{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:49:07Z","timestamp":1785912547981,"version":"3.56.0"},"posted":{"date-parts":[[2026,8,5]]},"group-title":"In Review","reference-count":0,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,7]]},"abstract":"<title>Abstract<\/title>\n                <p>Integrative modeling of metagenomic and clinical data can advance the study of host phenotypes, but remains challenged by cross-view heterogeneity, uncertain generalizability, and poor interpretability. We developed SAMECAT (Structure-Aware Metagenomics multi-viEw Contrastive AlignmenT), a structure-aware deep learning framework that integrates species-level shotgun metagenomic profiles with mixed-type clinical covariates through view-specific encoders, clustering-informed contrastive alignment, and adaptive representation fusion. Using two independent Louisiana Osteoporosis Study datasets generated through distinct sequencing and bioinformatics pipelines (development n = 1,990; external evaluation n = 481), we evaluated SAMECAT for bone mineral density prediction at four skeletal sites. SAMECAT consistently outperformed single-view models, naive concatenation, alternative deep learning integration approaches, and established machine learning baselines, with performance gains largely preserved in cross-pipeline external evaluation. To improve biological interpretability, we developed a stability-oriented interpretation workflow that aggregates individually low-magnitude and diffusely distributed feature attributions into structured modules, revealing reproducible site-dependent patterns, coherent functional themes, and representative hub taxa. SAMECAT thus provides a robust and interpretable framework for multi-view metagenomic modeling of microbiome-associated host phenotypes.<\/p>","DOI":"10.21203\/rs.3.rs-9956795\/v1","type":"posted-content","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:11:38Z","timestamp":1785910298000},"source":"Crossref","is-referenced-by-count":0,"title":["Robust and Interpretable Metagenomic Modeling Through Structure-Aware Multi-View Learning and Attribution-Guided Biological Insight"],"prefix":"10.21203","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0387-8818","authenticated-orcid":false,"given":"Hong-Wen","family":"Deng","sequence":"first","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9875-916X","authenticated-orcid":false,"given":"Lindong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martha","family":"Gonzalez-Ramirez","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5163-9774","authenticated-orcid":false,"given":"Kuan-Jui","family":"Su","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5829-2371","authenticated-orcid":false,"given":"Anqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Luo","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8624-8207","authenticated-orcid":false,"given":"Qing","family":"Tian","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Southern Mississippi"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Southern Mississippi"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0335-6064","authenticated-orcid":false,"given":"Hui","family":"Shen","sequence":"additional","affiliation":[{"name":"Tulane University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-9956795\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-9956795\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:12:09Z","timestamp":1785910329000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-9956795\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":0,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-9956795\/v1","relation":{},"subject":[],"published":{"date-parts":[[2026,8,5]]},"subtype":"preprint"}}