pdb stutructure:gcufbioinfo

phenylalanine amino lyase 1

Read more »

What I concluded:

Conclusion

From all these research papers I have concluded that from all the data mining techniques PCA is considered to be the best because it reduces large data set into smaller ones and narrow down our research that we can useful information from small data sets. Dimension of a large dataset can be reduced by using principal component analysis which is considered as one of the most popular and useful statistical method. This method transforms the original data in to new dimensions.          

Read more »

Combined Supervised and Unsupervised Learning in Genomic Data Mining

Last edited by

Quratt ul ain Siddique

Summary:

In this paper they introduced the most comprehensive method for predicting the function of proteins. Their approach differs in several respects from the earlier work in that it uses a multistage decomposition that makes use of both unsupervised and supervised machine learning techniques; they refer to this as Unsupervised-Supervised Tree (UST) algorithm.

The typical first stage (optional) of the UST uses clustering algorithms such as neural network self organizing maps (SOMs) and K-means; this is the unsupervised stage. Subsequent indispensable stages typically involve constructing a Maximum Contrast Tree (MCT) so that protein functional relationships can be mapped onto the relational tree structure.

The MCTs are a family of completely independent algorithms that can be used alone. Testing is based on a newly developed MLIC (Multiple-Labeled Instance Classifier) based on supervised K nearest neighbor classifier on the tree structure. Performance has been compared with the decision tree C4.5 and C5 programs and with support vector machines.

Based on the experiments, UST algorithms appear to perform considerably better than decision tree algorithms C4.5 and C5, and support vector machines, and can provide a viable alternative to supervised or unsupervised methods alone. In addition, UST and MLIC classifiers are capable of handling protein functional classes with a small number of proteins (rare events), and also handle multifunctional proteins. The abilities of the USTs and MLICs to handle such cases means that a larger dataset can be used, which may provide deeper insight into protein functional relationships at the genomic level, and thus may lead to a better understanding of evolution at a molecular and genomic level.

Read more »

Acute Coronary Syndrome Prediction Using Data Mining Techniques- An Application

Last edited by

Quratt ul ain Siddique

Summary:

In this research paper data mining techniques are used to investigate the factors that are responsible for enhancing the risk of acute coronary syndrome. They have applied binary regression to factors that effecting the dependent variable. For the better performance of regression model in predicting coronary syndrome the reduction technique which is principle component analysis is used and applied. Based on results of data reduction, they have considered only 14 out of sixteen factors.

In this research paper logistic regression model is used to find the factors which are responsible for this Acute Coronary Syndrome (ACS). For the analysis of this problem data mining technique is used for the comparasion of the persons who have ACS or who don’t have.  

In this paper first data reduction techniques are applied that reduce the dimensions. After data reduction, the fourteen independent variables are age, gender, smoke, hypertension, family history, diabetics mellitus, fasting blood sugar, random blood sugar, cholesterol, streptokinase, blood pressure (systolic), blood pressure (diastolic), heart rate and pulse rate. After the calculation of corresponding significance of smoking which is “0” indicating that it has a high prevalence in the risk of ACS. The calculation of wald statistics indicates positive coefficients of HR, RBS, and BPS revealed that the risk of ACS increases with the increasing value of these factors.

The negative coefficients of BPd and PR revealed that the more the negative these values the more the increase in the risk of this disease. They observed that smoking is considered to be the worst cause of this Acute Coronary Sysndrome.

Read more »