Abstract We present a system for generating suggestions from highly‐constrained, continuous design spaces. We formulate suggestion as sampling from a probability distribution; constraints are represented as factors that concentrate probability mass around sub‐manifolds of the design space. These sampling problems are intractable using typical random walk MCMC techniques, so we adopt Hamiltonian Monte Carlo (HMC), a gradient‐based MCMC method. We implement HMC in a high‐performance probabilistic programming language, and we evaluate its ability to efficiently generate suggestions for two different, highly‐constrained example applications: vector art coloring and designing stable stacking structures.

Color choice plays an important role in works of graphic art and design. However, it can be difficult to choose a compelling set of colors, or color theme, from scratch. In this work, we present a method for extracting color themes from images using a regression model trained on themes created by people. We collect 1600 themes from Mechanical Turk as well as from artists. We find that themes extracted by Turk participants were similar to ones extracted by artists. In addition, people tended to select diverse colors and focus on colors in salient image regions. We show that our model can match human-extracted themes more closely compared to previous work. Themes extracted by our model were also rated higher as representing the image than previous approaches in a Mechanical Turk study.

Abstract We introduce an algorithm for automatic selection of semantically‐resonant colors to represent data (e.g., using blue for data about “oceans”, or pink for “love”). Given a set of categorical values and a target color palette, our algorithm matches each data value with a unique color. Values are mapped to colors by collecting representative images, analyzing image color distributions to determine value‐color affinity scores, and choosing an optimal assignment. Our affinity score balances the probability of a color with how well it discriminates among data values. A controlled study shows that expert‐chosen semantically‐resonant colors improve speed on chart reading tasks compared to a standard palette, and that our algorithm selects colors that lead to similar gains. A second study verifies that our algorithm effectively selects colors across a variety of data categories.

We present a probabilistic factor graph model for automatically coloring 2D patterns. The model is trained on example patterns to statistically capture their stylistic properties. It incorporates terms for enforcing both color compatibility and spatial arrangements of colors that are consistent with the training examples. Using Markov Chain Monte Carlo, the model can be sampled to generate a diverse set of new colorings for a target pattern. This general probabilistic framework allows users to guide the generated suggestions via conditional inference or additional soft constraints. We demonstrate results on a variety of coloring tasks, and we evaluate the model through a perceptual study in which participants judged sampled colorings to be significantly preferable to other automatic baselines.

Unmodified or as a poly[lactide-co-glycolide] nanoparticle, tetraiodothyroacetic acid (tetrac) acts at the integrin αvβ3 receptor on human cancer cells to inhibit tumor cell proliferation and xenograft growth. To study in vitro the pharmacodynamics of tetrac formulations in the absence of and in conjunction with other chemotherapeutic agents, we developed a perfusion bellows cell culture system. Cells were grown on polymer flakes and exposed to various concentrations of tetrac, nano-tetrac, resveratrol, cetuximab, or a combination for up to 18 days. Cells were harvested and counted every one or two days. Both NONMEM VI and the exact Monte Carlo parametric expectation maximization algorithm in S-ADAPT were utilized for mathematical modeling. Unmodified tetrac inhibited the proliferation of cancer cells and did so with differing potency in different cell lines. The developed mechanism-based model included two effects of tetrac on different parts of the cell cycle which could be distinguished. For human breast cancer cells, modeling suggested a higher sensitivity (lower IC50) to the effect on success rate of replication than the effect on rate of growth, whereas the capacity (Imax) was larger for the effect on growth rate. Nanoparticulate tetrac (nano-tetrac), which does not enter into cells, had a higher potency and a larger anti-proliferative effect than unmodified tetrac. Fluorescence-activated cell sorting analysis of harvested cells revealed tetrac and nano-tetrac induced concentration-dependent apoptosis that was correlated with expression of pro-apoptotic proteins, such as p53, p21, PIG3 and BAD for nano-tetrac, while unmodified tetrac showed a different profile. Approximately additive anti-proliferative effects were found for the combinations of tetrac and resveratrol, tetrac and cetuximab (Erbitux), and nano-tetrac and cetuximab. Our in vitro perfusion cancer cell system together with mathematical modeling successfully described the anti-proliferative effects over time of tetrac and nano-tetrac and may be useful for dose-finding and studying the pharmacodynamics of other chemotherapeutic agents or their combinations.

The non-data components of a visualization, such as axes and legends, can often be just as important as the data itself. They provide contextual information essential to interpreting the data. In this paper, we describe an automated system for choosing positions and labels for axis tick marks. Our system extends Wilkinson’s optimization-based labeling approach to create a more robust, full-featured axis labeler. We define an expanded space of axis labelings by automatically generating additional nice numbers as needed and by permitting the extreme labels to occur inside the data range. These changes provide flexibility in problematic cases, without degrading quality elsewhere. We also propose an additional optimization criterion, legibility, which allows us to simultaneously optimize over label formatting, font size, and orientation. To solve this revised optimization problem, we describe the optimization function and an efficient search algorithm. Finally, we compare our method to previous work using both quantitative and qualitative metrics. This paper is a good example of how ideas from automated graphic design can be applied to information visualization.