Skip to main content
Figure 2 | BMC Bioinformatics

Figure 2

From: Semi-supervised learning for the identification of syn-expressed genes from fused microarray and in situ image data

Figure 2

Obtaining constraints from images. We depict the time course expression (top) and registered in situ images (middle) of genes twi, G12177, Ef2 and RhoGAP71E, which indicate their temporal and spatial expression patterns. From left to right, the embryo images are categorized into the time periods 0–3 h, 3–6 h, 6–9 h, 9–12 h, 12–15 h and 15–18 h. The microarray expression displays a similar expression pattern with maximal expression after 3 hours for all genes but weakly diverging at later time points. The in situ images indicates that twi and CG12177 have syn-expression at time periods 3–6, 6–9 and 9–12; while Ef2 and RhoGAP71E at periods 0–3, 3–6, 6–9, 9–12 and 15–18. At the bottom, we display how positive constraints are derived from in situ hybridization patterns. A heat-map displays the correlation coefficients between all pairs of in situ images of the corresponding time period (red values indicate positive correlations). After thresholding the correlation matrices, a constraint matrix for each time period is obtained. For example, constraint matrices from periods 3–6 and 6–9 indicates syn-expression of pairs (twi, CG1217) and (Ef2, RhoGAP71E), while the constraint matrix from period 9–12 also indicate that (CG1217, RhoGAP71E) are syn-expressed. The matrices are combined into one constraining genes that display syn-expression in at least three periods, as indicated in the matrix at the bottom.

Back to article page