We are seeking a talented Computational Scientist to carry out impactful and boundary-pushing research at the intersection of AI and Drug Development. While there have been major advances in the development of AI/ML algorithms, to enable Human-Machine Partnership in the context of Drug Development it is crucial that the models be explainable and generalizable. To this end, new methodologies need to be developed and demonstrated on large, longitudinal clinical datasets.

The AI Postdoctoral Fellow will develop methodologies for generating causal explanations from Neural-ODE models, to help surmount the existing challenges associated with the use of saliency maps on longitudinal data. A second focus revolves around using mechanism-informed Graph Neural Networks (GNNs) to enhance the generalizability of neural-ODE models, by leveraging the insight that models built on established mechanistic basis tend to enable better extrapolations. We expect that the research outcome will be published in top tier journals as well as influence the best practices within the drug development industry.

Requirements:

The candidate should possess a PhD in a quantitative discipline (Computer Science/Computational Sciences, Biomedical Informatics, Mathematics, Physics, Engineering, Pharmacometrics, Statistics, and others) and a track record of developing and implementing innovative ideas. Knowledge and/or experience with Neural-ODE, Graph Neural Networks and other Deep Learning architectures for longitudinal data are highly desirable. Experience with Pharmacometrics and Quantitative Systems Pharmacology (QSP) models is not required, but would be a plus. Excellent communications skills and a strong publication record are expected.

Relocation benefits are available for this position

Relevant publications:

• Lu, J., Bender, B., Jin, J.Y. and Guan, Y., 2021. Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modelling. Nature Machine Intelligence, pp.1-9.
• Lu, J., Deng, K., Zhang, X., Liu, G. and Guan, Y., 2021. Neural-ODE for pharmacokinetics modeling and its advantage to alternative machine learning models in predicting new dosing regimens. iScience, 24(7), p.102804.
• Sundrani, S. and Lu, J., 2021. Computing the Hazard Ratios Associated With Explanatory Variables Using Machine Learning Models of Survival Data. JCO Clinical Cancer Informatics, 5, pp.364-378.
• Bazgir, O., Zhang, R., Dhruba, S.R., Rahman, R., Ghosh, S. and Pal, R., 2020. Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks. Nature communications, 11(1), pp.1-13.

For information about the Postdoctoral Program at Genentech, please go to: https://www.gene.com/careers/university-and-early-career/postdocs

#gREDinformatics

#LI-PL1

#postdoc

Genentech is an equal opportunity employer, and we embrace the increasingly diverse world around us. Genentech prohibits unlawful discrimination based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin or ancestry, age, disability, marital status and veteran status.

Genentech requires all new hires to be fully vaccinated against COVID-19 as of their start date. This requirement is a condition of employment at Genentech, and it applies regardless of whether the position is located at a Genentech campus or is fully remote.  If you are unable to receive the vaccine due to a disability or serious medical condition, or because it is prohibited as a result of your sincerely held religious beliefs, you will have an opportunity to request a reasonable accommodation.