Journal of Molecular and Pharmaceutical Sciences


The Journal of Molecular and Pharmaceutical Sciences (JMPS) is the official journal of the Pharmaceutical Sciences Research Center (CRSP) –Constantine, Algeria. The Journal is devoted to the publication of scientific research papers in all branches of pharmaceutical sciences.







COVID-19 Diagnosis Empowered with Deep Semi-Supervised Learning Techniques Using X-Ray and CT Images: A Systematic Review

باهي مريم, 

Résumé: Abstract. Background: The early detection and diagnosis of COVID-19 and the accurate separation of non-COVID-19 cases in a quick and cheap manner are among the main challenges in the COVID- 19 pandemic to ensure recovery treatment for patients which will help to save patient’s lives. Deep learning techniques proved themselves to be a novel prediagnostic detection methodology of COVID- 19. In particular, the deep supervised learning has successfully applied to analyse and detect COVID-19 on chest X-ray and CT scan images. However, the performance of such models is heavily dependent on the availability of a large labelled dataset. This is often a limitation because the creation of which is a very expensive and time consuming task, and especially imposes a great challenge for a novel disease. Semi-supervised learning has shown the ability to improve the detection accuracy of supervised models whilst requiring a small labelled datasets. This makes the semi-supervised an interesting alternative of significant practical importance for identifying COVID-19. Material and Methods: The present systematic review was conducted by searching the three databases of PubMed, Web of Science and Science Direct from December 1, 2019, to May 15, 2022, based on a search strategy. A total of 392 articles were extracted and, by applying the inclusion and exclusion criteria, 33 articles were selected as the research population. Result: In this study we reviewed studies which used deep semi-supervised learning methods on chest X-ray images and CT scans for the detection and diagnosis of COVID-19 and compared their performance. According to the findings, deep semi-supervised learning-based models are able to improve the diagnostic accuracy and robustness without exhaustive labeling. Conclusion: The application of deep semi-supervised learning in the field of COVID-19 radiologic image processing facilitates an accurate and reliable diagnosis. The use of deep learning technology and semi-supervised learning paradigm in the detection and diagnosis for COVID-19 reduce false-positive and negative errors, leading to an improved patient care and management.

Mots clés: COVID-19 ; Deep Learning ; Semi-supervised Learning ; Detection ; Diagnosis ; X-ray images ; CT scan

Phytochemicals as antimicrobial potentiators: a review

Belattar Nadjah,  Barhouchi Badra,  Benayache Sara,  Merabet Souad, 

Résumé: In the last few decades, ethnopharmacology research has focused on finding novel anti-infection agents. The antimicrobial activity of plant extracts used in traditional medicine, essential oils, or isolated compounds such as alkaloids, flavonoids, terpenes, coumarins, quinones, etc., among others, is the subject of much research. Some of these compounds were procured through bio-guided isolation after the identification of plant antimicrobial activity. Particular research focuses on the natural flora of a specific region or country and the ability of a plant or principle to combat a concrete pathological microorganism. The investigation of plant extracts, essential oils, and their isolated compounds for their antimicrobial properties requires the establishment of some general considerations. The definition of common parameters, such as plant material, techniques used, growth medium, and microorganisms tested, is extremely important. This report describes the principal groups of phytochemicals, as well as the evaluation of their therapeutic potential to guide pharmacological research. It allows us to inventory the frequency of use of medicinal plants containing active substances of curative interest, so this work aimed to elaborate an exhaustive list of bioactive compounds and find a correlation between their quantification and their antimicrobial capacity.

Mots clés: Antimicrobials ; Phenolic compounds ; Quinones ; Flavonoids ; Tannins ; Coumarins ; Terpenoids and essential oils ; Alkaloids

Oxidative Stress and COV-19 Virus Propagation: Systematic review

بخوش خديجة,  بنوشن جميلة,  العابد اميرة,  جكون عبد الحميد, 

Résumé: It was in China, on December 31, 2019, that the infection with a new Coronavirus appeared, now well-identified: COVID-19. The epidemic is in full swing in China and the number of cases continues to expand across the world causing concern among health specialists and all populations. Oxidative stress is a main issue augmenting the gravity of COVID-19, particularly throughout chronic diseases coupled with the instability of the antioxidant system. In the present systematic review, a literature search was performed using PubMed and Science Direct databases to search for appropriate keywords such as Covid-19 and oxidative stress, for pertinent publications up to 06.10.2021. Data extraction and quality evaluation of articles were performed by three reviewers. The results of the search are based on the inclusions and exclusions criteria based on the PRISMA protocol. This review focuses on the relationship between oxidative stress and COVID-19 in the final 05 articles were comprised. The result of this study showed that there is a countless relationship between oxidative stress, the propagation, and gravity of COVID-19 disease.

Mots clés: Covid-19 ; Oxidative Stress ; Antioxidant ; Enzymes ; Docking

Exploring the possible use of saponins in the treatments of COVID-19

Bouchachoua Leyla,  Mameri Fatima,  Bekhouche Khadidja,  Djakoun Abedalhamid, 

Résumé: A new coronavirus called Severe Acute Respiratory Syndrome (SARS-CoV-2) appeared in Wuhan (China) on 2019 and became a pandemic owing to its rapid emergence. Until now, there is no effective treatment to fight against this disease. The plants continuously gave effective phytoconstituents with low toxicity. Saponins are a class of plants secondary metabolites that have shown good efficacy in several studies against several viruses. Some of them was attracted attention of Scientifics in the treatment of COVID-19. The purpose of our review is to examinate the use of saponins during the pandemic in the treatment of SARS-CoV-2, notably the antiviral activity. The literature search was executed using PubMed database to search for suitable keywords such as COVID-19, saponins for articles published till 20 August 2021. The present systematic review was performed based on PRISMA protocol. Data extraction and quality evaluation of articles were performed by three reviewers. 41 articles were the results of the search and based on the inclusions and exclusions criteria, 15 articles were included in this systematic review. Firstly, we focused on the in vitro and vivo studies. Glycyrrhizin, Escin, Esculentoside A and Saikosaponins have already been shown to be effective against certain coronaviruses. Platycodin D, Ginsenoside Rg6 and Oleanolic acid derivatives tested against SARS-CoV-2 and showed a good activity. In the second part of this systematic review, we anticipated in summarizing on the in-silico studies, especialy the computational molecular docking simulations of saponins against differents sets of SARS-CoV-2 binding protein. In-silico study revealed that, Saikosaponin-U, Saikosaponin-V, glycyrrhizin and Esculentoside A have good Molecular docking simulations.

Mots clés: SARS-CoV 2 ; COVID-19 ; saponins ; antiviral ; docking

Knowledge and Risk Awareness of Traditional Medicine Practitioners in Algeria Regarding Bitter Almond: A Qualitative Interview Study

Abdennour Sara,  Chelighem Zeyneb,  Bouadjar Yasmine,  Benchikha Imene,  Bensalhia Rawnak Rayane,  Boukhenaf Afaf,  Derouiche Mohamed Tahar Taha, 

Résumé: Bitter almonds (Prunus amygdalus) have historically been utilized in folk medicine to treat diabetes, deworming, and reducing kidney stones. However, their use is also acknowledged as a primary cause of plant poisoning in Algeria. This study aimed to assess the awareness of risks associated with bitter almonds and understand its usage practices in the Eastern Algerian provinces. A descriptive cross-sectional investigation spanning four months involved 106 practitioners from different Algerian provinces: Constantine, Mila, Skikda, Batna, Souk-Ahras, and El Taraf. The study sought insights into practitioners' knowledge about bitter almonds, and the collected data were analyzed using Microsoft Excel. The study revealed a predominant representation of males, with a sex ratio of 6.06. Indeed, Most practitioners (79.25%) recognized the medicinal value of bitter almonds. Traditional healers often recommended bitter almonds for various ailments, such as diabetes (51.89%), dermatological disorders (24.53%), and other metabolic disorders (10.38%). Concerning perceived risks, only 22.64% acknowledged the potential dangers, including poisoning, gastric disorders, hormonal imbalances, and metabolic disorders.

Mots clés: Bitter Almond ; Prunus amygdalus ; Traditional Medicine Practitioners ; Eastern Algeria

Multilayer Perceptron Networks for Aid in the Diagnosis of Coronary Heart Disease

بوفنارة محمد نجيب,  باهي مريم, 

Résumé: Heart disease, the predominant cause of morbidity and mortality worldwide, poses considerable diagnostic challenges. The imperative to identify and assess risks at an early stage requires the development of a robust and effective forecasting system. Machine learning enables accurate predictions, proving invaluable in various fields such as finance and healthcare. However, the varied performance of algorithms introduces complexities, with some achieving high prediction accuracy and others demonstrating comparatively lower precision. In this work, we introduce a method using a multi-layer perceptron neural network to provide decision support in the diagnosis of heart diseases in patients. This proposed model is systematically compared with four important machine learning counterparts: Random Forest, Logistic Regression, Naive Bayes, and SVM. Performance evaluations are conducted using a comprehensive dataset derived from a cardiovascular study including Massachusetts residents with coronary heart disease. The obtained results suggest that the accuracy of the model based on a multilayer perceptron is superior compared to the four other machine learning models. The use of MLPs appears to be a promising and effective approach for enhancing diagnostic accuracy in the field of cardiovascular health when employing this type of data.

Mots clés: Coronary Heart Disease ; Machine Learning ; MLP ; Multilayer Perceptron