Neuro-fuzzy Prediction of Biological Activity and Rule Extraction for HIV-1 Protease Inhibitors

Andonie, Răzvan; Fabry-Asztalos, Levente; Collar, Catharine J.; Abdul-Wahid, S.; Salim, Nicholas

doi:10.1109/cibcb.2005.1594906

Cited by 10 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, 30 molecular descriptors were selected, based on their contribution to molecular entity [21]. These descriptors are displayed in Table I.…”

Section: Iiic 50 Prediction Of Hiv-1 Protease Inhibitors Inputmentioning

confidence: 99%

“…Due to current drug resistance and toxicity, there is necessity for the developing drugs with less toxicity, different levels of resistance profiles and many type of inhibitory action. Thus, many novel methods for designing enzyme inhibitors, and subsequent prediction of their properties, are expected to have great value in drug discovery [21].…”

Section: Iiic 50 Prediction Of Hiv-1 Protease Inhibitors Inputmentioning

confidence: 99%

“…The data for training and testing consisted of 196 known compounds with determined IC 50 values. The IC 50 value represents the concentration of protease inhibitors required to reduce enzyme activity by 50% [21]. A total of 26 novel compounds were designed via a 'combinatorial' approach using known compounds with low IC 50 and high TI values.…”

Section: Iiic 50 Prediction Of Hiv-1 Protease Inhibitors Inputmentioning

confidence: 99%

See 2 more Smart Citations

A fuzzy based approach for prediction of biological activities of HIV -1 protease inhibitor compounds

Parthiban¹,

Parthiban

2011

2011 2nd International Conference on Intelligent Agent &Amp; Multi-Agent Systems

View full text Add to dashboard Cite

A neuro-fuzzy based approach for predicting the HIV-1 inhibitor compounds activity has been designed when the molecular descriptor attributes of the compound are known. Standard Fuzzy ARTMAP (FAM) is provided with 196 data sets which is divided into 176 training data and 20 test data. The normalized data is given to the FAM network and the result indicates whether the compound is a suitable inhibitor or not.The result analysis is done with/ without GA for the dataset and GA-FAMR algorithm is used to optimize the relevance's assigned to the training data and the accuracy obtained is 93.09%.

show abstract

“…In this study, 30 molecular descriptors were selected, based on their contribution to molecular entity [21]. These descriptors are displayed in Table I.…”

Section: Iiic 50 Prediction Of Hiv-1 Protease Inhibitors Inputmentioning

confidence: 99%

Section: Iiic 50 Prediction Of Hiv-1 Protease Inhibitors Inputmentioning

confidence: 99%

Section: Iiic 50 Prediction Of Hiv-1 Protease Inhibitors Inputmentioning

confidence: 99%

See 1 more Smart Citation

A fuzzy based approach for prediction of biological activities of HIV -1 protease inhibitor compounds

Parthiban¹,

Parthiban

2011

2011 2nd International Conference on Intelligent Agent &Amp; Multi-Agent Systems

View full text Add to dashboard Cite

show abstract

“…In previous work [2] we investigated the use of a fuzzy neural network (FNN) for biological activity (IC 50 ) prediction 1 . More recently [1], we improved this model by adding a two-stage GA-optimizer: one for selecting the best subset of features and the other for optimizing the FNN parameters.…”

Section: Introductionmentioning

confidence: 99%

A New Fuzzy ARTMAP Approach for Predicting Biological Activity of Potential HIV-1 Protease Inhibitors

Andonie

Fabry-Asztalos

Magill

et al. 2007

2007 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2007)

View full text Add to dashboard Cite

The Fuzzy ARTMAP with Relevance factor (FAMR) is a Fuzzy ARTMAP (FAM) neural architecture with the following property: Each training pair has a relevance factor assigned to it, proportional to the importance of that pair during the learning phase. Using a relevance factor adds more flexibility to the training phase, allowing ranking of sample pairs according to the confidence we have in the information source.We focus on the prediction of biological activities of HIV-1 protease inhibitory compounds, both known and novel, using a FAMR model. Our new approach consists of two stages: i) During the first stage, we use a genetic algorithm (GA) to optimize the relevances assigned to the training data. This improves the generalization capability of the FAMR. ii) In the second stage we use the optimized relevances to train the FAMR. Finally, the trained FAMR is used to predict the biological activities of newly designed potential HIV-1 protease inhibitors.

show abstract

“…In [7], we investigated the use of a fuzzy neural network (FNN) for (IC  ) prediction. In [1] and [2], we improved this model by adding a two-stage Genetic Algorithm (GA) optimizer: the first for selecting the best subset of features and the the second for optimizing the FNN parameters.…”

Section: Our Previous Workmentioning

confidence: 99%

Extreme Data Mining: Inference from Small Datasets

Andonie

2010

INT J COMPUT COMMUN

View full text Add to dashboard Cite

Neural networks have been applied successfully in many fields. However, satisfactory results can only be found under large sample conditions. When it comes to small training sets, the performance may not be so good, or the learning task can even not be accomplished. This deficiency limits the applications of neural network severely. The main reason why small datasets cannot provide enough information is that there exist gaps between samples, even the domain of samples cannot be ensured. Several computational intelligence techniques have been proposed to overcome the limits of learning from small datasets. We have the following goals: i. To discuss the meaning of "small" in the context of inferring from small datasets. ii. To overview computational intelligence solutions for this problem. iii. To illustrate the introduced concepts with a real-life application.

show abstract

Neuro-fuzzy Prediction of Biological Activity and Rule Extraction for HIV-1 Protease Inhibitors

Cited by 10 publications

References 43 publications

A fuzzy based approach for prediction of biological activities of HIV -1 protease inhibitor compounds

A fuzzy based approach for prediction of biological activities of HIV -1 protease inhibitor compounds

A New Fuzzy ARTMAP Approach for Predicting Biological Activity of Potential HIV-1 Protease Inhibitors

Extreme Data Mining: Inference from Small Datasets

Contact Info

Product

Resources

About