Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Flame: an open source framework for model development, hosting, and usage in production environments

  • Pastor Maeso, Manuel
  • Gómez-Tamayo, José C.
  • Sanz, Ferran
This article describes Flame, an open source software for building predictive models and supporting their use in production environments. Flame is a web application with a web-based graphic interface, which can be used as a desktop application or installed in a server receiving requests from multiple users. Models can be built starting from any collection of biologically annotated chemical structures since the software supports structural normalization, molecular descriptor calculation, and machine learning model generation using predefined workflows. The model building workflow can be customized from the graphic interface, selecting the type of normalization, molecular descriptors, and machine learning algorithm to be used from a panel of state-of-the-art methods implemented natively. Moreover, Flame implements a mechanism allowing to extend its source code, adding unlimited model customization. Models generated with Flame can be easily exported, facilitating collaborative model development. All models are stored in a model repository supporting model versioning. Models are identified by unique model IDs and include detailed documentation formatted using widely accepted standards. The current version is the result of nearly 3 years of development in collaboration with users from the pharmaceutical industry within the IMI eTRANSAFE project, which aims, among other objectives, to develop high-quality predictive models based on shared legacy data for assessing the safety of drug candidates., This work has received funding from the eTRANSAFE project (Grant Agreement No. 777365), developed under the Innovative Medicines Initiative Joint Undertaking (IMI2), resources of which are composed of a financial contribution from the European Union’s Seventh Framework Programme (FP7/2007–2013) and EFPIA companies’ in kind contributions. The authors of this article are also involved in other related IMI projects which contributed funding, such as TransQST (No. 116030) as well as the H2020 EU-ToxRisk project (No. 681002) and FAIRplus (No. 802750). The Research Programme on Biomedical Informatics (GRIB) is a member of the Spanish National Bioinformatics Institute (INB), funded by ISCIII and FEDER (PT17/0009/0014). The DCEXS is a ‘Unidad de Excelencia María de Maeztu’, funded by the AEI (CEX2018-000782-M). The GRIB is also supported by the Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR), Generalitat de Catalunya (2017 SGR 00519).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

“Be sustainable”: EOSC‐Life recommendations for implementation of FAIR principles in life science data handling

  • David, Romain
  • Lancelotti, Carla
  • Gribbon, Philip
Includes supplementary materials for the online appendix., The main goals and challenges for the life science communities in the Open Science framework are to increase reuse and sustainability of data resources, software tools, and workflows, especially in large‐scale data‐driven research and computational analyses. Here, we present key findings, procedures, effective measures and recommendations for generating and establishing sustainable life science resources based on the collaborative, cross‐disciplinary work done within the EOSC‐Life (European Open Science Cloud for Life Sciences) consortium. Bringing together 13 European life science research infrastructures, it has laid the foundation for an open, digital space to support biological and medical research. Using lessons learned from 27 selected projects, we describe the organisational, technical, financial and legal/ethical challenges that represent the main barriers to sustainability in the life sciences. We show how EOSC‐Life provides a model for sustainable data management according to FAIR (findability, accessibility, interoperability, and reusability) principles, including solutions for sensitive‐ and industry‐related resources, by means of cross‐disciplinary training and best practices sharing. Finally, we illustrate how data harmonisation and collaborative work facilitate interoperability of tools, data, solutions and lead to a better understanding of concepts, semantics and functionalities in the life sciences., This research is mainly a product of the EOSC‐Life European programme funding from the European Union's Horizon Europe Research and Innovation Programme under grant agreement No. 824087. Complementary support was provided through: EU funded project AgroServ (grant agreement No. 101058020), EU funded project BY‐COVID (grant agreement No. 101046203), EU funded project DANUBIUS‐IP (grant agreement No. 101079778), EU funded project EMPHASIS‐GO (grant agreement No. 101079772), EU funded project FAIRplus (IMI grant agreement No. 802750), EU funded project FAIRsharing (Wellcome grant agreement No. 212930/Z/18/Z), EU funded project ISIDORe (grant agreement No. 101046133), EU funded project Precision Toxicology (grant agreement No. 965406), UKRI DASH (grant agreement No. MR/V038966/1). Special thanks to T. Biro and her radical collaboration team from Research Data Alliance who gave us great inspiration on how to lead this radical collaboration work.Thanks are also due to Martina Esdaile for proofreading the final version of the manuscript. Open access funding enabled and organized by Projekt DEAL.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

A research data management (RDM) community for ELIXIR

  • D'Anna, Flora
  • D'Altri, Teresa, 1984-
  • Andrabi, Munazah
Research data management (RDM) is central to the implementation of the FAIR (Findable Accessible, Interoperable, Reusable) and Open Science principles. Recognising the importance of RDM, ELIXIR Platforms and Nodes have invested in RDM and launched various projects and initiatives to ensure good data management practices for scientific excellence. These projects have resulted in a rich set of tools and resources highly valuable for FAIR data management. However, these resources remain scattered across projects and ELIXIR structures, making their dissemination and application challenging. Therefore, it becomes imminent to coordinate these efforts for sustainable and harmonised RDM practices with dedicated forums for RDM professionals to exchange knowledge and share resources. The proposed ELIXIR RDM Community will bring together RDM experts to develop ELIXIR's vision and coordinate its activities, taking advantage of the available assets. It aims to coordinate RDM best practices and illustrate how to use the existing ELIXIR RDM services. The Community will be built around three integral pillars, namely, a network of RDM professionals, RDM knowledge management and RDM training expertise and resources. It will also engage with external stakeholders to leverage benefits and provide a forum to RDM professionals for regular knowledge exchange, capacity building and development of harmonised RDM practices, keeping in line with the overall scope of the RDM Community. In the short term, the Community aims to build upon the existing resources and ensure that the content of these remain up to date and fit for purpose. In the long run, the Community will aim to strengthen the skills and knowledge of its RDM professionals to support the emerging needs of the scientific community. The Community will also devise an effective strategy to engage with other ELIXIR structures and international stakeholders to influence and align with developments and solutions in the RDM field., ELIXIR-CONVERGE: European Union’s Horizon 2020 programme under grant agreement No 871075. FAIRplus: European Union’s Horizon 2020 programme under grant agreement No 802750.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Evaluating behavioral and linguistic changes during drug treatment for depression using tweets in spanish: pairwise comparison study

  • Leis Machín, Angela 1974-
  • Ronzano, Francesco
  • Mayer, Miguel Ángel, 1960-
  • Furlong, Laura I., 1971-
  • Sanz, Ferran
Background: Depressive disorders are the most common mental illnesses, and they constitute the leading cause of disability worldwide. Selective serotonin reuptake inhibitors (SSRIs) are the most commonly prescribed drugs for the treatment of depressive disorders. Some people share information about their experiences with antidepressants on social media platforms such as Twitter. Analysis of the messages posted by Twitter users under SSRI treatment can yield useful information on how these antidepressants affect users' behavior. Objective: This study aims to compare the behavioral and linguistic characteristics of the tweets posted while users were likely to be under SSRI treatment, in comparison to the tweets posted by the same users when they were less likely to be taking this medication. Methods: In the first step, the timelines of Twitter users mentioning SSRI antidepressants in their tweets were selected using a list of 128 generic and brand names of SSRIs. In the second step, two datasets of tweets were created, the in-treatment dataset (made up of the tweets posted throughout the 30 days after mentioning an SSRI) and the unknown-treatment dataset (made up of tweets posted more than 90 days before or more than 90 days after any tweet mentioning an SSRI). For each user, the changes in behavioral and linguistic features between the tweets classified in these two datasets were analyzed. 186 users and their timelines with 668,842 tweets were finally included in the study. Results: The number of tweets generated per day by the users when they were in treatment was higher than it was when they were in the unknown-treatment period (P=.001). When the users were in treatment, the mean percentage of tweets posted during the daytime (from 8 AM to midnight) increased in comparison to the unknown-treatment period (P=.002). The number of characters and words per tweet was higher when the users were in treatment (P=.03 and P=.02, respectively). Regarding linguistic features, the percentage of pronouns that were first-person singular was higher when users were in treatment (P=.008). Conclusions: Behavioral and linguistic changes have been detected when users with depression are taking antidepressant medication. These features can provide interesting insights for monitoring the evolution of this disease, as well as offering additional information related to treatment adherence. This information may be especially useful in patients who are receiving long-term treatments such as people suffering from depression., We received support from the Agency for Management of University and Research Grants in Catalonia (Spain) for the incorporation of new research personnel (FI2016) and from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement number 802750 (FAIRplus) with the support of the European Union’s Horizon 2020 research and innovation programme and European Federation of Pharmaceutical Industries and Associations Companies.
Dipòsit Digital de la UB
Publicación Artículo científico (JournalArticle)

FAIR Principles: Interpretations and Implementation Considerations

  • Jacobsen, Annika
  • Miranda Azevedo, Ricardo de
  • Juty, Nick
  • Batista, Dominique
  • Coles, Simon J.
  • Cornet, Ronald
  • Courtot, Mélanie
  • Crosas, Mercè
  • Dumontier, Michel
  • Evelo Chris, T.
  • Goble, Carole
  • Guizzardi, Giancarlo
  • Kryger-Hansen, Karsten
  • Hasnain, Ali
  • Hettne, Kristina
  • Heringa, Jaap
  • Hooft, Rob W. W.
  • Imming, Melanie
  • Jeffery, Keith G.
  • Kaliyaperumal, Rajaram
  • Kersloot, Martijn G.
  • Kirkpatrick, Christine R.
  • Kuhn, Tobias
  • Labastida i Juan, Ignasi, 1970-
  • Magagna, Barbara
  • McQuilton, Peter
  • Meyers, Natalie
  • Montesanti, Annalisa
  • van-Reisen, Mirjam
  • Rocca-Serra, Philippe
  • Pergl, Robert
  • Sansone, Susanna-Assunta
  • Bonino da Silva Santos, Luiz Olavo
  • Schneider, Juliane
  • Strawn, George
  • Thompson, Mark
  • Waagmeester, Andra
  • Weigel, Tobias
  • Wilkinson, Mark D.
  • Willighagen, Egon
The FAIR principles have been widely cited, endorsed and adopted by a broad range of stakeholders since their publication in 2016. By intention, the 15 FAIR guiding principles do not dictate specific technological implementations, but provide guidance for improving Findability, Accessibility, Interoperability and Reusability of digital resources. This has likely contributed to the broad adoption of the FAIR principles, because individual stakeholder communities can implement their own FAIR solutions. However, it has also resulted in inconsistent interpretations that carry the risk of leading to incompatible implementations. Thus, while the FAIR principles are formulated on a high level and may be interpreted and implemented in different ways, for true interoperability we need to support convergence in implementation choices that are widely accessible and (re)-usable. We introduce the concept of FAIR implementation considerations to assist accelerated global participation and convergence towards accessible, robust, widespread and consistent FAIR implementations. Any self-identified stakeholder community may either choose to reuse solutions from existing implementations, or when they spot a gap, accept the challenge to create the needed solution, which, ideally, can be used again by other communities in the future. Here, we provide interpretations and implementation considerations (choices and challenges) for each FAIR principle.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Community-driven governance of FAIRness assessment: an open issue, an open discussion

  • Wilkinson, Mark D.
  • Sansone, Susanna Assunta
  • Méndez, Eva
  • David, Romain
  • Dennis, Richard
  • Hecker, David
  • Kleemola, Mari
  • Lacagnina, Carlo
  • Nikiforova, Anastasija
  • Castro, Leyla Jael
29 Pág., Although FAIR Research Data Principles are targeted at and implemented by different communities, research disciplines, and research stakeholders (data stewards, curators, etc.), there is no conclusive way to determine the level of FAIRness intended or required to make research artefacts (including, but not limited to, research data) Findable, Accessible, Interoperable, and Reusable. The FAIR Principles cover all types of digital objects, metadata, and infrastructures. However, they focus their narrative on data features that support their reusability. FAIR defines principles, not standards, and therefore they do not propose a mechanism to achieve the behaviours they describe in an attempt to be technology/implementation neutral. Various FAIR assessment metrics and tools have been designed to measure FAIRness. Unfortunately, the same digital objects assessed by different tools often exhibit widely different outcomes because of these independent interpretations of FAIR. This results in confusion among the publishers, the funders, and the users of digital research objects. Moreover, in the absence of a standard and transparent definition of what constitutes FAIR behaviours, there is a temptation to define existing approaches as being FAIR-compliant rather than having FAIR define the expected behaviours. This whitepaper identifies three high-level stakeholder categories -FAIR decision and policymakers, FAIR custodians, and FAIR practitioners - and provides examples outlining specific stakeholders' (hypothetical but anticipated) needs. It also examines possible models for governance based on the existing peer efforts, standardisation bodies, and other ways to acknowledge specifications and potential benefits. This whitepaper can serve as a starting point to foster an open discussion around FAIRness governance and the mechanism(s) that could be used to implement it, to be trusted, broadly representative, appropriately scoped, and sustainable. We invite engagement in this conversation in an open Google Group fair-assessment-governance@googlegroups.com., : MDW acknowledges funds supporting his work, including the EJP RD initiative which has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement N°825575. SAS acknowledges funds that supports her, including FAIRplus (IMI 802750), EOSC-Life (H2020 EU 824087), FAIRsharing (Wellcome 212930), Precision Toxicology (H2020 EU 965406), UKRI DASH grant (MR/V038966/1), BY-COVID (Horizon EU 101046203), AgroServ (Horizon EU 10105 8020), and the ELIXIR Interoperability Platform. EM acknowledges support from the FAIRsFAIR Fostering FAIR Data Practices in Europe (funding number 831558). RD David was supported by the EOSC-Life European program under grant agreement Nº824087. LJC acknowledges support from the project NFDI4DataScience, part of the German National Research Data Infrastructure funded by the Joint Science Conference (GWK) and the German Research Foundation (DFG), funding number NFDI 34/1., Peer reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

FAIR Principles: Interpretations and Implementation Considerations

  • Jacobsen, Annika
  • Miranda Azevedo, Ricardo de
  • Juty, Nick
  • Batista, Dominique
  • Coles, Simon J.
  • Cornet, Ronald
  • Courtot, Mélanie
  • Crosas, Mercè
  • Dumontier, Michel
  • Evelo Chris, T.
  • Goble, Carole
  • Guizzardi, Giancarlo
  • Kryger-Hansen, Karsten
  • Hasnain, Ali
  • Hettne, Kristina
  • Heringa, Jaap
  • Hooft, Rob W. W.
  • Imming, Melanie
  • Jeffery, Keith G.
  • Kaliyaperumal, Rajaram
  • Kersloot, Martijn G.
  • Kirkpatrick, Christine R.
  • Kuhn, Tobias
  • Labastida i Juan, Ignasi, 1970-
  • Magagna, Barbara
  • McQuilton, Peter
  • Meyers, Natalie
  • Montesanti, Annalisa
  • van-Reisen, Mirjam
  • Rocca-Serra, Philippe
  • Pergl, Robert
  • Sansone, Susanna-Assunta
  • Bonino da Silva Santos, Luiz Olavo
  • Schneider, Juliane
  • Strawn, George
  • Thompson, Mark
  • Waagmeester, Andra
  • Weigel, Tobias
  • Wilkinson, Mark D.
  • Willighagen, Egon
The FAIR principles have been widely cited, endorsed and adopted by a broad range of stakeholders since their publication in 2016. By intention, the 15 FAIR guiding principles do not dictate specific technological implementations, but provide guidance for improving Findability, Accessibility, Interoperability and Reusability of digital resources. This has likely contributed to the broad adoption of the FAIR principles, because individual stakeholder communities can implement their own FAIR solutions. However, it has also resulted in inconsistent interpretations that carry the risk of leading to incompatible implementations. Thus, while the FAIR principles are formulated on a high level and may be interpreted and implemented in different ways, for true interoperability we need to support convergence in implementation choices that are widely accessible and (re)-usable. We introduce the concept of FAIR implementation considerations to assist accelerated global participation and convergence towards accessible, robust, widespread and consistent FAIR implementations. Any self-identified stakeholder community may either choose to reuse solutions from existing implementations, or when they spot a gap, accept the challenge to create the needed solution, which, ideally, can be used again by other communities in the future. Here, we provide interpretations and implementation considerations (choices and challenges) for each FAIR principle.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Flame: an open source framework for model development, hosting, and usage in production environments

  • Pastor Maeso, Manuel
  • Gómez-Tamayo, José C.
  • Sanz, Ferran
This article describes Flame, an open source software for building predictive models and supporting their use in production environments. Flame is a web application with a web-based graphic interface, which can be used as a desktop application or installed in a server receiving requests from multiple users. Models can be built starting from any collection of biologically annotated chemical structures since the software supports structural normalization, molecular descriptor calculation, and machine learning model generation using predefined workflows. The model building workflow can be customized from the graphic interface, selecting the type of normalization, molecular descriptors, and machine learning algorithm to be used from a panel of state-of-the-art methods implemented natively. Moreover, Flame implements a mechanism allowing to extend its source code, adding unlimited model customization. Models generated with Flame can be easily exported, facilitating collaborative model development. All models are stored in a model repository supporting model versioning. Models are identified by unique model IDs and include detailed documentation formatted using widely accepted standards. The current version is the result of nearly 3 years of development in collaboration with users from the pharmaceutical industry within the IMI eTRANSAFE project, which aims, among other objectives, to develop high-quality predictive models based on shared legacy data for assessing the safety of drug candidates., This work has received funding from the eTRANSAFE project (Grant Agreement No. 777365), developed under the Innovative Medicines Initiative Joint Undertaking (IMI2), resources of which are composed of a financial contribution from the European Union’s Seventh Framework Programme (FP7/2007–2013) and EFPIA companies’ in kind contributions. The authors of this article are also involved in other related IMI projects which contributed funding, such as TransQST (No. 116030) as well as the H2020 EU-ToxRisk project (No. 681002) and FAIRplus (No. 802750). The Research Programme on Biomedical Informatics (GRIB) is a member of the Spanish National Bioinformatics Institute (INB), funded by ISCIII and FEDER (PT17/0009/0014). The DCEXS is a ‘Unidad de Excelencia María de Maeztu’, funded by the AEI (CEX2018-000782-M). The GRIB is also supported by the Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR), Generalitat de Catalunya (2017 SGR 00519).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

“Be sustainable”: EOSC‐Life recommendations for implementation of FAIR principles in life science data handling

  • David, Romain
  • Lancelotti, Carla
  • Gribbon, Philip
Includes supplementary materials for the online appendix., The main goals and challenges for the life science communities in the Open Science framework are to increase reuse and sustainability of data resources, software tools, and workflows, especially in large‐scale data‐driven research and computational analyses. Here, we present key findings, procedures, effective measures and recommendations for generating and establishing sustainable life science resources based on the collaborative, cross‐disciplinary work done within the EOSC‐Life (European Open Science Cloud for Life Sciences) consortium. Bringing together 13 European life science research infrastructures, it has laid the foundation for an open, digital space to support biological and medical research. Using lessons learned from 27 selected projects, we describe the organisational, technical, financial and legal/ethical challenges that represent the main barriers to sustainability in the life sciences. We show how EOSC‐Life provides a model for sustainable data management according to FAIR (findability, accessibility, interoperability, and reusability) principles, including solutions for sensitive‐ and industry‐related resources, by means of cross‐disciplinary training and best practices sharing. Finally, we illustrate how data harmonisation and collaborative work facilitate interoperability of tools, data, solutions and lead to a better understanding of concepts, semantics and functionalities in the life sciences., This research is mainly a product of the EOSC‐Life European programme funding from the European Union's Horizon Europe Research and Innovation Programme under grant agreement No. 824087. Complementary support was provided through: EU funded project AgroServ (grant agreement No. 101058020), EU funded project BY‐COVID (grant agreement No. 101046203), EU funded project DANUBIUS‐IP (grant agreement No. 101079778), EU funded project EMPHASIS‐GO (grant agreement No. 101079772), EU funded project FAIRplus (IMI grant agreement No. 802750), EU funded project FAIRsharing (Wellcome grant agreement No. 212930/Z/18/Z), EU funded project ISIDORe (grant agreement No. 101046133), EU funded project Precision Toxicology (grant agreement No. 965406), UKRI DASH (grant agreement No. MR/V038966/1). Special thanks to T. Biro and her radical collaboration team from Research Data Alliance who gave us great inspiration on how to lead this radical collaboration work.Thanks are also due to Martina Esdaile for proofreading the final version of the manuscript. Open access funding enabled and organized by Projekt DEAL.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A research data management (RDM) community for ELIXIR

  • D'Anna, Flora
  • D'Altri, Teresa, 1984-
  • Andrabi, Munazah
Research data management (RDM) is central to the implementation of the FAIR (Findable Accessible, Interoperable, Reusable) and Open Science principles. Recognising the importance of RDM, ELIXIR Platforms and Nodes have invested in RDM and launched various projects and initiatives to ensure good data management practices for scientific excellence. These projects have resulted in a rich set of tools and resources highly valuable for FAIR data management. However, these resources remain scattered across projects and ELIXIR structures, making their dissemination and application challenging. Therefore, it becomes imminent to coordinate these efforts for sustainable and harmonised RDM practices with dedicated forums for RDM professionals to exchange knowledge and share resources. The proposed ELIXIR RDM Community will bring together RDM experts to develop ELIXIR's vision and coordinate its activities, taking advantage of the available assets. It aims to coordinate RDM best practices and illustrate how to use the existing ELIXIR RDM services. The Community will be built around three integral pillars, namely, a network of RDM professionals, RDM knowledge management and RDM training expertise and resources. It will also engage with external stakeholders to leverage benefits and provide a forum to RDM professionals for regular knowledge exchange, capacity building and development of harmonised RDM practices, keeping in line with the overall scope of the RDM Community. In the short term, the Community aims to build upon the existing resources and ensure that the content of these remain up to date and fit for purpose. In the long run, the Community will aim to strengthen the skills and knowledge of its RDM professionals to support the emerging needs of the scientific community. The Community will also devise an effective strategy to engage with other ELIXIR structures and international stakeholders to influence and align with developments and solutions in the RDM field., ELIXIR-CONVERGE: European Union’s Horizon 2020 programme under grant agreement No 871075. FAIRplus: European Union’s Horizon 2020 programme under grant agreement No 802750.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Evaluating behavioral and linguistic changes during drug treatment for depression using tweets in spanish: pairwise comparison study

  • Leis Machín, Angela 1974-
  • Ronzano, Francesco
  • Mayer, Miguel Ángel, 1960-
  • Furlong, Laura I., 1971-
  • Sanz, Ferran
Background: Depressive disorders are the most common mental illnesses, and they constitute the leading cause of disability worldwide. Selective serotonin reuptake inhibitors (SSRIs) are the most commonly prescribed drugs for the treatment of depressive disorders. Some people share information about their experiences with antidepressants on social media platforms such as Twitter. Analysis of the messages posted by Twitter users under SSRI treatment can yield useful information on how these antidepressants affect users' behavior. Objective: This study aims to compare the behavioral and linguistic characteristics of the tweets posted while users were likely to be under SSRI treatment, in comparison to the tweets posted by the same users when they were less likely to be taking this medication. Methods: In the first step, the timelines of Twitter users mentioning SSRI antidepressants in their tweets were selected using a list of 128 generic and brand names of SSRIs. In the second step, two datasets of tweets were created, the in-treatment dataset (made up of the tweets posted throughout the 30 days after mentioning an SSRI) and the unknown-treatment dataset (made up of tweets posted more than 90 days before or more than 90 days after any tweet mentioning an SSRI). For each user, the changes in behavioral and linguistic features between the tweets classified in these two datasets were analyzed. 186 users and their timelines with 668,842 tweets were finally included in the study. Results: The number of tweets generated per day by the users when they were in treatment was higher than it was when they were in the unknown-treatment period (P=.001). When the users were in treatment, the mean percentage of tweets posted during the daytime (from 8 AM to midnight) increased in comparison to the unknown-treatment period (P=.002). The number of characters and words per tweet was higher when the users were in treatment (P=.03 and P=.02, respectively). Regarding linguistic features, the percentage of pronouns that were first-person singular was higher when users were in treatment (P=.008). Conclusions: Behavioral and linguistic changes have been detected when users with depression are taking antidepressant medication. These features can provide interesting insights for monitoring the evolution of this disease, as well as offering additional information related to treatment adherence. This information may be especially useful in patients who are receiving long-term treatments such as people suffering from depression., We received support from the Agency for Management of University and Research Grants in Catalonia (Spain) for the incorporation of new research personnel (FI2016) and from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement number 802750 (FAIRplus) with the support of the European Union’s Horizon 2020 research and innovation programme and European Federation of Pharmaceutical Industries and Associations Companies.