Using MNIST (digit) dataset, use tSNE for dimensionality reduction, compare it to PCA and tweak some of the parameters to see the effect on clusters.

Machine Learning Classification Problem example. Uses different machine learning algorithms to classify patients with Chronic Kidney Disease or not based on 24 features. https://archive.ics.uci.edu/ml/datasets/Chronic_Kidney_Disease Implemented the SVM model as a web application https://shruti-marwaha.shinyapps.io/ KidneyDiseasePredictor/

Kaggle Challenge to classify 39 different crimes that occurred in SF in 12 years. https://www.kaggle.com/c/sf-crime

Machine Learning Classification Problem example. Use different machine learning algorithms to classify flowers into 3 different category based on 4 features.

machine learning for continous data, predict wages using multiple features.

HPV positive vs HPV negative analysis for Head and Neck cancer dataset - GSE65858 Tumor vs Normal analysis for Head and Neck cancer dataset - GSE65858 under different conditions: (HPV positive & negative) Tumor vs Normal (HPVnegative); HPV Positive Tumor vs Normal (HPV negative); HPV Negative Tumor vs Normal (HPVnegative); Tumor vs Normal - tonsil samples only.

HPV positive vs HPV negative analysis for Head and Neck cancer dataset - GSE40774

HPV positive vs HPV negative analysis for Head and Neck cancer dataset - GSE3292

HPV positive vs HPV negative analysis for Head and Neck cancer (OroPharyngeal Squamous Cell Carcinoma) dataset - GSE55542

HPV positive vs HPV negative analysis for Head and Neck cancer dataset - GSE65858

This is an R Markdown document to analyze qPCR data from an experiment which tests if SHH can further enhance the expression of cytokines (IL-12, IL-1β, CXCL-2 and TNF) in H. pylori stimulated macrophages.

Analysis of qPCR data obtained from WT and PC-SHH-KO mice infected with Helicobacter pylori or uninfected. Two types of statistical tests are performed: Interaction plots and Two-way ANOVA.

IL-1b, IL-10 and IFNg trajectories in Helicobacter pylori infection. We extracted and analyzed time-series data for IL-10, IFNγ, IL-1β from gse37938 dataset. For a given probe, median of its expression values was calculated for each time point. The median values for both control and H.pylori infection were plotted against time to study their trajectory. Probes with two or more missing values for more than one time point, were ignored. To address the problem of probe selection, median value was taken for probes with same Genbank ID (GB_list ID ) while probes with different Genbank ID were analyzed separately.