Data Centric Molecular Analysis and Evaluation of Hepatocellular Carcinoma Therapeutics Using Machine Intelligence-Based Tools

Cetin-Atalay, Rengul
Kahraman, Deniz Cansen
Sinoplu, Esra
Atakan, Ahmet
Dönmez, Ataberk
Atas, Heval
Atalay, Mehmet Volkan
Acar, Aybar C.
Purpose Computational approaches have been used at different stages of drug development with the purpose of decreasing the time and cost of conventional experimental procedures. Lately, techniques mainly developed and applied in the field of artificial intelligence (AI), have been transferred to different application domains such as biomedicine. Methods In this study, we conducted an investigative analysis via data-driven evaluation of potential hepatocellular carcinoma (HCC) therapeutics in the context of AI-assisted drug discovery/repurposing. First, we discussed basic concepts, computational approaches, databases, modeling approaches, and featurization techniques in drug discovery/repurposing. In the analysis part, we automatically integrated HCC-related biological entities such as genes/proteins, pathways, phenotypes, drugs/compounds, and other diseases with similar implications, and represented these heterogeneous relationships via a knowledge graph using the CROssBAR system. Results Following the system-level evaluation and selection of critical genes/proteins and pathways to target, our deep learning-based drug/compound-target protein interaction predictors DEEPScreen and MDeePred have been employed for predicting new bioactive drugs and compounds for these critical targets. Finally, we embedded ligands of selected HCC-associated proteins which had a significant enrichment with the CROssBAR system into a 2-D space to identify and repurpose small molecule inhibitors as potential drug candidates based on their molecular similarities to known HCC drugs. Conclusions We expect that these series of data-driven analyses can be used as a roadmap to propose early-stage potential inhibitors (from database-scale sets of compounds) to both HCC and other complex diseases, which may subsequently be analyzed with more targeted in silico and experimental approaches.


3D analysis of the binding sites for predicting binding affinities in drug design
Ataç, Ali Osman; Alpaslan, Ferda Nur; Büyükbingöl, Erdem; Department of Computer Engineering (2014)
Understanding the interaction between drug molecules and proteins is one of the main challenges in drug design. Several tools have been developed recently to decrease the complexity of the process. Artificial intelligence and machine learning methods have promising results in predicting the affinities. Recently, accurate estimations have been performed by extracting the electrostatic potentials from images of the drug-protein binding sites which were generated by autodocking simulator. In this study, a new ...
Data driven verification of synthetic gene networks
Aydın Göl, Ebru; Belta, Calin (2014-03-10)
Automatic design of synthetic gene networks with specific functions is an emerging field in synthetic biology. Quantitative evaluation of gene network designs is a missing feature of the existing automatic design tools. In this work, we address this issue and present a framework to probabilistically analyze the dynamic behavior of a gene network against specifications given in a rich and high level language. Given a gene network built from primitive DNA parts, and given experimental data for the parts, the ...
Reinvestigation of the synthetic and mechanistic aspects of Mn(III) acetate mediated oxidation of enones
Demir, Ayhan Sıtkı; Reis, O; Igdir, AC (Elsevier BV, 2004-04-05)
Mn(OAc)(3) mediated alpha'-acetoxylation of alpha,beta-unsaturated enones is reinvestigated from a synthetic and mechanistic point of view and an improved procedure based on the use of acetic acid as a co-solvent is presented. Excellent results were obtained for a variety of structurally diverse and synthetically important enones under the optimized conditions.
Systematic development of pH-independent controlled release tablets of carvedilol using central composite design and artificial neural networks
Aktas, Elcin; EROĞLU, HAKAN; Kockan, Umit; ÖNER, LEVENT (2013-08-01)
The purpose of this study was to apply the optimization method incorporating artificial neural network (ANN) using pH-independent release of weakly basic drug, carvedilol from HPMC-based matrix formulation. Because of weakly basic nature of carvedilol, drug shows pH-dependent solubility. The enteric polymer EUDRAGIT L100 was added formulations to overcome pH-dependent solubility of carvedilol. Effects of the Hydroxypropylmethyl cellulose (HPMC) K4M and EUDRAGIT L100 amount on drug release were investigated....
Applications of the multifunctional magnetic nanoparticles for development of molecular therapies for breast cancer
Aşık, Elif; Güray, Tülin; Volkan, Mürvet; Department of Biotechnology (2015)
The understanding of how magnetic nanoparticles (MNPs) interact with living system is one of the prerequisite pieces of information needed to be obtained before any further development for desired biomedical applications. In this study, Cobalt Ferrite magnetic nanoparticles (CoFe-MNPs) in their naked and silica-coated forms were characterized. In vitro cell culture for their likely cytotoxicity and genotoxicity potential were examined. The apoptosis, lipid peroxidation, ROS formation and oxidative stress re...
Citation Formats
R. Cetin-Atalay et al., “Data Centric Molecular Analysis and Evaluation of Hepatocellular Carcinoma Therapeutics Using Machine Intelligence-Based Tools,” JOURNAL OF GASTROINTESTINAL CANCER, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: