Search results for: drug property prediction

Authors: Jacob Green, Cecilia Cabrera, Maximilian Jakobs, Andrea Dimitracopoulos, Mark van der Wilk, Ryan Greenhalgh

Abstract:

Predicting drug properties is key in drug discovery to enable de-risking of assets before expensive clinical trials and to find highly active compounds faster. Interest from the machine learning community has led to the release of a variety of benchmark datasets and proposed methods. However, it remains unclear for practitioners which method or approach is most suitable, as different papers benchmark on different datasets and methods, leading to varying conclusions that are not easily compared. Our large-scale empirical study links together numerous earlier works on different datasets and methods, thus offering a comprehensive overview of the existing property classes, datasets, and their interactions with different methods. We emphasise the importance of uncertainty quantification and the time and, therefore, cost of applying these methods in the drug development decision-making cycle. To the best of the author's knowledge, it has been observed that the optimal approach varies depending on the dataset and that engineered features with classical machine learning methods often outperform deep learning. Specifically, QSAR datasets are typically best analysed with classical methods such as Gaussian Processes, while ADMET datasets are sometimes better described by Trees or deep learning methods such as Graph Neural Networks or language models. Our work highlights that practitioners do not yet have a straightforward, black-box procedure to rely on and sets a precedent for creating practitioner-relevant benchmarks. Deep learning approaches must be proven on these benchmarks to become the practical method of choice in drug property prediction.

Keywords: activity (QSAR), ADMET, classical methods, drug property prediction, empirical study, machine learning

Procedia PDF Downloads 44

Authors: Rashini Maduka, C. R. Wijesinghe, A. R. Weerasinghe

Abstract:

Drug-drug interactions (DDIs) can happen when two or more drugs are taken together. Today DDIs have become a serious health issue due to adverse drug effects. In vivo and in vitro methods for identifying DDIs are time-consuming and costly. Therefore, in-silico-based approaches are preferred in DDI identification. Most machine learning models for DDI prediction are used chemical and biological drug properties as features. However, some drug features are not available and costly to extract. Therefore, it is better to make automatic feature engineering. Furthermore, people who have diabetes already suffer from other diseases and take more than one medicine together. Then adverse drug effects may happen to diabetic patients and cause unpleasant reactions in the body. In this study, we present a model with a graph convolutional autoencoder and a graph decoder using a dataset from DrugBank version 5.1.3. The main objective of the model is to identify unknown interactions between antidiabetic drugs and the drugs taken by diabetic patients for other diseases. We considered automatic feature engineering and used Known DDIs only as the input for the model. Our model has achieved 0.86 in AUC and 0.86 in AP.

Keywords: drug-drug interaction prediction, graph embedding, graph convolutional networks, adverse drug effects

Procedia PDF Downloads 62

Authors: Muhammet Baldan, Emel Timuçin

Abstract:

Generally, absorption and bioavailability increase if solubility increases; therefore, it is crucial to predict them in drug discovery applications. Molecular descriptors and Molecular properties are traditionally used for the prediction of water solubility. There are various key descriptors that are used for this purpose, namely Drogan Descriptors, Morgan Descriptors, Maccs keys, etc., and each has different prediction capabilities with differentiating successes between different data sets. Another source for the prediction of solubility is structural features; they are commonly used for the prediction of solubility. However, there are little to no studies that combine three or more properties or descriptors for prediction to produce a more powerful prediction model. Unlike available models, we used a combination of those features in a random forest machine learning model for improved solubility prediction to better predict and, therefore, contribute to drug discovery systems.

Keywords: solubility, molecular descriptors, machine learning, random forest

Procedia PDF Downloads 16

Authors: Nishank Raisinghani

Abstract:

Efficiently predicting drug response remains a challenge in the realm of drug discovery. To address this issue, we propose four model architectures that combine graphical representation with varying positions of multiheaded self-attention mechanisms. By leveraging two types of multi-omics data, transcriptomics and genomics, we create a comprehensive representation of target cells and enable drug response prediction in precision medicine. A majority of our architectures utilize multiple transformer models, one with a graph attention mechanism and the other with a multiheaded self-attention mechanism, to generate latent representations of both drug and omics data, respectively. Our model architectures apply an attention mechanism to both drug and multiomics data, with the goal of procuring more comprehensive latent representations. The latent representations are then concatenated and input into a fully connected network to predict the IC-50 score, a measure of cell drug response. We experiment with all four of these architectures and extract results from all of them. Our study greatly contributes to the future of drug discovery and precision medicine by looking to optimize the time and accuracy of drug response prediction.

Keywords: drug discovery, transformers, graph neural networks, multiomics

Procedia PDF Downloads 109

Authors: Babak Bahri, Fatemeh Yassaee Meybodi, Changiz Eslahchi

Abstract:

In the pursuit of effective cancer therapies, the exploration of combinatorial drug regimens is crucial to leverage synergistic interactions between drugs, thereby improving treatment efficacy and overcoming drug resistance. However, identifying synergistic drug pairs poses challenges due to the vast combinatorial space and limitations of experimental approaches. This study introduces ClusterSyn, a machine learning (ML)-powered framework for classifying anti-cancer drug synergy scores. ClusterSyn employs a two-step approach involving drug clustering and synergy score prediction using a fully connected deep neural network. For each cell line in the training dataset, a drug graph is constructed, with nodes representing drugs and edge weights denoting synergy scores between drug pairs. Drugs are clustered using the Markov clustering (MCL) algorithm, and vectors representing the similarity of drug pairs to each cluster are input into the deep neural network for synergy score prediction (synergy or antagonism). Clustering results demonstrate effective grouping of drugs based on synergy scores, aligning similar synergy profiles. Subsequently, neural network predictions and synergy scores of the two drugs on others within their clusters are used to predict the synergy score of the considered drug pair. This approach facilitates comparative analysis with clustering and regression-based methods, revealing the superior performance of ClusterSyn over state-of-the-art methods like DeepSynergy and DeepDDS on diverse datasets such as Oniel and Almanac. The results highlight the remarkable potential of ClusterSyn as a versatile tool for predicting anti-cancer drug synergy scores.

Keywords: drug synergy, clustering, prediction, machine learning., deep learning

Procedia PDF Downloads 38

Authors: Umairah Natasya Binti Mohd Omeershffudin, Suresh Kumar

Abstract:

Klebsiella pneumoniae, a Gram-negative enteric bacterium that causes nosocomial and urinary tract infections. Particular concern is the global emergence of multidrug-resistant (MDR) strains of Klebsiella pneumoniae. Characterization of antibiotic resistance determinants at the genomic level plays a critical role in understanding, and potentially controlling, the spread of multidrug-resistant (MDR) pathogens. In this study, drug-resistant Klebsiella pneumoniae strain 825795-1 was investigated with extensive computational approaches aimed at identifying novel drug targets among hypothetical proteins. We have analyzed 1099 hypothetical proteins available in genome. We have used in-silico genome subtraction methodology to design potential and pathogen-specific drug targets against Klebsiella pneumoniae. We employed bioinformatics tools to subtract the strain-specific paralogous and host-specific homologous sequences from the bacterial proteome. The sorted 645 proteins were further refined to identify the essential genes in the pathogenic bacterium using the database of essential genes (DEG). We found 135 unique essential proteins in the target proteome that could be utilized as novel targets to design newer drugs. Further, we identified 49 cytoplasmic protein as potential drug targets through sub-cellular localization prediction. Further, we investigated these proteins in the DrugBank databases, and 11 of the unique essential proteins showed druggability according to the FDA approved drug bank databases with diverse broad-spectrum property. The results of this study will facilitate discovery of new drugs against Klebsiella pneumoniae.

Keywords: pneumonia, drug target, hypothetical protein, subtractive genomics

Procedia PDF Downloads 152

Authors: Hardeep

Abstract:

The aim of this research work to improve the solubility and bioavailability of Simvastatin using a self nanoemulsifying drug delivery system (SNEDDS). Self emulsifying property of various oils including essential oils was evaluated with suitable surfactants and co-surfactants. Validation of a method for accuracy, repeatability, Interday and intraday precision, ruggedness, and robustness were within acceptable limits. The liquid SNEDDS was prepared and optimized using a ternary phase diagram, thermodynamic, centrifugation and cloud point studies. The globule size of optimized formulations was less than 200 nm which could be an acceptable nanoemulsion size range. The mean droplet size, drug loading, PDI and zeta potential were found to be 141.0 nm, 92.22%, 0.23 and -10.13 mV and 153.5nm, 93.89 % ,0.41 and -11.7 mV and 164.26 nm, 95.26% , 0.41 and -10.66mV respectively.

Keywords: simvastatin, self nanoemulsifying drug delivery system, solubility, bioavailability

Procedia PDF Downloads 166

Authors: K. S. Hemant Yadav, H. G. Shivakumar

Abstract:

The present study investigation was to prepare and evaluate the mucoadhesive multi-particulate system for nasal drug delivery of anti-histaminic drug. Ebastine was chosen as the model drug. Drug loaded nanoparticles of Ebastine were prepared by ionic gelation method using chitosan as polymer using the drug-polymer weight ratios 1:1, 1:2, 1:3. Sodium tripolyphosphate (STPP) was used as the cross-linking agent in the range of 0.5 and 0.7% w/v. FTIR and DSC studies indicated that no chemical interaction occurred between the drug and polymers. Particle size ranged from 169 to 500 nm. The drug loading and entrapment efficiency was found to increase with increase in chitosan concentration and decreased with increase in poloxamer 407 concentration. The results of in vitro mucoadhesion carried out showed that all the prepared formulation had good mucoadhesive property and mucoadhesion increases with increase in the concentration of chitosan. The in vitro release pattern of all the formulations was observed to be in a biphasic manner characterized by slight burst effect followed by a slow release. By the end of 8 hrs, formulation F6 showed a release of only 86.9% which explains its sustained behaviour. The ex-vivo permeation of the pure drug ebastine was rapid than the optimized formulation(F6) indicating the capability of the chitosan polymer to control drug permeation rate through the sheep nasal mucosa. The results indicated that the mucoadhesive nanoparticulate system can be used for the nasal delivery of antihistaminic drugs in an effective manner.

Keywords: nasal, nanoparticles, ebastine, anti-histaminic drug, mucoadhesive multi-particulate system

Procedia PDF Downloads 397

Authors: Kuo-Chun Chien, Chia-Hui Chang, Ren-Der Sun

Abstract:

Legal Judgment Prediction (LJP) is a subtask for legal AI. Its main purpose is to use the facts of a case to predict the judgment result. In Taiwan's criminal procedure, when prosecutors complete the investigation of the case, they will decide whether to prosecute the suspect and which article of criminal law should be used based on the facts and evidence of the case. In this study, we collected 305,240 indictments from the public inquiry system of the procuratorate of the Ministry of Justice, which included 169 charges and 317 articles from 21 laws. We take the crime facts in the indictments as the main input to jointly learn the prediction model for law source, article, and charge simultaneously based on the pre-trained Bert model. For single article cases where the frequency of the charge and article are greater than 50, the prediction performance of law sources, articles, and charges reach 97.66, 92.22, and 60.52 macro-f1, respectively. To understand the big performance gap between articles and charges, we used a bipartite graph to visualize the relationship between the articles and charges, and found that the reason for the poor prediction performance was actually due to the wording precision. Some charges use the simplest words, while others may include the perpetrator or the result to make the charges more specific. For example, Article 284 of the Criminal Law may be indicted as “negligent injury”, "negligent death”, "business injury", "driving business injury", or "non-driving business injury". As another example, Article 10 of the Drug Hazard Control Regulations can be charged as “Drug Control Regulations” or “Drug Hazard Control Regulations”. In order to solve the above problems and more accurately predict the article and charge, we plan to include the article content or charge names in the input, and use the sentence-pair classification method for question-answer problems in the BERT model to improve the performance. We will also consider a sequence-to-sequence approach to charge prediction.

Keywords: legal judgment prediction, deep learning, natural language processing, BERT, data visualization

Procedia PDF Downloads 94

Authors: Ji Lian Yap

Abstract:

This paper will critically consider developments in 2014 in relation to the law relating to security over personal property in Hong Kong. The rules governing the registration of charges under the Hong Kong Companies Ordinance will be examined. Case law relating to personal property security will also be discussed. The transplantation of the floating charge into China’s Property Law will also be considered.

Keywords: personal property, security law, reform of the law, law

Procedia PDF Downloads 394

Authors: Luljeta Plakolli-Kasumi

Abstract:

In the digital age, the relationship between traditional property rights and online intellectual property rights is becoming increasingly complex. On the one hand, the internet and advancements in technology have allowed for the widespread distribution and use of digital content, making it easier for individuals and businesses to access and share information. On the other hand, the rise of digital piracy and illegal file-sharing has led to increased concerns about the protection of intellectual property rights. This paper aims to examine the relationship between traditional property rights and online intellectual property rights in the digital age by analyzing the current legal frameworks, key challenges and controversies that arise, and potential solutions for addressing these issues. The paper will look at how traditional property rights concepts such as ownership and possession are being applied in the online context and how they intersect with new and evolving forms of intellectual property such as digital downloads, streaming services, and online content creation. It will also discuss the tension between the need for strong intellectual property protection to encourage creativity and innovation and the public interest in promoting access to information and knowledge. Ultimately, the paper will explore how the legal system can adapt to better balance the interests of property owners, creators, and users in the digital age.

Keywords: intellectual property, traditional property, digital age, digital content

Procedia PDF Downloads 60

Authors: Khushbu Priyadarshi, Chandramani Pathak

Abstract:

Cancer cells can develop resistance to conventional therapies especially chemotherapeutic drugs. Resistance to chemotherapy is another challenge in cancer therapeutics. Therefore, it is important to address this issue. Gallic acid (GA) is a natural plant compound that exhibits various biological properties including anti-proliferative, anti-inflammatory, anti-oxidant and anti-bacterial. Despite of the wide spectrum biological properties GA has cytotoxic response and low bioavailability. To overcome this problem, GA was conjugated with the Polyamidoamine(PAMAM) dendrimer for improving the bioavailability and efficient delivery in drug-resistant HCT-116 Colon Cancer cells. Gallic acid was covalently linked to 4.0 G PAMAM dendrimer. PAMAM dendrimer is well established nanocarrier but has cytotoxicity due to presence of amphiphilic nature of amino group. In our study we have modified surface of PAMAM dendrimer with Gallic acid and examine their anti-proliferative effects in drug-resistant HCT-116 cells. Further, drug-resistant colon cancer cells were established and thereafter treated with different concentration of PAMAM-GA to examine their anti-proliferative potential. Our results show that PAMAM-GA conjugate induces apoptotic cell death in HCT-116 and drug-resistant cells observed by Annexin-PI staining. In addition, it also shows that multidrug-resistant drug transporter P-gp protein expression was downregulated with increasing the concentration of GA conjugate. After that we also observed the significant difference in Rh123 efflux and accumulation in drug sensitive and drug-resistant cancer cells. Thus, our study suggests that conjugation of anti-cancer agents with PAMAM could improve drug resistant property and cytotoxic response to treatment of cancer.

Keywords: drug resistance, gallic acid, PAMAM dendrimer, P-glycoprotein

Procedia PDF Downloads 120

Authors: Kankeyanathan Kannan

Abstract:

On approximation properties of group C* algebras is everywhere; it is powerful, important, backbone of countless breakthroughs. For a discrete group G, let A(G) denote its Fourier algebra, and let M₀A(G) denote the space of completely bounded Fourier multipliers on G. An approximate identity on G is a sequence (Φn) of finitely supported functions such that (Φn) uniformly converge to constant function 1 In this paper we prove that approximation property pass to free product.

Keywords: approximation property, weakly amenable, strong invariant approximation property, invariant approximation property

Procedia PDF Downloads 646

Authors: Deepika Bhaskar, Neena Wadehra, Megha Gulati, Aruna Narula, R. Vishnu, Gunjan Katyal

Abstract:

With drug resistance becoming widespread in Plasmodium falciparum infections, development of the alternative drugs is the desired strategy for prevention and cure of malaria. Three drug targets were selected to screen promising drug molecules from the GSK library of around 14000 molecules. Using an in silico structure-based drug designing approach, the differences in binding energies of the substrate and inhibitor were exploited between target sites of parasite and human to design a drug molecule against Plasmodium. The docking studies have shown several promising molecules from GSK library with more effective binding as compared to the already known inhibitors for the drug targets. Though stronger interaction has been shown by several molecules as compare to reference, few molecules have shown the potential as drug candidates though in vitro studies are required to validate the results.

Keywords: plasmodium, malaria, drug targets, in silico studies

Procedia PDF Downloads 418

Authors: Kamalpreet Kaur, Renu Dhir

Abstract:

Climate prediction is an essential component of climate research, which helps evaluate possible effects on economies, communities, and ecosystems. Climate prediction involves short-term weather prediction, seasonal prediction, and long-term climate change prediction. Climate prediction can use the information gathered from satellites, ground-based stations, and ocean buoys, among other sources. The paper's four architectures, such as ResNet50, VGG19, Inception-v3, and Xception, have been combined using an ensemble approach for overall performance and robustness. An ensemble of different models makes a prediction, and the majority vote determines the final prediction. The various architectures such as ResNet50, VGG19, Inception-v3, and Xception efficiently classify the dataset RSI-CB256, which contains satellite images into cloudy and non-cloudy. The generated ensembled S-E model (Sar-ensembled model) provides an accuracy of 99.25%.

Keywords: climate, satellite images, prediction, classification

Procedia PDF Downloads 32

Authors: Sara Ataei, Molouk Hadjibabaie, Shirinsadat Badri, Amirhossein Moslehi, Iman Karimzadeh, Ardeshir Ghavamzadeh

Abstract:

Purpose: To assess the pattern and probable risk factors for moderate and major drug–drug interactions in a referral hematology-oncology ward in Iran. Methods: All patients admitted to hematology–oncology ward of Dr. Shariati Hospital during a 6-month period and received at least two anti-cancer or non-anti-cancer medications simultaneously were included. All being scheduled anti-cancer and non-anti-cancer medications both prescribed and administered during ward stay were considered for drug–drug interaction screening by Lexi-Interact On- Desktop software. Results: One hundred and eighty-five drug–drug interactions with moderate or major severity were detected from 83 patients. Most of drug–drug interactions (69.73 %) were classified as pharmacokinetics. Fluconazole (25.95 %) was the most commonly offending medication in drug–drug interactions. Interaction of sulfamethoxazole-trimethoprim with fluconazole was the most common drug–drug interaction (27.27 %). Vincristine with imatinib was the only identified interaction between two anti-cancer agents. The number of administered medications during ward stay was considered as an independent risk factor for developing a drug–drug interaction. Conclusions: Potential moderate or major drug–drug interactions occur frequently in patients with hematological malignancies or related diseases. Performing larger standard studies are required to assess the real clinical and economical effects of drug–drug interactions on patients with hematological and non-hematological malignancies.

Keywords: drug–drug interactions, hematology–oncology ward, hematological malignancies

Procedia PDF Downloads 414

Authors: Junie B. Billones, Maria Constancia O. Carrillo, Voltaire G. Organo, Stephani Joy Y. Macalino, Inno A. Emnacen, Jamie Bernadette A. Sy

Abstract:

The drug discovery and development process is generally known to be a very lengthy and labor-intensive process. Therefore, in order to be able to deliver prompt and effective responses to cure certain diseases, there is an urgent need to reduce the time and resources needed to design, develop, and optimize potential drugs. Computer-aided drug design (CADD) is able to alleviate this issue by applying computational power in order to streamline the whole drug discovery process, starting from target identification to lead optimization. This drug design approach can be predominantly applied to diseases that cause major public health concerns, such as tuberculosis. Hitherto, there has been no concrete cure for this disease, especially with the continuing emergence of drug resistant strains. In this study, CADD is employed for tuberculosis by first identifying a key enzyme in the mycobacterium’s metabolic pathway that would make a good drug target. One such potential target is the lipoate protein ligase B enzyme (LipB), which is a key enzyme in the M. tuberculosis metabolic pathway involved in the biosynthesis of the lipoic acid cofactor. Its expression is considerably up-regulated in patients with multi-drug resistant tuberculosis (MDR-TB) and it has no known back-up mechanism that can take over its function when inhibited, making it an extremely attractive target. Using cutting-edge computational methods, compounds from AnalytiCon Discovery Natural Derivatives database were screened and docked against the LipB enzyme in order to rank them based on their binding affinities. Compounds which have better binding affinities than LipB’s known inhibitor, decanoic acid, were subjected to in silico toxicity evaluation using the ADMET and TOPKAT protocols. Out of the 31,692 compounds in the database, 112 of these showed better binding energies than decanoic acid. Furthermore, 12 out of the 112 compounds showed highly promising ADMET and TOPKAT properties. Future studies involving in vitro or in vivo bioassays may be done to further confirm the therapeutic efficacy of these 12 compounds, which eventually may then lead to a novel class of anti-tuberculosis drugs.

Keywords: pharmacophore, molecular docking, lipoate protein ligase B (LipB), ADMET, TOPKAT

Procedia PDF Downloads 387

Authors: Pimporn Thongmuang

Abstract:

The import value of antimicrobial drugs reached approximately fifteen million Baht in 2010, considered as the highest import value of all modern drugs, and this value is rising every year. Antimicrobials are considered the hazardous drugs by the Ministry of Public Health. This research was conducted in order to investigate the past knowledge of drug use and Antimicrobial drug use behavior. A total of 757 students were selected as the samples out of a population of 1,800 students. This selected students had the experience of Antimicrobial drugs use a year ago. A questionnaire was utilized in this research. The findings put on the view that knowledge gained by the students about proper use of antimicrobial drugs was not brought into practice. This suggests that the education procedure regarding drug use needs adjustment. And therefore the findings of this research are expected to be utilized as guidelines for educating people about the proper use of antimicrobial drugs. At a broader perspective, correct drug use behavior of the public may potentially reduce drug cost of the Ministry of Public Health of Thailand.

Keywords: drug use knowledge, antimicrobial drugs, drug use behavior, drug

Procedia PDF Downloads 247

Authors: The Danh Phan

Abstract:

House price forecasting is a main topic in the real estate market research. Effective house price prediction models could not only allow home buyers and real estate agents to make better data-driven decisions but may also be beneficial for the property policymaking process. This study investigates the housing market by using machine learning techniques to analyze real historical house sale transactions in Australia. It seeks useful models which could be deployed as an application for house buyers and sellers. Data analytics show a high discrepancy between the house price in the most expensive suburbs and the most affordable suburbs in the city of Melbourne. In addition, experiments demonstrate that the combination of Stepwise and Support Vector Machine (SVM), based on the Mean Squared Error (MSE) measurement, consistently outperforms other models in terms of prediction accuracy.

Keywords: house price prediction, regression trees, neural network, support vector machine, stepwise

Procedia PDF Downloads 185

Authors: Shital Suresh Borse, Vijayalaxmi Kadroli

Abstract:

E-commerce industries nowadays implement the latest AI, ML Techniques to improve their own performance and prediction accuracy. This helps to gain a huge profit from the online market. Ant Colony Optimization, Genetic algorithm, Particle Swarm Optimization, Neural Network & GWO help many e-commerce industries for up-gradation of their predictive performance. These algorithms are providing optimum results in various applications, such as stock price prediction, prediction of drug-target interaction & user ratings of similar products in e-commerce sites, etc. In this study, customer reviews will play an important role in prediction analysis. People showing much interest in buying a lot of services& products suggested by other customers. This ultimately increases net profit. In this work, a convolution neural network (CNN) is proposed which further is useful to optimize the prediction accuracy of an e-commerce website. This method shows that CNN is used to optimize hyperparameters of GWO algorithm using an appropriate coding scheme. Accurate model results are verified by comparing them to PSO results whose hyperparameters have been optimized by CNN in Amazon's customer review dataset. Here, experimental outcome proves that this proposed system using the GWO algorithm achieves superior execution in terms of accuracy, precision, recovery, etc. in prediction analysis compared to the existing systems.

Keywords: prediction analysis, e-commerce, machine learning, grey wolf optimization, particle swarm optimization, CNN

Procedia PDF Downloads 82

Authors: B. Sir, M. Podhoranyi, S. Kuchar, T. Kocyan

Abstract:

Rainfall-runoff models play important role in hydrological predictions. However, the model is only one part of the process for creation of flood prediction. The aim of this paper is to show the process of successful prediction for flood event (May 15–May 18 2014). The prediction was performed by rainfall runoff model HEC–HMS, one of the models computed within Floreon+ system. The paper briefly evaluates the results of automatic hydrologic prediction on the river Olše catchment and its gages Český Těšín and Věřňovice.

Keywords: flood, HEC-HMS, prediction, rainfall, runoff

Procedia PDF Downloads 362

Authors: Parthiban Srinivasan

Abstract:

With recent advances in computational power and access to enough data in biosciences, artificial intelligence methods are increasingly being used in drug discovery research. These methods are essentially a series of advanced statistics based exercises that review the past to indicate the likely future. Our goal is to develop a model that accurately predicts biological activity and toxicity parameters for novel compounds. We have compiled a robust library of over 150,000 chemical compounds with different pharmacological properties from literature and public domain databases. The compounds are stored in simplified molecular-input line-entry system (SMILES), a commonly used text encoding for organic molecules. We utilize an automated process to generate an array of numerical descriptors (features) for each molecule. Redundant and irrelevant descriptors are eliminated iteratively. Our prediction engine is based on a portfolio of machine learning algorithms. We found Random Forest algorithm to be a better choice for this analysis. We captured non-linear relationship in the data and formed a prediction model with reasonable accuracy by averaging across a large number of randomized decision trees. Our next step is to apply deep neural network (DNN) algorithm to predict the biological activity and toxicity properties. We expect the DNN algorithm to give better results and improve the accuracy of the prediction. This presentation will review all these prominent machine learning and deep learning methods, our implementation protocols and discuss these techniques for their usefulness in biomedical and health informatics.

Keywords: deep learning, drug discovery, health informatics, machine learning, toxicity prediction

Procedia PDF Downloads 328

Authors: Belkacem Selma, Boumediene Selma, Tourkia Guerzou, Abbes Labdelli

Abstract:

Natural disasters have occurred and will continue to cause human and material damage. Therefore, the idea of "preventing" natural disasters will never be possible. However, their prediction is possible with the advancement of technology. Even if natural disasters are effectively inevitable, their consequences may be partly controlled. The rapid growth and progress of artificial intelligence (AI) had a major impact on the prediction of natural disasters and risk assessment which are necessary for effective disaster reduction. The Earthquakes prediction to prevent the loss of human lives and even property damage is an important factor; that is why it is crucial to develop techniques for predicting this natural disaster. This present study aims to analyze the ability of artificial neural networks (ANNs) to predict earthquakes that occur in a given area. The used data describe the problem of high energy (higher than 10^4J) seismic bumps forecasting in a coal mine using two long walls as an example. For this purpose, seismic bumps data obtained from mines has been analyzed. The results obtained show that the ANN with high accuracy was able to predict earthquake parameters; the classification accuracy through neural networks is more than 94%, and that the models developed are efficient and robust and depend only weakly on the initial database.

Keywords: earthquake prediction, ANN, seismic bumps

Procedia PDF Downloads 94

Authors: N. H. Adenan, M. S. M. Noorani

Abstract:

River flow prediction is an essential to ensure proper management of water resources can be optimally distribute water to consumers. This study presents an analysis and prediction by using nonlinear prediction method involving monthly river flow data in Tanjung Tualang from 1976 to 2006. Nonlinear prediction method involves the reconstruction of phase space and local linear approximation approach. The phase space reconstruction involves the reconstruction of one-dimensional (the observed 287 months of data) in a multidimensional phase space to reveal the dynamics of the system. Revenue of phase space reconstruction is used to predict the next 72 months. A comparison of prediction performance based on correlation coefficient (CC) and root mean square error (RMSE) have been employed to compare prediction performance for nonlinear prediction method, ARIMA and SVM. Prediction performance comparisons show the prediction results using nonlinear prediction method is better than ARIMA and SVM. Therefore, the result of this study could be used to developed an efficient water management system to optimize the allocation water resources.

Keywords: river flow, nonlinear prediction method, phase space, local linear approximation

Procedia PDF Downloads 383

Authors: Farzad Jalilian, Mehdi Mirzaei Alavijeh, Fazel Zinat Motlagh

Abstract:

Social support is an important benchmark of health for people in avoidance conditions. The main goal of this study was to determine the three kinds of social support (family, friend and other significant) to drug cessation among male addicts, in Kermanshah, the west of Iran. This cross-sectional study was conducted among 132 addicts, randomly selected to participate voluntarily in the study. Data were collected from conduct interviews based on standard questionnaire and analyzed by using SPSS-18 at 95% significance level. The majority of addicts were young (Mean: 30.4 years), and with little education. Opium (36.4%), Crack (21.2%), and Methamphetamine (12.9%) were the predominant drugs. Inabilities to reject the offer and having addict friends are the most often reasons for drug usage. Almost, 18.9% reported history of drug injection. 43.2% of the participants already did drug cessation at least once. Logistic regression showed the family support (OR = 1.110), age (OR = 1.106) and drug use initiation age (OR = 0.918) was predicting drug cessation. Our result showed; family support is a more important effect among types of social support in drug cessation. It seems that providing educational program to addict’s families for more support of patients at drug cessation can be beneficial.

Keywords: drug cessation, family support, drug use, initiation age

Procedia PDF Downloads 505

Authors: Temesgen Geremew

Abstract:

Functionalized nanoparticles have emerged as a revolutionary platform for drug delivery, offering significant advantages over traditional methods. By strategically modifying their surface properties, these nanoparticles can be designed to target specific tissues and cells, significantly reducing off-target effects and enhancing therapeutic efficacy. This targeted approach allows for lower drug doses, minimizing systemic exposure and potential side effects. Additionally, functionalization enables controlled release of the encapsulated drug, improving drug stability and reducing the frequency of administration, leading to improved patient compliance. This work explores the immense potential of functionalized nanoparticles in revolutionizing drug delivery, addressing limitations associated with conventional therapies and paving the way for personalized medicine with precise and targeted treatment strategies.

Keywords: nanoparticles, drug, nanomaterials, applications

Procedia PDF Downloads 20

Authors: Jeff Clarine, Chang-Shyh Peng, Daisy Sang

Abstract:

Bioassay is the measurement of the potency of a chemical substance by its effect on a living animal or plant tissue. Bioassay data and chemical structures from pharmacokinetic and drug metabolism screening are mined from and housed in multiple databases. Bioassay prediction is calculated accordingly to determine further advancement. This paper proposes a four-step preprocessing of datasets for improving the bioassay predictions. The first step is instance selection in which dataset is categorized into training, testing, and validation sets. The second step is discretization that partitions the data in consideration of accuracy vs. precision. The third step is normalization where data are normalized between 0 and 1 for subsequent machine learning processing. The fourth step is feature selection where key chemical properties and attributes are generated. The streamlined results are then analyzed for the prediction of effectiveness by various machine learning algorithms including Pipeline Pilot, R, Weka, and Excel. Experiments and evaluations reveal the effectiveness of various combination of preprocessing steps and machine learning algorithms in more consistent and accurate prediction.

Keywords: bioassay, machine learning, preprocessing, virtual screen

Procedia PDF Downloads 246

Authors: Adegoke Yinka Adebayo

Abstract:

An understanding of the critical product attributes that impact on in vivo performance is key to the production of safe and effective medicines. Thus, a key driver for our research is the development of new basic science and technology underpinning the development of new pharmaceutical products. Research includes the structure and properties of drugs and excipients, biopharmaceutical characterisation, pharmaceutical processing and technology and formulation and analysis.

Keywords: drug discovery, drug development, drug delivery

Procedia PDF Downloads 458

Authors: S. Niamkaeo, O. Robert, O. Chaowalit

Abstract:

In this investigation, we focus on discovering spatial relationship of drug smuggling along the northern border of Thailand. Thailand is no longer a drug production site, but Thailand is still one of the major drug trafficking hubs due to its topographic characteristics facilitating drug smuggling from neighboring countries. Our study areas cover three districts (Mae-jan, Mae-fahluang, and Mae-sai) in Chiangrai city and four districts (Chiangdao, Mae-eye, Chaiprakarn, and Wienghang) in Chiangmai city where drug smuggling of methamphetamine crystal and amphetamine occurs mostly. The data on drug smuggling incidents from 2011 to 2017 was collected from several national and local published news. Geo-spatial drug smuggling database was prepared. Decision tree algorithm was applied in order to discover the spatial relationship of factors related to drug smuggling, which was converted into rules using rule-based system. The factors including land use type, smuggling route, season and distance within 500 meters from check points were found that they were related to drug smuggling in terms of rules-based relationship. It was illustrated that drug smuggling was occurred mostly in forest area in winter. Drug smuggling exhibited was discovered mainly along topographic road where check points were not reachable. This spatial relationship of drug smuggling could support the Thai Office of Narcotics Control Board in surveillance drug smuggling.

Keywords: decision tree, drug smuggling, Geographic Information System, GIS knowledge discovery, rule-based system

Procedia PDF Downloads 141

Authors: Venkata Srikanth Meka, Nur Arthirah Binti Ahmad Tarmizi Tan, Muhammad Syahmi Bin Md Nazir, Adinarayana Gorajana, Senthil Rajan Dharmalingam

Abstract:

Biphasic drug delivery systems are designed to release drug at two different rates, either fast/prolonged or prolonged/fast. A fast/prolonged release system provides a burst drug release at initial stage followed by a slow release over a prolonged period of time and in case of prolonged/fast release system, the release pattern is vice versa. Terminalia catappa gum (TCG) is a natural polymer and was successfully proven as a novel pharmaceutical excipient. The main objective of the present research is to investigate the applicability of natural polymer, Terminalia catappa gum in the design of oral biphasic drug delivery system in the form of mini tablets by using a model drug, buspirone HCl. This investigation aims to produce a biphasic release drug delivery system of buspirone by combining immediate release and prolonged release mini tablets into a capsule. For immediate release mini tablets, a dose of 4.5 mg buspirone was prepared by varying the concentration of superdisintegrant; crospovidone. On the other hand, prolonged release mini tablets were produced by using different concentrations of the natural polymer; TCG with a buspirone dose of 3mg. All mini tablets were characterized for weight variation, hardness, friability, disintegration, content uniformity and dissolution studies. The optimized formulations of immediate and prolonged release mini tablets were finally combined in a capsule and was evaluated for release studies. FTIR and DSC studies were conducted to study the drug-polymer interaction. All formulations of immediate release and prolonged release mini tablets were passed all the in-process quality control tests according to US Pharmacopoeia. The disintegration time of immediate release mini tablets of different formulations was varied from 2-6 min, and maximum drug release was achieved in lesser than 60 min. Whereas prolonged release mini tablets made with TCG have shown good drug retarding properties. Formulations were controlled for about 4-10 hrs with varying concentration of TCG. As the concentration of TCG increased, the drug release retarding property also increased. The optimised mini tablets were packed in capsules and were evaluated for the release mechanism. The capsule dosage form has clearly exhibited the biphasic release of buspirone, indicating that TCG is a suitable natural polymer for this study. FTIR and DSC studies proved that there was no interaction between the drug and polymer. Based on the above positive results, it can be concluded that TCG is a suitable polymer for the biphasic drug delivery systems.

Keywords: Terminalia catappa gum, biphasic release, mini tablets, tablet in capsule, natural polymers

Procedia PDF Downloads 357