SPP 2363:  Utilization and Development of Machine Learning for Molecular Applications – Molecular Machine Learning

• Subject Area: Chemistry ; Computer Science, Systems and Electrical Engineering ; Medicine
• Term: since 2022
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 460865652

Artificial intelligence is undoubtedly one of the fastest developing topics and is attracting a great deal of public interest. This technology makes everyday life easier and changes society as well as the workplace. While IT companies, and academic groups from the fields of computer science and mathematics rapidly adopted the new field, natural sciences such as biochemistry or chemistry only recently began to gradually explore the potential of machine learning (ML) methods. Our goal is to develop and apply modern ML algorithms in their entire range to molecular problems. While current approaches already help, for example, to determine molecular properties and to screen molecules virtually, future molecular machine learning should use generative models to suggest molecules with specific properties and activities, develop and optimize reactions independently, and evaluate and interpret analytical data within seconds. The first step is the design of molecular representations that increase the understanding of ML and enable robust and comparable applications. In clever combination with state-of-the-art machine learning algorithms, problems such as small data sets, highly complex questions and large experimental errors can be overcome, and previously unknown molecular relationships can be found. Ultimately, applications that are highly valuable in everyday laboratory work should be converted in easy-to-use software suites and experimental scientists should be trained on them. Thus, this priority program will help to modernize an entire subject area. To achieve this, it is necessary to unite existing innovative efforts in the fields of biochemistry, chemistry, computer science, mathematics and pharmacy in order to use all available knowledge on the one hand and to combine the most modern methods of the theoretical and practical world to develop advanced machine learning models and methods on the other. This program will fulfil the AI strategy of the Bundesregierung and can establish Germany internationally as a leading hub for molecular machine learning. The requested coordination funds and the underlying concept will help to bring together the individual research groups, to foster strong and beneficial relationships and collaborations, to train and enable the doctoral students, to connect the PP with the international community and also to reach out to the general public. I will work hard to ensure that this PP “Molecular Machine Learning” will become a scientific success story.

• DFG Programme: Priority Programmes
• International Connection: Switzerland

Projects

• Advanced learning strategies for potential energy surfaces applied to organic electrolytes (Applicants Holm, Christian ;  Kästner, Johannes )
• Coordination Funds (Applicant Glorius, Frank )
• Design of photocatalytic systems for CO2 reduction driven by synergistic cooperation of machine learning and automated labs (Applicants Bräse, Stefan ;  Friederich, Pascal ;  Jung, Nicole )
• Development and application of improved ligand descriptors and representations for inverse catalyst design (Applicants Däschlein-Gessner, Viktoria H. ;  Strieth-Kalthoff, Felix )
• Development and application of ML tools for energy transfer catalysed photocycloadditions (Applicant Glorius, Frank )
• DREAM: Developing Robust Evaluation and Analysis Methodologies for Chemical Reactions (Applicant Glorius, Frank )
• Efficient Semiempirical Quantum Mechanical Method with Adaptive Learning (Applicant Grimme, Stefan )
• Elucidating Fingerprints – Towards a Holistic Explanatory Toolbox for Molecular Machine Learning (Applicants Glorius, Frank ;  Jiang, Xiaoyi )
• Exploring tailored Ru-triphos catalysts for hydrogenation reactions by combination of experimental, computational, and machine learning techniques (Applicants Bannwarth, Christoph ;  Klankermayer, Jürgen )
• Foundational Implicit Solvent Machine Learning Potentials for Organic Molecules (Applicant Zavadlav, Ph.D., Julija )
• Fourth-Generation Neural Network Potentials for Molecular Chemistry (Applicant Behler, Jörg )
• GML4Space: Generative Machine Learning Operating on Chemical Fragment Spaces (Applicant Rarey, Matthias )
• High Throughput Enabled Optimization of Machine Learning for Property Targeted Spiropyran Design (Applicants Hecht, Stefan ;  Reuter, Karsten )
• Highlighting molecular similarity using explainable artificial intelligence (Applicants Koch, Oliver ;  Risse, Benjamin )
• Machine learning approaches for faster discovery and adaptation of enzymes for difficult chemical reactions. (MacBioSyn 2.0) Phase II: predicting and expanding the enzymatic reaction scope to include new-to-nature reactions (Applicant Davari Dolatabadi, Ph.D., Mehdi )
• Machine Learning for asymmetric and electrochemical 3d transition metal catalyzed C–H activations (Applicant Ackermann, Lutz )
• Machine Learning for Molecular-Precision Design of Multifunctional Materials (Applicants Bocklitz, Thomas ;  Presselt, Martin )
• Machine Learning for Organocatalysis in the Small Data Regime (Applicant Schreiner, Peter R. )
• Machine-Learning-guided chemical space exploration: automatic creation and navigation of ultra-large open-source molecular libraries (Applicant Kolb, Peter )
• Machine learning of hierarchical ultrafast molecular forcefields (HUMF) (Applicant Wenzel, Wolfgang )
• Molecular Descriptors in Matrix Completion Methods (Applicants Jirasek, Fabian ;  Leitte, Heike )
• Multi-fidelity, active learning strategies for exciton transfer in cryptophyte antenna complexes (Applicants Kleinekathöfer, Ulrich ;  Zaspel, Peter )
• Overcoming the limits of remote functionalization through machine learning guided catalyst identification (Applicant Schoenebeck, Franziska )
• Reliable scoring and synthesis of bioactive molecules beyond combinatorial chemical space (Applicants Meiler, Jens ;  Stadler, Peter Florian )
• SAFE: Synthetically Accessible Fragment Space Extensions by Machine Learning-Based Approaches (Applicants Glorius, Frank ;  Rarey, Matthias )
• Understanding the interaction of organic molecules and metal ions by robot-based high-throughput experimentation and molecular machine-learning (Applicants Gräfe, Stefanie ;  Schubert, Ulrich S. )

• Spokesperson: Professor Dr. Frank Glorius