A5019867445- Computational Drug Discovery Methods
- Metabolomics and Mass Spectrometry Studies
- Bioinformatics and Genomic Networks
- Receptor Mechanisms and Signaling
- Cell Image Analysis Techniques
- Nanoparticles: synthesis and applications
- Chemical Synthesis and Analysis
- Machine Learning in Materials Science
- Microbial Natural Products and Biosynthesis
- Protein Structure and Dynamics
- Semantic Web and Ontologies
- Animal testing and alternatives
- Neuroscience and Neuropharmacology Research
- Advanced Fluorescence Microscopy Techniques
- Diverse Scientific Research Studies
- Biotechnology and Related Fields
- Analytical Chemistry and Chromatography
- Advanced Materials Characterization Techniques
- Pharmacological Effects of Natural Compounds
- Monoclonal and Polyclonal Antibodies Research
- Machine Learning in Bioinformatics
- Biomedical Text Mining and Ontologies
- Air Quality and Health Impacts
- Electron and X-Ray Spectroscopy Techniques
- Environmental Impact and Sustainability
University of Cambridge
2013-2019
National Technical University of Athens
2016-2017
Unilever (United Kingdom)
2013-2014
In silico analyses are increasingly being used to support mode-of-action investigations; however many such approaches do not utilise the large amounts of inactive data held in chemogenomic repositories. The objective this work is concerned with integration bioactivity target prediction orphan compounds produce probability activity and inactivity for a range targets. To end, novel human set was constructed through assimilation over 195 million points deposited ChEMBL PubChem repositories,...
Integrating gene expression profiles with certain proteins can improve our understanding of the fundamental mechanisms in protein-ligand binding. This paper spotlights integration data and target prediction scores, providing insight into mechanism action (MoA). Compounds are clustered based upon similarity their predicted protein targets each cluster is linked to sets using Linear Models for Microarray Data. MLP analysis used generate biological processes a qualitative search performed on...
Background: An in silico mechanism-of-action analysis protocol was developed, comprising molecule bioactivity profiling, annotation of predicted targets with pathways and calculation enrichment factors to highlight more likely be implicated the studied phenotype. Results: The method applied a cytotoxicity phenotypic endpoint, enriched targets/pathways found statistically significant when compared 100 random datasets. Application on smaller apoptotic set (10 molecules) did not allowed obtain...
Diversity selection is a frequently applied strategy for assembling high-throughput screening libraries, making the assumption that diverse compound set increases chances of finding bioactive molecules. Based on previous work experimental 'affinity fingerprints', in this study, novel diversity method benchmarked utilizes predicted bioactivity profiles as descriptors. Compounds were selected based their activity against half targets (training set), and was assessed coverage remaining (test...
Abstract The simultaneous increase of computational power and the availability chemical biological data have contributed to recent popularity in silico bioactivity prediction algorithms. Such methods are commonly used infer ‘Mechanism Action’ small molecules they can also be employed cases where full profiles not been established experimentally. However, protein target predictions by themselves do necessarily capture information about effect a compound on system, hence merging their output...
Engineered nanomaterials (ENMs) are increasingly infiltrating our lives as a result of their applications across multiple fields. However, ENM formulations may in the modulation pathways and mechanisms toxic action that endanger human health environment. Alternative testing methods such silico approaches becoming popular for assessing safety ENMs, they cost- time-effective. Additionally, computational support industrial safer-by-design challenge REACH legislation objective reducing animal...
Traditional Chinese medicine (TCM) still needs more scientific rationale to be proven for it accepted further in the West. We are now position propose computational hypotheses mode-of-actions (MOAs) of 45 TCM therapeutic action (sub)classes from silico target prediction algorithms, whose was later annotated with Kyoto Encyclopedia Genes and Genomes pathway, discover relationship between them by generating a hierarchical clustering. The results 10,749 compounds showed 183 enriched targets 99...
The increase of publicly available bioactivity data has led to the extensive development and usage in silico prediction algorithms. A particularly popular approach for such analyses is multiclass Naïve Bayes, whose output commonly processed by applying empirically-derived likelihood score thresholds. In this work, we describe a systematic way deriving cut-offs on per-protein target basis compare their performance with global thresholds large scale using both 5-fold cross-validation (ChEMBL...
Decision trees are renowned in the computational chemistry and machine learning communities for their interpretability. Their capacity usage somewhat limited by fact that they normally work on categorical data. Improvements to known decision tree algorithms usually carried out increasing tweaking parameters, as well post-processing of class assignment. In this we attempted tackle both these issues. Firstly, conditional mutual information was used criterion selecting attribute which split...
In this work, we describe the computational ("in silico") mode-of-action analysis of CNS-active drugs, which is taking both multiple simultaneous hypotheses as well sets protein targets for each into account, and was followed by successful prospective in vitro vivo validation. Using sleep-related phenotypic readouts describing efficacy side effects 491 compounds tested rat, defined an "optimal" (desirable) sleeping pattern. Compounds were subjected to silico target prediction (which...
Understanding the mode of action small molecules is critical for drug research, both with respect to efficacy and anticipated side effects. Given that many compounds act on multiple targets simultaneously, it appears linking single outcomes no longer sufficient. Hence, in this work we explore machine learning methods rationalising phenotypic readouts from a rat model hypnotics based polypharmacology approach. We hypothesise by combining target prediction techniques are able derive...
Given the increasing utilization of phenotypic screens in drug discovery also subsequent mechanism-of-action analysis gains increased attention.
Abstract The modes of action (MoAs) drugs frequently are unknown, because many small molecules initially identified from phenotypic screens, giving rise to the need elucidate their MoAs. In addition, high attrition rate for candidate in preclinical studies due intolerable toxicity has motivated development computational approaches predict drug (cyto)toxicity as early possible drug‐discovery process. Here, we provide detailed instructions capitalizing on bioactivity predictions MoAs and infer...
G protein-coupled receptors (GPCRs) are a major family of membrane in eukaryotic cells and play crucial role various biological processes. They represent protein targets with significant therapeutic value, accordingly more than 30% prescription drugs GPCR ligands [1]. Extending previous attempts to map the pharmacological space solely based on ligand chemical similarity,[2,3] we this work relate GPCRs by combining structure-activity data from ChEMBL WOMBAT that covers 167 human 67k...