Hybrid of all methods above

For the hit identification we rely on the combination of different methods used and developed in our group. The workflow follows the visual inspection of all structures together with quality assessment in order to choose the most suitable virtual screening workflow.

Expansion of the co-crystallized fragments is planned to be done in parallel from two main approaches:

i) our in-house protocol Artificial Intelligence-driven Optimization of Ligands (AIOLI) that incorporates various enumeration methods: reaction-based (e.g. with Synthesia), Rgroup-based, scaffold hopping, and similarity searches in large chemical spaces (e.g. Ftrees and SpaceLight searches in the Enamine REAL Space) together with our in-house state of the art retrosynthesis tool CHAI ("Chemistry with Artificial Intelligence").

ii) use of molecular field-based method Ignite, developed jointly with Cresset, which allows tridimensional complementary searches for the hit identification process.

On both approaches the filtering of undesirable chemical matter will be applied using a large Bayer proprietary collection of structure filter definitions, grown over years with Bayer's Medicinal Chemistry knowledge. We will apply Bayer's in silico ADMET platform for additional filtering to find compounds suitable for lead-optimization.

Generated compounds will be further filtered and prioritized by Docking with Glide (Schrödinger Inc.) and Absolute Binding Free Energy Perturbation (ABFEP, Schrödinger Inc.).

 

 

 

Our approach combines many state-of-the-art in silico methods. AI-driven versatile virtual compound generation methods in conjunction with retrosynthesis models trained with in-house data produce novel lead compounds that are further evaluated with a large scale FEP calculation. This approach is available from one common design platform, called AIOLI and it is used as one of the main workflows for our drug discovery projects. Therefore, we will be able to tackle the challenge with a broader methodological spectrum in the most efficient way.

Artificial Intelligence-driven Optimization of Ligands (AIOLI)

• Pipeline Pilot (BioVia)
• Spark, Ignite (Cresset)
• Glide, ABFEP (Schrodinger)
• FlexX, Ftrees, SpaceLight (BioSolveIT)
• Synthesia (Univ. Hamburg) -> free for academic use
• Arthor (NextMove)

Winter, R.; Montanari, F.; Steffen, A.; Briem, H.; Noé, F.; Clevert, D.-A.:

Efficient Multi-Objective Molecular Optimization in a Continuous Latent Space.

Chem. Sci., 10:8016-8024 (2019)

 

Dolfus, U.; Briem, H.; Rarey, M.:

Synthesis-Aware Generation of Structural Analogs

J. Chem. Inf. Mod. (2022) 62, 15, 3565–3576

 

Mortier, J.; Friberg, A.; Badock, V.; Moosmayer, D.; Schroeder, J.; Steigemann, P.; Siegel, F.; Gradl, S.; Bauser, M.; Hillig, R.C.; Briem, H.; Eis, K.; Bader, B.; Nguyen, D.; Christ, C.D.:

Computationally Empowered Workflow Identifies Novel Covalent Allosteric Binders for KRASG12C

ChemMedChem 15, 827-832 (2020)

 

AIOLI: Oral presentations @ Biovia user group meeting 2020 and ICCS Noordwijkerhout 2022

Ignite: Oral presentation @ Cresset User Group Meeting 2021 and German Cheminformatics Conference 2022