Submit to Special Issue Submit Abstract to Special Issue Review for Pharmaceuticals Propose a Special Issue

Journal Menu

Journal Browser

Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs

Print Special Issue Flyer
Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Pharmaceuticals (ISSN 1424-8247). This special issue belongs to the section "AI in Drug Development".

Deadline for manuscript submissions: 25 November 2026 | Viewed by 9220

Share This Special Issue

Editors

Dr. Francisco Rivas García

E-Mail Website
Guest Editor

Municipal Health and Consumer Unit, Guadix City Council (Granada), School of Health Sciences, Valencia International University, 46010 Valencia, Spain
Interests: bioethics; parenteral nutrition; health education; pharmacy
Special Issues, Collections and Topics in MDPI journals

Dr. Maria José Zarzuelo Romero

E-Mail Website1 Website2
Guest Editor

Department of Pharmacy and Pharmaceutical Technology, University of Granada, Granada, Spain
Interests: pharmaceutical care; health education; pharmacy education; social pharmacy
Special Issues, Collections and Topics in MDPI journals

Dr. Margarita López-Viota

E-Mail Website
Guest Editor

Department of Pharmacy and Pharmaceutical Technology, University of Granada, Granada, Spain
Interests: pharmacy; pharmaceutical technology
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI), whose origins date back to the 1950s, has experienced exponential growth and is becoming increasingly integrated into our lives. It is defined as a system capable of exhibiting human behaviour and of learning and reasoning through algorithms and mathematical models. In the pharmaceutical and healthcare industries, AI is a tool with great potential, optimising research and development processes. It plays a decisive role in identifying new molecules or therapeutic targets, performing simulations and data analysis, and can be useful in the discovery of new drugs.

This Special Issue aims to address how AI can be applied to the design of drugs, new molecules, and compounds.

Dr. Francisco Rivas García
Dr. Maria José Zarzuelo Romero
Dr. Margarita López-Viota
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Pharmaceuticals is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

artificial intelligence
drug design
pharmaceutical technology
molecular dynamics simulation

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (9 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review, Other

31 pages, 7672 KB

Open AccessArticle

Synthetic Elaboration, DFT Profiling, and Molecular-Dynamics-Guided Computational Validation Toward Anti-Diabetic Therapeutics: Tailored Pyrimidine-Derived Pyrazole-Thiadiazole Hybrid Scaffolds

by Nahed Sail Alharthi

Pharmaceuticals 2026, 19(6), 915; https://doi.org/10.3390/ph19060915 - 10 Jun 2026

Viewed by 277

Abstract

Background/Objectives: Diabetes mellitus (DM) is a critical metabolic condition with escalated blood glucose levels caused by insulin resistance, restricted insulin production, and the activity of alpha-amylase and alpha-glucosidase enzymes. Methods: This current work focuses on the synthesis and evaluation of novel Pyrimidine-derived pyrazole-based thiadiazole derivatives to target DM by inhibiting α-amylase and α-glucosidase. Results: The findings exhibited that, except for three compounds, all other synthesized derivatives inhibited α-amylase and α-glucosidase enzymes with IC₅₀ values ranging from 5.17 μM to 29.84 μM on α-amylase and 7.60 μM to 31.62 μM on α-glucosidase, in comparison to the standard drug Acarbose (α-amylase IC₅₀ = 8.25 ± 0.80 μM; α-glucosidase IC₅₀ = 10.75 ± 1.10 μM). Analogs 8g, 8k, and 8b displayed superior or comparable inhibitory activity compared to the reference drug Acarbose. The inhibition potential of the derivatives can be attributed to their stable contacts with crucial amino acid residues of targeted enzymes, as shown through molecular docking analysis. Moreover, DFT-calculated HOMO–LUMO parameters and electrostatic potential (ESP) maps were used to gain complementary insight into the electronic characteristics, charge distribution, and potential interaction behavior of the synthesized derivatives, which supported the molecular docking observations. Conclusions: Experimental outcomes and in silico support display that these derivatives serve as potential leads for anti-diabetic drug development. These potent pyrimidine-derived pyrazole-based thiadiazole derivatives were comparable to an existing diabetic mellitus inhibitor, specifying potential for further therapeutic development and optimization against diabetic mellitus. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Figure 1

24 pages, 5807 KB

Open AccessArticle

Machine Learning-Driven QSAR Modeling of FXIa Inhibitors for Virtual Screening and Rational Drug Design

by Ali Onur Kaya, Mert Can Emre and Nesrin Emre

Pharmaceuticals 2026, 19(6), 912; https://doi.org/10.3390/ph19060912 - 10 Jun 2026

Viewed by 390

Abstract

Background/Objectives: Coagulation factor XIa (FXIa) has emerged as a promising therapeutic target for the development of safer anticoagulant therapies with reduced bleeding risk. This study aimed to develop an interpretable machine learning-driven quantitative structure–activity relationship (QSAR) framework for predicting the inhibitory activity of FXIa inhibitors and supporting virtual screening applications. Methods: A total of 3026 curated compounds retrieved from the ChEMBL database were used for regression modeling, whereas 2119 compounds were retained for classification modeling after excluding intermediate-activity molecules. Molecular descriptors were generated using RDKit, Mordred, and Morgan fingerprint representations. Following preprocessing and feature selection, multiple machine learning algorithms were systematically benchmarked. Model robustness and reliability were further evaluated using 5-fold cross-validation, scaffold-aware validation, applicability domain analysis, and Y-randomization testing. Results: Nonlinear ensemble learning approaches consistently outperformed conventional linear algorithms. The optimized HistGradientBoostingRegressor achieved the best regression performance, with an independent test-set R² value of 0.711 and an RMSE value of 0.759, whereas the optimized classification model achieved accuracies approaching 95%. SHAP analysis identified lipophilicity-related descriptors, aromatic scaffold organization, electrostatic surface properties, and molecular topology as major contributors to FXIa inhibitory activity prediction. In addition, a proof-of-concept virtual screening workflow successfully identified several candidate compounds exhibiting high predicted pKi values and elevated active-class probabilities. Conclusions: The proposed framework provides a robust, interpretable, and reproducible machine learning-driven QSAR strategy for FXIa inhibitor discovery and may facilitate future virtual screening campaigns and medicinal chemistry optimization studies targeting FXIa-associated anticoagulant drug discovery. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Figure 1

27 pages, 4468 KB

Open AccessArticle

A Molecular–Protein Fusion Framework for Rapid Virtual Screening: Accelerating Lead Discovery for “Undruggable’’ Oncogenic Targets

by Chenxi Zhou, Yanni Zhu, Chenrui Yang, Yu Gao, Jianyang Lu and Dengming Ming

Pharmaceuticals 2026, 19(5), 753; https://doi.org/10.3390/ph19050753 - 12 May 2026

Viewed by 512

Abstract

Background/Objectives: KRAS G12D is one of the most frequent oncogenic mutations in pancreatic ductal adenocarcinoma (PDAC) and remains challenging to target because of its limited druggable binding pockets. This study aimed to develop a machine learning-based framework for rapid virtual screening of potential KRAS G12D inhibitors. Methods: A molecular–protein fusion prediction framework, MPFF-IS, was constructed by integrating the ESM2 protein language model with an MPNN-GNN molecular graph network to enable joint representation learning of protein and compound features. The model was trained using a KRAS G12D inhibitor dataset and applied to screen compounds from multiple chemical libraries. AutoDock Vina docking and 300 ns GROMACS molecular dynamics simulations were subsequently performed for structural validation. Results: MPFF-IS achieved favorable predictive performance on the test dataset and identified 2663 candidate compounds from more than 134,000 screened molecules. Several candidate ligands exhibited favorable binding affinity, stable proteinligand interactions, and enhanced structural stability compared with reference inhibitors, including MRTX1133 and BI-2852. Molecular dynamics analyses further supported the stability of the predicted complexes and the involvement of key binding residues within the KRAS G12D pocket. Conclusions: These findings demonstrate that MPFF-IS can efficiently identify potential KRAS G12D inhibitors and may provide a useful computational framework for precision drug discovery targeting difficult oncogenic proteins. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Figure 1

23 pages, 2449 KB

Open AccessArticle

Computational Discovery of Dual-Target LDHA/BRD4 Inhibitors Targeting the Lactate–Kla–B7-H3 Immunosuppressive Axis Through AI-Driven Virtual Screening

by Ruiqi Zhao, Mengyao Han, Bei Zhang, Mengqing Ma, Xiaozhou Zhou and Jialing Sun

Pharmaceuticals 2026, 19(5), 736; https://doi.org/10.3390/ph19050736 - 7 May 2026

Viewed by 755

Abstract

Background/Objectives: Immune evasion remains a critical barrier to effective hepatocellular carcinoma (HCC) therapy. Lactate dehydrogenase A (LDHA) drives lactate accumulation and histone lysine lactylation (Kla), reshaping the immunosuppressive microenvironment, while bromodomain-containing protein 4 (BRD4) sustains B7-H3 transcription via super-enhancer occupancy. Despite their synergistic roles in the lactate–Kla–B7-H3 immunosuppressive axis, no dual-target inhibitor simultaneously engaging both proteins has been reported. This study aimed to discover dual LDHA/BRD4 inhibitors from natural product libraries using an integrated AI-driven computational pipeline. Methods: We established a multi-tier virtual screening cascade comprising Lipinski/QED drug-likeness filtration, DiffDock-based AI docking, QuickVina binding energy validation, PLIP interaction profiling, 200 ns all-atom molecular dynamics simulations, MM-GBSA binding free energy calculations, and density functional theory analysis. Natural product libraries from COCONUT and CMNPD databases (84,730 compounds post-filtration) were screened against both targets. Results: High-throughput DiffDock screening identified 11 dual-target hits, from which CNP0038114.1 and CMNPD16582 emerged as prioritized lead candidates. All four protein–ligand complexes maintained structural stability throughout MD simulations, with MM-GBSA binding free energies ranging from −27.24 to −32.45 kcal/mol, predominantly driven by van der Waals interactions. DFT calculations revealed distinct electronic profiles: CNP0038114.1 exhibited a narrow HOMO–LUMO gap (2.718 eV) favoring charge-transfer reactivity, whereas CMNPD16582 displayed a larger gap (4.822 eV), suggesting superior chemical stability. Conclusions: This computational study furnishes two novel natural product leads for targeting the lactate–Kla–B7-H3 immunosuppressive axis in HCC, establishing a generalizable AI-driven workflow for dual-target inhibitor discovery. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Graphical abstract

22 pages, 5132 KB

Open AccessArticle

Integrative Spatial Transcriptomics and Immunoinformatics for Prognostic Multi-Epitope Vaccine Construct Prediction Against Synovial Sarcoma

by Maha A. Aljumaa, Maher S. Alwethaynani, Hanan Abdulrahman Sagini, Fakhria A. Al-Joufi and Ghulam Nabi

Pharmaceuticals 2026, 19(2), 282; https://doi.org/10.3390/ph19020282 - 7 Feb 2026

Viewed by 789

Abstract

Background/Objectives: Synovial sarcoma (SS) is a rare and aggressive soft-tissue malignancy characterized by complex molecular alterations and poor prognosis, highlighting the need for targeted immunotherapeutic strategies. This study aimed to design a rational multi-epitope vaccine targeting the FKBP10 oncoprotein to elicit effective immune responses against SS. Methods: Transcriptomic data from the GEO dataset GSE144190, comprising 10 tumor and 9 normal tissue samples, were analyzed to identify differentially expressed genes (DEGs). Results: Our findings revealed significantly upregulated FKBP10 with a log2 fold change of 3.55, baseMean expression of 1521.84, and adjusted p-value of 8.37 × 10⁻²⁶. Mutational analysis across 7782 sarcoma samples indicated a low alteration frequency of ~1.5%, primarily missense variants. Functional mapping showed FKBP10 as a hub interacting with multiple collagen chains and chaperone proteins, implicating its role in extracellular matrix organization and protein folding. Linear B-cell epitope prediction identified 17 epitopes (6–21 amino acids), while T-cell mapping yielded 10 MHC class I and 9 MHC class II high-affinity epitopes, all antigenic (VaxiJen > 0.5) and non-allergenic. A multi-epitope vaccine was constructed incorporating a 50S ribosomal protein L22 adjuvant, linkers, and a 6× histidine tag. Physicochemical analysis showed a molecular weight of 36.43 kDa, pI 6.97, instability index 31.79, aliphatic index 64.88, and GRAVY −0.509, indicating stability and hydrophilicity. Structural modeling validated 82.5% residues in favored regions. Molecular docking revealed strong binding with TLR4 (−9.7 kcal/mol) and TLR9 (−9.4 kcal/mol), and 200 ns molecular dynamics simulations confirmed stable RMSD trajectories, low RMSF at binding residues (<4 Å), persistent hydrogen bonding, compact radius of gyration (38–42 Å for TLR4; ~20 Å for TLR9), favorable total energy (−1400 to −1500 kcal/mol for TLR4; −650 to −720 kcal/mol for TLR9), and stable SASA (~52,000–54,000 Å²). Conclusions: These findings demonstrate that the FKBP10 multi-epitope vaccine is structurally stable, immunogenic, and capable of engaging key innate immune receptors, supporting its potential as a promising immunotherapeutic candidate for synovial sarcoma. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Figure 1

Review

Jump to: Research, Other

43 pages, 3484 KB

Open AccessReview

AI in Drug Discovery: Clinical Failures, Regulatory Reality, and the Validation Crisis Behind the Hype

by Lisa Khairil, Koay Hean Seng Benny, Jesreena Jerry, Farhat Mussa Khatib, Muhammad Danial Che Ramli and Suresh Kumar

Pharmaceuticals 2026, 19(6), 916; https://doi.org/10.3390/ph19060916 - 10 Jun 2026

Viewed by 1662

Abstract

The integration of artificial intelligence (AI) into the life sciences has accelerated significantly between 2022 and 2026, accompanied by global investment exceeding USD 100 billion and widespread expectations of a transformative impact in drug discovery. Despite these advances, the extent to which AI has improved clinical outcomes remains unclear. This study presents a structured narrative review evaluating the economic, technical, clinical, and regulatory dimensions of AI adoption in drug discovery. Current evidence indicates that clinical attrition rates remain high, with approximately 90% of drug candidates entering clinical development failing to achieve regulatory approval. Although AI systems such as AlphaFold have achieved high structural prediction accuracy, with predicted local distance difference test (pLDDT) scores exceeding 90 for well-structured proteins and root mean square deviation (RMSD) values comparable to experimental methods, limitations persist in modelling protein dynamics, post-translational modifications, and protein–ligand interactions. Clinical case studies demonstrate that while AI can accelerate early-stage discovery timelines, these advantages do not consistently translate into improved late-stage success rates. Furthermore, reproducibility challenges, limited data transparency, and regulatory gaps continue to constrain reliable implementation. These findings suggest that AI in drug discovery is currently in a transitional phase characterised by high investment but limited validated clinical impact. Future progress will depend on strengthening validation frameworks, improving data sharing practices, and aligning regulatory standards with real-world clinical performance. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Graphical abstract

32 pages, 2147 KB

Open AccessReview

Harnessing Machine Learning for Accelerated Drug Discovery: Opportunities and Unmet Challenges

by Mohamed El-Tanani, Syed Arman Rabbani, Adil Farooq Wali, Frezah Muhana, Yahia El-Tanani and Rakesh Kumar

Pharmaceuticals 2026, 19(6), 810; https://doi.org/10.3390/ph19060810 - 22 May 2026

Cited by 1 | Viewed by 844

Abstract

The process of drug discovery is one of the most expensive, time-consuming, and high-risk endeavors in modern science. Translating initial scientific insights into safe and effective therapies, supported by genomics, structural biology, and computational chemistry, typically requires more than a decade and substantial financial investment. Machine learning (ML) has emerged as a powerful tool for improving efficiency across the drug discovery pipeline. By enabling the analysis of large and complex datasets, ML supports target identification, lead discovery, optimization, and prediction of preclinical and clinical outcomes. Its integration with experimental validation and automation is illustrated by recent advances such as protein structure prediction, AI-driven antifibrotic compound discovery, and antibiotic identification. Despite these advances, significant challenges remain. Model generalizability is limited by data scarcity, heterogeneity, and hidden biases. In addition, the translation of in silico predictions into clinically validated outcomes remains a major bottleneck, and regulatory acceptance is constrained by limited model interpretability. Ethical considerations, including data privacy, equitable representation, and the potential misuse of generative models, further complicate adoption. This review examines the applications of ML across the drug discovery pipeline, with a focus on translational and regulatory considerations. It also discusses emerging directions, including hybrid physics–AI approaches, multimodal foundation models, federated learning, and explainable AI. The effective integration of ML will depend on rigorous validation, interdisciplinary collaboration, responsible data governance, and alignment with regulatory frameworks. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Graphical abstract

47 pages, 8017 KB

Open AccessReview

From Algorithms to Assets: A Comprehensive Review of AI’s Role in Preclinical Drug Discovery and the Hurdles to Clinical Translation

by Mengqi Cai and Tiancai Liu

Pharmaceuticals 2026, 19(5), 696; https://doi.org/10.3390/ph19050696 - 28 Apr 2026

Viewed by 2564

Abstract

The integration of artificial intelligence (AI) and big data is poised to significantly augment drug research and development, offering the potential to address persistent challenges such as lengthy timelines and high failure rates. This review provides a critical overview of AI applications across the preclinical drug discovery pipeline (the 2020–2026 literature), covering drug–target interaction prediction, structure prediction, de novo design, virtual screening, drug repurposing, and ADMET forecasting. Beyond surveying technical developments, we critically discuss key translational hurdles, including data quality, model interpretability, patient heterogeneity, and regulatory adaptation, and provide structured summaries of representative models. We conclude by outlining future directions, such as multimodal AI, digital twins, and closed-loop automation, that aim to bridge the gap between computational prediction and clinical application. This review aims to inform researchers and accelerate the delivery of safe and effective therapies. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Figure 1

Other

Jump to: Research, Review

25 pages, 814 KB

Open AccessSystematic Review

Advances in Biosimilars: A Systematic Review of Machine Learning Applications

by Vannessa Duarte and Tomas Gabriel Bas

Pharmaceuticals 2026, 19(5), 745; https://doi.org/10.3390/ph19050745 - 8 May 2026

Viewed by 721

Abstract

Background/Objectives: Biosimilars are medicinal products derived from reference biologics and designed to demonstrate a high degree of similarity in quality, efficacy, safety, and immunogenicity. Machine learning (ML) and other artificial intelligence (AI) methodologies have emerged as important tools in this field in biosimilar research and development. This systematic review identifies ML applications throughout the biosimilar lifecycle while distinguishing them from the broader AI literature and from health technology evaluation, economic, and decision-analytic studies. Methods: Following PRISMA, records were retrieved from Scopus, PubMed, and Web of Science. After applying predefined inclusion and exclusion criteria, 44 original peer-reviewed studies were selected. Only studies that implemented a data-driven ML method for a biosimilar-relevant problem were included. Results: The review mapped AI applications at different stages of biosimilar development and characterized emerging trends and the types of methods used at each stage. Evidence indicates that the most mature empirical ML applications are concentrated in manufacturing optimization and analytical comparability, where supervised learning, ensemble models, and neural networks support process control, glycan or spectral analysis, and similarity assessment. By contrast, biosimilar-specific ML applications in clinical prediction and pharmacovigilance remain comparatively limited. Conclusions: These advances support the mission of biosimilars to provide affordable and high-quality biologic therapies. Using ML, developers can reduce timelines, reduce costs, and strengthen safety and efficacy assessments through the analysis of complex datasets that are difficult to address with traditional approaches. The main contribution of this review is to provide a clearer map of methodological maturity, translational relevance, and future opportunities for data-driven biosimilar development. Full article

(This article belongs to the Special Issue Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs)

► Show Figures

Journal Menu

Journal Browser

Artificial Intelligence: New Molecules, Therapeutic Targets and Discovery of New Drugs

Share This Special Issue

Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (9 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI