Machine learning lies at the core of insitro’s approach to rethinking drug discovery and development. As our first structural biology scientist you will take on a key role, bridging our machine learning and drug design teams, working closely with engineers and scientists in these fields to create, organize and analyze large scale datasets relating ligand structure to protein-binding affinity. You will be a member of cross-functional teams, comprised of machine learning engineers, life scientists, bioengineers, automation engineers and data scientists, bringing machine learning to bear on the challenges of molecular target discovery and drug design. You will demonstrate world-class research skills and experience in developing and using cutting-edge tools to study protein structure/function, and protein-ligand interactions. You will also demonstrate strong interpersonal skills, an ability to influence multidisciplinary teams, a strong collaborative work ethic, the ability to adapt to changing needs, and the capacity to multitask to meet key goals. Strong communication and presentation skills are essential to success in this position.
Specifically, you will:
- Lead the design of protein constructs to support our DNA-encoded library selection platform and structure-based drug design projects
- Oversee external partnerships delivering proteins as well as X-ray crystallographic data to support internal programs
- Be an integral member of drug discovery project teams, contributing protein structure/function insights to optimize ligand design
- Develop methods for data mining and analysis of protein structure datasets, and internally-generated protein-ligand interaction datasets.
- Develop methods for retrieving and archiving data on protein structures and protein-ligand interactions for use in the generation of machine learning models.
- Identify protein binding site classifications and trends from such databases using mathematical techniques.
- Enhance insitro’s current suite of informatics tools to advance our protein informatics and drug design environment, and integrate them with our machine learning platform.
- Identify and evaluate new modeling and informatics technology and software applications for analyzing protein structure/function and protein-ligand interactions from commercial sources or through external collaborations.
- Contribute to the design of molecule screening strategies based upon protein structural insights.
- Contribute to the design of small molecule libraries based upon structural insights gleaned from mining the protein data bank.
- Design and develop novel tools for analyses and visualization of chemical, biological, and structural data.
You will be joining the founding team of a biotech startup that has long-term stability due to significant funding, but yet is very much in formation. Much can change in this early and exciting phase, providing many opportunities for significant impact. You will work closely with an exceptionally talented team, learn a broad range of skills, and help shape insitro’s culture, strategic direction, and outcomes. Join us, and help make a difference to patients!
- Ph.D. in protein X-ray crystallography, protein NMR or cryo-EM, protein design or equivalent experience
- 5+ years of relevant experience in the pharmaceutical or biotech industry
- An outstanding scientific track record in your area of expertise
- Good working knowledge of the protein data bank, uniprot, and other online chemical and biological databases.
- Good working knowledge of common biases and other problems in deposited protein structures, and practical experience in removing such problems.
- Experience in CADD strategies, including: structure-based drug design, molecular docking, molecular simulations, virtual screening, free-energy perturbation methods.
- A demonstrated deep understanding of 3D protein-ligand interactions applied to molecular design concepts
- Experience in applying protein structural information to solving problems in data mining, implementing new tools, and generating automated workflows
- Excellent oral and written communication skills
- Ability to communicate effectively and collaborate with people of diverse backgrounds and job functions in a fast-paced, goal-oriented team environment
- Passion for making a difference in the world
Nice to Have
- Good working knowledge of medicinal and organic chemistry, DMPK, and preclinical toxicology principles
- Experience in machine learning and bioinformatics
- Experience with using PHENIX or other softwares used for determination of molecular structures
- Experience with homology modeling and/or other template based structural modeling techniques
- Working knowledge of existing application containment systems (Docker etc), molecular software (RDKit, Schrodinger suite), and pipeline managers (Knime, Airflow, Nextflow etc)
- Experience with biological data (DNA sequences, RNAseq, proteomics, microscopy images, etc.)
- A demonstrated expertise in scientific programming (e.g., Python, Java, C++, SVL) with practical application of these skills is a strong plus
- Familiarity with cloud computing services (AWS)
insitro is a data-driven drug discovery and development company using machine learning and data generation at scale to transform the way that drugs are discovered and delivered to patients. insitro’s approach focuses on the development of predictive machine learning models to be brought to bear on key bottlenecks in pharmaceutical R&D. The company has established enabling collaborations with Gilead in NASH and Bristol Myers Squibb in ALS. insitro is located in South San Francisco, CA and has been supported by top tech, biotech, and crossover investors since formation in 2018. For more information on insitro, please visit the company’s website at www.insitro.com.