Artificial Neural Networks Indicate Cardiac TIMP1, JNK, and Collagen I & III Predict Sex Hormone Status in Female Aortic‐Banded Yucatan Mini‐Swine in a Chamber‐Specific Manner
Bibliographic record
Abstract
The prevalence of heart failure (HF) with preserved ejection fraction (HFpEF) is increased in older, postmenopausal women and often associated with an increase in cardiac fibrosis. Therefore, the goal of this study was to assess the role of female sex hormones on chamber‐dependent differences i.e., left ventricle (LV) vs. right ventricle (RV), in extracellular matrix (ECM) remodeling and regulation in a mini‐swine model of pressure overload‐induced heart failure. We hypothesized molecular markers involved in the bioregulation of the cardiac ECM can predict experimental intervention combinations in a chamber‐specific manner. An ovariectomy (OVX) model of surgical menopause was used in aortic‐banded (AB) female Yucatan mini‐swine (sex hormones X pressure‐overload) divided into 4 groups: 1) Control, intact (CON‐INT; n=6); 2) CON‐OVX (n=5); 3) AB‐INT (n=7;) and 4) AB‐OVX (n=6). Seventy‐seven input variables from both the LV and RV included: 1) mRNA levels of estrogen (isoforms 1, 2) and progesterone receptors; ERK/JNK signaling and regulation including MAPK isoforms 1, 3, 8, and 9, MAPKK isoforms 1, 2, 4, and 7, and dual specificity phosphatases (DUSP) isoforms 1, 4, 6, 9, and 10; matrix metalloproteinase (MMP) isoforms 1, 2, 3, 9, 13, and 14; tissue inhibitors of MMP (TIMP) isoforms 1, 2, and 4; the ECM components collagen (isoforms 1 and 3) and fibronectin; and 2) protein levels of ERK/JNK (total and phosphorylated), MMP14, TIMP2, and fibronectin. Missing data were mean imputed and the min‐max normalization method was used for all measures. One‐way ANOVA models were used to identify mRNA or protein targets associated with group status. Resulting molecular predictors were then used in an artificial neural network (ANN) model, with logistic activation function, composed of 1 hidden layer and 5 nodes. 5‐fold cross‐validation conditioned on group i.e., at least one observation from each of the four groups, and confusion matrices were used to test the developed ANN model. One observation from each group (n=4 total) was retained for later model testing with the remaining observations used for ANN development i.e., 84% training and 16% testing. One‐way ANOVA models indicated TIMP1 mRNA and total JNK protein levels in the LV, and Collagen I and III mRNA levels in the RV, were associated with group status (p<0.05). These 4 molecular markers were then used to develop the ANN model (Figure 1). Cross‐validation and confusion matrices indicate all 4 targets formed a linear relationship predictive of group with an accuracy of 70.8%. In conclusion, molecular mechanisms involved in the bioregulation of the ECM have analytical power to extrapolate sex hormone and aortic‐banding status in a pre‐clinical model of pressure overload‐induced HF. Ongoing work will compare multiple activation functions to improve prediction accuracy and delineate non‐linear relationships amongst these molecular ECM targets.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".