Cheminformatics and Machine Learning
Electronic laboratory notebooks (ELN)
As a member of the NFDI4Chem consortium we are involved in the further development of the Chemotion electronic laboratory notebook (ELN) application.
- D. Rauh, C. Blankenburg, T. Fischer, N. Jung, S. Kuhn, U. Schatzschneider, T. Schulze, Steffen Neumann, Data format standards in analytical chemistry, Pure Appl. Chem. 94, 725-736 (2022)
Digital molecular representations
We are one of the lead developers of TUCAN, a molecular identifier and descriptor for all domains of chemistry. Based on the NetworkX python library, TUCAN will generate a canonical string representation of any molecule and also allows you to add custom node and edge attributes for machine learning (ML) applications.
You can try an online demo version of the TUCAN package here which exclusively runs inside a browser window.
- J.C. Brammer, G. Blanke, C. Kellner, A. Hoffmann, S. Herres-Pawlis, U. Schatzschneider, TUCAN: A molecular identifier and descriptor applicable to the whole periodic table from hydrogen to oganesson, J. Cheminf. 14, 66 (2022)
Machine Learning (ML)
In future projects, we want to tap into the data collected in the ELN sub-project for machine learning applications. In particular, we are interested in the prediction of NMR chemical shifts and luminescence properties.
- M. Krenn, Q. Ai, S. Barthel, N. Carson, A. Frei, N.C. Frey, P. Friederich, T. Gaudin, A.A. Gayle, K.M. Jablonka, R.F. Lameiro, D. Lemm, A. Lo, S.M. Moosavi, J.M. Nápoles-Duarte, A.K. Nigam, R. Pollice, K. Rajan, U. Schatzschneider, P. Schwaller, M. Skreta, B. Smit, F. Strieth-Kalthoff, C. Sun, G. Tom, G.F. von Rudorff, A. Wang, A. White, A. Young, R. Yu, A. Aspuru-Guzik, SELFIES and the future of molecular string representations, Patterns 3, 100588 (2022)
