PhD student position in multi-modal AI for biomolecular engineering
at Chalmers
Göteborg, Västra Götalands län, Sweden -
Start Date | Expiry Date | Salary | Posted On | Experience | Skills | Telecommute | Sponsor Visa |
---|---|---|---|---|---|---|---|
Immediate | 23 Sep, 2024 | Not Specified | 09 Aug, 2024 | 5 year(s) or above | Molecular Modeling,English,Communication Skills,Biology,Deep Learning,Computer Science,Swedish,Chemistry | No | No |
Required Visa Status:
Citizen | GC |
US Citizen | Student Visa |
H1B | CPT |
OPT | H4 Spouse of H1B |
GC Green Card |
Employment Type:
Full Time | Part Time |
Permanent | Independent - 1099 |
Contract – W2 | C2H Independent |
C2H W2 | Contract – Corp 2 Corp |
Contract to Hire – Corp 2 Corp |
Description:
For this project, the PhD candidate will work on a novel, multi-modal deep learning approach to accelerate computational drug discovery, with a focus on degraders, ADME modeling, and generative AI. The PhD candidate will work in the AI Laboratory for Molecular Engineering, led by Assist. Prof. Rocío Mercado Oropeza at Chalmers. This position is funded by the Swedish Research Council.
PROJECT DESCRIPTION
Data-driven approaches to drug design, such as deep biomolecular generative models, have emerged as powerful strategies for engineering new molecules with desired properties and repurposing existing molecules for new tasks. As implied by the term “data-driven”, these methods require large amounts of data to make accurate predictions, ranging from structural and biochemical information about targets and ligands, to genomic and phenotypic data. Such data can be used to build computational models which improve our understanding of the complex relationships between molecular structure and biological function. By using machine learning, statistical modeling, and simulation, data-driven drug design can help identify new drug candidates, optimize leads, and predict drug efficacy and toxicity with greater accuracy and speed than with traditional rule-based methods.
One key advantage of data-driven drug design is its ability to account for the many factors that affect drug behavior in vivo, including pharmacokinetics, pharmacodynamics, and toxicity, before synthesizing and testing a compound. By integrating data from multiple sources and applying data-driven methods, generative models can propose new drug candidates which fulfill a desired property profile, or repurpose existing drugs for new indications, with greater efficiency and precision than traditional drug discovery approaches. Furthermore, data-driven drug design enables the development of personalized medicine by enabling the identification of patient subpopulations that may benefit from specific drugs, doses, or drug combinations.
Of particular interest in this project are new modalities for targeted protein degradation, such as PROteolysis TArgeting Chimeras (PROTACs), Regulated Induced Proximity TArgeting Chimeras (RIPTACs), etc. Multi-target therapeutic modalities such as these have become increasingly important for the treatment of complex diseases like cancer, cardiovascular disease, and neurodegenerative disorders. Unlike traditional single-target drugs that aim to modulate the activity of a single protein or pathway, multi-target drugs are designed to simultaneously interact with multiple targets involved in the disease pathway(s) that contribute to disease progression. By modulating multiple targets, multi-target drugs can achieve synergistic effects, reduce the risk of drug resistance, and improve therapeutic outcomes. Multi-target drugs can offer a more comprehensive approach to disease treatment than single-target drugs by addressing the complexity and heterogeneity of a range of diseases. They can, for instance, be used to target proteins without well-defined binding pockets, and their catalytic mechanism of action means lower doses could potentially be used to observe a desired therapeutic effect.
QUALIFICATIONS
To qualify as a PhD student, applicants must have a master’s level degree corresponding to at least 240 higher education credits in Computer Science, Chemistry, Biology, or a related field. The applicant should have strong background and experience in Python programming and deep learning. Previous experience in Generative AI and/or molecular modeling is a merit, but not required.
The position requires sound verbal and written communication skills in English. If Swedish is not your native language, Chalmers offers Swedish courses.
Responsibilities:
The major responsibilities for a PhD student position in the division include conducting doctoral research and coursework. By the end of the PhD, students will be able to identify novel research directions and design the appropriate computational experiments to answer key questions. Students are expected to effectively communicate the results of their research verbally and in writing, and will receive specific training towards building these skills. This position also includes teaching at Chalmers’ undergraduate level, or performing other teaching duties corresponding to 20% of working hours. The appointment is a full-time temporary employment for a period of not more than 5 years, funded by the Swedish Research Council.
Read more about doctoral studies at Chalmers here.
REQUIREMENT SUMMARY
Min:5.0Max:10.0 year(s)
Education Management
IT Software - Application Programming / Maintenance
Education, Teaching
Graduate
Proficient
1
Göteborg, Sweden