Locus-specific DNA methylation prediction in cord blood and placenta

Figures & data

Figure 1. R² of the 169 samples. The x-axis represents the sample index from 1 to 169, and the y-axis represents the CpG-wise R² of the 169 samples. The red line represents the CpG-wise R² of measured methylation beta values in the cord blood and measured methylation beta values in the placenta, and the purple line represents the CpG-wise R² of measured methylation beta values in the placenta and predicted methylation beta values in the placenta by single-CpG-based SVM and leave-one-out cross-validation.

Figure 2. Methylation pattern across tissues and the between-tissue differences across individuals. (2a). Red circles indicate measured placenta beta values vs. measured cord blood beta values (x = measured placenta beta values, y = measured cord blood beta values), and purple circles indicate measured placenta beta values vs. SVM predicted placenta beta values (x = measured placenta beta values, y = predicted placenta beta values by single-CpG-based SVM and leave-one-out cross-validation). R²(raw) = CpG-wise R² between measured methylation beta values in the placenta and measured methylation beta values in the cord blood. R²(svm) = CpG-wise R² between measured methylation beta values in the placenta and predicted methylation beta values in the placenta by single-CpG-based SVM and leave-one-out cross-validation.

Figure 2b. Red circles indicate measured placenta beta values–measured cord blood beta values of sample #1 vs. measured placenta beta values–measured cord blood beta values of sample #2(x = measured placenta beta values–measured cord blood beta values of sample #1, y = measured placenta beta values–measured cord blood beta values of sample #2). Purple circles indicate measured placenta beta values–SVM predicted placenta beta values in sample #1 vs. measured placenta beta values–SVM predicted placenta beta values in sample #2(x = measured placenta beta values–SVM predicted placenta beta values of sample #1, y = measured placenta beta values–SVM predicted placenta beta values of sample #2). Note: ‘–’ represents minus sign.

Table 1. CpG-wise R² in different tissue pairs.

	All CpGs		Removed CpGs with min methylation beta values >0.9 or max beta values <0.1			Removed CpGs with min methylation beta values >0.8 or max beta values <0.2
Tissue pair	Mean R^2	Range	Mean R^2	Range	CpGs removed	Mean R^2	Range	CpGs removed
measured Placenta- measured Cord Blood	0.66	0.61, 0.76	0.63	0.58, 0.74	15822	0.51	0.43, 0.65	99076
measured Placenta- SVM predicted Placenta	0.97	0.92, 0.98	0.97	0.91, 0.98	15822	0.95	0.87, 0.97	99076

For the ‘All CpGs’ column, we used all CpG sites in each sample to calculate the CpG-wise R². For the ‘Removed CpGs with min methylation beta values>0.9 or max beta values<0.1’ column, we excluded the extreme CpGs that fell within this range and used the remaining data to calculate the CpG-wise R², and this column is similar to the ‘Removed CpGs with min methylation beta values >0.8 or max beta values<0.2’ column. For the ‘measured Placenta-measured Cord Blood’ row, the R² is the squared correlation coefficient of measured methylation in both placenta and cord blood. For the ‘measured Placenta-SVM predicted Placenta’ row, the R² is the squared correlation coefficient of measured methylation in the placenta and predicted methylation in the placenta by single-CpG-based SVM and leave-one-out cross-validation.

Figure 3. Relationship between R² and mean absolute error. The y-axis is the sample-wise mean absolute error (MAE) of measured placenta methylation beta values and predicted placenta methylation beta values by single-CpG-based SVM and leave-one-out cross-validation, and the x-axis is the sample-wise R² of measured placenta methylation beta values and predicted placenta methylation beta values by single-CpG-based SVM and leave-one-out cross-validation (CpGs with SD > 0.1).

Table 2. Mean R² using the twofold and threefold cross-validation methods.

	2-fold cross-validation			3-fold cross-validation
Tissue pair	All CpGs	Removed CpGs with min methylation beta values >0.9 or max beta values <0.1	Removed CpGs with min methylation beta values >0.8 or max beta values <0.2	All CpGs	Removed CpGs with min methylation beta values >0.9 or max beta values <0.1	Removed CpGs with min methylation beta values >0.8 or max beta values <0.2
measured Placenta-measured Cord Blood	0.6567879	0.6333165	0.5079859	0.6567879	0.6333165	0.5079859
measured Placenta- SVM predicted Placenta	0.9672072	0.9644117	0.9472045	0.9676109	0.9648506	0.9478592

For the ‘All CpGs’ column, we used all CpG sites in each sample to calculate the CpG-wise R², and then obtained the mean R². For the ‘Removed CpGs with min methylation beta values>0.9 or max beta values<0.1’ column, we excluded the extreme CpGs that fell within this range and used the remaining data to calculate the mean CpG-wise R², and this column is similar to the ‘Removed CpGs with min methylation beta values>0.8 or max beta values<0.2’ column. For the ‘measured Placenta-measured Cord Blood’ row, the R² is the squared correlation coefficient of measured methylation in both placenta and cord blood. For the ‘measured Placenta-SVM predicted Placenta’ row, the R² is the squared correlation coefficient of measured methylation in the placenta and predicted methylation in the placenta by single-CpG-based SVM.

Figure 4. Effect of sample size on prediction accuracy. The x-axis is the sample size of the training dataset, and the y-axis is the mean of CpG-wise R² for measured placenta methylation beta values and predicted placenta methylation beta values by single-CpG-based SVM for 100 testing samples. For the blue line, the extreme CpG sites with a minimum methylation beta value >0.8 or a maximum beta value <0.2 were removed.

Figure 5. Venn diagram of well-predicted CpGs across the three datasets. The numbers in the circle represent the well-predicted CpGs (sample-wise R² > 0.8) in the three datasets, and the Venn diagram shows the intersection of the well-predicted CpGs across the following three datasets: cord blood–placenta, blood–artery and blood–atrium.

Table 3. CpG island-related distributions.

Dataset	Island	N_Shelf	N_Shore	S_Shelf	S_Shore	Other
All CpGs	0.3199	0.0501	0.1318	0.0445	0.1031	0.3506
Well-predicted CpGs	0.3192	0.0642	0.1196	0.0583	0.0672	0.3715

The categories were designated by Illumina annotation. Five genomic annotation categories including island, northern shelf (N_shelf), southern shelf (S_shelf), northern shore (N_shore) and southern shore (S_shore) are listed. Each proportion is the number of the CpGs belonging to the same category divided by the sum of CpGs in the dataset. The ‘All CpGs’ row is the proportion for the all CpGs dataset and the ‘Well-predicted CpGs’ row is the proportion for the well-predicted CpGs dataset.