Fig. 1
From: Novel clinical, molecular and bioinformatics insights into the genetic background of autism
Flowchart of the classification process suing a linear regression classifier and PLINK as the feature (variants) selection tools. Step 1—Describes the dataset with 2 classes of patients with Severe and Non-severe autism. Step 2—Denotes the selection of a set of variants to be used during the leave-one-out classification (LOOCV) process. Step 3—The LOOCV is initiated by extracting one sample from the dataset. Step 4—PLINK is used to perform odds ratio analysis on the remaining samples (this avoids overfitting). X number of variants top significant variants are used for the next. Step 5—A linear regression model is trained using the data and features for the specific iteration. Step 6—the LOOCV process (Steps 3–5) is repeated for every sample (N = 33) and statistics recorder. Step 7—Steps 2–5 are repeated for every value of X