SavedAdd your journal

Journals / Journal of Kocaeli Health and Technology University / 2026 / Cilt: 4 Sayı: 1

MindNexQua: An Autonomous Generative AI Framework for De Novo Drug Design and In Silico Molecular Docking Orchestration

MindNexQua: De Novo İlaç Tasarımı ve İn Siliko Moleküler Docking Yönetimi için Otonom Üretken Yapay Zeka Sistemi

Soykan Agar(KOCAELİ SAĞLIK VE TEKNOLOJİ ÜNİVERSİTESİ)0000-0002-9870-6882
Erfan Akhavan(KOCAELİ SAĞLIK VE TEKNOLOJİ ÜNİVERSİTESİ)0009-0007-7475-391X
Erkan Gökoluk(KOCAELİ SAĞLIK VE TEKNOLOJİ ÜNİVERSİTESİ)0009-0004-7372-7515
Ghassan Issa(KOCAELİ SAĞLIK VE TEKNOLOJİ ÜNİVERSİTESİ)0000-0002-0229-7632
Muzaffer Elmas(KOCAELİ SAĞLIK VE TEKNOLOJİ ÜNİVERSİTESİ)0000-0003-3202-6689
Pages
71–86
Publication Date
2026-04-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Consequently, MNQ offers a sustainable, autonomous, and integrated research ecosystem for de novo drug design and in silico molecular docking orchestration.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Drug development processes face significant challenges, including lengthy time requirements, high costs, and success rates below 15% in clinical trials.
📊
Key Findings & Data:MNQ integrates RDKit for the generation of structural derivatives, AutoDock Vina for molecular docking calculations, and Mistral 7B-based large language models for interpreting results.
💡
Conclusion & Impact:Consequently, MNQ offers a sustainable, autonomous, and integrated research ecosystem for de novo drug design and in silico molecular docking orchestration.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:De Novo İlaç Tasarımı · Yapay Zeka · Moleküler Doklama

Abstract

Drug development processes face significant challenges, including lengthy time requirements, high costs, and success rates below 15% in clinical trials. To optimize these costly and complex processes, the KOSTU Biochemistry Department Soykan Agar’s research group has developed an autonomous artificial intelligence called MindNexQua (MNQ). This work aims to update the drug discovery pipeline by offering an accessible, open-source, and self-sufficient alternative to expensive licensed platforms. The system has a workflow that automates the process from in silico biochemical docking to final visualization, using target receptor protein structures and drug candidate ligands as initial input. MNQ integrates RDKit for the generation of structural derivatives, AutoDock Vina for molecular docking calculations, and Mistral 7B-based large language models for interpreting results. To improve the reliability of simulations and minimize random errors, a "multi-run" strategy consisting of 20 independent simulations is applied to each ligand candidate. At the end of this process, the system automatically selects and statistically validates the "Top-5" candidate molecule with the lowest binding energy (ΔG). The findings show that the candidate molecules designed by MindNexQua exhibit high steric fit (-8.6 kcal/mol) to the active site of target proteins and display thermodynamically stable conformations. Consequently, MNQ offers a sustainable, autonomous, and integrated research ecosystem for de novo drug design and in silico molecular docking orchestration.

Özet

İlaç geliştirme süreçleri; uzun zaman gereksinimleri, yüksek maliyetler ve klinik denemelerde %15’in altında başarı oranları gibi önemli zorluklarla karşı karşıyadır. Bu maliyetli ve karmaşık süreçleri optimize etmek amacıyla, KOSTU Biyokimya Departmanı’ndan Soykan Ağar’ın araştırma grubu, MindNexQua (MNQ) adını verdikleri otonom bir yapay zekâ sistemi geliştirmiştir. Bu çalışma, pahalı lisanslı platformlara alternatif olarak erişilebilir, açık kaynaklı ve kendi kendine yeten bir sistem sunarak ilaç keşif sürecini güncellemeyi amaçlamaktadır. Sistem, hedef reseptör protein yapıları ve ilaç adayı ligandları başlangıç girdileri olarak kullanarak, in silico biyokimyasal kenetlenmeden, nihai görselleştirmeye kadar olan süreci otomatikleştiren bir iş akışı sunmaktadır. MNQ; yapısal türevlerin üretilmesi için RDKit’i, moleküler kenetlenme hesaplamaları için AutoDock Vina’yı ve sonuçların yorumlanması için Mistral 7B tabanlı büyük dil modellerini entegre etmektedir. Simülasyonların güvenilirliğini artırmak ve rastgele hataları en aza indirmek amacıyla, her bir ligand adayı için 20 bağımsız simülasyondan oluşan çoklu çalıştırma (multi-run) stratejisi uygulanmaktadır. Sürecin sonunda sistem, en düşük bağlanma enerjisine (ΔG) sahip en iyi 5 aday molekülü otomatik olarak seçmekte ve istatistiksel olarak doğrulamaktadır. Elde edilen bulgular, MNQ tarafından tasarlanan aday moleküllerin hedef proteinlerin aktif bölgelerine yüksek sterik uyum (-8,6 kcal/mol) gösterdiğini ve termodinamik olarak kararlı konformasyonlar sergilediğini ortaya koymaktadır. Sonuç olarak MNQ, de novo ilaç tasarımı ve in silico moleküler kenetlenme süreçlerinin koordinasyonu için sürdürülebilir, otonom ve entegre bir araştırma ekosistemi sunmaktadır.

🔖

Cite This Article

Agar, S., Akhavan, E., Gökoluk, E., Issa, G., Elmas, M. (2026). MindNexQua: An Autonomous Generative AI Framework for De Novo Drug Design and In Silico Molecular Docking Orchestration. Journal of Kocaeli Health and Technology University, Cilt: 4 Sayı: 1, 71–86. https://doi.org/10.66163/jokohtu.1889565

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (37)

  1. DiMasi, J. A., Grabowski, H. G., & Hansen, R. W. (2016). Innovation in the pharmaceutical industry: New estimates of R&D costs. Journal of Health Economics, 47, 20–33.
  2. Song, C. M., Lim, S. J., & Tong, J. C. (2009). Recent advances in computer-aided drug design. Briefings in Bioinformatics, 10(5), 579–591.
  3. Kalyan, K. (2018). Pharmaceutical medicine and translational clinical research. Current Science, 115(8), 1403–1405.
  4. Sabe, V. T., Ntombela, T., Jhamba, L. A., Maguire, G. E., Govender, T., Naicker, T., & Kruger, H. G. (2021). Current trends in computer-aided drug design and a highlight of drugs discovered via computational techniques: A review. European Journal of Medicinal Chemistry, 224, Article 113705.
  5. Gurung, A. B., Ali, M. A., Lee, J., Farah, M. A., & Al-Anazi, K. M. (2021). An updated review of computer‐aided drug design and its application to COVID‐19. BioMed research international, 2021(1), 8853056.
  6. Zhong, F., Xing, J., Li, X., Liu, X., Fu, Z., Xiong, Z., Lu, D., Wu, X., Zhao, J., & Tan, X. (2018). Artificial intelligence in drug design. Science China Life Sciences, 61(10), 1191–1204.
  7. Hou, T., & Xu, X. (2004). Recent development and application of virtual screening in drug discovery: An overview. Current Pharmaceutical Design, 10(9), 1011–1033.
  8. Overington, J. P., Hann, M. M., & Green, D. V. S. (2021). The Reality of AI in Drug Discovery. Highlights from The Society for Medicines Research Online Meeting. Virtual-March 4, 2021. Drugs of the Future, 46(5).
  9. Durrant, J. D., & McCammon, J. A. (2011). Molecular dynamics simulations and drug discovery. BMC Biology, 9, Article 71.
  10. Mak, K. K., & Pichika, M. R. (2019). Artificial intelligence in drug development: present status and future prospects. Drug discovery today, 24(3), 773-780.
  11. ChemIntelligence. (n.d.). AI for chemistry. Retrieved December 20, 2020, from https://chemai.io/
  12. McCarthy, J., & Hayes, P. J. (1981). Some philosophical problems from the standpoint of artificial intelligence. Readings in artificial intelligence (pp. 431-450). Morgan Kaufmann.
  13. Yang, X., Wang, Y., Byrne, R., Schneider, G., & Yang, S. (2019). Concepts of artificial intelligence for computer-assisted drug discovery. Chemical reviews, 119(18), 10520-10594.
  14. Bobrow, D. G. (1964). Natural language input for a computer problem-solving system. In M. Minsky (Ed.), Semantic information processing (pp. 146–226). MIT Press.
  15. Weizenbaum, J. (1966). ELIZA—A computer program for the study of natural language communication between man and machine. Communications of the ACM, 9(1), 36–45.
  16. Baum, E. B. (1988). On the capabilities of multilayer perceptrons. Journal of Complexity, 4(3), 193–215.
  17. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning internal representations by error propagation. In D. E. Rumelhart & J. L. McClelland (Eds.), Parallel distributed processing: Explorations in the microstructure of cognition (Vol. 1, pp. 318–362). MIT Press.
  18. Qian, N., & Sejnowski, T. J. (1988). Predicting the secondary structure of globular proteins using neural network models. Journal of Molecular Biology, 202(4), 865–884.
  19. Hammett, L. P. (1937). The effect of structure upon the reactions of organic compounds. Benzene derivatives. Journal of the American Chemical Society, 59(1), 96–103.
  20. Hansch, C., & Fujita, T. (1964). $\rho$-$\sigma$-$\pi$ analysis. A method for the correlation of biological activity and chemical structure. Journal of the American Chemical Society, 86(8), 1616–1626.
  21. Kopecký, J., Boček, K., & Vlachová, D. (1965). Chemical structure and biological activity on m- and p-disubstituted derivatives of benzene. Nature, 207(5000), 981–981.
  22. Wessel, M. D., Jurs, P. C., Tolan, J. W., & Muskal, S. M. (1998). Prediction of human intestinal absorption of drug compounds from molecular structure. Journal of Chemical Information and Computer Sciences, 38(4), 726–735.
  23. Yang, G. F., & Huang, X. (2006). Development of quantitative structure-activity relationships and its application in rational drug design. Current pharmaceutical design, 12(35), 4601-4611.
  24. Basile, A. O., Yahi, A., & Tatonetti, N. P. (2019). Artificial intelligence for drug toxicity and safety. Trends in Pharmacological Sciences, 40(9), 624–635.
  25. Bunney, P. E., Zink, A. N., Holm, A. A., Billington, C. J., & Kotz, C. M. (2017). Orexin activation counteracts decreases in non-exercise activity thermogenesis (NEAT) caused by a high-fat diet. Physiology & Behavior, 176(1), 139–148.
  26. Huang, D., & Caflisch, A. (2011). The free energy landscape of small molecule unbinding. PLoS Computational Biology, 7(2), Article e1002002.
  27. Honarparvar, B., Govender, T., Maguire, G. E., Soliman, M. E., & Kruger, H. G. (2014). Integrated approach to structure-based enzymatic drug design. Chemical Reviews, 114(1), 493–537.
  28. Honarparvar, B., Govender, T., Maguire, G. E., Soliman, M. E., & Kruger, H. G. (2014). Integrated approach to structure-based enzymatic drug design: molecular modeling, spectroscopy, and experimental bioactivity. Chemical reviews, 114(1), 493–537.
  29. Hafner, J. (2008). Ab‐initio simulations of materials using VASP: Density‐functional theory and beyond. Journal of Computational Chemistry, 29(13), 2044-2078.
  30. Sebastiani, D., & Rothlisberger, U. (2003). Advances in density-functional-based modeling techniques: Recent extensions of the Car-Parrinello approach. Methods and Principles in Medicinal Chemistry, 17, 5–40.
  31. Şenel, P., Faysal, A. A., Agar, S., Yurtsever, M., & Gölcü, A. (2025). Investigating the interactions of Axitinib, a tyrosine kinase inhibitor, with DNA: experimental studies, molecular docking, and molecular dynamics simulations. Nucleosides, Nucleotides & Nucleic Acids, 1–24.
  32. Agar, S., Şenel, P., Al Faysal, A., Gölcü, A., & Yurtsever, M. (2025). An in-depth study of clofarabine's binding mechanism to DNA: A thorough experimental and theoretical investigation. Computational Biology and Chemistry, 117, 108418.
  33. Agar, S., Acar, E., Gökoluk, E., Akhavan Giglou, E., Şimşek, D., & Issa, G. (2026). In silico biochemical de novo drug design of valproic acid derivatives to suppress cancerous DNA: Comprehensive molecular docking, molecular dynamics, 1H NMR, ADME. Acta Medica Nicomedia, 9, 1–8.
  34. Agar, S., Arasan, Y., Akkurt, B., & Ulukaya, E. (2025). Inhibition of pancreatic cancer via LPAR4 receptor with a de novo drug complex design using theoretical organic chemistry: Comprehensive molecular docking, molecular dynamics. Journal of Research in Pharmacy, 28(4), 1033-1040.
  35. Daniş, İ., Agar, S., Yurtsever, M., & Özer Ünal, D. (2024). High Performance Liquid Chromatography-Tandem Mass Spectrometric determination of carcinogen nitrosamine impurities from pharmaceuticals and DNA binding confirmation aided by molecular docking application. İstanbul Journal of Pharmacy, 54(3), 386-394.
  36. Agar, S., Mokhtari, M., Yanik, M., Akkurt, B., Ulukaya, E., & Terzi, R. (2024). De novo antineoplastic drug design to suppress head, neck and oral cancer using theoretical organic and biochemistry via comprehensive molecular docking and dynamics. Asian Pacific Journal of Cancer Prevention, 25(8), 2905–2909.
  37. Agar, S., Akkurt, B., & Alparslan, L. (2024). De novo drug design to suppress coronavirus RNA-glycoprotein via PNA-calcitonin. Journal of the Turkish Chemical Society Section A: Chemistry, 11(2), 623–632.