RESUMO
BACKGROUND: The Random Forest (RF) algorithm for supervised machine learning is an ensemble learning method widely used in science and many other fields. Its popularity has been increasing, but relatively few studies address the parameter selection process: a critical step in model fitting. Due to numerous assertions regarding the performance reliability of the default parameters, many RF models are fit using these values. However there has not yet been a thorough examination of the parameter-sensitivity of RFs in computational genomic studies. We address this gap here. RESULTS: We examined the effects of parameter selection on classification performance using the RF machine learning algorithm on two biological datasets with distinct p/n ratios: sequencing summary statistics (low p/n) and microarray-derived data (high p/n). Here, p, refers to the number of variables and, n, the number of samples. Our findings demonstrate that parameterization is highly correlated with prediction accuracy and variable importance measures (VIMs). Further, we demonstrate that different parameters are critical in tuning different datasets, and that parameter-optimization significantly enhances upon the default parameters. CONCLUSIONS: Parameter performance demonstrated wide variability on both low and high p/n data. Therefore, there is significant benefit to be gained by model tuning RFs away from their default parameter settings.
Assuntos
Algoritmos , Biologia Computacional/métodos , Modelos Teóricos , Reprodutibilidade dos TestesRESUMO
Actinobacillus equuli subsp. equuli is a member of the family Pasteurellaceae that is a common resident of the oral cavity and alimentary tract of healthy horses. At the same time, it can also cause a fatal septicemia in foals, commonly known as sleepy foal disease or joint ill disease. In addition, A. equuli subsp. equuli has recently been reported to act as a primary pathogen in breeding sows and piglets. To better understand how A. equuli subsp. equuli can cause disease, the genome of the type strain of A. equuli subsp. equuli, ATCC 19392(T), was sequenced using the PacBio RSII sequencing system. Its genome is comprised of 2,431,533 bp and is predicted to encode 2,264 proteins and 82 RNAs.