Amir Lakizadeh | University of Qom (original) (raw)

Papers by Amir Lakizadeh

Best values are bolded.</p

Informatics in Medicine Unlocked

Scientific Reports

The prevalence of multi_drug therapies has been increasing in recent years, particularly among th... more The prevalence of multi_drug therapies has been increasing in recent years, particularly among the elderly who are suffering from several diseases. However, unexpected Drug_Drug interaction (DDI) can cause adverse reactions or critical toxicity, which puts patients in danger. As the need for multi_drug treatment increases, it's becoming increasingly necessary to discover DDIs. Nevertheless, DDIs detection in an extensive number of drug pairs, both in-vitro and in-vivo, is costly and laborious. Therefore, DDI identification is one of the most concerns in drug-related researches. In this paper, we propose GNN-DDI, a deep learning-based method for predicting DDI-associated events in two stages. In the first stage, we collect the drugs information from different sources and then integrate them through the formation of an attributed heterogeneous network and generate a drug embedding vector based on different drug interaction types and drug attributes. In the second stage, we aggrega...

The actual numbers of T (mesostable) and F (thermostable) classes in the original datase... more The actual numbers of T (mesostable) and F (thermostable) classes in the original datasets were 1544 and 513, respectively. The highest accuracy (100%) was observed when the EMC clustering method was applied to datasets generated by Correlation and Uncertainty attribute weighting algorithms that highlighted in the table.</p

The prevalence of multi_drug therapies has been increasing in recent years, particularly among th... more The prevalence of multi_drug therapies has been increasing in recent years, particularly among the elderly who are suffering from several diseases. However, unexpected Drug_Drug interaction (DDI) can cause adverse reactions or critical toxicity, which puts patients in danger. As the need for multi_drug treatments increases, it's becoming increasingly necessary to discover DDIs. Nevertheless, the DDIs detection in an extensive number of drug pairs, both in-vitro and in-vivo, is costly and laborious, Therefore, DDI identification is one of the most concerns in drug-related researches. In this paper, we propose GNN-DDI, a deep learning-based method for predicting DDI-associated events in two stages. In the first stage, it collects drugs information from different sources then integrates them through the formation of an attributed heterogeneous network. In the second stage, predictions of the DDIs and their events are performed through a deep multi-model framework. Various evaluatio...

X, TS-X and Bi-X refer to static version, dynamic version of X correspondence to recent ... more X, TS-X and Bi-X refer to static version, dynamic version of X correspondence to recent dynamic method presented in TS-OCD and dynamic version of X according to GA-DCM dynamic method presented in this paper.</p

Sample encoding of a bicluster.</p

The comparison results are based on BioGrid dataset in terms of f1-measure with respect ... more The comparison results are based on BioGrid dataset in terms of f1-measure with respect to CYC2008 benchmark complex set.</p

Best values are bolded.</p

general view of the GA-PCD, the proposed biclustering genetic algorithm.</p

The comparison results are based on DIP dataset in terms of f1-measure with respect to C... more The comparison results are based on DIP dataset in terms of f1-measure with respect to CYC2008 benchmark complex set.</p

Topologies and overall, true, and false accuracies of the best neural networks run on wh... more Topologies and overall, true, and false accuracies of the best neural networks run on whole database (with 794 features) and step-wised feature selected database (with 27 features).</p

The comparison of GA-DCT with other biclustering algorithms in case of protein complex d... more The comparison of GA-DCT with other biclustering algorithms in case of protein complex detection metrics.</p

Molecular diversity, 2022

The consumption of drug combinations, named polypharmacy, is commonly used for treating patients ... more The consumption of drug combinations, named polypharmacy, is commonly used for treating patients with several diseases or those with complex conditions. However, the main drawback of polypharmacy is the increased probability of harmful side effects. The polypharmacy side effects are caused by an interaction between two medications. It means that the drug-drug interaction causes changes in their activities due to interfering in each other's performance. Therefore, discovering these side effects is one of the most challenging and important aspects of drug production and consumption as it is associated with human health. In this paper, a method has been introduced for predicting the polypharmacy side effects, called PSECNN. It is a multi-label multi-class deep learning method that combines various basic features of drugs to predict the polypharmacy side effects. Firstly, PSECNN collects five basic features of drugs, such as individual drug's side effects, drug-protein interacti...

DOI:10.22044/JADM.2021.11022.2249 Text sentiment classification in aspect level is one of the hot... more DOI:10.22044/JADM.2021.11022.2249 Text sentiment classification in aspect level is one of the hottest research topics in the field of natural language processing. The purpose of the aspect-level sentiment analysis is to determine the polarity of the text according to a particular aspect. Recently, various methods have been developed in order to determine sentiment polarity of the text at the aspect level; however, these studies have not yet been able to model well the complementary effects of the context and aspect in the polarization detection process. Here, we present ACTSC, a method for determining the sentiment polarity of the text based on separate embedding of aspects and context. In the first step, ACTSC deals with the separate modelling of the aspects and context in order to extract new representation vectors. Next, by combining generative representations of aspect and context, it determines the corresponding polarity to each particular aspect using a short-term memory netwo...

Prediction of protein secondary structures is one of the oldest problems in Bioinformatics. Altho... more Prediction of protein secondary structures is one of the oldest problems in Bioinformatics. Although several different methods have been proposed to tackle this problem, none of these methods are perfect. Recently, it is proposed that addition of other structural information like accessible surface area of residues or prior information about protein structural class can sig-nificantly improve the prediction of secondary structures. In this work, we propose that con-tact number information can be considered as another useful source of information for im-provement of secondary structure prediction. Since contact number, i. e. the number of other amino acid residues in the structural neighbourhood of a certain residue, depends on the sec-ondary structure of the residue, we conjectured that contact number data can improve secon-dary structure prediction. We used two closely related neural networks to predict secondary structures. The only difference in the neural networks was that one o...

Prediction of protein secondary structures is one of the oldest problems in Bioinformatics. Altho... more Prediction of protein secondary structures is one of the oldest problems in Bioinformatics. Although several different methods have been proposed to tackle this problem, none of these methods are perfect. Recently, it is proposed that addition of other structural information like accessible surface area of residues or prior information about protein structural class can sig- nificantly improve the prediction of secondary structures. In this work, we propose that con- tact number information can be considered as another useful source of information for im- provement of secondary structure prediction. Since contact number, i. e. the number of other amino acid residues in the structural neighbourhood of a certain residue, depends on the sec- ondary structure of the residue, we conjectured that contact number data can improve secon- dary structure prediction. We used two closely related neural networks to predict secondary structures. The only difference in the neural networks was that ...

There is a high demand for engineering thermostable enzymes in some industries; especially in pap... more There is a high demand for engineering thermostable enzymes in some industries; especially in paper industries to use environmental friendly enzymes instead of toxic chlorine chemicals. Hence, understanding protein attributes involved in enzyme thermostability is important. Herein, the most important protein features contributing to enzyme thermostability was searched by using data mining algorithms. Combination of attribute weighting and unsupervised clustering algorithms were used to explore protein attributes which play major roles in thermostability. The results showed that expectation maximization clustering with uncertainly and correlation attribute weighting algorithms can effectively (100%) classify thermo- and meso-stable proteins. Gln content and frequency of hydrophilic residues were the most important protein features selected by 70% of weighing methods. The findings of this research provide the required knowledge for engineering thermostable enzymes in laboratory.

Informatics in Medicine Unlocked, 2021

Abstract The most significant drawback of experimental methods in drug development and discovery ... more Abstract The most significant drawback of experimental methods in drug development and discovery is that they are time-consuming and costly. Researches have indicated that designing a new drug from primary stages to its delivery to the consumer market lasts between 10 and 15 years. Moreover, this process costs about 0.8–1.5 billion dollars. Drug repurposing refers to seeking new indications for approved drugs. Recently, some methods have attempted to repurpose drugs based on incorporating computational approaches. In the present research, a method has been proposed for drug repurposing with the aim of integrating diverse and heterogeneous data sources, called DRSE. The proposed method can predict drug-disease associations based on the integration of multiple data sources through a matrix factorization algorithm considering side effect features of the drugs. The experimental results confirmed that the proposed method can improve accuracy of the drug repurposing task. In addition, the AUC and AUPR criteria have been improved by 1.13 and 14.23%, respectively, compared to the state-of-the-art methods.

Best values are bolded.</p

Informatics in Medicine Unlocked

Scientific Reports

The prevalence of multi_drug therapies has been increasing in recent years, particularly among th... more The prevalence of multi_drug therapies has been increasing in recent years, particularly among the elderly who are suffering from several diseases. However, unexpected Drug_Drug interaction (DDI) can cause adverse reactions or critical toxicity, which puts patients in danger. As the need for multi_drug treatments increases, it's becoming increasingly necessary to discover DDIs. Nevertheless, the DDIs detection in an extensive number of drug pairs, both in-vitro and in-vivo, is costly and laborious, Therefore, DDI identification is one of the most concerns in drug-related researches. In this paper, we propose GNN-DDI, a deep learning-based method for predicting DDI-associated events in two stages. In the first stage, it collects drugs information from different sources then integrates them through the formation of an attributed heterogeneous network. In the second stage, predictions of the DDIs and their events are performed through a deep multi-model framework. Various evaluatio...

Sample encoding of a bicluster.</p

Best values are bolded.</p

general view of the GA-PCD, the proposed biclustering genetic algorithm.</p

Molecular diversity, 2022

Prediction of protein secondary structures is one of the oldest problems in Bioinformatics. Altho... more Prediction of protein secondary structures is one of the oldest problems in Bioinformatics. Although several different methods have been proposed to tackle this problem, none of these methods are perfect. Recently, it is proposed that addition of other structural information like accessible surface area of residues or prior information about protein structural class can sig- nificantly improve the prediction of secondary structures. In this work, we propose that con- tact number information can be considered as another useful source of information for im- provement of secondary structure prediction. Since contact number, i. e. the number of other amino acid residues in the structural neighbourhood of a certain residue, depends on the sec- ondary structure of the residue, we conjectured that contact number data can improve secon- dary structure prediction. We used two closely related neural networks to predict secondary structures. The only difference in the neural networks was that ...

Informatics in Medicine Unlocked, 2021