Marie-Sklodowska Curie PROTrEIN-ITN Early Stage Researcher (Ph.D. student) position:
Machine Learning predictions of peptide behaviour for improved identification of modified peptides
The Flemish Institute for Biotechnology (VIB) in Ghent is a life sciences research institute that operates in close partnership with Ghent University. Dedicated to cutting-edge basic research with a strong focus on translating scientific results into pharmaceutical, medical, agricultural, and industrial applications.
Thanks to the hard work of many people for almost 25 years and the support of sustained investment by the government of Flanders, VIB is widely recognized as an established and world-leading knowledge center in life sciences and biotechnology with an excellent reputation in technology transfer.
The framework agreement between VIB and Ghent University stipulates the ability of VIB researchers to register in the Doctoral Programme at Ghent University and obtain their Ph.D. at Ghent University. Today Ghent University attracts over 43,000 students, with a foreign student population of about 10% (42% of Ph.D. students) and employs around 7,300 academic staff members. Ghent University is 66th in the Shanghai ranking and 103rd in the Times ranking.
About the Project
PROTrEIN (www.protrein.eu) is a European Innovative Training Network composed of 11 beneficiaries, and 6 partner organizations, from the academic and non-academic sectors (including two SMEs and two large companies).
The network’s mission is to train a new generation of computational proteomics researchers by providing them an inter-sectoral and interdisciplinary set of skills to tackle the main challenges in the field and improve their future employability.
This position is for the Machine Learning research part of the project. Please find more information at http://protrein.eu/project/mac...
The overall objective of this research project is to enable a much more sensitive yet reliable identification of (modified) peptides through DDA and DIA approaches. This will be achieved through four sub-goals: first, a novel predictor will be made for ion mobility behaviour (collisional cross-section) of (modified) peptides; second, a novel predictor will be made for the retention time of (modified) peptides; third, based on these two predictors alongside our existing MS2PIP predictor for fragmentation spectra, advanced theoretical spectral libraries will be built for DIA-based identification; fourth, we will add these two predictors to complement the core modules in our existing cloud-based ionbot tool (https://ionbot.cloud) for open modification searching in DDA data.
Machine Learning approaches to predict analyte behaviour; gradient boosting and deep learning algorithms will be employed, based on large amounts of available public data.
- Python programming (Numpy, Pandas)
- Experience with a Python Machine Learning library (e.g. Scikit-learn).
Nice to have
- Experience in Deep Learning
- Programming in C, C++
- Host: FHOOE (V. Dorfer), Duration: 1 Month; When: Year 1; Goal: Analysis of chimeric MS2 spectra.
- Host: CRG (E. Sabido), Duration: 3 Month; When: Year 2; Goal: Experience in DIA proteomics acquisition methods.
- Host: EMBO (B. Pulverer), Duration: 2 Weeks, When: Year 3, Goal: Scientific writing and editing.
Enrolment in doctoral programs
Ph.D. in Bioinformatics from Ghent University
How to apply?
An application is solely possible via the PROTrEIN application form: http://protrein.eu/call-for-ap...
Applications must be in English. Applicants may indicate 3 ESR Projects which they would like to work on, ranking them in order to preference. Uploading reference letters is not mandatory, but applicants should be aware that referees will be automatically contacted after submission and receive a questionnaire. Candidates must provide all information before the deadline. Candidates should ensure that referees answer the questionnaire.
Application deadline: 31 January 2021
Some relevant references
1. Gabriels, R., Martens, L., & Degroeve, S. (2019). Updated MS2PIP web server delivers fast and accurate MS2 peak intensity prediction for multiple fragmentation methods, instruments, and labeling techniques. Nucleic Acids Research, 47(W1), W295–W299. https://doi.org/10.1093/nar/gk...
2. Bouwmeester, R., Gabriels, R., Hulstaert, N., Martens, L., & Degroeve, S. (2020). DeepLC can predict retention times for peptides that carry as-yet unseen modifications. BioRxiv, https://doi.org/10.1101/2020.0...
3. Bouwmeester, R., Gabriels, R., Van Den Bossche, T., Martens, L., & Degroeve, S. (2020). The Age of Data‐Driven Proteomics: How Machine Learning Enables Novel Workflows. PROTEOMICS, 20(21–22), 1900351. https://doi.org/10.1002/pmic.2...