Miquel Duran-Frigola
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Miquel Duran-Frigola has a total of 233 co-authors. Here are the top co-authors by number of shared publications:
- Patrick Aloy
Institute for Research in Biomedicine (IRB Barcelona), The Barcelona Institute of Science and Technology, Barcelona, Catalonia, Spain
18 shared publications Gemma Turon
9 shared publicationsMartino Bertoni
Joint IRB-BSC-CRG Programme in Computational Biology, Institute for Research in Biomedicine (IRB Barcelona), The Barcelona Institute of Science and Technology, Barcelona, Catalonia, Spain
9 shared publicationsEduardo Pauls
Joint IRB-BSC-CRG Programme in Computational Biology, Institute for Research in Biomedicine (IRB Barcelona), The Barcelona Institute of Science and Technology, Barcelona, Spain
8 shared publicationsOriol Guitart-Pla
Joint IRB-BSC-CRG Programme in Computational Biology, Institute for Research in Biomedicine (IRB Barcelona), The Barcelona Institute of Science and Technology, Barcelona, Spain
8 shared publications- Gemma Turon
Ersilia Open Source Initiative
7 shared publications
Latest Publications
- Open Access
- 7 August 2026
- Published by American Chemical Society (ACS) in Journal of Medicinal Chemistry
- Vol. 69 (16) , 19593-19600
Bridging the AI Divide in Drug Discovery: Practical Lessons from Capacity Strengthening in Africa
Artificial Intelligence (AI) has become an integral part of drug discovery in high-income countries. However, these advances have yet to be broadly adopted by research ecosystems in many low- and middle-income countries in Africa, where understudied infectious diseases, compounded by a growing noncommunicable disease burden, cause millions of deaths each year. Given adequate support and appropriate models AI could play a transformative role in under-resourced biomedical research ecosystems in Africa, democratizing drug discovery research. There is an urgent need to invest in building the critical infrastructure, tools, and capacity required. To drive this agenda forward, Ersilia, the H3D Centre, and H3D Foundation with support from the AI2050 program at Schmidt Sciences hosted a series of in-person and online workshops in Africa to grow the AI skills base for medicinal chemistry and enable adoption across regional research hubs. In this perspective article, we discuss the lessons learnt from this program, the fit-for-purpose open-source tools developed, and key considerations for future initiatives.
- 7 August 2026
- Published by American Chemical Society (ACS) in Journal of Medicinal Chemistry
- Vol. 69 (16) , 19593-19600
Open AccessBridging the AI Divide in Drug Discovery: Practical Lessons from Capacity Strengthening in Africa
Artificial Intelligence (AI) has become an integral part of drug discovery in high-income countries. However, these advances have yet to be broadly adopted by research ecosystems in many low- and middle-income countries in Africa, where understudied infectious diseases, compounded by a growing noncommunicable disease burden, cause millions of deaths each year. Given adequate support and appropriate models AI could play a transformative role in under-resourced biomedical research ecosystems in Africa, democratizing drug discovery research. There is an urgent need to invest in building the critical infrastructure, tools, and capacity required. To drive this agenda forward, Ersilia, the H3D Centre, and H3D Foundation with support from the AI2050 program at Schmidt Sciences hosted a series of in-person and online workshops in Africa to grow the AI skills base for medicinal chemistry and enable adoption across regional research hubs. In this perspective article, we discuss the lessons learnt from this program, the fit-for-purpose open-source tools developed, and key considerations for future initiatives.
- Open Access
- 20 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-12
Artificial intelligence coupled to pharmacometrics modelling to tailor malaria and tuberculosis treatment in Africa
Africa’s vast genetic diversity poses challenges for optimising drug treatments in the continent, which is exacerbated by the fact that drug discovery and development efforts have historically been performed outside Africa. This has led to suboptimal therapeutic outcomes in African populations and overall scarcity of relevant pharmacogenetic data, including characteristic genotypes as well as drugs prescribed in the continent to treat infectious diseases. Here, we propose a general approach to identify drug-gene pairs with potential pharmacogenetic interest. Our pipeline couples machine learning and artificial intelligence with physiologically-based pharmacokinetic (PBPK) and non-linear mixed effects (NLME) modelling to hypothesize which pharmacogenes could be of potential clinical interest, and which dose adjustments could be made to provide better treatment outcomes for African populations. Drug-gene pairs are first ranked with the latest knowledge embedding techniques, based on public structural and bioactivity data for drugs and genes, followed by a large language model-based refinement. Selected genes are then evaluated for their sensitivity in PBPK analysis, and relevant variants subsequently inspected with NLME for dose optimization. The analysis is focused on genes with potential clinical relevance in Africa. We delve deeper into malaria and tuberculosis therapies, many of which remain uncharacterised from a pharmacogenetic perspective.
- 20 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-12
Open AccessArtificial intelligence coupled to pharmacometrics modelling to tailor malaria and tuberculosis treatment in Africa
Africa’s vast genetic diversity poses challenges for optimising drug treatments in the continent, which is exacerbated by the fact that drug discovery and development efforts have historically been performed outside Africa. This has led to suboptimal therapeutic outcomes in African populations and overall scarcity of relevant pharmacogenetic data, including characteristic genotypes as well as drugs prescribed in the continent to treat infectious diseases. Here, we propose a general approach to identify drug-gene pairs with potential pharmacogenetic interest. Our pipeline couples machine learning and artificial intelligence with physiologically-based pharmacokinetic (PBPK) and non-linear mixed effects (NLME) modelling to hypothesize which pharmacogenes could be of potential clinical interest, and which dose adjustments could be made to provide better treatment outcomes for African populations. Drug-gene pairs are first ranked with the latest knowledge embedding techniques, based on public structural and bioactivity data for drugs and genes, followed by a large language model-based refinement. Selected genes are then evaluated for their sensitivity in PBPK analysis, and relevant variants subsequently inspected with NLME for dose optimization. The analysis is focused on genes with potential clinical relevance in Africa. We delve deeper into malaria and tuberculosis therapies, many of which remain uncharacterised from a pharmacogenetic perspective.
- Top Cited PapersOpen Access
- 15 February 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-23
Learning and actioning general principles of cancer cell drug sensitivity
High-throughput screening of drug sensitivity of cancer cell lines (CCLs) holds the potential to unlock anti-tumor therapies. In this study, we leverage such datasets to predict drug response using cell line transcriptomics, focusing on models’ interpretability and deployment on patients’ data. We use large language models (LLMs) to match drug to mechanisms of action (MOA)-related pathways. Genes crucial for prediction are enriched in drug-MOAs, suggesting that our models learn the molecular determinants of response. Furthermore, by using only LLM-curated, MOA-genes, we enhance the predictive accuracy of our models. To enhance translatability, we align RNAseq data from CCLs, used for training, to those from patient samples, used for inference. We validated our approach on TCGA samples, where patients’ best scoring drugs match those prescribed for their cancer type. We further predict and experimentally validate effective drugs for the patients of two highly lethal solid tumors, i.e., pancreatic cancer and glioblastoma.
- 15 February 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-23
Top Cited PapersOpen AccessLearning and actioning general principles of cancer cell drug sensitivity
High-throughput screening of drug sensitivity of cancer cell lines (CCLs) holds the potential to unlock anti-tumor therapies. In this study, we leverage such datasets to predict drug response using cell line transcriptomics, focusing on models’ interpretability and deployment on patients’ data. We use large language models (LLMs) to match drug to mechanisms of action (MOA)-related pathways. Genes crucial for prediction are enriched in drug-MOAs, suggesting that our models learn the molecular determinants of response. Furthermore, by using only LLM-curated, MOA-genes, we enhance the predictive accuracy of our models. To enhance translatability, we align RNAseq data from CCLs, used for training, to those from patient samples, used for inference. We validated our approach on TCGA samples, where patients’ best scoring drugs match those prescribed for their cancer type. We further predict and experimentally validate effective drugs for the patients of two highly lethal solid tumors, i.e., pancreatic cancer and glioblastoma.
- Open Access
- 5 December 2024
- Published by Elsevier in Artificial Intelligence in the Life Sciences
- Vol. 7
The path to adoption of open source AI for drug discovery in Africa
- 5 December 2024
- Published by Elsevier in Artificial Intelligence in the Life Sciences
- Vol. 7
Open AccessThe path to adoption of open source AI for drug discovery in Africa
- Open Access
- 23 November 2024
- Published by Wiley in Molecular Informatics
- Vol. 44 (1) , e202400293
The Chemical Space Spanned by Manually Curated Datasets of Natural and Synthetic Compounds with Activities against SARS‐CoV‐2
Diseases caused by viruses are challenging to contain, as their outbreak and spread could be very sudden, compounded by rapid mutations, making the development of drugs and vaccines a continued endeavour that requires fast discovery and preparedness. Targeting viral infections with small molecules remains one of the treatment options to reduce transmission and the disease burden. A lesson learned from the recent coronavirus disease (COVID‐19) is to collect ready‐to‐screen small molecule libraries in preparation for the next viral outbreak, and potentially find a clinical candidate before it becomes a pandemic. Public availability of diverse compound libraries, well annotated in terms of chemical structures and scaffolds, modes of action, and bioactivities are, therefore, crucial to ensure the participation of academic laboratories in these screening efforts, especially in resource‐limited settings where synthesis, testing and computing capacity are scarce. Here, we demonstrate a low‐resource approach to populate the chemical space of naturally occurring and synthetic small molecules that have shown in vitro and/or in vivo activities against the severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) and its target proteins. We have manually curated two datasets of small molecules (naturally occurring and synthetically derived) by reading and collecting (hand‐curating) the published literature. Information from the literature reveals that a majority of the reported SARS‐CoV‐2 compounds act by inhibiting the main protease, while 25% of the compounds currently have no known target. Scaffold analysis and principal component analysis revealed that the most common scaffolds in the datasets are quite distinct. We then expanded the initially manually curated dataset of over 1200 compounds via an ultra‐large scale 2D and 3D similarity search, obtaining an expanded collection of over 150 k purchasable compounds. The spanned chemical space significantly extends beyond that of a commercially available coronavirus library of more than 20 k small molecules and constitutes a good starting collection for virtual screening campaigns given its manageable size and proximity to hand‐curated compounds.
- 23 November 2024
- Published by Wiley in Molecular Informatics
- Vol. 44 (1) , e202400293
Open AccessThe Chemical Space Spanned by Manually Curated Datasets of Natural and Synthetic Compounds with Activities against SARS‐CoV‐2
Diseases caused by viruses are challenging to contain, as their outbreak and spread could be very sudden, compounded by rapid mutations, making the development of drugs and vaccines a continued endeavour that requires fast discovery and preparedness. Targeting viral infections with small molecules remains one of the treatment options to reduce transmission and the disease burden. A lesson learned from the recent coronavirus disease (COVID‐19) is to collect ready‐to‐screen small molecule libraries in preparation for the next viral outbreak, and potentially find a clinical candidate before it becomes a pandemic. Public availability of diverse compound libraries, well annotated in terms of chemical structures and scaffolds, modes of action, and bioactivities are, therefore, crucial to ensure the participation of academic laboratories in these screening efforts, especially in resource‐limited settings where synthesis, testing and computing capacity are scarce. Here, we demonstrate a low‐resource approach to populate the chemical space of naturally occurring and synthetic small molecules that have shown in vitro and/or in vivo activities against the severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) and its target proteins. We have manually curated two datasets of small molecules (naturally occurring and synthetically derived) by reading and collecting (hand‐curating) the published literature. Information from the literature reveals that a majority of the reported SARS‐CoV‐2 compounds act by inhibiting the main protease, while 25% of the compounds currently have no known target. Scaffold analysis and principal component analysis revealed that the most common scaffolds in the datasets are quite distinct. We then expanded the initially manually curated dataset of over 1200 compounds via an ultra‐large scale 2D and 3D similarity search, obtaining an expanded collection of over 150 k purchasable compounds. The spanned chemical space significantly extends beyond that of a commercially available coronavirus library of more than 20 k small molecules and constitutes a good starting collection for virtual screening campaigns given its manageable size and proximity to hand‐curated compounds.
- Open Access
AI coupled to pharmacometric modelling to tailor malaria and tuberculosis treatment in Africa
Africa’s vast genetic diversity poses challenges for optimising drug treatments in the continent, which is exacerbated by the fact that drug discovery and development efforts have historically been performed outside Africa. This has led to suboptimal therapeutic outcomes in African populations and overall scarcity of relevant pharmacogenetic data, including characteristic genotypes as well as drugs prescribed in the continent to treat infectious diseases. Here, we propose a general approach to identify drug-gene pairs with potential pharmacogenetic interest. Furthermore, we delve deeper into the analysis of malaria and tuberculosis therapies, many of which remain uncharacterised from a pharmacogenetic perspective. Our pipeline leverages artificial intelligence and the latest advances in knowledge embedding techniques to exploit currently available biomedical data and subsequently prioritise pharmacogenes for each drug. Predicted pharmacogenes are then incorporated into pharmacometric modelling to hypothesise which ones might be of clinical interest, and which dose adjustments could be made to provide better treatment outcomes for the African population.
Open AccessAI coupled to pharmacometric modelling to tailor malaria and tuberculosis treatment in Africa
Africa’s vast genetic diversity poses challenges for optimising drug treatments in the continent, which is exacerbated by the fact that drug discovery and development efforts have historically been performed outside Africa. This has led to suboptimal therapeutic outcomes in African populations and overall scarcity of relevant pharmacogenetic data, including characteristic genotypes as well as drugs prescribed in the continent to treat infectious diseases. Here, we propose a general approach to identify drug-gene pairs with potential pharmacogenetic interest. Furthermore, we delve deeper into the analysis of malaria and tuberculosis therapies, many of which remain uncharacterised from a pharmacogenetic perspective. Our pipeline leverages artificial intelligence and the latest advances in knowledge embedding techniques to exploit currently available biomedical data and subsequently prioritise pharmacogenes for each drug. Predicted pharmacogenes are then incorporated into pharmacometric modelling to hypothesise which ones might be of clinical interest, and which dose adjustments could be made to provide better treatment outcomes for the African population.
- 2 August 2024
- Published by American Chemical Society (ACS) in ACS Infectious Diseases
- Vol. 10 (9) , 3083-3085
Infectious Disease Research Laboratories in Africa Are Not Using AI Yet─Large Language Models May Facilitate Adoption
- 2 August 2024
- Published by American Chemical Society (ACS) in ACS Infectious Diseases
- Vol. 10 (9) , 3083-3085
Infectious Disease Research Laboratories in Africa Are Not Using AI Yet─Large Language Models May Facilitate Adoption
- 1 August 2024
- Published by American Chemical Society (ACS) in ACS Medicinal Chemistry Letters
- Vol. 15 (9) , 1645-1650
Open Source Code Contributions to Global Health: The Case of Antimalarial Drug Discovery
The discovery of treatments for infectious diseases that affect the poorest countries has been stagnant for decades. As long as expected returns on investment remain low, pharmaceutical companies' lack of interest in this disease area must be compensated for with collaborative efforts from the public sector. New approaches to drug discovery, inspired by the "open source" philosophy prevalent in software development, offer a platform for experts from diverse backgrounds to contribute their skills, enhancing reproducibility, progress tracking, and public discussion. Here, we present the first efforts of Ersilia, an initiative focused on attracting data scientists into contributing to global health, toward meeting the goals of Open Source Malaria, a consortium of medicinal chemists investigating antimalarial compounds using a purely open science approach. We showcase the chemical space exploration of a set of triazolopyrazine compounds with potent antiplasmodial activity and discuss how open source practices can serve as a common ground to make drug discovery more inclusive and participative.
- 1 August 2024
- Published by American Chemical Society (ACS) in ACS Medicinal Chemistry Letters
- Vol. 15 (9) , 1645-1650
Open Source Code Contributions to Global Health: The Case of Antimalarial Drug Discovery
The discovery of treatments for infectious diseases that affect the poorest countries has been stagnant for decades. As long as expected returns on investment remain low, pharmaceutical companies' lack of interest in this disease area must be compensated for with collaborative efforts from the public sector. New approaches to drug discovery, inspired by the "open source" philosophy prevalent in software development, offer a platform for experts from diverse backgrounds to contribute their skills, enhancing reproducibility, progress tracking, and public discussion. Here, we present the first efforts of Ersilia, an initiative focused on attracting data scientists into contributing to global health, toward meeting the goals of Open Source Malaria, a consortium of medicinal chemists investigating antimalarial compounds using a purely open science approach. We showcase the chemical space exploration of a set of triazolopyrazine compounds with potent antiplasmodial activity and discuss how open source practices can serve as a common ground to make drug discovery more inclusive and participative.
- Top Cited Papers
- 26 April 2024
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 384 (6694) , eadk5864
Large-scale chemoproteomics expedites ligand discovery and predicts ligand behavior in cells
Chemical modulation of proteins enables a mechanistic understanding of biology and represents the foundation of most therapeutics. However, despite decades of research, 80% of the human proteome lacks functional ligands. Chemical proteomics has advanced fragment-based ligand discovery toward cellular systems, but throughput limitations have stymied the scalable identification of fragment-protein interactions. We report proteome-wide maps of protein-binding propensity for 407 structurally diverse small-molecule fragments. We verified that identified interactions can be advanced to active chemical probes of E3 ubiquitin ligases, transporters, and kinases. Integrating machine learning binary classifiers further enabled interpretable predictions of fragment behavior in cells. The resulting resource of fragment-protein interactions and predictive models will help to elucidate principles of molecular recognition and expedite ligand discovery efforts for hitherto undrugged proteins.
- 26 April 2024
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 384 (6694) , eadk5864
Top Cited PapersLarge-scale chemoproteomics expedites ligand discovery and predicts ligand behavior in cells
Chemical modulation of proteins enables a mechanistic understanding of biology and represents the foundation of most therapeutics. However, despite decades of research, 80% of the human proteome lacks functional ligands. Chemical proteomics has advanced fragment-based ligand discovery toward cellular systems, but throughput limitations have stymied the scalable identification of fragment-protein interactions. We report proteome-wide maps of protein-binding propensity for 407 structurally diverse small-molecule fragments. We verified that identified interactions can be advanced to active chemical probes of E3 ubiquitin ligases, transporters, and kinases. Integrating machine learning binary classifiers further enabled interpretable predictions of fragment behavior in cells. The resulting resource of fragment-protein interactions and predictive models will help to elucidate principles of molecular recognition and expedite ligand discovery efforts for hitherto undrugged proteins.
- 9 April 2024
- Published by Springer Nature in Nature
- Vol. 628 (8007) , 265-267
AI can help to tailor drugs for Africa — but Africans should lead the way
- 9 April 2024
- Published by Springer Nature in Nature
- Vol. 628 (8007) , 265-267
AI can help to tailor drugs for Africa — but Africans should lead the way