applsci-logo

Journal Browser

Journal Browser

Computational Approaches to the Discovery and Design of Pharmaceutical Drugs

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Biomedical Engineering".

Deadline for manuscript submissions: 20 February 2026 | Viewed by 530

Special Issue Editors


E-Mail Website
Guest Editor
Departamento de Farmacia, Universidad Cardenal Herrera-CEU, CEU Universities C/Ramón y Cajal s/n, 46115 Alfara del Patriarca, Valencia, Spain
Interests: quantitative structure–activity relationship; molecular topology; drug discovery
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Departamento de Farmacia, Universidad Cardenal Herrera-CEU, CEU Universities C/Ramón y Cajal s/n, 46115 Alfara del Patriarca, Valencia, Spain
Interests: antibacterials; antibiotics; computational chemistry; linear discriminant analysis; molecular topology; molecular connectivity; topological indices; quinolones; QSAR; drug repurposing; drug development; escherichia coli; anti-mrsa
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In molecular science, there is currently a vital and ongoing need for multidisciplinary collaboration between experimentalists and theoretical scientists from different fields. One of the more important forces driving this need is the accumulation of large amounts of data in the form of results from important advances in cheminformatics. Computational modelling is becoming increasingly important in biomedical research for understanding how biomolecules interact. In medicine, computational methods are fundamental for the discovery of drugs due to their range of uses in the collection, processing, analysis, and modelling of data. Drug design is a multi-objective process in which various characteristics, such as efficacy, pharmacokinetics, and safety, are optimized.

Since the introduction of quantitative structure–activity relationships (QSARs) in the 1960s, when the biological activities of molecules (potential drugs) were first modelled, the application of this methodology has extended to modelling a number of the physicochemical properties of molecules (QSPR). Initially, these models started as small sets of molecules that had a limited number of easily interpretable molecular descriptors. At present, QSAR/QSPR models have become a well-established field of scientific research and present the complex relationships between input descriptors and between the input descriptors and a modelled activity/property. In addition, numerous biological, physicochemical, or pharmacokinetic effects of molecules have been modelled, meaning that the QSAR/QSPR methodology is applied to detect predictive relationships between molecular structure and pharmacological activities, toxicological properties, and the adverse effects of molecules on public health.

In the proposed Special Issue, we aim to cover aspects connected to the improvement of QSAR/QSPR methodology and perform comparative studies of cheminformatic softwares or in silico modelling methods. Authors are also invited to pay attention to the applications of QSAR/QSPR methodology or different problems related to regression or classification endpoints in drug design within chemical, pharmaceutical, biotechnological or environmental sciences.

Dr. Jose Ignacio Bueso-Bordils
Dr. Pedro A. Alemán-López
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 100 words) can be sent to the Editorial Office for announcement on this website.

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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly 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 2400 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

  • cheminformatics
  • data mining
  • drug discovery
  • drug design
  • graph theory
  • molecular descriptors
  • QSAR/QSPR modelling
  • biological activity
  • physicochemical property
  • pharmacokinetic property

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 (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

14 pages, 881 KiB  
Article
Fine-Tuning BiomedBERT with LoRA and Pseudo-Labeling for Accurate Drug–Drug Interactions Classification
by Ioan-Flaviu Gheorghita, Vlad-Ioan Bocanet and Laszlo Barna Iantovics
Appl. Sci. 2025, 15(15), 8653; https://doi.org/10.3390/app15158653 - 5 Aug 2025
Viewed by 201
Abstract
In clinical decision support systems (CDSSs), where accurate classification of drug–drug interactions (DDIs) can directly affect treatment safety and outcomes, identifying drug interactions is a major challenge, introducing a scalable approach for classifying DDIs utilizing a finely-tuned biomedical language model. The method shown [...] Read more.
In clinical decision support systems (CDSSs), where accurate classification of drug–drug interactions (DDIs) can directly affect treatment safety and outcomes, identifying drug interactions is a major challenge, introducing a scalable approach for classifying DDIs utilizing a finely-tuned biomedical language model. The method shown here uses BiomedBERT, a domain-specific version of bidirectional encoder representations from transformers (BERT) that was pre-trained on biomedical literature, to reduce the number of resources needed during fine-tuning. Low-rank adaptation (LoRA) was used to fine-tune the model on the DrugBank dataset. The objective was to classify DDIs into two clinically distinct categories, that is, synergistic and antagonistic interactions. A pseudo-labeling strategy was created to deal with the problem of not having enough labeled data. A curated ground-truth dataset was constructed using polarity-labeled interaction entries from DrugComb and verified DrugBank antagonism pairs. The fine-tuned model is used to figure out what kinds of interactions there are in the rest of the unlabeled data. A checkpointing system saves predictions and confidence scores in small pieces, which means that the process can be continued and is not affected by system crashes. The framework is designed to log every prediction it makes, allowing results to be refined later, either manually or through automated updates, without discarding low-confidence cases, as traditional threshold-based methods often do. The method keeps a record of every output it generates, making it easier to revisit earlier predictions, either by experts or with improved tools, without depending on preset confidence cutoffs. It was built with efficiency in mind, so it can handle large amounts of biomedical text without heavy computational demands. Rather than focusing on model novelty, this research demonstrates how existing biomedical transformers can be adapted to polarity-aware DDI classification with minimal computational overhead, emphasizing deployment feasibility and clinical relevance. Full article
Show Figures

Figure 1

Back to TopTop