that attains the goal.…”

Seed Endophytic Achromobacter sp. F23KW as a Promising Growth Promoter and Biocontrol of Rhizoctonia Root Rot of Fenugreek

“…strain F23KW, which is included in the genus Achromobacter , under the family Alcaligenaceae in the order Burkholderiales [ 24 ]. Molecular identification is usually performed because of its sensitivity and specificity for the rapid identification of various organisms [ 36 ]. The sequence used for constructing the phylogeny is, totally, interpreted and firmly correlated with the other similar bacterial strains in the GeneBank database.…”