Propostas atribuídas ano letico 2025/2026

DEI - FCTUC
Gerado a 2025-12-04 12:36:33 (Europe/Lisbon).
Voltar

Titulo Estágio

Interplay between protein structure prediction algorithms and metrics for de novo protein generation

Local do Estágio

Roche Diagnostics GmbH, Roche Diagnostics GmbH, Penzberg, Germany

Enquadramento

Protein structure prediction algorithms have gained traction and utility in recent years, inspiring a plethora of de novo protein generation development. While the experimental validation of these binders show significant promise and improvement over time, the in silico characterisation sees a potential to be further sophisticated.

Objetivo

- Compare different protein structure prediction and de novo binder generation algorithms
- Develop a multi-agentic system to incorporate statistical and physicochemical potentials to cross-evaluate the generated binders
- Deploy the algorithm in a webapp/other suitable interfaces

Plano de Trabalhos - Semestre 1

Familiarisation with the Roche environment
Review, familiarise and deploy state-of-the-art binder generation algorithms
First prototype of the comparison between algorithms with different mechanisms (graph/statistical vs physicochemical)
Write-up of interim report

Plano de Trabalhos - Semestre 2

Build multi-agentic system to cross-evaluate the generated binders
Build an API to allow for easy access of these tools
Document codes and approaches and write-up of master thesis

Condições

The work will be carried out at Roche Diagnostics in Penzberg, Germany. At Roche the student will have at his disposal all the tools and resources (hardware and software) required.

Observações

This work will be developed in Roche Diagnostics GmbH, Penzberg, Germany

Orientador

Catherine Wong
catherine.wong.cw3@roche.com 📩