2. Academic Validation
  3. DrugAppy - An end-to-end deep learning framework for computational drug discovery

DrugAppy - An end-to-end deep learning framework for computational drug discovery

  • Comput Biol Med. 2025 Oct 18;198(Pt B):111201. doi: 10.1016/j.compbiomed.2025.111201.
Elisa Poyatos-Racionero 1,  Lucía Paniagua-Herranz 2,  Cristian Privat 1,  Carmen Martín-Hernández 3,  Cristina Nieto-Jiménez 2,  Cristina Herrero-Igartua 3,  Ramón García-Escudero 4,  Pawel Gancarski 1,  Corina Lorz 5,  Alberto Ocana 6
Affiliations

Affiliations

  • 1 Cancerappy S.L., 48950, Erandio, Biscay, Spain.
  • 2 Experimental Therapeutics in Cancer Unit, Instituto de Investigación Sanitaria San Carlos (IdISSC), Madrid, Spain.
  • 3 Biomedical Oncology Unit, CIEMAT (ed 70A), Ave Complutense 40, 28040, Madrid, Spain; Research Institute 12 de Octubre i+12, University Hospital 12 de Octubre, Ave Córdoba s/n, 28041, Madrid, Spain.
  • 4 Biomedical Oncology Unit, CIEMAT (ed 70A), Ave Complutense 40, 28040, Madrid, Spain; Research Institute 12 de Octubre i+12, University Hospital 12 de Octubre, Ave Córdoba s/n, 28041, Madrid, Spain; Centro de Investigación Biomédica en Red de Cáncer (CIBERONC), Ave Monforte de Lemos 3-5, 28029, Madrid, Spain.
  • 5 Biomedical Oncology Unit, CIEMAT (ed 70A), Ave Complutense 40, 28040, Madrid, Spain; Research Institute 12 de Octubre i+12, University Hospital 12 de Octubre, Ave Córdoba s/n, 28041, Madrid, Spain; Centro de Investigación Biomédica en Red de Cáncer (CIBERONC), Ave Monforte de Lemos 3-5, 28029, Madrid, Spain. Electronic address: clorz@ciemat.es.
  • 6 Experimental Therapeutics in Cancer Unit, Instituto de Investigación Sanitaria San Carlos (IdISSC), Madrid, Spain; Medical Oncology Department, Hospital Clínico Universitario San Carlos, Instituto de Investigación Sanitaria San Carlos (IdISSC), and CIBERONC, Madrid, Spain; START Madrid-Fundación Jiménez Díaz (FJD) Early Phase Program, Fundación Jiménez Díaz Hospital, Madrid, Spain. Electronic address: alberto.ocana@salud.madrid.org.
PMID: 41110298 DOI: 10.1016/j.compbiomed.2025.111201
Abstract

Identification of druggable oncogenic vulnerabilities and the design of novel chemical entities against them is crucial in Cancer research due to the limited curative options for some advanced cancers. However, the drug design process is costly and time-consuming. As a result, the use of computational tools to accelerate and optimize this process is a promising approach. We present DrugAppy, a computational tool for the identification of inhibitors, built on a hybrid model that combines Artificial Intelligence (AI) algorithms and computational and medicinal chemistry methodologies using an imbrication of models such as SMINA and GNINA for High Throughput Virtual Screening (HTVS) and GROMACS for Molecular Dynamics (MD). Additionally, the prediction of key parameters such as drug pharmacokinetics, selectivity, and potential activity was conducted using both publicly available models and proprietary artificial intelligence models trained on public datasets. We validated DrugAppy through two case studies targeting Poly(ADP-ribose) polymerase (PARP) and the transcriptional enhanced associate domain (TEAD) family of proteins. Using the methodology outlined, several molecules have been identified that either match or surpass the in vitro activity of current inhibitors. For PARP1, two molecules were found with activity comparable to olaparib. For TEAD4, a compound was identified that outperforms the activity of IK-930, the reference inhibitor for this target. In this work, we demonstrate how the workflow can be effectively used to discover novel molecular structures, using the protein families PARP and TEAD as case studies. For each target, one active compound has been identified and confirmed for target engagement that matches the reference inhibitor.

Keywords

And cancer; Artificial intelligence; Drug design; Medicinal chemistry.

Figures
Products