Data science models, although successful in a number of commercial domains, have had limited applicability in scientific problems involving complex physical phenomena. Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of data science models in enabling scientific discovery. The overarching vision of TGDS is to introduce scientific consistency as an essential component for learning generalizable models. Further, by producing scientifically interpretable models, TGDS aims to advance our scientific understanding by discovering novel domain insights. Indeed, the paradigm of TGDS has started to gain prominence in a number of scientific disciplines such as turbulence modeling, material discovery, quantum chemistry, bio-medical science, bio-marker discovery, climate science, and hydrology. In this paper, we formally conceptualize the paradigm of TGDS and present a taxonomy of research themes in TGDS. We describe several approaches for integrating domain knowledge in different research themes using illustrative examples from different disciplines. We also highlight some of the promising avenues of novel research for realizing the full potential of theory-guided data science.

Genetic interactions provide a powerful perspective into gene function, but our knowledge of the specific mechanisms that give rise to these interactions is still relatively limited. The availability of a global genetic interaction map in Saccharomyces cerevisiae, covering~30% of all possible double mutant combinations, provides an unprecedented opportunity for an unbiased assessment of the native structure within genetic interaction networks and how it relates to gene function and modular organization. Toward this end, we developed a data mining approach to exhaustively discover all block structures within this network, which allowed for its complete modular decomposition. The resulting modular structures revealed the importance of the context of individual genetic interactions in their interpretation and revealed distinct trends among genetic interaction hubs as well as insights into the evolution of duplicate genes. Block membership also revealed a surprising degree of multifunctionality across the yeast genome and enabled a novel association of VIP1 and IPK1 with DNA replication and repair, which is supported by experimental evidence. Our modular decomposition also provided a basis for testing the between-pathway model of negative genetic interactions and within-pathway model of positive genetic interactions. While we find that most modular structures involving negative genetic interactions fit the betweenpathway model, we found that current models for positive genetic interactions fail to explain 80% of the modular structures detected. We also find differences between the modular structures of essential and nonessential genes.

Understanding the categorization of human diseases is critical for reliably identifying disease causal genes. Recently, genome-wide studies of abnormal chromosomal locations related to diseases have mapped >2000 phenotype–gene relations, which provide valuable information for classifying diseases and identifying candidate genes as drug targets. In this article, a regularized non-negative matrix tri-factorization (R-NMTF) algorithm is introduced to co-cluster phenotypes and genes, and simultaneously detect associations between the detected phenotype clusters and gene clusters. The R-NMTF algorithm factorizes the phenotype–gene association matrix under the prior knowledge from phenotype similarity network and protein–protein interaction network, supervised by the label information from known disease classes and biological pathways. In the experiments on disease phenotype–gene associations in OMIM and KEGG disease pathways, R-NMTF significantly improved the classification of disease phenotypes and disease pathway genes compared with support vector machines and Label Propagation in cross-validation on the annotated phenotypes and genes. The newly predicted phenotypes in each disease class are highly consistent with human phenotype ontology annotations. The roles of the new member genes in the disease pathways are examined and validated in the protein–protein interaction subnetworks. Extensive literature review also confirmed many new members of the disease classes and pathways as well as the predicted associations between disease phenotype classes and pathways.