Multimodal Model for Efficacy Prediction Cetuximab in Colorectal Cancer Liver Metastasis Patient
Ontology highlight
ABSTRACT:
DISEASE(S): Neoplasm Metastasis,Colorectal Neoplasms,Liver Neoplasms,Colorectal Cancer Liver Metastases
PROVIDER: 61197 | ecrin-mdr-crc |
REPOSITORIES: ECRIN MDR
Similar Datasets
Project description:Establishment and validation of the deep learning signature of bevacizumab efficacy in initially unresectable CRLM patients
| 2720827 | ecrin-mdr-crc
Project description:establishment and validation of the prediction model of avastin plus chemotherapy as first line treatment in simultaneous ras mutant unresectable CRLM patients
| 2349750 | ecrin-mdr-crc
Project description:The liver is the most common site for colorectal cancer (CRC) metastasis and new tissue culture models are needed to study hepatic metastasis from CRC as none of the current models mimic the biological, biochemical and structural characteristics of the metastatic microenvironment. Decellularization provides a novel approach for the study of cancer extracellular matrix (ECM) as decellularized scaffolds retained their tissue-specific features and biological properties. In the present study we created a 3D model of CRC and matched CRC liver metastasis (CRLM) using patient-derived decellularized ECM scaffolds seeded with HT-29 CRC cell line. Here we show increased HT-29 cell proliferation and migration capability when cultured in cancer-derived scaffolds compared to same-patient healthy colon and liver tissues. CRLM scaffolds also induced activation of epithelial-mesenchymal transition (EMT) with cancer cells showing loss of E-cadherin expression and increased Vimentin expression. EMT was confirmed by gene expression profiling, with the most represented biological processes in CRLM-seeded scaffolds involving demethylation, deacethylation, cellular response to stress metabolic processes, response to oxygen level and to starvation. The complex 3D culture environment reduced the HT-29 cell response to anti-CRC drug 5-FU when used at standard IC50 determined in 2D cultures. In conclusion, our 3D culture system with patient-derived tissue-specific decellularized ECM better recapitulates the metastatic microenvironment compared to conventional 2D culture conditions and represents a relevant approach for the study of liver CRC metastasis formation and progression. Transcriptomic analysis was performed comparing the global gene expression profiles of HT29 cells grown on CRLM and HL scaffolds. The transcriptomic profile of each 3D subtype was compared with HT29 cells grown in plastic. Hierarchical clustering analysis revealed that the gene expression signature of recellularized CRLM scaffolds was more comparable to recellularized HL scaffolds, than to HT29 cells grown in 2D. Gene set enrichment analysis (GSEA) of the differently expressed genes (DEG) up-regulated in recellularized CRLM scaffolds compared to HT29 grown in 2D revealed that genes involved in demethylation, deacethylation and metabolic process belong to the most enriched biological pathways in repopulated-CRLM scaffolds. Comparing the DEG between recellularized CRLM scaffolds vs HT29 grown in 2D with a series of a-priori defined gene-set, called Hallmark, we obtained concordant results with the “HYPOXIA” and “EPITHELIAL_MESENCHYMAL_TRANSITION” pathway, enriched in recellularized CRLM, supporting the idea that 3D culture models are the ability to re-create a complex environment in terms of oxygen tension, nutrients, and metabolic gradient, similarly to the in vivo environment.
2019-11-30 | GSE125404 | GEO
Project description:Background: Primary knee osteoarthritis (KOA) is a heterogeneous disease with clinical and molecular contributors. Biofluids contain microRNAs and metabolites that can be measured by omic technologies. Deep learning captures complex non-linear associations within multimodal data but, to date, has not been used for multi-omic-based endotyping of KOA patients. We developed a novel multimodal deep learning framework for clustering of multi-omic data from three subject-matched biofluids to identify distinct KOA endotypes and classify one-year post-total knee arthroplasty (TKA) pain/function responses. Materials and Methods: In 414 KOA patients, subject-matched plasma, synovial fluid and urine were analyzed by microRNA sequencing or metabolomics. Integrating 4 high-dimensional datasets comprising metabolites from plasma (n=151 features), along with microRNAs from plasma (n=421), synovial fluid (n=930), or urine (n=1225), a multimodal deep learning variational autoencoder architecture with K-means clustering was employed. Features influencing cluster assignment were identified and pathway analyses conducted. An integrative machine learning framework combining 4 molecular domains and a clinical domain was then used to classify WOMAC pain/function responses post-TKA within each cluster. Findings: Multimodal deep learning-based clustering of subjects across 4 domains yielded 3 distinct patient clusters. Feature signatures comprising microRNAs and metabolites across biofluids included 30, 16, and 24 features associated with Clusters 1-3, respectively. Pathway analyses revealed distinct pathways associated with each cluster. Integration of 4 multi-omic domains along with clinical data improved response classification performance, with Cluster 3 achieving AUC=0·879 for subject pain response classification and Cluster 2 reaching AUC=0·808 for subject function response, surpassing individual domain classifications by 12% and 15% respectively. Interpretation: We have developed a deep learning-based multimodal clustering model capable of integrating complex multi-fluid, multi-omic data to assist in KOA patient endotyping and test outcome response to TKA surgery.
2024-12-29 | GSE222979 | GEO
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress
Project description:The Open Problems Perurbation Prediction (OP3) dataset is to-date the largest single-cell small molecule perturbation dataset in primary tissue with multiple donor replicates. Compounds are dosed in cultured peripheral blood mononuclear cells (PBMCs), enabling the robust computation of perturbation effects on gene expression across four distinct cell type populations: T-cells, B-cells, NK cells, and Myeloid cells. This dataset is the basis for the OP3 benchmark, which evaluates machine learning models on the task of extrapolation perturbation effects into unseen cell types.
2024-10-22 | GSE279945 | GEO
Project description:Prediction of protein localization plays an important role in understanding protein function and mechanism. A deep learning-based localization prediction tool (“MULocDeep”) assessing each amino acid’s contribution to the localization process provides insights into the mechanism of protein sorting and localization motifs. A dataset with 45 sub-organellar localization annotations under 10 major sub-cellular compartments was produced and the tool was tested on an independent dataset of mitochondrial proteins that were extracted from Arabidopsis thaliana cell cultures, Solanum tuberosum tubers, and Vicia faba roots, and analyzed by shotgun mass spectrometry.
2022-02-15 | PXD019987 | Pride
Project description:Background:
To assist clinicians with diagnosis and optimal treatment decision-making, we attempted to develop and validate an artificial intelligence prediction model for lung metastasis (LM) in colorectal cancer (CRC) patients.
Method:
The clinicopathological characteristics of 46037 CRC patients from the Surveillance, Epidemiology, and End Results (SEER) database and 2779 CRC patients from a multi-center external validation set were collected retrospectively. After feature selection by univariate and multivariate analyses, six machine learning (ML) models, including logistic regression, K-nearest neighbor, support vector machine, decision tree, random forest, and balanced random forest (BRF), were developed and validated for the LM prediction. The optimization model with best performance was compared to the clinical predictor. In addition, stratified LM patients by risk score were utilized for survival analysis.
| 46649 | ecrin-mdr-crc
Project description:Deep learning has achieved a notable success in mass spectrometry-based proteomics and is now emerging in glycoproteomics. While various deep learning models can predict fragment mass spectra of peptides with good accuracy, they cannot cope with the non-linear glycan structure in an intact glycopeptide. Herein, we propose a deep learning-based approach for the prediction of fragment spectra of intact glycopeptides. Our model adopts tree-structured long-short term memory networks to process the glycan moiety and a graph neural network architecture to incorporate potential fragmentation pathways of a specific glycan structure. This feature is beneficial to model explainability and differentiation ability of glycan structural isomers. We further demonstrated that predicted spectral libraries can be used for analyzing DIA data of glycopeptides as a supplement for library completeness. We expect that this work will provide a valuable deep learning resource for glycoproteomics.
2023-12-17 | PXD045248 |
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status.
2013-01-01 | GSE29210 | GEO