Geono-Cluster: Interactive Visual Cluster Analysis for Biologists

The cluster analysis of traditional Chinese medicine authenticity identification technique assisted by chemometrics

This study explore the authenticity identification technique of traditional Chinese medicine (TCM) using chemometrics in conjunction with cluster analysis. A clustering Gaussian mixture model was constructed and applied for the data clustering analysis of four types of TCM. Chemical measurements combined with discrete wavelet transform (DWT), Fourier transform infrared spectroscopy (FTIR), and Fourier self-deconvolution (FSD) were utilized for the detailed differentiation of Bupleurum scorzonerifolium, Bupleurum yinchowense, Bupleurum marginatum, and Bupleurum smithii Wolff var. parvifolium. Differences in the attenuated total reflection-FTIR (ATR-FTIR) spectra among the four TCMs were observed. Utilizing clustering algorithms, the one-dimensional DWT of the infrared spectra of samples was employed for the authentication of Chinese herbal medicines. The model demonstrates optimal performance throughout 2000 rounds of network training. The accuracy (88.6 %), sensitivity (86.5 %), and specificity (82.7 %) of the model constructed in this study significantly surpassed those of the CNN model: accuracy (67.7 %), sensitivity (70.4 %), and specificity (68.5 %) (P < 0.05). By setting the cluster size K = 5 and the number of Gaussian mixture model components to 5, the model effectively fits the actual number of categories within the dataset. Infrared spectroscopy analysis revealed distinct carbon-oxygen stretching vibration absorption peaks between 1025 and 1200 cm-1 for Bupleurum scorzonerifolium, Bupleurum yinchowense, Bupleurum marginatum, and Bupleurum smithii Wolff var. parvifolium, indicating strong absorption peaks of carbohydrates. A comprehensive structural information analysis revealed a similarity of above 0.982 among the four types of TCM. Combined with chemometrics and intelligent algorithm-based cluster analysis, successful and accurate authentication of TCM authenticity was achieved, providing an effective methodology for quality control in TCM.

Incorporation of Human Knowledge into Data Embeddings to Improve Pattern Significance and Interpretability

Embedding is a common technique for analyzing multi-dimensional data. However, the embedding projection cannot always form significant and interpretable visual structures that foreshadow underlying data patterns. We propose an approach that incorporates human knowledge into data embeddings to improve pattern significance and interpretability. The core idea is (1) externalizing tacit human knowledge as explicit sample labels and (2) adding a classification loss in the embedding network to encode samples' classes. The approach pulls samples of the same class with similar data features closer in the projection, leading to more compact (significant) and class-consistent (interpretable) visual structures. We give an embedding network with a customized classification loss to implement the idea and integrate the network into a visualization system to form a workflow that supports flexible class creation and pattern exploration. Patterns found on open datasets in case studies, subjects' performance in a user study, and quantitative experiment results illustrate the general usability and effectiveness of the approach.

Interactive Visual Cluster Analysis by Contrastive Dimensionality Reduction

We propose a contrastive dimensionality reduction approach (CDR) for interactive visual cluster analysis. Although dimensionality reduction of high-dimensional data is widely used in visual cluster analysis in conjunction with scatterplots, there are several limitations on effective visual cluster analysis. First, it is non-trivial for an embedding to present clear visual cluster separation when keeping neighborhood structures. Second, as cluster analysis is a subjective task, user steering is required. However, it is also non-trivial to enable interactions in dimensionality reduction. To tackle these problems, we introduce contrastive learning into dimensionality reduction for high-quality embedding. We then redefine the gradient of the loss function to the negative pairs to enhance the visual cluster separation of embedding results. Based on the contrastive learning scheme, we employ link-based interactions to steer embeddings. After that, we implement a prototype visual interface that integrates the proposed algorithms and a set of visualizations. Quantitative experiments demonstrate that CDR outperforms existing techniques in terms of preserving correct neighborhood structures and improving visual cluster separation. The ablation experiment demonstrates the effectiveness of gradient redefinition. The user study verifies that CDR outperforms t-SNE and UMAP in the task of cluster identification. We also showcase two use cases on real-world datasets to present the effectiveness of link-based interactions.