A5054058101- Computational Drug Discovery Methods
- Machine Learning in Bioinformatics
- Protein Structure and Dynamics
- Bioinformatics and Genomic Networks
- HIV/AIDS drug development and treatment
- Genetics, Bioinformatics, and Biomedical Research
- Microbial Natural Products and Biosynthesis
- Multiple Myeloma Research and Treatments
- Cancer therapeutics and mechanisms
- Gene expression and cancer classification
- Cell Image Analysis Techniques
- Advanced Biosensing Techniques and Applications
- Genomics and Phylogenetic Studies
- Scientific Computing and Data Management
- Biomedical Text Mining and Ontologies
- Distributed and Parallel Computing Systems
- Viral Infectious Diseases and Gene Expression in Insects
- Microbial Metabolism and Applications
Hacettepe University
2022-2023
Middle East Technical University
2016-2022
Abstract Despite decades of intensive search for compounds that modulate the activity particular protein targets, a large proportion human kinome remains as yet undrugged. Effective approaches are therefore required to map massive space unexplored compound–kinase interactions novel and potent activities. Here, we carry out crowdsourced benchmarking predictive algorithms kinase inhibitor potencies across multiple families tested on unpublished bioactivity data. We find top-performing...
The identification of drug/compound-target interactions (DTIs) constitutes the basis drug discovery, for which computational predictive approaches have been developed. As a relatively new data-driven paradigm, proteochemometric (PCM) modeling utilizes both protein and compound properties as pair at input level processes them via statistical/machine learning. representation samples (i.e., proteins their ligands) in form quantitative feature vectors is crucial extraction interaction-related...
Abstract Systemic analysis of available large-scale biological/biomedical data is critical for studying biological mechanisms, and developing novel effective treatment approaches against diseases. However, different layers the are produced using technologies scattered across individual computational resources without any explicit connections to each other, which hinders extensive integrative multi-omics-based analysis. We aimed address this issue by a new integration/representation...
Predictive approaches such as virtual screening have been used in drug discovery with the objective of reducing developmental time and costs. Current machine learning network-based issues related to generalization, usability, or model interpretability, especially due complexity target proteins' structure/function, bias system training datasets. Here, we propose a new method "DRUIDom" (DRUg Interacting Domain prediction) identify bio-interactions between candidate compounds targets by...
Abstract Data-centric approaches have been utilized to develop predictive methods for elucidating uncharacterized aspects of proteins such as their functions, biophysical properties, subcellular locations and interactions. However, studies indicate that the performance these should be further improved effectively solve complex problems in biomedicine biotechnology. A data representation method can defined an algorithm calculates numerical feature vectors samples a dataset, later used...
Abstract Systemic analysis of available large-scale biological and biomedical data is critical for developing novel effective treatment approaches against both complex infectious diseases. Owing to the fact that different sections produced by organizations/institutions using various types technologies, are scattered across individual computational resources, without any explicit relations/connections each other, which greatly hinders comprehensive multi-omics-based data. We aimed address...
Abstract The identification of drug/compound-target interactions (DTIs) constitutes the basis drug discovery, for which computational predictive approaches have been applied. As a relatively new data-driven paradigm, proteochemometric (PCM) modeling utilizes both protein and compound properties as pair at input level processes them via statistical/machine learning. representation samples (i.e., proteins their ligands) in form quantitative feature vectors is crucial extraction...
Abstract Predictive approaches such as virtual screening have been used in drug discovery with the objective of reducing developmental time and costs. Current machine learning network- based issues related to generalization, usability, or model interpretability, especially due complexity target proteins’ structure/function, bias system training datasets. Here, we propose a new computational method “DRUIDom” predict bio- interactions between candidate compounds proteins by utilizing domain...