Category Archives: Research

Feature Selection & Variable Screening

Introduction

With the recent advances in theoretical and computational methods for characterizing chemical, physicochemical and biological phenomena, volumes of information (data matrices) are often available for analysis. This is however not necessarily all advantageous as it usually engenders high dimensionality (i.e. “small sample-many features”) space, which has detrimental influence on the performance of regression and classification algorithms. Moreover, an exhaustive examination of the entire feature (variable) space in the search of subsets that best describe a specified phenomenon comes along with high computational complexity, in addition to the fact that such exploration may lead to the selection of features that aggravate data overfitting. It is thus important to develop procedures that filter out noisy, redundant or highly correlated variables without affecting the learning performance. It is known that dimensionality reduction usually improves the quality of models (especially, their predictive power), in addition to permitting greater computational efficiency. In this sense, the IMMAN (acronym for Information theory-based CheMoMetrics ANalysis) software is conceived as a free computational tool for supervised and unsupervised feature selection based on information-theoretic parameters.
Read More »

Identification and design of novel antimicrobial peptides

Introduction

The Antimicrobial Peptides (AMPs) have emerged as an alternative solution to fight against multi-drug-resistance infections. However, they have not been translated successfully to the therapeutic application as one would expect since its discovery in the early 1980s. Its limitations are the main reasons why there are many researchers that continue isolating and studying the AMPs. There is the conviction that this type of compounds will enter the marketplace as a valuable antimicrobial weapon in the next years.

During the last decade, the number of AMPs databases has increased thanks to the significant efforts made by researchers in the field. These databases hold thousands of naturally occurring examples and synthetic ones, providing valuable information regarding the structure and functions of AMPs. Particularly, we believe that there is an implicit knowledge that must be discovered and applied in the identification and design of novel antimicrobial agents that mimic the biological activity of AMPs.
Read More »