Derek van Tilborg

Mr. Derek van Tilborg

Wageningen University & Research
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 June 2024 in Digital Discovery
Verified
Journal Article
Open access
PDF file
AOAna Ortiz-Perez
Ana Ortiz-Perez
Derek van TilborgDerek van Tilborg
Derek van Tilborg
RMRoy van der Meel
Roy van der Meel
FGFrancesca Grisoni
Francesca Grisoni
LALorenzo Albertazzi
Lorenzo Albertazzi
Designing nanoparticles with desired properties is challenging due to the large combinatorial space and complex structure–function relationships. This process can be accelerated by combining microfluidics, high content imaging and active learning.

13 June 2023 in ChemBioChem
Verified
Journal Article
Open access
RÖR. Özçelik
R. Özçelik
Derek van TilborgDerek van Tilborg
Derek van Tilborg
JJJosé Jiménez-Luna
José Jiménez-Luna
FGFrancesca Grisoni
Francesca Grisoni
Artificial intelligence (AI) in the form of deep learning has promise for drug discovery and chemical biology, for example, to predict protein structure and molecular bioactivity, plan organic synthesis, and design moleculesde novo. While most of the deep learning efforts in drug discovery have focused on ligand‐based approaches, structure‐based drug discovery has the potential to tackle unsolved challenges, such as affinity prediction for unexplored protein targets, binding‐mechanism elucidation, and the rationalization of related chemical kinetic properties. Advances in deep‐learning methodologies and the availability of accurate predictions for protein tertiary structure advocate for arenaissancein structure‐based approaches for drug discovery guided by AI. This review summarizes the most prominent algorithmic concepts in structure‐based deep learning for drug discovery, and forecasts opportunities, applications, and challenges ahead.

21 January 2021 in Cancers
Verified
Journal Article
Open access
PDF file
Derek van TilborgDerek van Tilborg
Derek van Tilborg
Edoardo SaccentiEdoardo Saccenti
Edoardo Saccenti
One of the major hallmarks of cancer is the derailment of a cell’s metabolism. The multifaceted nature of cancer and different cancer types is transduced by both its transcriptomic and metabolomic landscapes. In this study, we re-purposed the publicly available transcriptomic and metabolomics data of eight cancer types (breast, lung, gastric, renal, liver, colorectal, prostate, and multiple myeloma) to find and investigate differences and commonalities on a pathway level among different cancer types. Topological analysis of inferred graphical Gaussian association networks showed that cancer was strongly defined in genetic networks, but not in metabolic networks. Using different statistical approaches to find significant differences between cancer and control cases, we highlighted the difficulties of high-level data-merging and in using statistical association networks. Cancer transcriptomics and metabolomics and landscapes were characterized by changed macro-molecule production, however, only major metabolic deregulations with highly impacted pathways were found in liver cancer. Cell cycle was enriched in breast, liver, and colorectal cancer, while breast and lung cancer were distinguished by highly enriched oncogene signaling pathways. A strong inflammatory response was observed in lung cancer and, to some extent, renal cancer. This study highlights the necessity of combining different omics levels to obtain a better description of cancer characteristics.

25 January 2024 in ChemRxiv
Verified
Preprint
Open access
PDF file
Derek van TilborgDerek van Tilborg
Derek van Tilborg
HBHelena Brinkmann
Helena Brinkmann
ECEmanuele Criscuolo
Emanuele Criscuolo
LRLuke Rossen
Luke Rossen
RÖRıza Özçelik
Rıza Özçelik
FGFrancesca Grisoni
Francesca Grisoni
Deep learning is becoming increasingly relevant in drug discovery, from de novo design to protein structure prediction and synthesis planning. However, it is often challenged by the small data regimes typical of certain drug discovery tasks. In such scenarios, deep learning approaches – which are notoriously ‘data-hungry’ – might fail to live up to their promise. Developing novel approaches to leverage the power of deep learning in low-data scenarios is sparking great attention, and future developments are expected to propel the field further. This minireview provides an overview of recent low-data-learning approaches in drug discovery, analyzing their hurdles and advantages. Finally, we venture to provide a forecast of future research directions in low-data learning for drug discovery.

23 February 2024 in ChemRxiv
Verified
Preprint
Open access
PDF file
Derek van TilborgDerek van Tilborg
Derek van Tilborg
FGFrancesca Grisoni
Francesca Grisoni
Deep learning is accelerating drug discovery. However, current approaches are often affected by limitations in the available data, e.g., in terms of size or molecular diversity. Active deep learning has an untapped potential for low-data drug discovery, as it allows to improve a model iteratively during the screening process by acquiring new data, and to adjust its course along the way. However, several known unknowns exist when it comes to active learning: (a) what the best computational strategies are for chemical space exploration, (b) how active learning holds up to traditional, non-iterative, approaches, and (c) how it should be used in the low-data scenarios typical of drug discovery. These open questions currently limit the wider adoption of active learning in drug discovery. To provide answers, this study simulates a real-world low-data drug discovery scenario, and systematically analyses six active learning strategies combined with two deep learning architectures, on three large- scale molecular libraries. Not only do we show that active learning can achieve up to a six-fold improvement in hit discovery compared to traditional methods, but we also identify the most important determinants of its success in low-data regimes. This study lays the first-in-time foundations for the prospective use of active deep learning for low-data drug discovery and is expected to accelerate its adoption.

6 March 2022 in bioRxiv
Verified
Preprint
Open access
PDF file
FPFarzaneh Meimandi Parizi
Farzaneh Meimandi Parizi
DMDario F. Marzella
Dario F. Marzella
Derek van TilborgDerek van Tilborg
Derek van Tilborg
NRNicolas Renaud
Nicolas Renaud
DSDaan Sybrandi
Daan Sybrandi
LXLi C. Xue
Li C. Xue
Deeper understanding T-cell mediated adaptive immune responses bears important implications in designing cancer immunotherapies and antiviral vaccines against pandemic outbreaks. T cells fire when they recognize foreign peptides that are presented on the cell surface by Major Histocompatibility Complexes (MHC), forming peptide:MHC (pMHC) complexes. 3D structure of pMHC complexes provides fundamental insight of T-cell recognition mechanism and aids immunotherapy design. High MHC and peptide diversities necessitate efficient computational modelling to enable whole proteome structural analysis. Here we present PANDORA, a robust pMHC structure modelling pipeline. Given a query, PANDORA searches for structural templates in its extensive database and then applies anchor restraints to the modelling process. This restrained energy minimization ensures one of the fastest pMHC modelling pipelines so far. On a set of 835 pMHC-I complexes over 78 MHC types, PANDORA generated models with a median RMSD of 0.68 Å and achieved a 93% success rate in top 10 models. PANDORA performs competitively with three pMHC-I modelling state-of-the-art approaches and outperforms AlphaFold in terms of accuracy while being superior to it in speed. PANDORA is a modularized and user-configurable python package with easy installation. We envision PANDORA to fuel deep learning with large-scale high-quality 3D models to tackle long-standing immunology challenges.