Elisa Gómez de Lope's Projects
Bayesian Optimization and Design of Experiments
Deep learning specialization on coursera consists on a series of 5 courses: Neural Networks and deep learning / Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization / Structuring Machine Learning Projects / Convolutional Neural Networks / Sequence Models. In this repository you can find the notebooks with the exercises.
Basics of data wrangling in R with the 'tidyverse'
Datatathon Critical Care Tarragona 2018
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Spin off the datathon Tarragona 2018 challenge
My personal repository.
Personal website using R Markdown & Hugo.
Aggregates or summarizes omics data into higher level functional representations such as GO terms gene sets or KEGG metabolic pathways, facilitating the analysis of functional molecular sets that allow to reduce dimensionality and provide easier and faster biological interpretations.
Graph representation learning modelling pipeline exploiting molecular interaction networks derived from high-throughput omics profiles to learn PD-specific fingerprints in an end-to-end fashion. It is applied to transcriptomics and metabolomics data from the PPMI and the LuxPARK cohort, respectively.
Graph representation learning modelling pipeline exploiting sample-similarity networks derived from high-throughput omics profiles to learn PD-specific fingerprints in an end-to-end fashion. It is applied to transcriptomics and metabolomics data from the PPMI and the LuxPARK cohort, respectively.
Histopathological cancer detection from kaggle competition
ML basis scripts
ML models for Parkinson's disease case-control classification using blood-based transcriptomics and metabolomics measurements at the baseline clinical visit along with dynamic features engineered from short longitudinal series to assess diff. algorithms & identify static and dynamic molecular and higher-level functional biomarkers of PD diagnosis.
ML models to predict motor ability scores (UPDRS III) in Parkinson's disease using blood-based transcriptomics and metabolomics profiles. Leveraging baseline and temporal features engineered from short longitudinal series (4 and 3 timepoints), the goal is to identify molecular and functional fingerprints linked to motor symptoms in PD patients.
Some of the scripts developed in Pharmacelera S.L. for my Master Thesis (Parametrization of atom-types LogP-based hydrophobic descriptors for virtual screening). The project was developed within the framework of Pharmacelera S.L. intelecutal property (IP), so only a short representation of the scripts developed can be uploaded to this publicly available repository.
Package and environment with the NestedCV() class - a scikit-learn compatible class for nested cross-validation.
Jupyter notebooks for learning and having an overview of Pandas library and Plotly with some exercises
PyTorch tutorials.
Repo containing SAS papers and scripts hopefully useful for SAS beginners
CS224W Stanford 2019fall -- Machine Learning with Graphs.
Statistical analyses for cross-sectional and longitudinal profiling of Parkinson's disease patients and controls transcriptomics and metabolomics from the PPMI cohort and the LuxPARK cohort respectively, to identify differential molecular and higher-level functional features in PD.
A playbook for systematically maximizing the performance of deep learning models.