M3dical/HMOTP: HMOTP v1.0.0
Fuente:
Zenodo
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Recurso digital |
| Publicado: |
Zenodo
2026
|
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866901085683187712 |
|---|---|
| author | yihuizhou |
| author_facet | yihuizhou |
| contents | <p>Fecal microbiota transplantation (FMT) is effective for recurrent <span>Clostridioides difficile</span> infection, but many analyses stay descriptive and do not predict individual trajectories or early response. <span>Hierarchical Multi-Omics Trajectory Prediction (HMOTP)</span> is a purpose-built machine learning framework for <span>small-sample, longitudinal, multi-omics</span> settings with high dimensionality, integration across omics, temporal structure, and interpretability. HMOTP uses <span>hierarchical feature construction</span> (domain knowledge), <span>multi-level attention</span>, and <span>patient-specific trajectory prediction</span> (transfer-style parameter sharing). It was evaluated on 15 recurrent CDI patients with lipidomics (397 features) and metagenomic pathways (10,634 features) at four time points over six months, using <span>leave-one-patient-out cross-validation</span>. HMOTP achieved strong accuracy versus single-omics and multi-omics baselines (e.g. Random Forest, Logistic Regression) and supports <span>exploratory</span> cross-omics and biomarker-oriented interpretation. This archive accompanies the HMOTP manuscript; the repository includes code, installation notes, and materials to reproduce reported results.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19239746 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | M3dical/HMOTP: HMOTP v1.0.0 yihuizhou <p>Fecal microbiota transplantation (FMT) is effective for recurrent <span>Clostridioides difficile</span> infection, but many analyses stay descriptive and do not predict individual trajectories or early response. <span>Hierarchical Multi-Omics Trajectory Prediction (HMOTP)</span> is a purpose-built machine learning framework for <span>small-sample, longitudinal, multi-omics</span> settings with high dimensionality, integration across omics, temporal structure, and interpretability. HMOTP uses <span>hierarchical feature construction</span> (domain knowledge), <span>multi-level attention</span>, and <span>patient-specific trajectory prediction</span> (transfer-style parameter sharing). It was evaluated on 15 recurrent CDI patients with lipidomics (397 features) and metagenomic pathways (10,634 features) at four time points over six months, using <span>leave-one-patient-out cross-validation</span>. HMOTP achieved strong accuracy versus single-omics and multi-omics baselines (e.g. Random Forest, Logistic Regression) and supports <span>exploratory</span> cross-omics and biomarker-oriented interpretation. This archive accompanies the HMOTP manuscript; the repository includes code, installation notes, and materials to reproduce reported results.</p> |
| title | M3dical/HMOTP: HMOTP v1.0.0 |
| url | https://doi.org/10.5281/zenodo.19239746 |