Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques.

BACKGROUND: Antimicrobial peptides are promising tools to fight against ever-growing antibiotic resistance. However, despite many advantages, their toxicity to mammalian cells is a critical obstacle in clinical application and needs to be addressed. RESULTS: In this study, by using an up-to-date dataset, a machine learning model has been trained successfully to predict the toxicity of antimicrobial peptides. The comprehensive set of features of both physico-chemical and linguistic-based with local and global essences have undergone feature selection to identify key properties behind toxicity of antimicrobial peptides. After feature selection, the hybrid model showed the best performance with a recall of 0. 876 and a F1 score of 0. 849. CONCLUSIONS: The obtained model can be useful in extracting AMPs with low toxicity from AMP libraries in clinical applications. On the other hand, several properties with local nature including positions of strand forming and hydrophobic residues in final selected features show that these properties are critical definer of peptide properties and should be considered in developing models for activity prediction of peptides. The executable code is available at https://git.io/JRZaT .

Study on the Interaction of the CpG Alternating DNA with CdTe Quantum Dots.

A novel sensitive method for detection of DNA methylation was developed with thioglycollic acid (TGA)-capped CdTe quantum dots (QDs) as fluorescence probes. Recognition of methylated DNA sites would be useful strategy due to the important roles of methylation in disease occurrence and developmental processes. DNA methylation occurs most often at cytosine-guanine sites (CpG dinucleotides) of gene promoters. The QDs significantly interacted with hybridized unmethylated and methylated DNA. The interaction of CpG rich methylated and unmethylated DNA hybrid with quantum dots as an optical probe has been investigated by fluorescence spectroscopy and electrophoresis assay. The fluorescence intensity of QDs was highly dependent to unmethylated and methylated DNA. Specific site of CpG islands of Adenomatous polyposis coli (APC), a well-studied tumor suppressor gene, was used as the detection target. Under optimum conditions, upon the addition of unmethylated dsDNA, the fluorescence intensity increased in linear range from 1.0 × 10- 10 to 1.0 × 10- 6M with detection limit of 6.2 × 10- 11 M and on the other hand, the intensity of QDs showed no changes with addition of methylated dsDNA. We also demonstrated that the unmethylated and methylated DNA and QDs complexes showed different mobility in electrophoresis assay. This easy and reliable method could distinguish between methylated and unmethylated DNA sequences.

FRET-based aptamer biosensor for selective and sensitive detection of aflatoxin B1 in peanut and rice.

Aflatoxins are potential food pollutants produced by fungi. Among them, Aflatoxin B1 (AFB1) is the most toxic. Therefore, a great deal of concern is associated with AFB1 toxicity. In this work, utilizing a FRET-based method, we have developed a nanobiosensor for detection of AFB1 in agricultural foods. Aptamer-conjugated Quantum dots (QDs) are adsorbed to Au nanoparticles (AuNPs) due to interaction of aptamers with AuNPs leading to quenching effect on QDs fluorescence. Upon the addition of AFB1, the specific aptamers are attracted to AFB1, getting distance from AuNPs which result in fluorescence recovery. Under optimized conditions the detection limit of proposed nanobiosensor was 3.4nM with linear range of 10-400nM. Selectivity test demonstrates that the nanobiosensor could be a promising tool for specific evaluation of food stuff. This method was successfully applied for the analysis of AFB1 in rice and peanut samples.

Aptamer-based Colorimetric and Chemiluminescence Detection of Aflatoxin B1 in Foods Samples.

We developed a new biosensor for the detection of aflatoxin B1(AFB1) based on the interaction of gold nanoparticles (AuNPs) with the aptamer. Aggregation of AuNPs was induced by desorption of the AFB1 binding aptamer from the surface of AuNPs as a result of the aptamer target interaction leading to the color change of AuNPs from red to purple. The linear range of the colorimetric aptasensor covered a large variation of AFB1 concentrations from 80 to 270 nM and the detection limit of 7 nM was obtained. Also, the catalytic activity of the aggregated AuNPs greatly enhanced the chemiluminescence (CL) reaction, where the detection limit was determined at 0.5 nM with a regression coefficient of R(2) = 0.9921. We have also shown that the sensitivity of detection was increased by employing CL and using the catalytic activity of aggregated AuNPs, during luminol-hydrogen peroxide reaction. Therefore the proposed nanobiosensor was demonstrated to be sensitive, selective, and simple, introducing a viable alternative for rapid screening of toxin in foods.

Selective recognition of Glutamate based on fluorescence enhancement of graphene quantum dot.

Graphene quantum dots (GQDs) have successfully been utilized as an efficient nano-sized fluorescence chemosensor to detect selectively Glutamate (Glu) in Tris-HCl buffer solution (pH=9). The fluorescence emission spectrum of graphene quantum dots was at about 430nm. The study showed that fluorescence intensity of the quantum dot gradually enhanced with increase in concentration of Glutamate and any change in fluorescence intensity was directly proportional to the concentration of Glutamate. Under optimum conditions, the linear range for the detection of Glutamate was 1.6×10(-7)M to 1.0×10(-5)M with a detection limit of 5.2×10(-8)M. The sensor showed high selectivity toward Glutamate in comparison with other amino acids.