diff --git a/dev/flat_full.Rmd b/dev/flat_full.Rmd
index 7ad9b3f575d9d654d741df69bc57c93f4ba20a13..7d6d48de470c2e7fab4f5b99cb818ceded0d772f 100644
--- a/dev/flat_full.Rmd
+++ b/dev/flat_full.Rmd
@@ -8798,6 +8798,7 @@ is_formula_mixedTypeI <- function(formula) {
if (length(all.vars(formula)) != 3) return(FALSE)
if (sum(all.names(formula) == "+") > 1) return(FALSE)
if (sum(all.names(formula) == "/") > 0) return(FALSE)
+ if (length(all_var_in_formula) == 4 && all_var_in_formula[2] != all_var_in_formula[3]) return(FALSE)8
return(TRUE)
}
@@ -9055,11 +9056,14 @@ test_that("Test is_formula_mixedTypeI", {
formula2 <- y ~ z + group1 + (1 | group1)
formula3 <- y ~ z + (1 | group1 + group2)
formula4 <- y ~ z + (1 | group1/z)
-
+ formula5 <- y ~ z + ( group | z ) ## z is fixed then expected on the left in parenthesis
+
expect_true(is_formula_mixedTypeI(formula1))
expect_false(is_formula_mixedTypeI(formula2))
expect_false(is_formula_mixedTypeI(formula3))
expect_false(is_formula_mixedTypeI(formula4))
+ expect_false(is_formula_mixedTypeI(formula5))
+
})
@@ -9388,7 +9392,7 @@ mock_data <- mock_rnaseq(list_var, N_GENES,
## Set dispersion of gene expression
-The dispersion parameter ($\alpha_i$), characterizes the relationship between the variance of the observed read counts and its mean value. In simple terms, it quantifies how much we expect observed counts to deviate from the mean value. You can specify the dispersion for individual genes using the dispersion parameter.
+The dispersion parameter ($dispersion_i$), characterizes the relationship between the variance of the observed read counts and its mean value. In simple terms, it quantifies how much we expect observed counts to deviate from the mean value. You can specify the dispersion for individual genes using the dispersion parameter.
```{r example-mock_rnaseq_disp, warning = FALSE, message = FALSE}
@@ -9436,7 +9440,7 @@ mock_data <- mock_rnaseq(list_var, N_GENES,
## Mock RNAseq object
```{r example-str_obj_mock, warning=FALSE, message=FALSE}
-str(mock_data)
+str(mock_data, max.level = 1)
```
@@ -9447,11 +9451,11 @@ str(mock_data)
</div>
-In this modeling framework, counts denoted as $K_{ij}$ for gene i and sample j are generated using a negative binomial distribution. The negative binomial distribution considers a fitted mean $\mu_{ij}$ and a gene-specific dispersion parameter $\alpha_i$.
+In this modeling framework, counts denoted as $K_{ij}$ for gene i and sample j are generated using a negative binomial distribution. The negative binomial distribution considers a fitted mean $\mu_{ij}$ and a gene-specific dispersion parameter $dispersion_i$.
The fitted mean $\mu_{ij}$ is determined by a parameter, $q_{ij}$, which is proportionally related to the sum of all effects specified using `init_variable()` or `add_interaction()`. If basal gene expressions are provided, the $\mu_{ij}$ values are scaled accordingly using the gene-specific basal expression value ($bexpr_i$).
-Furthermore, the coefficients $\beta_i$ represent the natural logarithm fold changes for gene i across each column of the model matrix X. The dispersion parameter $\alpha_i$ plays a crucial role in defining the relationship between the variance of observed counts and their mean value. In simpler terms, it quantifies how far we expect observed counts to deviate from the mean value.
+Furthermore, the coefficients $\beta_i$ represent the natural logarithm fold changes for gene i across each column of the model matrix X. The dispersion parameter $dispersion_i$ plays a crucial role in defining the relationship between the variance of observed counts and their mean value. In simpler terms, it quantifies how far we expect observed counts to deviate from the mean value for each genes.
# Fitting models
@@ -9485,7 +9489,8 @@ metaData <- mock_data$metadata
## -- convert counts matrix and samples metadatas in a data frame for fitting
data2fit = prepareData2fit(countMatrix = count_matrix,
metadata = metaData,
- normalization = F)
+ normalization = F,
+ response_name = "kij")
## -- median ratio normalization
@@ -9656,7 +9661,7 @@ The dispersion plot, generated by the `evaluation_report()` function, offers a v
The Receiver Operating Characteristic (ROC) curve is a valuable tool for assessing the performance of classification models, particularly in the context of identifying differentially expressed genes. It provides a graphical representation of the model's ability to distinguish between genes that are differentially expressed and those that are not, by varying the `coeff_threshold` and the `alt_hypothesis` parameters.
-```{r example-outputROC, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=9}
+```{r example-outputROC, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=7}
## -- ROC curve
resSimu$roc$params
```
@@ -9668,7 +9673,7 @@ resSimu$roc$params
The precision-recall curve (PR curve) illustrates the relationship between precision and recall at various classification thresholds. It is particularly valuable in the context of imbalanced data, where one class is significantly more prevalent than the other. Unlike the ROC curve, which can be influenced by class distribution, the PR curve focuses on the model's ability to correctly identify examples of the minority class while maintaining high precision.
-```{r example-outputPR, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=9}
+```{r example-outputPR, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=7}
## -- precision-recall curve
resSimu$precision_recall$params
```
@@ -9681,7 +9686,7 @@ The area under the ROC curve (AUC) provides a single metric that summarizes the
In addition to evaluating model performance through the AUC for both ROC and PR curves, we provide access to key classification metrics, including Accuracy, Precision, Recall (or Sensitivity), and Specificity. These metrics offer a comprehensive view of the model's classification capabilities. These metrics are computed for each parameter (excluding the intercept when skip_eval_intercept = TRUE), providing detailed insights into individual parameter contributions. Furthermore, an aggregated assessment is performed, considering all parameters (except the intercept by default), offering a perspective on the model's overall classification effectiveness.
-```{r example-outputPerf, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=9}
+```{r example-outputPerf, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=7}
## -- precision-recall curve
resSimu$performances
```
@@ -9719,7 +9724,7 @@ resSimu$identity$params
resSimu$identity$dispersion
```
-```{r example-outputResSimu_metric, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=9}
+```{r example-outputResSimu_metric, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=7}
## -- precision-recall curve
resSimu$precision_recall$params
## -- ROC curve
@@ -9757,7 +9762,7 @@ resSimu$identity$params
resSimu$identity$dispersion
```
-```{r example-subsetGenes_metrics, warning=FALSE, message=FALSE, fig.align='center', fig.height=4, fig.width=9}
+```{r example-subsetGenes_metrics, warning=FALSE, message=FALSE, fig.align='center', fig.height=4, fig.width=7}
## -- precision-recall curve
resSimu$precision_recall$params
## -- ROC curve
@@ -9813,7 +9818,8 @@ mock_data <- mock_rnaseq(input_var_list,
## -- prepare data & fit a model with mixed effect
data2fit = prepareData2fit(countMatrix = mock_data$counts,
metadata = mock_data$metadata,
- normalization = F)
+ normalization = F,
+ response_name = "kij")
l_tmb <- fitModelParallel(formula = kij ~ varB + (varB | varA),
data = data2fit,
group_by = "geneID",
@@ -9835,7 +9841,7 @@ resSimu$identity$params
resSimu$identity$dispersion
```
-```{r example-outputResSimuMixed_metric, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=9}
+```{r example-outputResSimuMixed_metric, warning = FALSE, message = FALSE, fig.align='center', fig.height=4, fig.width=7}
## -- precision-recall curve
resSimu$precision_recall$params
## -- ROC curve
@@ -9844,7 +9850,7 @@ resSimu$roc$params
resSimu$performances
```
-## Strure of evaluation report object
+## Structure of evaluation report object
```{r example-str_eval_report, warning=FALSE, message=FALSE}
diff --git a/vignettes/htrfit.Rmd b/vignettes/htrfit.Rmd
index d7d1d681b8e85cbf5d2fa51bd6647ae2da68a088..ca71e1573f939f49d6992e6fd659a27ddba6170d 100644
--- a/vignettes/htrfit.Rmd
+++ b/vignettes/htrfit.Rmd
@@ -165,7 +165,7 @@ mock_data <- mock_rnaseq(list_var, N_GENES,
## Set dispersion of gene expression
-The dispersion parameter ($\alpha_i$), characterizes the relationship between the variance of the observed read counts and its mean value. In simple terms, it quantifies how much we expect observed counts to deviate from the mean value. You can specify the dispersion for individual genes using the dispersion parameter.
+The dispersion parameter ($dispersion_i$), characterizes the relationship between the variance of the observed read counts and its mean value. In simple terms, it quantifies how much we expect observed counts to deviate from the mean value. You can specify the dispersion for individual genes using the dispersion parameter.
@@ -212,7 +212,7 @@ mock_data <- mock_rnaseq(list_var, N_GENES,
## Mock RNAseq object
```{r example-str_obj_mock, warning = FALSE, message = FALSE}
-str(mock_data)
+str(mock_data, max.level = 1)
```
# Theory behind HTRfit
@@ -222,11 +222,11 @@ str(mock_data)
</div>
-In this modeling framework, counts denoted as $K_{ij}$ for gene i and sample j are generated using a negative binomial distribution. The negative binomial distribution considers a fitted mean $\mu_{ij}$ and a gene-specific dispersion parameter $\alpha_i$.
+In this modeling framework, counts denoted as $K_{ij}$ for gene i and sample j are generated using a negative binomial distribution. The negative binomial distribution considers a fitted mean $\mu_{ij}$ and a gene-specific dispersion parameter $dispersion_i$.
The fitted mean $\mu_{ij}$ is determined by a parameter, $q_{ij}$, which is proportionally related to the sum of all effects specified using `init_variable()` or `add_interaction()`. If basal gene expressions are provided, the $\mu_{ij}$ values are scaled accordingly using the gene-specific basal expression value ($bexpr_i$).
-Furthermore, the coefficients $\beta_i$ represent the natural logarithm fold changes for gene i across each column of the model matrix X. The dispersion parameter $\alpha_i$ plays a crucial role in defining the relationship between the variance of observed counts and their mean value. In simpler terms, it quantifies how far we expect observed counts to deviate from the mean value.
+Furthermore, the coefficients $\beta_i$ represent the natural logarithm fold changes for gene i across each column of the model matrix X. The dispersion parameter $dispersion_i$ plays a crucial role in defining the relationship between the variance of observed counts and their mean value. In simpler terms, it quantifies how far we expect observed counts to deviate from the mean value.
@@ -623,7 +623,7 @@ resSimu$roc$params
resSimu$performances
```
-## Strure of evaluation report object
+## Structure of evaluation report object
```{r example-str_eval_report, warning = FALSE, message = FALSE}
str(resSimu, max.level = 1)