Adrián Bazaga
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Adrián Bazaga has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Hendrik Weisser
Storm Therapeutics Limited, Cambridge, UK
2 shared publications - Adrià de Gispert
Amazon AGI
1 shared publication - Alexis Kalderimis
Department of Genetics, University of Cambridge
1 shared publication - Alfonso Valencia
Barcelona Supercomputing Center
1 shared publication Alfredo Vellido
Universitat Politecnica de Catalunya
1 shared publication- Archie Wise
Department of Genetics, University of Cambridge
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 28014-28033
Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models
Adrián Bazaga, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 28014-28033
Open AccessLearning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models
Adrián Bazaga, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
HumanMine: advanced data searching, analysis and cross-species comparison
HumanMine ( www.humanmine.org ) is an integrated database of human genomics and proteomics data that provides a powerful interface to support sophisticated exploration and analysis of data compiled from experimental, computational and curated data sources. Built using the InterMine data integration platform, HumanMine includes genes, proteins, pathways, expression levels, SNPs, diseases and more, integrated into a single searchable database. HumanMine promotes integrative analysis, a powerful approach in modern biology that allows many sources of evidence to be analysed together. The data can be accessed through a user-friendly web interface as well as a powerful, scriptable web service API to allow programmatic access to data. The web interface includes a useful identifier resolution system, sophisticated query options and interactive results tables that enable powerful exploration of data, including data summaries, filtering, browsing and export. A set of graphical analysis tools provide a rich environment for data exploration including statistical enrichment of sets of genes or other biological entities. HumanMine can be used for integrative multi-staged analysis that can lead to new insights and uncover previously unknown relationships. Database URL: https://www.humanmine.org
Open AccessHumanMine: advanced data searching, analysis and cross-species comparison
HumanMine ( www.humanmine.org ) is an integrated database of human genomics and proteomics data that provides a powerful interface to support sophisticated exploration and analysis of data compiled from experimental, computational and curated data sources. Built using the InterMine data integration platform, HumanMine includes genes, proteins, pathways, expression levels, SNPs, diseases and more, integrated into a single searchable database. HumanMine promotes integrative analysis, a powerful approach in modern biology that allows many sources of evidence to be analysed together. The data can be accessed through a user-friendly web interface as well as a powerful, scriptable web service API to allow programmatic access to data. The web interface includes a useful identifier resolution system, sophisticated query options and interactive results tables that enable powerful exploration of data, including data summaries, filtering, browsing and export. A set of graphical analysis tools provide a rich environment for data exploration including statistical enrichment of sets of genes or other biological entities. HumanMine can be used for integrative multi-staged analysis that can lead to new insights and uncover previously unknown relationships. Database URL: https://www.humanmine.org
- Open Access
- 1 July 2020
- Published by Springer Nature in Scientific Reports
- Vol. 10 (1) , 1-10
Genome-wide investigation of gene-cancer associations for the prediction of novel therapeutic targets in oncology
A major cause of failed drug discovery programs is suboptimal target selection, resulting in the development of drug candidates that are potent inhibitors, but ineffective at treating the disease. In the genomics era, the availability of large biomedical datasets with genome-wide readouts has the potential to transform target selection and validation. In this study we investigate how computational intelligence methods can be applied to predict novel therapeutic targets in oncology. We compared different machine learning classifiers applied to the task of drug target classification for nine different human cancer types. For each cancer type, a set of “known” target genes was obtained and equally-sized sets of “non-targets” were sampled multiple times from the human protein-coding genes. Models were trained on mutation, gene expression (TCGA), and gene essentiality (DepMap) data. In addition, we generated a numerical embedding of the interaction network of protein-coding genes using deep network representation learning and included the results in the modeling. We assessed feature importance using a random forests classifier and performed feature selection based on measuring permutation importance against a null distribution. Our best models achieved good generalization performance based on the AUROC metric. With the best model for each cancer type, we ran predictions on more than 15,000 protein-coding genes to identify potential novel targets. Our results indicate that this approach may be useful to inform early stages of the drug discovery pipeline.
- 1 July 2020
- Published by Springer Nature in Scientific Reports
- Vol. 10 (1) , 1-10
Open AccessGenome-wide investigation of gene-cancer associations for the prediction of novel therapeutic targets in oncology
A major cause of failed drug discovery programs is suboptimal target selection, resulting in the development of drug candidates that are potent inhibitors, but ineffective at treating the disease. In the genomics era, the availability of large biomedical datasets with genome-wide readouts has the potential to transform target selection and validation. In this study we investigate how computational intelligence methods can be applied to predict novel therapeutic targets in oncology. We compared different machine learning classifiers applied to the task of drug target classification for nine different human cancer types. For each cancer type, a set of “known” target genes was obtained and equally-sized sets of “non-targets” were sampled multiple times from the human protein-coding genes. Models were trained on mutation, gene expression (TCGA), and gene essentiality (DepMap) data. In addition, we generated a numerical embedding of the interaction network of protein-coding genes using deep network representation learning and included the results in the modeling. We assessed feature importance using a random forests classifier and performed feature selection based on measuring permutation importance against a null distribution. Our best models achieved good generalization performance based on the AUROC metric. With the best model for each cancer type, we ran predictions on more than 15,000 protein-coding genes to identify potential novel targets. Our results indicate that this approach may be useful to inform early stages of the drug discovery pipeline.
- Open Access
Genome-wide investigation of gene-cancer associations for the prediction of novel therapeutic targets in oncology
A major cause of failed drug discovery programs is suboptimal target selection, resulting in the development of drug candidates that are potent inhibitors, but ineffective at treating the disease. In the genomics era, the availability of large biomedical datasets with genome-wide readouts has the potential to transform target selection and validation. In this study we investigate how computational intelligence methods can be applied to predict novel therapeutic targets in oncology. We compared different machine learning classifiers applied to the task of drug target classification for nine different human cancer types. For each cancer type, a set of “known” target genes was obtained and equally-sized sets of “non-targets” were sampled multiple times from the human protein-coding genes. Models were trained on mutation, gene expression (TCGA), and gene essentiality (DepMap) data. In addition, we generated a numerical embedding of the interaction network of protein-coding genes using deep network representation learning and included the results in the modeling. We assessed feature importance using a random forests classifier and performed feature selection based on measuring permutation importance against a null distribution. Our best models achieved good generalization performance based on the AUROC metric. With the best model for each cancer type, we ran predictions on more than 15,000 protein-coding genes to identify potential novel targets. Our results indicate that this approach may be useful to inform early stages of the drug discovery pipeline.
Open AccessGenome-wide investigation of gene-cancer associations for the prediction of novel therapeutic targets in oncology
A major cause of failed drug discovery programs is suboptimal target selection, resulting in the development of drug candidates that are potent inhibitors, but ineffective at treating the disease. In the genomics era, the availability of large biomedical datasets with genome-wide readouts has the potential to transform target selection and validation. In this study we investigate how computational intelligence methods can be applied to predict novel therapeutic targets in oncology. We compared different machine learning classifiers applied to the task of drug target classification for nine different human cancer types. For each cancer type, a set of “known” target genes was obtained and equally-sized sets of “non-targets” were sampled multiple times from the human protein-coding genes. Models were trained on mutation, gene expression (TCGA), and gene essentiality (DepMap) data. In addition, we generated a numerical embedding of the interaction network of protein-coding genes using deep network representation learning and included the results in the modeling. We assessed feature importance using a random forests classifier and performed feature selection based on measuring permutation importance against a null distribution. Our best models achieved good generalization performance based on the AUROC metric. With the best model for each cancer type, we ran predictions on more than 15,000 protein-coding genes to identify potential novel targets. Our results indicate that this approach may be useful to inform early stages of the drug discovery pipeline.
- 1 December 2019
- Published by Elsevier in Applied Soft Computing
- Vol. 85
A Convolutional Neural Network for the automatic diagnosis of collagen VI-related muscular dystrophies
- 1 December 2019
- Published by Elsevier in Applied Soft Computing
- Vol. 85
A Convolutional Neural Network for the automatic diagnosis of collagen VI-related muscular dystrophies
- 1 October 2019
- Published by Elsevier in Neuromuscular Disorders
- Vol. 29, S194
P.385Automated diagnosis of collagen VI related muscular dystrophies using advanced image analysis and machine learning
- 1 October 2019
- Published by Elsevier in Neuromuscular Disorders
- Vol. 29, S194
P.385Automated diagnosis of collagen VI related muscular dystrophies using advanced image analysis and machine learning
- 28 April 2019
- Published by Springer Nature
- p. 314-323
Network Community Cluster-Based Analysis for the Identification of Potential Leukemia Drug Targets
- 28 April 2019
- Published by Springer Nature
- p. 314-323
Network Community Cluster-Based Analysis for the Identification of Potential Leukemia Drug Targets
- Open Access
- 5 December 2018
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 35 (14) , 2518-2520
BIOLITMAP: a web-based geolocated, temporal and thematic visualization of the evolution of bioinformatics publications
The fast growth of bioinformatics adds a significant difficulty to assess the contribution, geographical and thematic distribution of the research publications. To help researchers, grant agencies and general public to assess the progress in bioinformatics, we have developed BIOLITMAP, a web-based geolocation system that allows an easy and sensible exploration of the publications by institution, year and topic. BIOLITMAP is available at http://socialanalytics.bsc.es/biolitmap and the sources have been deposited at https://github.com/inab/BIOLITMAP. Supplementary data are available at Bioinformatics online.
- 5 December 2018
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 35 (14) , 2518-2520
Open AccessBIOLITMAP: a web-based geolocated, temporal and thematic visualization of the evolution of bioinformatics publications
The fast growth of bioinformatics adds a significant difficulty to assess the contribution, geographical and thematic distribution of the research publications. To help researchers, grant agencies and general public to assess the progress in bioinformatics, we have developed BIOLITMAP, a web-based geolocation system that allows an easy and sensible exploration of the publications by institution, year and topic. BIOLITMAP is available at http://socialanalytics.bsc.es/biolitmap and the sources have been deposited at https://github.com/inab/BIOLITMAP. Supplementary data are available at Bioinformatics online.