SUMMARY: Nuclei counting provides a low-cost, metabolic-independent alternative to ATP- or tetrazolium-based cell viability assays. However, the fragmentation of image processing, normalization, and statistical modeling across multiple software platforms hinders high-throughput adoption. We present CellPyAbility, a Python-based suite that automates image processing, dose-response fitting, and synergy analysis. It converts unedited whole-well images into publication-ready graphics in under 1 minute per 96-well plate on standard desktop hardware. AVAILABILITY AND IMPLEMENTATION: CellPyAbility is open-source (MIT License) and available as a Python package via PyPI and Bioconda, or as a code-free application for macOS and Windows. Source code and documentation are available at https://github.com/bindralab/cellpyability and on Zenodo at https://doi.org/10.5281/zenodo.20693745.

In this paper, we propose an improvement of the Hungarian method to optimally solve the task assignment problem for a multi-robot team. Our proposed method involves all robots collaboratively working together to disseminate cost information and then individually computing an assignment that optimizes a particular global goal. Through theoretical analysis, we show that our approach is able to produce a common optimal assignment, sending significantly fewer messages and resulting in faster convergence than other approaches based on the Hungarian method. Our experimental results back up this claim, demonstrating that, even in the worst case, our approach sends a fraction of the messages required by other assignment methods and as a result scales better as team size increases.

SUMMARY: We investigate convolutional neural networks (CNNs) for filtering small genomic variants in short-read DNA sequence data. Errors created during sequencing and library preparation make variant calling a difficult task. Encoding the reference genome and aligned reads covering sites of genetic variation as numeric tensors allows us to leverage CNNs for variant filtration. Convolutions over these tensors learn to detect motifs useful for classifying variants. Variant filtering models are trained to classify variants as artifacts or real variation. Visualizing the learned weights of the CNN confirmed it detects familiar DNA motifs known to correlate with real variation, like homopolymers and short tandem repeats (STR). After confirmation of the biological plausibility of the learned features we compared our model to current state-of-the-art filtration methods like Gaussian Mixture Models, Random Forests and CNNs designed for image classification, like DeepVariant. We demonstrate improvements in both sensitivity and precision. The tensor encoding was carefully tailored for processing genomic data, respecting the qualitative differences in structure between DNA and natural images. Ablation tests quantitatively measured the benefits of our tensor encoding strategy. Bayesian hyper-parameter optimization confirmed our notion that architectures designed with DNA data in mind outperform off-the-shelf image classification models. Our cross-generalization analysis identified idiosyncrasies in truth resources pointing to the need for new methods to construct genomic truth data. Our results show that models trained on heterogenous data types and diverse truth resources generalize well to new datasets, negating the need to train separate models for each data type. AVAILABILITY AND IMPLEMENTATION: This work is available in the Genome Analysis Toolkit (GATK) with the tool name CNNScoreVariants (https://github.com/broadinstitute/gatk). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We present a method for discovering the structure of trees in 3D point clouds by linking wavelets with shape grammars. Given a range scan of a tree we find a grammar that can reproduce that tree, and others like it, with sub-voxel accuracy. The grammar inferred is stochastic, allowing us to generate many permutations of related trees. The method of multi-resolution analysis, employed by the discrete wavelet transform, gives great insight into tree structure. Trees are self-similar and exhibit similar branching patterns at different resolutions. The wavelets make these patterns explicit by decomposing the tree into different levels of detail. The multi-resolution structure of the wavelet transform also allows us to infer an L-System grammar. The productions in the grammar are derived from the progressive levels of refinement in the wavelet transform. Each production maps a vector in the low resolution image to a set of vectors in the higher resolution image. Our method utilizes the Fast Wavelet Transform opening the door to real-time inference of procedural models. The grammar inferred is concise and generative, allowing for compression and graphics applications of our algorithm. We demonstrate novel applications of the grammar for shape completion, scan enhancement and geometry propagation.