The new technology of single-cell RNA sequencing (scRNA-seq) can yield valuable insights into gene expression and give critical information about the cellular compositions of complex tissues. In recent years, vast numbers of scRNA-seq datasets have been generated and made publicly available, and this has enabled researchers to train supervised machine learning models for predicting or classifying various cell-level phenotypes. This has led to the development of many new methods for analyzing scRNA-seq data. Despite the popularity of such applications, there has as yet been no systematic investigation of the performance of these supervised algorithms using predictors from various sizes of scRNA-seq datasets. In this study, 13 popular supervised machine learning algorithms for cell phenotype classification were evaluated using published real and simulated datasets with diverse cell sizes. This benchmark comprises two parts. In the first, real datasets were used to assess the computing speed and cell phenotype classification performance of popular supervised algorithms. The classification performances were evaluated using the area under the receiver operating characteristic curve, F1-score, Precision, Recall, and false-positive rate. In the second part, we evaluated gene-selection performance using published simulated datasets with a known list of real genes. The results showed that ElasticNet with interactions performed the best for small and medium-sized datasets. The NaiveBayes classifier was found to be another appropriate method for medium-sized datasets. With large datasets, the performance of the XGBoost algorithm was found to be excellent. Ensemble algorithms were not found to be significantly superior to individual machine learning methods. Including interactions in the ElasticNet algorithm caused a significant performance improvement for small datasets. The linear discriminant analysis algorithm was found to be the best choice when speed is critical; it is the fastest method, it can scale to handle large sample sizes, and its performance is not much worse than the top performers.
27 September 2022 in Applied Stochastic Models in Business and Industry
In this paper, we systematically investigate the regulation of retention behavior of amphoteric compounds, amino acids, and small peptides in the whole pH range in reversed-phase liquid chromatography (RPLC) using methanol-ammonium acetate buffer solution as a binary mobile phase. According to Snyder-Soczewinski equation, logarithm of hypothetical retention factor corresponding to neat aqueous fraction of hydroorganic mobile phase (logkw) is obtained by extrapolation from different compositions of the mobile phase. Then, we establish the relationship between octanol-water partition coefficient (P) and kw of these amphoteric compounds and discuss the dependence of retention behavior on mobile phase pH. The experimental results reveal that the linear correlation between logarithm of apparent octanol-water coefficient (logD) and logkw is better than that between logP and logkw, as well as that between logD and logk, the logarithm of retention factor at a specific organic modifier fraction for common amphoteric compounds. The linear relationships of logD–logkw approximate those of logP–logkw, and they are superior to those of logD–logk for amino acids and small peptides. In addition, we provide an insight into the fact that isoelectric point (pI), dissociation constants (p Ka1 and p Ka2) of amphoteric compounds affect their RPLC retention behavior significantly.
Dementia is characterized as a decline in cognitive function, including memory, language and problem-solving abilities. In this paper, we conducted a Genome-Wide Association Study (GWAS) using data from the electronic Medical Records and Genomics (eMERGE) network. This study has two aims, (1) to investigate the genetic mechanism of dementia and (2) to discuss multiple p-value thresholds used to address multiple testing issues. Using the genome-wide significant threshold (), we identified four SNPs. Controlling the False Positive Rate (FDR) level below leads to one extra SNP. Five SNPs that we found are also supported by QQ-plot comparing observed p-values with expected p-values. All these five SNPs belong to the TOMM40 gene on chromosome 19. Other published studies independently validate the relationship between TOMM40 and dementia. Some published studies use a relaxed threshold () to discover SNPs when the statistical power is insufficient. This relaxed threshold is more powerful but cannot properly control false positives in multiple testing. We identified 13 SNPs using this threshold, which led to the discovery of extra genes (such as ATP10A-DT and PTPRM). Other published studies reported these genes as related to brain development or neuro-development, indicating these genes are potential novel genes for dementia. Those novel potential loci and genes may help identify targets for developing new therapies. However, we suggest using them with caution since they are discovered without proper false positive control.