Umeå University announces a stipend for postdoctoral qualification in machine learning focusing on sequence modeling for protein property prediction. The deadline for application is May, 31, 2021.
The Department of Computing Science (www.cs.umu.se) is a dynamic department with about 140 employees from over twenty countries. We are providing research and education within a broad spectrum of areas, and offer education on basic, advanced, and PhD levels. The research is internationally well recognized and includes basic research, methods development, and software development, but also research and development within various application domains.
We seek a highly motivated postdoctoral researcher with established expertise in sequence modeling. Extensive experience in machine learning or experience with (plant) protein sequence data is a merit.
An aim in the European Green Deal is sustainable food production. One important step towards reaching this goal is to reduce fertilizer application in agriculture — a major contributor to pollution. To reduce nutrient losses and fertilizer input, it is of great importance to interconnect different research disciplines and to engage in joint advances. Reduction of applied fertilizer can be achieved through improvement of nutrient uptake and thorough characterization of involved plant proteins. More efficient uptake processes would automatically reduce nutrient losses and the need for over-fertilization. Most knowledge generated to date is based on laborious trial-and-error-approaches and result in time-consuming and costly wet lab research experiments.
Recent developments in machine learning have opened up for significant improvements in many different areas of life science. In particular, sequence models, such as large transformer models, can be used to encode protein sequences. Intrinsic biological properties of proteins are retained in the encoded proteins, in their embedding spaces, when training sequence models on large-scale protein sequence data. In this project, we will use and tailor-make such embeddings to predict protein properties. The aim of this project is thus to develop novel machine learning methods, specifically sequence methods, to investigate protein characteristics which will fast-track the hands-on lab work performed in a parallel applied project.
This is a collaborative research project between associate professor Tommy Löfstedt at the Department of Computing Science and post-doctoral fellow Regina Gratz at the Swedish University of Agricultural Sciences (SLU). The successful candidate will get the opportunity to collaborate with PhD students active within the parallel applied project at SLU.
The stipend is financed by the Kempe foundations and is for two years with a starting date to be negotiated.
A qualified applicant is required to have a PhD degree or a foreign degree that is deemed equivalent in Computer Science, Mathematics, Statistics, Bioinformatics, or another subject of relevance for the project. Priority should be given to candidates who have completed their doctoral degree no more than three years before the closing date of the application. A candidate who has completed their degree prior to this may be considered if special circumstances exist. Special circumstances include absence due to illness, parental leave or clinical practice, appointments of trust in trade unions or similar circumstances.
Documented knowledge and proven research experiences in sequence modeling is required. A very good command of the English language, both written and spoken, are key requirements.
A successful candidate should be capable of performing numerical implementations of theoretical models as well as producing scientific publications in English. The applicant should be strongly motivated and interested in developing new competences, as well as to act in an international environment.
Good research merits and scientific publications in the area of the position are strongly meriting. Extensive experience with machine learning, large transformer models, natural language processing, interpretability, or protein sequence data is a merit. International research experience is also a merit.
The application should include:
Submit your application as a PDF marked with the reference number FS 2.1.6-881-21, both in the file name and in the subject field of the email, to email@example.com. The application can be written in English (preferably) or Swedish. Application deadline is May 31, 2021.
The Department of Computing Science values the qualities that an even gender distribution brings to the department, and therefore we particularly encourage women to apply for the stipend.
For more information, please contact associate professor Tommy Löfstedt, firstname.lastname@example.org.
We look forward to receiving your application.Continue reading
|Title||Postdoc in machine learning focusing on sequence modeling for protein property predictions|
|Job location||Biblioteksgränd 6, 901 87 Umeå|
|Published||April 23, 2021|
|Application deadline||May 31, 2021|
|Job types||Postdoc  |
|Fields||Biostatistics,   Botany and plant science,   Food Science,   Bioinformatics,   Plant Fertilization, Animal and Human Nutrition,   Computational Biology,   Machine Learning  |