We seek a driven and technically adept Postdoctoral Fellow to develop and deploy a comprehensive chemical probes library and machine learning-driven assessment tool to inform cancer translational research. The primary research focus is to apply cutting-edge cheminformatics and data science methods to curate and quantitatively assess chemical probes used throughout the literature using factors such as selectivity and potency, among others. In particular, the aim is two-fold: to identify the most informative chemical probes and to avoid the usage of misleading probes for a particular problem. These efforts will directly impact novel drug discovery at MD Anderson as well as inform the wider community on the application of the right probe for the right problem.

LEARNING OBJECTIVES
Gain a molecular understanding of probes, their features, and their applications. Curate a knowledge base to advance target validation as part of drug development. Build predictive models that evaluate a probe's fitness for given applications.

ELIGIBILITY REQUIREMENTS
Individuals with a PhD degree in computational or medicinal chemistry, computational structural biology, or data science with a strong history of application in the life sciences are encouraged to apply. A strong computational background is required, with proficiency in Python. Familiarity with RDKit, DeepChem, and other cheminformatics libraries is essential. Experience working in a high-performance computing environment (Unix/Linux) is highly preferred. Some understanding of cancer biology and molecular biology is a plus, but a desire to expand in these related fields is crucial. The ability to work with multidisciplinary partners is a must. A strong publication