Data Science Projects – Portfolio

Evaluating ProteinBERT-GraphSAGE

LLM

BERT

Deep learning

GNN

This is the third part of the series using ProtenBERT and Graph neural networks (GNNs). On this part, we’re gonna use the trained model and see if the protein-protein…

Predict Protein-Protein Interactions with GraphSAGE

LLM

BERT

Deep learning

GNN

This is the second of a Protein Embedding with ProteinBERT and STRING. On this part, we are gonna build a graph neural network (GNN) to update the embeddings of PorteinBERT…

Protein Embedding with ProteinBERT and STRING

Deep learning

BERT

LLM

On this project we’ll learn how to use ProteinBERT (a large language model trained developed protein sequences) to get embeddings for aminoacids sequences and how to use…

Analysis of Time-series Data

statistics

time-series

On this project we’ll analyze a time-series data. Specifically, we’ll analyze the annual average temperature from Junin, Peru. The objective is build a model that can helps…

Analysis of Hyper-parameters on Single Cell RNA-Seq Data

scrnaseq

high-dimensional

statistics

regression

We will analyze three types of hyper-parameters: Perplexity on t-SNE, number of clusters chosen from an unsupervised method and how these affect the quality of the selected…

Likelihood Ratio Test, Regression and Gradient Descent

statistics

regression

The file gamma-ray.csv contains a small quantity of data collected from the Compton Gamma Ray Observatory, a satellite launched by NASA in 1991…