Identifying spatially similar gene expression patterns in early stage fruit fly embryo images: binary feature versus invariant moment digital representations

Abstract

Background: Modern developmental biology relies heavily on the analysis of embryonic gene expression patterns. Investigators manually inspect hundreds or thousands of expression patterns to identify those that are spatially similar and to ultimately infer potential gene interactions. However, the rapid accumulation of gene expression pattern data over the last two decades, facilitated by high-throughput techniques, has produced a need for the development of efficient approaches for direct comparison of images, rather than their textual descriptions, to identify spatially similar expression patterns.

Results: The effectiveness of the Binary Feature Vector (BFV) and Invariant Moment Vector (IMV) based digital representations of the gene expression patterns in finding biologically meaningful patterns was compared for a small (226 images) and a large (1819 images) dataset. For each dataset, an ordered list of images, with respect to a query image, was generated to identify overlapping and similar gene expression patterns, in a manner comparable to what a developmental biologist might do. The results showed that the BFV representation consistently outperforms the IMV representation in finding biologically meaningful matches when spatial overlap of the gene expression pattern and the genes involved are considered. Furthermore, we explored the value of conducting image-content based searches in a dataset where individual expression components (or domains) of multi-domain expression patterns were also included separately. We found that this technique improves performance of both IMV and BFV based searches.

Conclusions: We conclude that the BFV representation consistently produces a more extensive and better list of biologically useful patterns than the IMV representation. The high quality of results obtained scales well as the search database becomes larger, which encourages efforts to build automated image query and retrieval systems for spatial gene expression patterns.

Figure 1

BESTi search results with smaller dataset. Results from the BESTi-search for the same query image [22] based on (A) BFV [S_S], (B) IMV [D_φ] and (C) BFV [S_C] representations in the original dataset (226 images); and based on (D) BFV [S_S] and (E) IMV [D_φ] representations in the domain database (in which distinct domains of the multi-domain expression patterns were added to the original dataset as additional data points). The search argument and the results retrieved are shown on the left and right of the arrow, respectively. The original data used to generate these expression patterns are shown above this row. BESTi-matches are arranged in descending order starting with the best hit for the given search image. Values of difference in centroids (ΔC_XY) and principal angles (Δθ) are also given. Each image is identified by the last name of the first author of the original research article and the figure number with the following abbreviations: Ashe [19]; Casares [20]; Gaul1 [28]; Grossniklaus [22]; Hartmann [24]; Hulskamp1 [27]; Hulskamp3 [26].

Figure 2

BESTi search results for S_S with larger dataset. Comparison of search results from the small (226 images) and large (1819 images) dataset using the S_S measure for the same query image (Figure 1A) [22]. Panels (A-K) are based on the genes whose expression patterns were retrieved as follows (A) slp1, (B) slp1 and otd, (C) otd, (D) slp2, (E) Kr, (F) hb, (G) hb and bcd, (H) Hb, bcd and nanos, (I) snail, (J) hts and (K) hairy. Images are referenced with the last name of the first author of the original article and its figure number: Grossniklaus [22]; Zhao [43]; Gao [44]; Wimmer [45]; Schulz1 [46]; Tsai [47]; Janody [48]; Stathopoulos [31]; Brent [32]; Zhang [33]. Common search results between the small and large dataset are indicated with dark blue image names.

Figure 3

BESTi search results for D_φ with larger dataset. Comparison of search results from the small (226 images) and large (1819 images) dataset using the D_φ measure for the same query image (Figure 1A) [22]. Panels (A-O) are based on the genes whose expression patterns were retrieved as follows (A) slp1, (B) bcd, (C) Kr, (D) hb(D1,D3) and Hb(D2), (E) tll, (F) gt, (G) hairy, (H) AS-C, (I) hb and Kr, (J) kni, (K) iab (type I transcript), (L) IAB5 enhancer, (M) vnd, (N) sog and (O) nanos, bcd and cnc. Images are referenced with the last name of the first author of the original article and its figure number: Grossniklaus [22]; Sauer[49]; Tsai[47]; Hulskamp1[27]; Gaul1[28]; Strunk[50]; Colas[51]; Wu[52]; Ghiglione[53]; Pankratz[54]; Melnick[55]; Janody[48]; Zhang[33]; Parkhurst[56]; Zhou[57]; Stathopoulos[31]. Common search results between the small and large datasets are indicated with dark blue image names.

Figure 4

BESTi search results for S_C with larger dataset. Comparison of search results from the small (226 images) and large (1819 images) dataset using the D_φ measure for the same query image (Figure 1A) [22]. Panels (A-Z) are based on the genes whose expression patterns were retrieved as follows (A) slp1, (B) otd, (C) hb, (D) AS-C, (E) nanos, bcd and Hb, (F) Kr, (G) sc, (H) snail, (I) en and hb, (J) bcd and hb, (K) kni and hb, (L) tll, (M) eve, (N) twist, (O) dpp, (P) en, (Q) arm, (R) hairy, (S) zen, (T) run, (U) Hsp83, (V) nmo, (W) Tc'hb, (X) iab, (Y) hts and (Z) sog. Images are referenced with the last name of the first author of the original article and its figure number: Grossniklaus [22]; Gao [44]; Hulskamp1 [27]; Hulskamp3 [26]; Zhao [43]; Gaul1 [28]; Tsai [47]; Niessing [58]; Sauer [49]; Parkhurst [56]; Janody [48]; Schulz2 [46]; Yagi [59] Cowden [60]; Stathopoulos [31]; Miskiewicz [61]; Schulz1 [62]; Goff [63]; Sackerson [64]; Rusch [65]; Steingrimsson [66]; Hamada [67]; Zhang [33]; Klingler [68]; Bashirullah [69]; Verheyen [70]; Wolff [71]; Casares [20]; Brent [32]. Common search results between the small and large dataset are indicated with dark blue image names.

Figure 5

BESTi search results with multiple domains of expression using smaller database. Results from BESTi-search for a query image with multiple domains of expression. (A) BFV [S_S], (B) IMV [D_φ] and (C) BFV [S_C] searches for the same expression pattern in the original database (226 images). (D) BFV [S_S] search using the complete multi-domain expression in the original database and (E) BFV [S_S] search using only the pattern on the left in the domain database. Search argument and the results retrieved are shown on the left and right of the arrow, respectively. Original data used to generate these expression patterns are shown above this row. BESTi-matches are arranged in descending order starting with the best hit for the given search statistic. Values of difference in centroids (ΔC_XY) and principal angles (Δθ) are also given for panels A, B and C. Each image is identified by the last name of the first author of the original research article and the figure number; with the abbreviations as follows: Ashe [19]; Arnosti [17]; Borggreve [18]; Casares [20]; Gaul1 [28]; Gaul2 [29]; Grossniklaus [22]; Hartmann [24]; Hulskamp1 [27]; Hulskamp2 [25]; Hulskamp3 [26].