Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB.

BACKGROUND: Endothelial healing after deployment of cardiovascular devices is particularly important in the context of clinical outcome. It is therefore of great interest to develop tools for a precise prediction of endothelial growth after injury in the process of implant deployment. For experimental investigation of re-endothelialization in vitro cell migration assays are routinely used. However, semi-automatic analyses of live cell images are often based on gray value distributions and are as such limited by image quality and user dependence. The rise of deep learning algorithms offers promising opportunities for application in medical image analysis. Here, we present an intelligent cell detection (iCD) approach for comprehensive assay analysis to obtain essential characteristics on cell and population scale. RESULTS: In an in vitro wound healing assay, we compared conventional analysis methods with our iCD approach. Therefore we determined cell density and cell velocity on cell scale and the movement of the cell layer as well as the gap closure between two cell monolayers on population scale. Our data demonstrate that cell density analysis based on deep learning algorithms is superior to an adaptive threshold method regarding robustness against image distortion. In addition, results on cell scale obtained with iCD are in agreement with manually velocity detection, while conventional methods, such as Cell Image Velocimetry (CIV), underestimate cell velocity by a factor of 0.5. Further, we found that iCD analysis of the monolayer movement gave results just as well as manual freehand detection, while conventional methods again shows more frayed leading edge detection compared to manual detection. Analysis of monolayer edge protrusion by ICD also produced results, which are close to manual estimation with an relative error of 11.7%. In comparison, the conventional Canny method gave a relative error of 76.4%. CONCLUSION: The results of our experiments indicate that deep learning algorithms such as our iCD have the ability to outperform conventional methods in the field of wound healing analysis. The combined analysis on cell and population scale using iCD is very well suited for timesaving and high quality wound healing analysis enabling the research community to gain detailed understanding of endothelial movement.

Unravelling Differences in Candidate Genes for Drought Tolerance in Potato (Solanum tuberosum L.) by Use of New Functional Microsatellite Markers.

Potato is regarded as drought sensitive and most vulnerable to climate changes. Its cultivation in drought prone regions or under conditions of more frequent drought periods, especially in subtropical areas, requires intensive research to improve drought tolerance in order to guarantee high yields under limited water supplies. A candidate gene approach was used to develop functional simple sequence repeat (SSR) markers for association studies in potato with the aim to enhance breeding for drought tolerance. SSR primer combinations, mostly surrounding interrupted complex and compound repeats, were derived from 103 candidate genes for drought tolerance. Validation of the SSRs was performed in an association panel representing 34 mainly starch potato cultivars. Seventy-five out of 154 SSR primer combinations (49%) resulted in polymorphic, highly reproducible banding patterns with polymorphic information content (PIC) values between 0.11 and 0.90. Five SSR markers identified allelic differences between the potato cultivars that showed significant associations with drought sensitivity. In all cases, the group of drought-sensitive cultivars showed predominantly an additional allele, indicating that selection against these alleles by marker-assisted breeding might confer drought tolerance. Further studies of these differences in the candidate genes will elucidate their role for an improved performance of potatoes under water-limited conditions.

Network Candidate Genes in Breeding for Drought Tolerant Crops.

Climate change leading to increased periods of low water availability as well as increasing demands for food in the coming years makes breeding for drought tolerant crops a high priority. Plants have developed diverse strategies and mechanisms to survive drought stress. However, most of these represent drought escape or avoidance strategies like early flowering or low stomatal conductance that are not applicable in breeding for crops with high yields under drought conditions. Even though a great deal of research is ongoing, especially in cereals, in this regard, not all mechanisms involved in drought tolerance are yet understood. The identification of candidate genes for drought tolerance that have a high potential to be used for breeding drought tolerant crops represents a challenge. Breeding for drought tolerant crops has to focus on acceptable yields under water-limited conditions and not on survival. However, as more and more knowledge about the complex networks and the cross talk during drought is available, more options are revealed. In addition, it has to be considered that conditioning a crop for drought tolerance might require the production of metabolites and might cost the plants energy and resources that cannot be used in terms of yield. Recent research indicates that yield penalty exists and efficient breeding for drought tolerant crops with acceptable yields under well-watered and drought conditions might require uncoupling yield penalty from drought tolerance.