Utilization and Development of Machine Learning for Molecular Applications - Molecular Machine Learning (SPP 2363)
Termin:
01.09.2021
Fördergeber:
Deutsche Forschungsgemeinschaft (DFG)
The Senate of the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) has established the Priority Programme ,,Utilization and Development of Machine Learning for Molecular Applications - Molecular Machine Learning" (SPP 2363). The programme is designed to run for six years; the present call invites proposals for the first three-year funding period.
This programme aims at connecting communities from the fields of machine learning and data science with scientists working in the areas of molecular chemistry and pharmacology. Machine learning for molecular applications and questions (Molecular Machine Learning, MML) has emerged as an area of interest with high potential to change current workflows in all fields of chemistry as well as pharmacology and thereby poses several outstanding challenges. This Priority Programme aims at tackling these challenges in a holistic fashion covering a spectrum of topics ranging from data generation and the application of new algorithms to explainable artificial intelligence (ExAI). In general, all projects are required to contribute to the whole MML community by developing reusable tools, methodologies, datasets, or broadly utilizable applications. Each proposal must be positioned at the interface of chemistry/pharmacology and machine learning in at least one of the following five areas:
o design and evaluation of molecular representations for machine learning;
o machine learning as a tool for theoretical and organic chemistry;
o machine learning for medicinal chemistry and drug design;
o overcoming data limitations by data-generation, evaluation, and data-free approaches;
o development of machine learning tools for molecular applications including ExAI, data-augmentation strategies and software suites.
The first funding period aims at improving methodologies for MML and understanding underlying principles. Therefore, new representations need to be developed, datasets shall be generated, and methods need to be adapted, based on knowledge from the chemical and computer scientific domain. Within these topics, projects designed to gain deep knowledge (ExAI) about chemical and chemoinformatic relationships are highly encouraged. In addition, first feasibility studies should be carried out, examining state-of-the-art concepts on various applications. The focus of the second funding period aims at using prior knowledge to develop these applications further and transform them into software tools, usable in scientists' every-day work. These tools should not only be applied in the MML domain but impact different areas of chemistry as well as pharmacology. As developments in the field of MML will further accelerate, it is necessary that, if required by the state of knowledge, all topics addressed can be eligible for funding within both periods.
While machine learning finds many applications in various overlapping fields, this programme specifically focuses on MML. This excludes the modelling of protein surfaces, properties of entire materials and periodic systems if these are not predominantly governed by the molecular constituents (e. g. molecular crystals). This also excludes projects that target the development or improvement of heterogeneous catalysts without explicitly describing them by their molecular structure.
All of the above mentioned areas must not be considered in isolation but should be closely connected or integrated. This link must be explicitly presented in the application. Since MML is a highly interdisciplinary field of research, applicants will belong to various subject areas that can roughly be assigned to three groups: computer and data science (C), practical chemistry (P), and theoretical chemistry and chemoinformatics (T). In order to promote interdisciplinarity and networking, the applicants' research areas need to be anchored within at least two of these three groups. Ideally, this will be realised by tandem applications of researchers from complementary areas that can be closely linked.
For scientific enquiries, please contact the Priority Programme coordinator:
Professor Dr. Frank Glorius
Westfälische Wilhelms-Universität Münster
Organisch-Chemisches Institut
Corrensstr. 36
48149 Münster
phone +49 251 83-33248
glorius@uni-muenster.de
For questions related to the DFG review process, please contact:
Dr. Markus Behnke, phone +49 228 885-2181, markus.behnke@dfg.de
For administrative questions regarding the DFG application, please contact:
Angelika Spahn, phone +49 228 885-2440, angelika.spahn@dfg.de
Further information:
https://www.dfg.de/foerderung/info_wissenschaft/2021/info_wissenschaft_21_44
This programme aims at connecting communities from the fields of machine learning and data science with scientists working in the areas of molecular chemistry and pharmacology. Machine learning for molecular applications and questions (Molecular Machine Learning, MML) has emerged as an area of interest with high potential to change current workflows in all fields of chemistry as well as pharmacology and thereby poses several outstanding challenges. This Priority Programme aims at tackling these challenges in a holistic fashion covering a spectrum of topics ranging from data generation and the application of new algorithms to explainable artificial intelligence (ExAI). In general, all projects are required to contribute to the whole MML community by developing reusable tools, methodologies, datasets, or broadly utilizable applications. Each proposal must be positioned at the interface of chemistry/pharmacology and machine learning in at least one of the following five areas:
o design and evaluation of molecular representations for machine learning;
o machine learning as a tool for theoretical and organic chemistry;
o machine learning for medicinal chemistry and drug design;
o overcoming data limitations by data-generation, evaluation, and data-free approaches;
o development of machine learning tools for molecular applications including ExAI, data-augmentation strategies and software suites.
The first funding period aims at improving methodologies for MML and understanding underlying principles. Therefore, new representations need to be developed, datasets shall be generated, and methods need to be adapted, based on knowledge from the chemical and computer scientific domain. Within these topics, projects designed to gain deep knowledge (ExAI) about chemical and chemoinformatic relationships are highly encouraged. In addition, first feasibility studies should be carried out, examining state-of-the-art concepts on various applications. The focus of the second funding period aims at using prior knowledge to develop these applications further and transform them into software tools, usable in scientists' every-day work. These tools should not only be applied in the MML domain but impact different areas of chemistry as well as pharmacology. As developments in the field of MML will further accelerate, it is necessary that, if required by the state of knowledge, all topics addressed can be eligible for funding within both periods.
While machine learning finds many applications in various overlapping fields, this programme specifically focuses on MML. This excludes the modelling of protein surfaces, properties of entire materials and periodic systems if these are not predominantly governed by the molecular constituents (e. g. molecular crystals). This also excludes projects that target the development or improvement of heterogeneous catalysts without explicitly describing them by their molecular structure.
All of the above mentioned areas must not be considered in isolation but should be closely connected or integrated. This link must be explicitly presented in the application. Since MML is a highly interdisciplinary field of research, applicants will belong to various subject areas that can roughly be assigned to three groups: computer and data science (C), practical chemistry (P), and theoretical chemistry and chemoinformatics (T). In order to promote interdisciplinarity and networking, the applicants' research areas need to be anchored within at least two of these three groups. Ideally, this will be realised by tandem applications of researchers from complementary areas that can be closely linked.
For scientific enquiries, please contact the Priority Programme coordinator:
Professor Dr. Frank Glorius
Westfälische Wilhelms-Universität Münster
Organisch-Chemisches Institut
Corrensstr. 36
48149 Münster
phone +49 251 83-33248
glorius@uni-muenster.de
For questions related to the DFG review process, please contact:
Dr. Markus Behnke, phone +49 228 885-2181, markus.behnke@dfg.de
For administrative questions regarding the DFG application, please contact:
Angelika Spahn, phone +49 228 885-2440, angelika.spahn@dfg.de
Further information:
https://www.dfg.de/foerderung/info_wissenschaft/2021/info_wissenschaft_21_44