In analytical science, data extraction from complex or extensive datasets can be a laborious task that takes a long time to complete. Machine learning (ML) offers a pioneering opportunity to rapidly extract information from chromatography, spectroscopy, and mass spectrometry datasets, among others. Over the past few years, new approaches have been developed for the rapid processing of Raman spectra using ML. This review will discuss different applications of ML techniques employed in Raman.

Nitrogen (N) is one of the most important nutrients for plant growth and is therefore largely
applied in agricultural systems through fertilization. However, nitrification leads to nitrate
leaching and the production of gaseous nitrous oxide, which can result in a loss of up to 50% of
nitrogen availability to the plant.
There are different strategies to prevent nitrification, such as the use of synthetic nitrification
inhibitors (SNI), biological nitrification inhibitors (BNI), controlled slow-release fertilizers and
keeping plants in continuous growth to assimilate nitrogen. However, when making a decision on
which methodology to use to manage fertilization, the advantages and disadvantages of each must
be known in order to achieve efficient nitrogen use (NUE). This mini-review will show some
strategies used in agriculture.

Computers can analyze information faster than people but cannot make decisions. Computers of today are acquiring machine learning techniques to enhance analysis and prediction. These techniques enable expert assistance systems and enhance computer decision-making. Machine learning algorithms are assisting medical professionals in making rapid diagnoses thanks to their successful classification and diagnostic capabilities. Machine learning may be effective and is used more frequently in cancer diagnosis. The second most common disease in the world and the main reason for death among women is breast cancer. Like other malignancies, early identification of breast cancer lowers mortality. Machine learning techniques assist in diagnosing breast cancer, which calls for specialized human knowledge. With machine learning, computers can swiftly identify patterns in complex and large data sets. Due to these qualities, machine learning is frequently used to detect breast cancer.

Yarrowia lipolytica is a saccharomycetous oleaginous yeast with a long history of industrial use. Thanks to the increasingly advanced knowledge of its metabolic pathways, this yeast has had a great opening in the market, giving way to great business opportunities, becoming a great cellular factory.
Y. lipolytica meets all the requirements for the economic viability of a microbial bioprocess. Therefore, different companies such as Biocatalysts Ltd, Mayoly, DSM, Microbia Inc among others, have found a great potential to use it to produce different products such as citric acid, carotenoids and proteins, moving large millions of euros.
More and more companies are betting on the research and biotechnological application of Y. lipolytica thanks to its unique metabolic, genetic and physiological characteristics

The popular use of medicinal plants in healthcare practices among indigenous communities provides the basis for natural drug discovery development. The present research aimed to document detailed ethnoveterinary knowledge of medicinal plants used for medicinal purposes. The field study was carried out from January 2016 to December 2020 in Zemmour and Zayane tribes (Middle Atlas). In total, 300 local informants were interviewed using open-ended and semi-structured interviews. The benefits, coverage, and importance of ethnoveterinary were expressed through several quantitative indices, including Informant Consensus Factor (FIC), Fidelity Level (FL), Relative Popularity Level (RPL), Rank Order Priority (ROP), and Jaccard Index (JI). A total of 150 plant species belonging to 129 genera and 56 families were found to be used in ethnoveterinary practices. The most commonly used ethnoveterinary plant species in the study areas was Allium sativum L. (16.7%). Leaves were found to be the most frequent plant part used (46.5%). The highest FIC value was 0.9 for digestive disorders. Artemisia herba-alba Asso and Asparagus officinalis L. show a 100% fidelity level for diarrhea and rabies, respectively. Rank Order Priority (ROP) results showed that Eucalyptus globulus Labill. (ROP=74), was the most preferred species for the treatment of fever. The present study showed that local communities in the Middle Atlas consistently know ethnoveterinary plants. We invite the attention of chemists and pharmacologists for further phytochemical and pharmacological investigations of medicinal plants having high ROP, FL, and FIC values in this study.

To avoid traffic accidents, parked and abandoned objects must be detected quickly and precisely. Most detection techniques employ 2D image attributes like the area of different target types and properly generate the background model. Background influences these algorithms, and target kinds are inaccurate. Thus, this study provides a parked and abandoned item recognition technique that employs accurate 3D target information to discriminate target types. First, state evolution detects anomalous areas. Second, it tracks the initial anomalous area two-way and utilizes the eight-neighborhood seed-filling technique to partition the parked and abandoned item area. Finally, it distinguishes parked from abandoned objects using three ways. The first technique calculates the relative height between feature sites by comparing their projection velocities. Then, the height distinguishes parking from abandoned objects. The second technique uses 3D model appropriateness to differentiate parked and abandoned objects. The third approach calculates the inverse projection map by setting the reverse projection planes at different heights in the area. Then, the inverse projection maps' heights establish the goal length, breadth, and height, distinguishing parked and abandoned objects. Tunnels, highways, urban expressways, and country roadways tested the algorithm. The system successfully detects parked and abandoned objects with a low miss and false detection rates. It was also real-time.

Plant viruses are infective particles, considered obligate intracellular parasites. They are generally composed of single-stranded positive ribonucleic acid (RNA) and only in a few cases of single or double-stranded deoxyribonucleic acid (DNA). These are introduced into the plant cell through wounds caused by physical damage due to the environment or by the action of vectors, among the vectors are several species of insects, mites, nematodes and certain fungi, The interaction between viruses and plants adversely affects the morphology and physiology of the host, causing diseases.
It has been estimated that plant viruses can cause an annual loss of up to 50 billion euros worldwide, a situation that may be worsened by recent climate change events and associated changes in disease epidemiology. The lack of curative measures for virus infections has prompted the use of risk reduction measures, which have included exclusion, avoidance, and eradication techniques, along with vector management practices. Also, the advent of next-generation sequencing technologies has great potential for detecting unknown viruses.

In recent years, the use of cannabidiol (CBD) for medicinal purposes has gained increasing attention due to its potential health benefits. Even so, the long-term effects are not fully understood, therefore, it is important to continue studying the risks, the potential benefits and also the optimal way to apply it in the medicinal area. In this review, the potential therapeutic uses and the extraction methods of CBD will be discussed.

The quality indicators of medicinal products, which ensure their effectiveness and safety, are established in the registration documentation and Pharmacopoeia. At the same time, the quality of medicinal products is established at the stage of pharmaceutical development, for which a general methodological approach and special approaches are defined in relation to different dosage forms, generic drugs, original drugs, etc. Considering the fact that there is no monograph on ramipril tablets in the European Pharmacopoeia of the 11th edition, but only on the ramipril substance, we drew attention to the need to develop an analytical method for determining related substances in ramipril tablets. It is clear that the approaches described in the development of the technique in the substance are unsuitable for the analysis of tablets. Therefore, the aim of our work was the development of HPLC method for the determination of related substances in ramipril tablets.

Material and methods. Analytical equipment: Agilent 1200 liquid chromatograph, 4.6x150 mm chromatographic column filled with octadecylsilyl silica gel for chromatography with a particle size of 3 μm (for example, Inertsil ODS-3). Chromatography was carried out in the mode of gradient elution. Mobile phase A - solution of 0.2 g/L of sodium hexanesulfonate R, the pH of which is adjusted to 2.7 with phosphoric acid; Mobile phase B - Acetonitrile.

Results and discussion. To separate the components of the model mixture, sodium hexanesulfonate was used, the pH of which was adjusted to 2.7 with phosphoric acid, and an organic modifier - acetonitrile in a gradient elution mode, a flow rate of 1.5 mL/min, and a detection wavelength at 210 nm. The retention time of impurity A, ramipril, impurity B, impurity C, impurity D was 13.2, 13.8, 14.5, 15.1, 19.4 min, respectively. Rationing at the time of release: impurities A, B, C: no more than 0.5% of each; amount of impurities D and E: no more than 0.5%; any impurity: no more than 0.2%; amount of impurities: no more than 1.0%. Rationing during the shelf life: impurities A, B, C: no more than 0.5% of each; amount of impurities D and E: no more than 5.0%; any impurity: no more than 0.5%; amount of impurities: no more than 5.0%. To confirm the efficiency of the method, the following parameters were studied specificity, linearity, acсuracy and precision, limit of detection and limit of quantification.

Conclusions. Data on the influence of components interfering with the analysis were not found. The method is linear in the range of application. The acсuracy and precision of the method are sufficient. The method provides the necessary level of detection of related substances. The limit of detection of unidentified impurities is 0.03%. To calculate the content of impurity C, a conversion factor of 2.5 must be used. The modified technique meets the established requirements and can be used for quality control of the drugs "Ramipril, tablets 2.5 mg", "Ramipril, tablets 5 mg", "Ramipril, tablets 10 mg" according to the quality indicator "Related substances".

The pharmaceutical industry is experiencing significant changes and is adopting new technologies at a faster rate than before. The application of 4.0 technologies increases the productivity and effectiveness of automated pharmacy processes, therefore, these technologies are driving the industry's growth. These include artificial intelligence (AI), Machine learning (ML), Internet of Thing (IoT), Big data, and other Industry 4.0 technologies. This review will discuss the use of AI and ML in the pharmaceutical industry. Moreover, some pharmaceutical startups that implemented these technologies will be presented.