Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

De novo design of protein-protein interactions modulators

  • González-García, Eduardo
  • Ulzurrun, Eugenia
  • Miró, Celia
  • Muñoz-Reyes, Daniel
  • Pérez-Suárez, Sara
  • Sánchez-Barrena, María José
  • Naveiro Flores, Roi
  • Campillo, Nuria E.
1 p.-4 fig.-1 tab., The process of drug development is inherently lengthy and costly, often taking over a decade and requiring substantial financial investment. Deep learning models offer a promising solution by enhancing both the exploration of the chemical space with generative models and the identification of potential drug candidates with property predictors. This work focuses on generating modulators of protein-protein interactions (PPIs), which are important therapeutic targets due to their central role in numerous biological processes and their potential in treating various diseases. We present a comprehensive framework for the de novo generation of PPI modulators, structured around three main pillars. First, we employ a diverse set of state-of-the-art molecular generators to effectively explore the chemical space, ensuring a wide range of molecular diversity. Second, we adapt existing research to develop a novel PPI bioactivity regressor, designed to predict the affinity of molecules to specific PPIs. This regressor guides the generative process toward compounds with high therapeutic potential. Third, we incorporate various auxiliary property filters, focusing on predicting toxicity, blood-brain barrier penetration capability, drug-likeness, synthetic accessibility, molecular similarity to known compounds, and the binding affinity to specific protein pockets. These filters are essential for eliminating low-quality compounds and refining the selection of viable candidates. This framework is applied to generate modulators for two specific PPIs, NCS-1/Ric8A and NCS- 1/D2R. The resulting compounds are compiled into two virtual chemical libraries, which are currently undergoing further testing to identify new and effective modulators. This work highlights the potential of deep learning in drug discovery and proposes a robust methodology for developing targeted PPI modulators., This research work was funded by “Proyectos de Generación de Conocimiento 2022”(PID2022-137331OB-C33), Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

FDA Drug Repurposing Uncovers Modulators of Dopamine D2 Receptor Localization via Disruption of the NCS-1 Interaction

  • Muñoz-Reyes, Daniel
  • Aguado, Lorena
  • Arroyo-Urea, Sandra
  • Requena, Carlos
  • Pérez-Suárez, Sara
  • Sánchez-Yepes, Sonia
  • Argerich, Josep
  • Miró-Rodríguez, Celia
  • Ulzurrun, Eugenia
  • Rodríguez-Martín, Eulalia
  • García-Nafría, Javier
  • Campillo, Nuria E.
  • Mansilla, Alicia
  • Sánchez-Barrena, María José
Dopamine D2 receptor (D2 R) regulates key aspects of motor control, cognition, and reward. Its function depends not only on ligand binding and signaling efficacy but also on the dynamic control of receptor localization at the cell surface. Neuronal calcium sensor 1 (NCS-1) interacts with D2 R in a Ca2+ -dependent manner. Using in vitro and cellular assays, we found that NCS-1 promotes D2 R trafficking to the plasma membrane through active exocytosis while preserving canonical receptor pharmacology. A screen of FDA-approved drugs identified protein–protein interaction (PPI) modulators targeting the NCS-1/D2 R interface. Azilsartan medoxomil, atorvastatin, and vilazodone disrupt this interaction, reducing D2 R surface expression. Structural studies revealed that these compounds target NCS-1, overlap the D2 R binding site, and perturb the dynamics of the regulatory helix H10. These findings reveal an unexploited intracellular mechanism to modulate D2 R function via PPI modulation, offering a novel strategy to fine-tune dopaminergic tone beyond receptor blockade or direct agonism., This work was supported by grants PID2019-111737RB-I00 and PID2022-137331OB-C31 (to M.J.S.B.); PID2020 113359GA-I00 and PID2023-148739NB-I00 (to J.G.N.);PID2022-137331OB-C32 (to A.M.); PID2022-137331OB-C33 (to N.E.C.); and the Spanish “Ramón y Cajal” program (to J.G.N. and A.M.), which were funded by the MICIU/AEI/ 10.13039/501100011033, FEDER and EU. S.P.S. was supported by a contract from the “Programa de Empleo Juvenil de la Comunidad de Madrid” PEJ-2020-AI/BMD 18666 and CMR by a Spanish National Research Council JAE Intro grant (JAEINT_23_00101)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

MolOrgGPT: De Novo Generation via Large Language Models and Reinforcement Learning

  • Varas Pardo, Pablo
  • Toledano, Oscar
  • Marcos-Ayuso, Guillermo
  • Quesada, David
  • Campillo, Nuria E
We present a general framework for the de novo design of small molecules with desirable chemical properties, developed to aid the creation of novel chemical entities with potential therapeutic use. The system is built upon a foundational Large Language Model trained on a large comprehensive chemical database capable of generating structurally diverse and synthetically accessible compounds. It is then fine-tuned through reinforcement learning to enhance its capacity to generate molecules tailored to specific biological targets. As a case study, we apply this framework to design molecules targeting key proteins involved in Alzheimer's disease. The generated compounds underwent molecular docking studies to assess their binding affinities and prioritize candidates with optimal predicted interactions. The top-ranked molecules were further analyzed based on their binding modes and key molecular interactions with the target proteins. The results suggest that our generative model produces viable, drug-like molecules with favorable interactions, underscoring its potential as a valuable tool in early stage drug discovery., This work was funded by grants PID2022-137331OB-C33 (N.E.C.) and MICIU/AEI/10.13039/501100011033, FEDER and EUandproject TED2021-129970B-C21 (N.E.C.) financed by MCIN/AEI and European Union “NextGenerationEU”/ PRTR, IND2023/BMD-27452 (P.V.P.) financed by CAM, and PTQ2023-012950 (G.M.-A.) financed by MCIU/AEI, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

An AI-based approach accelerates the discovery of protein–protein interaction modulators targeting NCS-1

  • González-García, Eduardo
  • Miró-Rodríguez, Celia
  • Ulzurrun, Eugenia
  • Toledano, Óscar
  • Pérez-Suarez, Sara
  • Aguado, Lorena
  • Sánchez-Barrena, M José
  • Mansilla, Alicia
  • Naveiro, Roi
  • Campillo, Nuria E.
Drug repurposing is an efficient strategy to accelerate the identification of therapeutic compounds by finding new uses for existing drugs. Here, we leveraged artificial intelligence (AI) to optimize this process and discover protein–protein interaction (PPI) modulators targeting the Neuronal Calcium Sensor 1. AI models were trained on large datasets of known PPIs, protein structures, and small molecular graphs to predict binding score. Using virtual screening of an FDA-approved drug library, the models generated a prioritized list of candidates. The most promising compounds were selected for experimental validation. This integrated approach efficiently reduced experimental workload, time, and cost, leading to the identification of dipyridamole as a selective modulator of the interaction between NCS-1 and the dopamine D2 receptor. The crystal structure of NCS-1 in complex with dipyridamole elucidates its mechanism of modulation. Our findings highlight the potential of AI to streamline and accelerate the discovery of novel therapeutic PPI modulators, The work was supported by grants PID2022-137331OB-C31 (to MJSB), PID2022-137331OB-C32 (to AM) and PID2022-137331OB-C33 (to NEC), which were funded by MICIU/AEI/10.13039/501100011033, FEDER and EU. SPS was contracted through project PDC2022-133775 I00/AEI/10.13039/501100011033, co-funded by the European Union Next Generation EU., Peer reviewed, Modelo experimental alternativo-NAM, in silico, in vitro - Tipos celulares - líneas inmortalizadas humanas
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A Multimodal Sequence-to-Sequence Model for Automatic Assignment of ATC Codes in Drug Discovery and Repurposing

  • Crozes, Trinidad
  • Ulzurrun, Eugenia
  • Páez, Juan A.
  • Campillo, Nuria E.
  • Soto, Axel J.
  • Ponzoni, Ignacio
The Anatomical Therapeutic Chemical (ATC) code is a drug classification system that indicates the therapeutic potential use of a compound. Predicting ATC codes for drugs using automatic approaches is key to guide clinical trials and for drug repurposing. However, such automatic assignment is challenging due to the hierarchical organization of the code in four levels, possible polypharmacological behavior, and the imbalance and scarcity of annotated data in relation to the large number of compounds and possible ATC codes a drug may have. In this work, we propose a novel multimodal generative approach for predicting ATC codes, which leverages molecular information using a sequence-to-sequence architecture. Our hypothesis explores the idea that describing the chemical structure of the input compounds using two different representations, i.e., modes, the SMILES code and its molecular descriptors, provides complementary information, hence improving the accuracy of the predictions. Furthermore, given the multilabel nature of generative sequence-based models, we also present an additional prediction method to determine when to stop generating ATC labels for each compound. We compared the performance of our proposed methods against several baselines, both for new drugs and in drug repurposing tasks. In all of these cases, the superior performance of our multimodal proposals is clearly demonstrated. The source code and different data sets used to train and evaluate the models are made publicly available., Thea uthors thank Emilia Bayo for their invaluable support in curating the data fromapreliminary in-house dataset in the past,which ha sbeen instrumental inbuilding ourcurrent data set. This work was partially supported by the Argentinean National Scientific and Technological Research Council (CONICET) [Grants PIP 112-2021-0100600 and PIBAA 2872021010 1236CO], by the National Agency for the Promotion of Research, Technological Development and Innovation of Argentina(AGENCIA), through the Fund for Scientific and Technological Research (FONCyT) [Grants PICT-2019-03350 and PICT-PRH-2021-0008], and by Universidad Nacional del Sur(UNS),Bahía Blanca , Argentina [Grants No. PGI 24/N061 and 24/ZN47] and PID2022137331OB-C33(to N.E.C.),which were funded by MICIU/ AEI/10.13039/501100011033,FEDER, and EU., Peer reviewed
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

FDA Drug Repurposing Uncovers Modulators of Dopamine D<sub>2</sub> Receptor Localization via Disruption of the NCS-1 Interaction

  • Muñoz-Reyes, Daniel
  • Aguado, Lorena
  • Arroyo-Urea, Sandra
  • Requena, Carlos
  • Pérez-Suárez, Sara
  • Sánchez-Yepes, Sonia
  • Argerich, Josep
  • Miró-Rodríguez, Celia
  • Ulzurrun, Eugenia
  • Rodríguez-Martín, Eulalia
  • García-Nafría, Javier
  • Campillo, Nuria E.
  • Mansilla, Alicia
  • Sánchez-Barrena, María José
Dopamine D2 receptor (D2R) regulates key aspects of motor control, cognition, and reward. Its function depends not only on ligand binding and signaling efficacy but also on the dynamic control of receptor localization at the cell surface. Neuronal calcium sensor 1 (NCS-1) interacts with D2R in a Ca2+-dependent manner. Using in vitro and cellular assays, we found that NCS-1 promotes D2R trafficking to the plasma membrane through active exocytosis while preserving canonical receptor pharmacology. A screen of FDA-approved drugs identified protein–protein interaction (PPI) modulators targeting the NCS-1/D2R interface. Azilsartan medoxomil, atorvastatin, and vilazodone disrupt this interaction, reducing D2R surface expression. Structural studies revealed that these compounds target NCS-1, overlap the D2R binding site, and perturb the dynamics of the regulatory helix H10. These findings reveal an unexploited intracellular mechanism to modulate D2R function via PPI modulation, offering a novel strategy to fine-tune dopaminergic tone beyond receptor blockade or direct agonism.