Bioinformatics; Peptide Design; Membrane; Antibiotics; Drug discovery
Müller Alex T., Hiss Jan A., Schneider Gisbert (2018), Recurrent Neural Network Model for Constructive Peptide Design, in Journal of Chemical Information and Modeling
, 58(2), 472-479.
Gupta Anvita, Müller Alex T., Huisman Berend J. H., Fuchs Jens A., Schneider Petra, Schneider Gisbert (2018), Generative Recurrent Networks for De Novo Drug Design, in Molecular Informatics
, 37(1-2), 1700111-1700111.
Pillong Max, Hiss Jan A., Schneider Petra, Lin Yen-Chu, Posselt Gernot, Pfeiffer Bernhard, Blatter Markus, Müller Alex T., Bachler Simon, Neuhaus Claudia S., Dittrich Petra S., Altmann Karl-Heinz, Wessler Silja, Schneider Gisbert (2017), Rational Design of Membrane-Pore-Forming Peptides, in Small
, 13(40), 1701316-1701316.
Stutz Katharina, Müller Alex T., Hiss Jan A., Schneider Petra, Blatter Markus, Pfeiffer Bernhard, Posselt Gernot, Kanfer Gil, Kornmann Benoît, Wrede Paul, Altmann Karl-Heinz, Wessler Silja, Schneider Gisbert (2017), Peptide–Membrane Interaction between Targeting and Lysis, in ACS Chemical Biology
, 12(9), 2254-2259.
Müller Alex T., Gabernet Gisela, Hiss Jan A., Schneider Gisbert (2017), modlAMP: Python for antimicrobial peptides, in Bioinformatics
, 33(17), 2753-2755.
Schneider Petra, Müller Alex T., Gabernet Gisela, Button Alexander L., Posselt Gernot, Wessler Silja, Hiss Jan A., Schneider Gisbert (2017), Hybrid Network Model for “Deep Learning” of Chemical Data: Application to Antimicrobial Peptides, in Molecular Informatics
, 36(1-2), 1600011-1600011.
Armbrecht L., Gabernet G., Kurth F., Hiss J. A., Schneider G., Dittrich P. S. (2017), Characterisation of anticancer peptides at the single-cell level, in Lab on a Chip
, 17(17), 2933-2940.
Müller Alex T., Kaymaz Aral C., Gabernet Gisela, Posselt Gernot, Wessler Silja, Hiss Jan A., Schneider Gisbert (2016), Sparse Neural Network Models of Antimicrobial Peptide-Activity Relationships, in Molecular Informatics
, 35(11-12), 606-614.
Gawehn Erik, Hiss Jan A., Schneider Gisbert (2016), Deep Learning in Drug Discovery, in Molecular Informatics
, 35(1), 3-14.
Gabernet G., Müller A. T., Hiss J. A., Schneider G. (2016), Membranolytic anticancer peptides, in MedChemComm
, 7(12), 2232-2245.
In the proposed project we will investigate and extract sequence features of lipid membrane-lytic peptides. The study integrates both computational and biochemical experiments. We introduce the concept of "peptide-morphing" as a means for the systematic analysis and generation of structure-activity relationship models. The morphing process allows for physicochemically-motivated quasi-continuous sequence transitions which we will monitor by biophysical measurements. The gathered experimental data serves as guidance for the subsequent de novo peptide design with modulated membrane activity and defined biophysical properties. The research project is structured in three tiers, the i) computational design and biophysical/biochemical characterization of antimicrobial peptides and their morphed derivatives, ii) investigation of the property patterns that are responsible for the mechanisms of action of cationic helical antimicrobial peptides, and iii) development and implementation of software algorithms for length-invariant de novo design of peptides with the desired activity spectra. The project will result in profound insights into the biophysical nature of peptide-membrane interaction and help elicit the causative amino acid sequence patterns. From the perspective of applied research, the projects addresses the pressing need for new antibacterial molecular agents by translating these insights into an original algorithm for the rational design of membrane-active peptides with modulated levels of activity.