Computational Chemistry and Molecular Design
Provide hands-on computational chemistry support to small-molecule discovery programs from target evaluation, hit identification, hit-to-lead, and lead optimization through candidate nomination.
Apply structure-based and ligand-based design approaches to guide compound design, including docking, molecular dynamics, pharmacophore modeling, QSAR, scaffold hopping, virtual screening, FEP/free-energy methods, and multi-parameter optimization.
Use structural biology data, including X-ray structures, cryo-EM structures, homology models, and AlphaFold-derived models, to generate actionable design hypotheses.
Partner with the medicinal chemistry team to interpret SAR, optimize potency, selectivity, physicochemical properties, ADME/PK, developability, and synthetic feasibility.
Contribute to computational design discussions with project teams and translate complex modeling results into clear, practical medicinal chemistry recommendations.
Support portfolio prioritization by evaluating target tractability, ligandability, binding-site quality, chemical matter, and developability risks.
Cheminformatics and Data Infrastructure
Use and help improve chem and bioinformatics tools that support compound registration, structure-searching, SAR analysis, property visualization, compound triage, library design, and project decision-making.
Apply tools for chemical data handling, including similarity and substructure searching, R-group analysis, matched molecular pairs, reaction enumeration, compound clustering, property prediction, and visualization.
Work with internal or external engineering and data science teams to integrate chemical, biological, DMPK, structural, and assay data into usable project dashboards and design tools.
Follow best practices for chemical data quality, assay data curation, compound annotation, metadata standards, and reproducible computational workflows.
Use commercial and open-source computational tools, including platforms such as Schrödinger, MOE, CCDC tools, ChemAxon, KNIME, Pipeline Pilot, RDKit, DataWarrior, Spotfire, and related systems.
AI/ML and Digital Chemistry Tools
Apply user-friendly AI/ML-enabled molecular design tools, including generative chemistry, predictive ADME/Tox models, property prediction, active learning, virtual screening, and decision-support systems.
Help incorporate AI tools into the DMTA cycle, including compound prioritization, library design, synthetic route ideation, molecular-property prediction, and design hypothesis generation.
Support AI literacy across chemistry and project teams by helping colleagues understand appropriate use, limitations, and interpretation of predictive models.
Help develop workflows that allow medicinal chemists to use modeling and AI tools without requiring deep computational expertise.
Collaboration and Continuous Improvement
Contribute to the computational chemistry approach for projects and align it with discovery program needs.
Serve as a subject-matter resource for computational chemistry, cheminformatics, AI-enabled design, and molecular modeling.
Support collaborations with CROs, software vendors, academic groups, and computational chemistry consultants where appropriate.
Represent computational chemistry in project team meetings and program discussions.
Maintain awareness of emerging computational, AI, and cheminformatics technologies and recommend adoption where scientifically and operationally justified.