Accurate transfer learning of clinical outcomes from one cellular context to another, between cell types, developmental stages, omics modalities or species, is considered tremendously useful. When transferring a prediction task from a source domain to a target domain, what counts is the high quality of the predictions in the target domain, requiring states or processes common to both the source and the target that can be learned by the predictor reflected by shared denominators. These may form a compendium of knowledge that is learned in the source to enable predictions in the target, usually with few, if any, labeled target training samples to learn from. Transductive transfer learning refers to the learning of the predictor in the source domain, transferring its outcome label calculations to the target domain, considering the same task. Inductive transfer learning considers cases where the target predictor is performing a different yet related task as compared with the source predictor. Often, there is also a need to first map the variables in the input/feature spaces and/or the variables in the output/outcome spaces. We here discuss and juxtapose various recently published transfer learning approaches, specifically designed (or at least adaptable) to predict clinical (human in vivo) outcomes based on preclinical (mostly animal-based) molecular data, towards finding the right tool for a given task, and paving the way for a comprehensive and systematic comparison of the suitability and accuracy of transfer learning of clinical outcomes.
Partial or transient cellular reprogramming is defined by the limited induction of pluripotency factors without full dedifferentiation of cells to a pluripotent state. Comparing in vitro and in vivo mouse studies, and in vitro studies in humans, supported by visualizations of data interconnections, we show consistent patterns in how such reprogramming modulates key biological processes. Generally, partial reprogramming drives dynamic chromatin remodelling, involving histone modifications that regulate accessibility and facilitate pluripotency gene activation while silencing somatic identity. These changes are accompanied by modifications in stress response programs, such as inflammation, autophagy, and cellular senescence, as well as improved mitochondrial activity and dysregulation of extracellular matrix pathways. We also underscore the challenges in evaluating complex processes like aging and cellular senescence, given the variability in biomarkers used across studies. Overall, we highlight biological processes consistently influenced by reprogramming while noting that some effects are context-dependent, varying according to cell type, species, sex, recovery time, and the reprogramming method employed. These insights inform future research and potential therapeutic applications in aging and regenerative medicine.
Background: Both bromodomain and extra-terminal domain (BET) proteins and spleen tyrosine kinase (SYK) represent promising targets in diffuse large B-cell (DLBCL) and Burkitt’s lymphoma (BL). We evaluated the anti-lymphoma activity of the isoform-specific bivalent BET inhibitor AZD5153 (AZD) and the pan-BET inhibitor I-BET151 (I-BET) as single agents and in combination with SYK inhibitor Entospletinib (Ento) in vitro. Methods: The effect of the single agents on cell proliferation and metabolic activity was evaluated in two DLBCL and two BL cell lines. Proliferation, metabolic activity, apoptosis, cell cycle and morphology were further investigated after a combined treatment of AZD or I-BET and Ento. RNAseq profiling of combined AZD+Ento treatment was performed in SU-DHL-4 cells. Results: Both BET inhibitors reduced cell proliferation and metabolic activity in a dose- and time-dependent manner. Combined BET and SYK inhibition enhanced the anti-proliferative effect and induced a G0/G1 cell cycle arrest. SU-DHL-4 demonstrated a pronounced modulation of gene expression by AZD, which was markedly increased by additional SYK inhibition. Functional enrichment analyses identified combination-specific GO terms related to DNA replication and cell division. Genes such as ADGRA2, MYB, TNFRSF11A, S100A10, PLEKHH3, DHRS2 and FOXP1-AS1 were identified as possible key regulators. Conclusion: Simultaneous inhibition of BET and SYK enhanced the anti-proliferative effects, and induced a combination-specific gene expression signature.
Objectives To validate and test the generalisability of the SASKit-ML pipeline, a prepublished feature selection and machine learning pipeline for the prediction of health deterioration after a stroke or pancreatic adenocarcinoma event, by using it to identify biomarkers of health deterioration in chronic disease. Design This is a validation study using a predefined protocol applied to multiple publicly available datasets, including longitudinal data from cohorts with type 2 diabetes (T2D), inflammatory bowel disease (IBD), rheumatoid arthritis (RA) and various cancers. The datasets were chosen to mimic as closely as possible the SASKit cohort, a prospective, longitudinal cohort study. Data sources Public data were used from the T2D (77 patients with potential pre-diabetes and 18 controls) and IBD (49 patients with IBD and 12 controls) branches of the Human Microbiome Project (HMP), RA Map (RA-MAP, 92 patients with RA, 22 controls) and The Cancer Genome Atlas (TCGA, 16 cancers). Methods Data integration steps were performed in accordance with the prepublished study protocol, generating features to predict disease outcomes using 10-fold cross-validated random survival forests. Outcome measures Health deterioration was assessed using disease-specific clinical markers and endpoints across different cohorts. In the HMP-T2D cohort, the worsening of glycated haemoglobin (HbA1c) levels (5.7% or more HbA1c in the blood), fasting plasma glucose (at least 100 mg/dL) and oral glucose tolerance test (at least 140) results were considered. For the HMP-IBD cohort, a worsening by at least 3 points of a disease-specific severity measure, the "Simple Clinical Colitis Activity Index" or "Harvey-Bradshaw Index" indicated an event. For the RA-MAP cohort, the outcome was defined as the worsening of the "Disease Activity Score 28" or "Simple Disease Activity Index" by at least five points, or the worsening of the "Health Assessment Questionnaire" score or an increase in the number of swollen/tender joints were evaluated. Finally, the outcome for all TCGA datasets was the progression-free interval. Results Models for the prediction of health deterioration in T2D, IBD, RA and 16 cancers were produced. The T2D (C-index of 0.633 and Integrated Brier Score (IBS) of 0.107) and the RA (C-index of 0.654 and IBS of 0.150) models were modestly predictive. The IBD model was uninformative. TCGA models tended towards modest predictive power. Conclusions The SASKit-ML pipeline produces informative and useful features with the power to predict health deterioration in a variety of diseases and cancers; however, this performance is disease-dependent.
This study investigates the potential risks and mechanisms of action of rejuvenation therapies, focusing on metformin and partial reprogramming, using an integrative approach that combines gene expression, protein interaction networks, and toxicological annotations.
A major challenge in aging research is identifying interventions that can improve lifespan and health and minimize toxicity. Clinical studies cannot consider decades-long follow-up periods, and therefore, in-silico evaluations using omics-based surrogate biomarkers are emerging as key tools. However, many current approaches train predictive models on observational data, rather than on intervention data, which can lead to biased conclusions. Yet, the first classifiers for lifespan extension by compounds are now available, learned on intervention data. Here, we review evaluation methodologies and we prioritize training on intervention data whenever available, highlight the importance of safety and toxicity assessments, discuss the role of standardized benchmarks, and present a range of feature processing and predictive modeling approaches. We consider linear and non-linear methods, and automated machine learning workflows. We conclude by emphasizing the need for explainable and reproducible strategies, the integration of safety metrics, and the careful validation of predictors based on interventional benchmarks.