2 code implementations • 25 Apr 2024 • Jonas Teufel, Pascal Friederich
Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.
no code implementations • 2 Feb 2024 • Henrik Schopmans, Pascal Friederich
Recently, instead of generating long molecular dynamics simulations, generative machine learning methods such as normalizing flows have been used to learn the Boltzmann distribution directly, without samples.
no code implementations • 11 Oct 2023 • Jannik Deuschel, Caleb N. Ellington, Yingtao Luo, Benjamin J. Lengerich, Pascal Friederich, Eric P. Xing
Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models force a tradeoff between accuracy and interpretability, limiting data-driven interpretations of human decision-making processes.
no code implementations • 3 Jun 2023 • Hunter Sturm, Jonas Teufel, Kaitlin A. Isfeld, Pascal Friederich, Rebecca L. Davis
As the importance of high-throughput screening (HTS) continues to grow due to its value in early stage drug discovery and data generation for training machine learning models, there is a growing need for robust methods for pre-screening compounds to identify and prevent false-positive hits.
no code implementations • 25 May 2023 • Jonas Teufel, Luca Torresi, Pascal Friederich
In this work, we extend artificial simulatability studies to the domain of graph neural networks.
1 code implementation • 21 Mar 2023 • Henrik Schopmans, Patrick Reiser, Pascal Friederich
However, training directly on simulated diffractograms from databases such as the ICSD is challenging due to its limited size, class-inhomogeneity, and bias toward certain structure types.
1 code implementation • 27 Feb 2023 • Robin Ruff, Patrick Reiser, Jan Stühmer, Pascal Friederich
Graph neural networks (GNNs) have been applied to a large variety of applications in materials science and chemistry.
3 code implementations • 23 Nov 2022 • Jonas Teufel, Luca Torresi, Patrick Reiser, Pascal Friederich
Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of task specifications.
1 code implementation • 23 Nov 2022 • André Eberhard, Houssam Metni, Georg Fahland, Alexander Stroh, Pascal Friederich
Transfer of recent advances in deep reinforcement learning to real-world applications is hindered by high data demands and thus low efficiency and scalability.
no code implementations • 5 Aug 2022 • Patrick Reiser, Marlen Neubert, André Eberhard, Luca Torresi, Chen Zhou, Chen Shao, Houssam Metni, Clint van Hoesel, Henrik Schopmans, Timo Sommer, Pascal Friederich
Machine learning plays an increasingly important role in many areas of chemistry and materials science, e. g. to predict materials properties, to accelerate simulations, to design new materials, and to predict synthesis routes of new materials.
no code implementations • 4 Apr 2022 • Mario Krenn, Robert Pollice, Si Yue Guo, Matteo Aldeghi, Alba Cervera-Lierta, Pascal Friederich, Gabriel dos Passos Gomes, Florian Häse, Adrian Jinich, AkshatKumar Nigam, Zhenpeng Yao, Alán Aspuru-Guzik
Imagine an oracle that correctly predicts the outcome of every particle physics experiment, the products of every chemical reaction, or the function of every protein.
1 code implementation • 31 Mar 2022 • Mario Krenn, Qianxiang Ai, Senja Barthel, Nessa Carson, Angelo Frei, Nathan C. Frey, Pascal Friederich, Théophile Gaudin, Alberto Alexander Gayle, Kevin Maik Jablonka, Rafael F. Lameiro, Dominik Lemm, Alston Lo, Seyed Mohamad Moosavi, José Manuel Nápoles-Duarte, AkshatKumar Nigam, Robert Pollice, Kohulan Rajan, Ulrich Schatzschneider, Philippe Schwaller, Marta Skreta, Berend Smit, Felix Strieth-Kalthoff, Chong Sun, Gary Tom, Guido Falk von Rudorff, Andrew Wang, Andrew White, Adamo Young, Rose Yu, Alán Aspuru-Guzik
We hope that these proposals will inspire several follow-up works exploiting the full potential of molecular string representations for the future of AI in chemistry and materials science.
1 code implementation • 7 Mar 2021 • Patrick Reiser, Andre Eberhard, Pascal Friederich
Graph neural networks are a versatile machine learning architecture that received a lot of attention recently.
no code implementations • 2 Feb 2021 • Patrick Reiser, Manuel Konrad, Artem Fediai, Salvador Léon, Wolfgang Wenzel, Pascal Friederich
Organic semiconductors are indispensable for today's display technologies in form of organic light emitting diodes (OLEDs) and further optoelectronic applications.
1 code implementation • 19 Jan 2021 • Yuri Koide, Arjun J. Kaithakkal, Matthias Schniewind, Bradley P. Ladewig, Alexander Stroh, Pascal Friederich
Numerical simulation of fluids plays an essential role in modeling many physical phenomena, which enables technological advancements, contributes to sustainable practices, and expands our understanding of various natural and engineered systems.
no code implementations • 27 Oct 2020 • Pascal Friederich, Mario Krenn, Isaac Tamblyn, Alan Aspuru-Guzik
Machine learning with application to questions in the physical sciences has become a widely used tool, successfully applied to classification, regression and optimization tasks in many areas.
no code implementations • 24 Feb 2020 • Daniel Flam-Shepherd, Tony Wu, Pascal Friederich, Alan Aspuru-Guzik
Graph neural network have achieved impressive results in predicting molecular properties, but they do not directly account for local and hidden structures in the graph such as functional groups and molecular geometry.
2 code implementations • ICLR 2020 • AkshatKumar Nigam, Pascal Friederich, Mario Krenn, Alán Aspuru-Guzik
Challenges in natural sciences can often be phrased as optimization problems.
2 code implementations • 31 May 2019 • Mario Krenn, Florian Häse, AkshatKumar Nigam, Pascal Friederich, Alán Aspuru-Guzik
SELFIES can be directly applied in arbitrary machine learning models without the adaptation of the models; each of the generated molecule candidates is valid.