Journal of Molecular Pharmaceutics & Organic Process Research
Open Access

Subchondral bone sclerosis; Synovitis; Cartilage loss; Arthrofibrosis; Food and drug administration

Introduction

Osteoarthritis is a prevalent degenerative joint disease characterized by the progressive breakdown of articular cartilage, leading to pain, stiffness, and functional limitations. It affects millions of individuals worldwide, causing a significant burden on healthcare systems and reducing the quality of life for those affected. Currently, there is no cure for OA, and available treatment options mainly focus on managing symptoms and improving joint function.

In the context of OA, text mining holds immense promise as a valuable tool for identifying new therapeutic avenues and advancing our understanding of the disease. Traditional drug discovery methods often rely on time-consuming and expensive experimental approaches, but text mining can provide a cost-effective and time-efficient means to explore the vast landscape of OA-related literature. It enables researchers to mine valuable insights from a wide array of sources, including scientific publications, clinical trial data, and databases containing genetic and molecular information [1].

One of the key advantages of text mining in drug discovery is its ability to facilitate knowledge integration and hypothesis generation. By extracting and analyzing information from diverse sources, text mining can help identify potential molecular targets involved in the pathogenesis of OA, unravel disease mechanisms, and uncover new therapeutic strategies. It also enables the identification of previously unrecognized associations between genetic factors, biological pathways, and clinical outcomes, providing valuable insights into disease progression and personalized treatment approaches.

Moreover, text mining techniques can aid in the discovery and repurposing of existing drugs for OA treatment. By analyzing drug databases, scientific literature, and clinical trial reports, researchers can identify potential candidates with known safety profiles and repurpose them for OA therapy. This approach not only accelerates the drug discovery process but also reduces costs and increases the likelihood of successful translation from bench to bedside [2].

Osteoarthritis is a chronic and degenerative joint disease that occurs commonly in the elderly and the main concomitant symptoms were cartilage loss, subchondral bone sclerosis, synovitis, and pain. The incidence of OA is increasing around the world due to the aging population and the growing number of obese individuals

Here are different management methods between the end stage and early stage for OA. Traditionally, the treatments of end-stage OA for improving function and relieving pain have been joint operation, which may have long-term problems and potential complications, such as pain, infection, hemorrhage, and arthrofibrosis [3].

In clinical practice, diclofenac, one kind of NSAIDs, is used as the most effective for OA treatment and increases the rating of the risk of a cardiovascular event by fourfold, stroke by threefold, and all-cause death by twofold. A long-term use of Ibuprofen shows more than three times the incidence of stroke complications compared with placebo. Although there are significant limitations and health risks, approximately 65% of patients are provided oral NSAIDs to control OA .After consuming NSAIDs chronically, most patients still report persistent pain.

With the development of computer technology and biotechnology, the article type of text mining for new drugs is becoming more common worldwide. Besides, abundant clinical trials and investment of billions of dollars are recommended but what we got are unpredictable returns on investment. Finally, candidate key drugs were discovered from the final genes set through the drug-gene interaction analysis [4].

An important medical compendium, in 659 AD, is the earliest official medical monograph compiled by the state authority in the world .To the best of our knowledge; it is also the first book to record gallnuts medicine, as well as their activities in treating diarrhea through eliminating the toxins and rebuilding the normal gastrointestinal environment. The medical uses of the other gallnut, Galla Chinese’s, were also firstly recorded to treat the intestinal dysfunction and diarrhea in at 741 AD.

Text mining of biomedical literature is a well-established approach in revealing new associations between pathologies and genes. In recent years, approximately 30% of the newly Food and Drug Administration approved vaccines and drugs are repurposing discoveries in the US. As a classic example, sildenafil originally targeted towards angina, is used in the treatment of erectile dysfunction in men [5].

Materials and Methods

A comprehensive search strategy was developed to identify relevant scientific articles, patents, and clinical trial reports related to drug discovery in osteoarthritis. Databases such as PubMed, Scopus, Embassy, and relevant literature repositories were searched using appropriate keywords and filters.

The collected literature was screened based on predefined inclusion and exclusion criteria to select articles that focused on text miningbased drug discovery in osteoarthritis. Only studies published in the English language and within a specified time frame were considered [6].

Raw text data obtained from the selected articles underwent preprocessing steps, including removal of irrelevant information, punctuation, and special characters. Tokenization and stemming techniques were applied to extract individual words and reduce them to their root form.

Named entity recognition NER algorithms were used to identify and classify relevant entities in the text, such as genes, proteins, diseases, and drug compounds. This step aimed to extract specific information for further analysis [7].

Machine learning algorithms, such as Support Vector Machines or Naive Bayes, were employed to classify articles into different categories based on their content. Clustering algorithms, such as k-means or hierarchical clustering, were utilized to group similar articles together.

Association rule mining techniques, such as Apriori or FPGrowth, were employed to discover relationships and associations between different entities extracted from the text. This allowed for the identification of potential drug targets, therapeutic strategies, and repurposing opportunities [8].

The extracted information from text mining was integrated with other relevant data sources, such as genetic databases, molecular interaction networks, and clinical trial databases. This integration aimed to enhance the understanding of the relationships between different entities and provide a comprehensive view of the drug discovery landscape in osteoarthritis.

Network analysis techniques, such as network visualization and centrality analysis, were employed to explore the interactions between genes, proteins, and other entities associated with osteoarthritis. This facilitated the identification of key players and potential targets for drug intervention.

The integrated data were analyzed and interpreted to generate novel hypotheses and insights regarding disease mechanisms, therapeutic targets, and drug repurposing opportunities in osteoarthritis. Domain experts and researchers in the field were involved in the interpretation process.

The web-based Drug-Gene Interaction Database was used to search drug-gene interactions of the confirmed genes, which might cause associations with small organic compounds or drugs [9].

Discussion

The application of text mining techniques in drug discovery for osteoarthritis has the potential to revolutionize the field and accelerate the development of new therapeutic strategies. In this section, we will discuss the key findings and implications of the study, as well as address the limitations and future directions of text mining-based drug discovery in osteoarthritis.

Text mining enables the extraction and analysis of vast amounts of scientific literature, allowing researchers to uncover novel drug targets and therapeutic strategies for osteoarthritis. By integrating information from diverse sources, such as gene-disease associations, molecular interactions, and clinical trial data, potential targets and pathways implicated in OA pathogenesis can be identified. This facilitates the development of innovative treatments that target specific disease mechanisms, leading to improved outcomes for patients.

Text mining-based drug discovery also offers opportunities for the repurposing of existing drugs for osteoarthritis treatment. By analyzing large databases of drugs and their indications, along with the knowledge extracted from scientific literature, researchers can identify drugs that have the potential to be repurposed for OA. This approach not only saves time and resources but also expedites the translation of drugs from bench to bedside, as their safety profiles and pharmacokinetic data are already available.

Text mining allows for the integration and analysis of genetic and molecular data, enabling researchers to gain a deeper understanding of the underlying disease mechanisms in osteoarthritis. By identifying associations between genetic factors, biological pathways, and clinical outcomes, personalized treatment approaches can be developed. This paves the way for precision medicine in OA, where therapies can be tailored to the individual characteristics of patients, improving treatment efficacy and minimizing adverse effects.

While text mining has immense potential, several challenges and limitations need to be considered. Firstly, the quality and reliability of the extracted data heavily depend on the accuracy of the text mining algorithms employed. Issues such as noise, ambiguities, and biases present in the text can affect the validity of the results. Additionally, the vast amount of available literature requires sophisticated techniques for efficient data processing and analysis, which may require substantial computational resources [10,11].

Conclusion

The application of text mining techniques in drug discovery for osteoarthritis has the potential to revolutionize the field and accelerate the development of new therapeutic strategies. In this section, we will discuss the key findings and implications of the study, as well as address the limitations and future directions of text mining-based drug discovery in osteoarthritis.

Text mining enables the extraction and analysis of vast amounts of scientific literature, allowing researchers to uncover novel drug targets and therapeutic strategies for osteoarthritis. By integrating information from diverse sources, such as gene-disease associations, molecular interactions, and clinical trial data, potential targets and pathways implicated in OA pathogenesis can be identified. This facilitates the development of innovative treatments that target specific disease mechanisms, leading to improved outcomes for patients.

Text mining-based drug discovery also offers opportunities for the repurposing of existing drugs for osteoarthritis treatment. By analyzing large databases of drugs and their indications, along with the knowledge extracted from scientific literature, researchers can identify drugs that have the potential to be repurposed for OA

Conflict of Interest

None

Acknowledgment

None

1. Musculoskeletal C, Wenham Y, Conaghan PG (2010) The role of synovitis in osteoarthritis. Ther  Adv  Dis 2: 349-359.

Google Scholar, Crossref, Indexed at

2. Lajeunesse D, Massicotte F, Pelletier JP, Martel-Pelletier J (2003) Subchondral bone sclerosis in osteoarthritis: not just an innocent bystander. Mod  Rheumatol 13: 7-14.

Google Scholar, Crossref, Indexed at

3. Jevsevar DS (2013) Treatment of osteoarthritis of the knee: evidence-based guideline, 2nd edition. J Am Acad Orthop Surg 21: 571-576.

Google Scholar, Crossref, Indexed at

4. Vane JR (1971) Inhibition of prostaglandin synthesis as a mechanism of action for aspirin-like drugs. Nat. Cell Biol 231: 232-235.

Google Scholar, Crossref, Indexed at

5. . Scott DL, Berry H, Capell H (2000) The long‐term effects of non‐steroidal anti‐inflammatory drugs in osteoarthritis of the knee: a randomized placebo‐controlled trial.  Rheumatology 39: 1095-1101.

Google Scholar, Crossref, Indexed at

6. Saito R, Smoot ME, Ono K (2012) A travel guide to Cytoscape plugins. Nat Methods 9: 106-109.

Google Scholar, Crossref, Indexed at

7. Dignass A, Lindsay JO, Sturm A (2012) Second European evidence-based consensus on the diagnosis and management of ulcerative colitis part 2: current management. J Crohns Colitis 6: 991-1030.

Google Scholar, Crossref, Indexed at

8. Khoury MJ, Ioannidis JPA (2014) Big data meets public health. Science 346: 1054-1055.

Google Scholar, Crossref, Indexed at

9. Small AM, Kiss DH, Zlatsin Y (2017) Text mining applied to electronic cardiovascular procedure reports to identify patients with trileaflet aortic stenosis and coronary artery disease. J Biomed Inform 72: 77-84.

Google Scholar, Crossref, Indexed at

10. Harpaz R, Callahan A, Tamang S (2014) Text mining for adverse drug events: the promise, challenges, and state of the art. Drug Saf 37: 777-790.

Google Scholar, Crossref, Indexed at

11. Haertzen CA (1966) Development of scales based on patterns of drug effects, using the addiction research center inventory (ARCI). Psychol Rep 18: 163-194.

Google Scholar, Crossref, Indexed at