ABSTRACT28 The high failure rate of therapeutics showing promise in mouse disease models to translate to 29 patients is a pressing challenge in biomedical science. However, mouse models are a useful 30 tool for evaluating mechanisms of disease and prioritizing novel therapeutic agents for clinical 31 trials. Though retrospective studies have examined the fidelity of mouse models of inflammatory 32 disease to their respective human in vivo conditions, approaches for prospective translation of 33 insights from mouse models to patients remain relatively unexplored. Here, we develop a semi-34 supervised learning approach for prospective inference of disease-associated human in vivo 35 differentially expressed genes and pathways from mouse model experiments. We examined 36 36 transcriptomic case studies where comparable phenotypes were available for mouse and 37 human inflammatory diseases and assessed multiple computational approaches for inferring 38 human in vivo biology from mouse model datasets. We found that a semi-supervised artificial 39 neural network identified significantly more true human in vivo associations than interpreting (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint . http://dx.doi.org/10.1101/346122 doi: bioRxiv preprint first posted online Jun. 13, 2018; 97The utility of mouse models for studying inflammatory pathologies in particular was recently 98 assessed by a pair of studies examining the correspondence between gene expression in 99 murine models of inflammatory pathologies and human contexts (1, 2). The human and mouse 100 microarray cohorts assembled by the two studies had the rare property that mouse molecular 101 and phenotype data were well matched to human in vivo molecular and phenotype data. This 102property enabled systematic examination of the similarities and discrepancies between mice 103 and humans. These studies analyzed the same cohorts of mouse and human studies and came 104to conflicting conclusions about the relevance of mouse models for inflammatory disease . CC-BY 4.0 International license It is made available under a (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint . http://dx.doi.org/10.1101/346122 doi: bioRxiv preprint first posted online Jun. 13, 2018; 105 research, with Seok et al. concluding that mouse models poorly mimic human pathologies, 106whereas Takao et al. concluded that mouse models usefully mimic human pathologies (1, 2). 107The key methodological difference between the two studies was that while Seok et al. examined 117The aim of our study here is to address the challenge of prospective inference of human . CC-BY 4.0 International license It is made available under a (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. 142Developing a framework fo...