Computational Senior Scientist, Computer Aided Drug Design

 entry-level positions for talented computational Senior Scientists, Computer Aided Drug Design joining our cutting edge In Silico Discovery department

The positions require using computational methods in areas such as structure-based drug design, physics-based modeling, machine learning, co-folding and more, to identify hits, design molecules and drive our early drug discovery projects. A particular focus for these positions is to contribute to virtual screening (VS), physics-based methods (e.g. FEP) especially for VS, co-folding structure prediction and the increased overlap and use of these methods.

Tasks:

• Explore and develop workflows that lead to improvements for virtual screening and early hit-finding efforts. Assess and recommend best practices on for instance the use of free energy methods or co-folding for VS
• Work with others to explore and develop best practices for the use of co-folding in many different computational workflows
• In the long term, and with the support of colleagues, identify emerging technologies and methods in structure-based, physics-based, or 3D AIML fields and test and introduce them into In Silico Discovery
• Work with the broader VS team to contribute to the databases, evaluating methods, best practice workflows, VS informatics platform and improving success rates
• Impact drug discovery projects by developing and executing clear computational strategies and workflows to design complex molecules and predict their properties using structure-based and machine learning methodologies
• Contribute your recommendations to drug discovery project teams consisting of medicinal chemists, disease biologists, structural biologists, etc.
• external collaborations and consortia in the key areas mentioned: physics-based, VS, co-folding etc. Integrate collaboration deliverables internally
•  Silico Discovery with our global CADD, Drug Discovery Data Sciences, Cheminformatics and In Silico Biologics teams.
• Ensure optimal interaction/communication and provide updates on project status to discovery leadership

Required:

• A PhD in computational chemistry or a related field
• Good knowledge of chemistry and protein structure
• Experience working in 3D protein-ligand computational modeling, whether AIML or physics-based
• Strong problem-solving skills for developing creative, innovative solutions, and meeting project objectives are required
• Experience with HPC and general compute and job management
• Track record of scientific deliveries, including peer reviewed first-author publications and presentations at major national meetings is required
• Experience coding and developing workflows in Python
• understanding of medicinal chemistry principals and concepts that are applied in drug discovery
• Bonus:Computational chemistry Postdoctoral studies, limited industry experience or exposure to drug discovery is beneficial.

• Deeper multi-year exposure to areas such as free energy methods, or 3D AIML affinity or structure prediction
• Experience with open-source resources, libraries and toolkits such as ChEMBL, RDKit, etc
• Experience with modern AIML libraries and platforms
•  generative design
• Experience with commercial software packages for molecular modeling: Maestro (Schrodinger), Openeye, MOE (Chemical computing group)
• Experience with large chemical spaces used in virtual screening
• Experience with existing virtual screening methodologies such as docking, and ligand-based methods

The positions require using computational methods in areas such as structure-based drug design, physics-based modeling, machine learning, co-folding and more, to identify hits, design molecules and drive our early drug discovery projects. A particular focus for these positions is to contribute to virtual screening (VS), physics-based methods (e.g. FEP) especially for VS, co-folding structure prediction and the increased overlap and use of these methods.

Tasks:

• Explore and develop workflows that lead to improvements for virtual screening and early hit-finding efforts. Assess and recommend best practices on for instance the use of free energy methods or co-folding for VS
• Work with others to explore and develop best practices for the use of co-folding in many different computational workflows
• In the long term, and with the support of colleagues, identify emerging technologies and methods in structure-based, physics-based, or 3D AIML fields and test and introduce them into In Silico Discovery
• Work with the broader VS team to contribute to the databases, evaluating methods, best practice workflows, VS informatics platform and improving success rates
• Impact drug discovery projects by developing and executing clear computational strategies and workflows to design complex molecules and predict their properties using structure-based and machine learning methodologies
• Contribute your recommendations to drug discovery project teams consisting of medicinal chemists, disease biologists, structural biologists, etc.
• external collaborations and consortia in the key areas mentioned: physics-based, VS, co-folding etc. Integrate collaboration deliverables internally
•  Silico Discovery with our global CADD, Drug Discovery Data Sciences, Cheminformatics and In Silico Biologics teams.
• Ensure optimal interaction/communication and provide updates on project status to discovery leadership

Required:

• A PhD in computational chemistry or a related field
• Good knowledge of chemistry and protein structure
• Experience working in 3D protein-ligand computational modeling, whether AIML or physics-based
• Strong problem-solving skills for developing creative, innovative solutions, and meeting project objectives are required
• Experience with HPC and general compute and job management
• Track record of scientific deliveries, including peer reviewed first-author publications and presentations at major national meetings is required
• Experience coding and developing workflows in Python
• understanding of medicinal chemistry principals and concepts that are applied in drug discovery
• Bonus:Computational chemistry Postdoctoral studies, limited industry experience or exposure to drug discovery is beneficial.

• Deeper multi-year exposure to areas such as free energy methods, or 3D AIML affinity or structure prediction
• Experience with open-source resources, libraries and toolkits such as ChEMBL, RDKit, etc
• Experience with modern AIML libraries and platforms
•  generative design
• Experience with commercial software packages for molecular modeling: Maestro (Schrodinger), Openeye, MOE (Chemical computing group)
• Experience with large chemical spaces used in virtual screening
• Experience with existing virtual screening methodologies such as docking, and ligand-based methods

Required:

• A PhD in computational chemistry or a related field
• Good knowledge of chemistry and protein structure
• Experience working in 3D protein-ligand computational modeling, whether AIML or physics-based
• Strong problem-solving skills for developing creative, innovative solutions, and meeting project objectives are required
• Experience with HPC and general compute and job management
• Track record of scientific deliveries, including peer reviewed first-author publications and presentations at major national meetings is required
• Experience coding and developing workflows in Python
• understanding of medicinal chemistry principals and concepts that are applied in drug discovery
• Bonus:Computational chemistry Postdoctoral studies, limited industry experience or exposure to drug discovery is beneficial.

• Deeper multi-year exposure to areas such as free energy methods, or 3D AIML affinity or structure prediction
• Experience with open-source resources, libraries and toolkits such as ChEMBL, RDKit, etc
• Experience with modern AIML libraries and platforms
•  generative design
• Experience with commercial software packages for molecular modeling: Maestro (Schrodinger), Openeye, MOE (Chemical computing group)
• Experience with large chemical spaces used in virtual screening
• Experience with existing virtual screening methodologies such as docking, and ligand-based methods