The present study investigated developing biological control agents against plant pathogens as an alternative to pesticides. The plant growth-promoting (PGP) and biocontrol potential of bacteria from the Bacillus genus is due to their ability to produce proteolytic and amylolytic enzymes, assist in the solubilization of phosphorus and zinc, and the production of siderophores. Cell culture and cell-free supernatant were used to investigate the antimicrobial activity of different Bacillus strains against the phytopathogenic fungus Fusarium graminearum in vitro. Fusarium graminearum is a fungus that causes plant disease, particularly in cereals like wheat and barley. As a result, significant suppression of the growth and development of this plant pathogen was observed. Plant growth-promoting activity manifested when the bacteria were applied alone and in combination. A single strain and combinations of two, three, and four strains of Bacillus were tested for their antimicrobial effects against Fusarium graminearum. The fluorescence spectroscopy results proved that the combination of Bacillus subtilis, Bacillus circulans, Bacillus megaterium, and Bacillus licheniformis showed the best stimulation of development, expressed as a comparative evaluation of the yield compared to the untreated control variant. The four strains showed their potential application as a biocontrol agent against Fusarium graminearum. The four Bacillus strains also can promote plant growth by affecting nutrition, root structure, and plant health, and they have the capacity to dissolve phosphates and zinc.

Artificial-intelligence-based analysis methods can provide objective and accurate results. This study aimed to evaluate the performance of machine learning algorithms to classify yeast-inoculated and uninoculated tomato samples using fluorescent spectroscopic data. For this purpose, three different tomato types were used: ‘local dwarf’, ‘Picador’, and ‘Ideal’. Discrimination analysis was applied with six different machine learning (ML) algorithms. Confusion matrices, average accuracies, F-Measure, Precision, ROC (receiver operating characteristic) Area, MCC (Matthews Correlation Coefficient), and precision-recall area values obtained as a result of the application of different ML algorithms were compared. Based on the fluorescence spectroscopic data, the application of six ML algorithms showed that the first two tomato types were classified with 100% accuracy and the last type was classified with 95% accuracy. The results of the study show that the fluorescence spectroscopy data are strongly representative of tomato species. ML methods fed with these data provide high-performance discrimination.

Camelina (Camelina sativa (L.) Crantz) is a valuable source of essential amino acids, especially sulphur-containing ones, which are generally lacking in leguminous crops, thus representing an alternative source of protein for both humans and farm animals. Rhizosphere soil samples from five experimental plots with mono- and mixed cultivations of three camelina cultivars, including two introduced varieties Cs1.Pro (Luna) and Cs2.Pro (Lenka) and one Bulgarian variety Cs3.Pro (local Bulgarian landrace) with variety 666 of vetch (Vicia sativa L.) (Cs3-Vs.Pro) and variety Mir of pea (Pisum sativum L.) (Cs3-Ps.Pro), were collected and analysed. The total DNA was isolated from the rhizosphere soils and the presence of the 16S rRNA gene was confirmed by amplification with the universal primer 16SV34. In the present study, the structure of the soil bacterial community in five different plots (Cs1.S.Pro, Cs2.S.Pro, Cs3.S.Pro, Cs3.Vs.S.Pro, and Cs3.Ps.S.Pro) where camelina was grown alone and by being intercropped with pea and vetch was analysed via a metagenomic approach. The number of observed species was highest in the local genotype of the camelina Cs3 grown alone, followed by soil from the intercropped variants Cs3-Vs and CsS-Ps. The soil bacterial communities differed between the sole cultivation of camelina and that grown with joint cultivation with vetch and peas, indicating that legumes considerably affected the growth and development of beneficial microorganisms by aspects such as nitrogen fixing, levels of nitrifying bacteria, and levels of phosphorus-dissolving bacteria, thus helping to provide better plant nutrition. The α-diversity indicated that bacterial communities in the rhizosphere were higher in soils intercropped with vetch and pea. The optical properties of cereals and legumes were determined by their energy structure, which includes both their occupied and free electronic energy levels and the energy levels of the atomic vibrations of the molecules or the crystal lattice.

The objective of this study was to distinguish leek seeds belonging to the Starozagorski kamush variety and two breeding lines based on the selected fluorescence spectroscopic data. The classification models were developed for three classes of Starozagorski kamush vs. breeding line 4 vs. breeding line 39 and pairs of classes of Starozagorski kamush vs. breeding line 4, Starozagorski kamush vs. breeding line 39, and breeding line 4 vs. breeding line 39. The traditional machine learning algorithms, such as PART, Logistic, Naive Bayes, Random Forest, IBk, and Filtered Classifier were applied. All three classes were distinguished with an average accuracy of up to 93.33% for models built using IBk and Filtered Classifier. In the case of each model, Starozagorski kamush variety was completely different (accuracy of 100%, precision, and F-measure, MCC (Matthews correlation coefficient), and ROC (receiver operating characteristic) area of 1.000) from breeding lines, and the mixing of cases was observed between breeding line 4 and breeding line 39. The models built for pairs of leek seed classes distinguished Starozagorski kamush and breeding line 4 with an average accuracy reaching 100% (Logistic, Naive Bayes, Random Forest, IBk). The classification accuracy of Starozagorski kamush and breeding line 39 also reached 100% (Logistic, Naive Bayes, Random Forest, IBk), whereas breeding line 4 and breeding line 39 were classified with an average accuracy of up to 80% (Logistic, Naive Bayes, Random Forest, Filtered Classifier). The proposed approach combining fluorescence spectroscopy and machine learning may be used in practice to distinguish leek seed varieties and breeding lines.