OSCR

MCVAE-based multi-omic anomaly detection in Fragile X Syndrome.

Code ↔ Paper

14 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

10 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.

The 14 matches
  1. [1] § Results › Signaling pathways linked to translatomic anomalies ↔ utils/enrichment.Rmd, lines 6 to 78 · score 0.97 · Receptor Tyrosine Kinases, VPS4B, growth factor mediated, PRKAR2A, Signal Transduction, brain function · block oscr:b:GSR8GV3JDCRMT-D · Report a mismatch
  2. [2] § Materials and methods › Data collection and pre-processing ↔ pre-processing/DESeq.Rmd, lines 160 to 213 · score 0.86 · DESeq2, Rlog transformation, external validation, pre processing, integer, genotype · block oscr:b:WXFPNHNG14830-W · Report a mismatch
  3. [3] § Results › Translatomic and transcriptomic anomalies align with regulatory hubs potentially underlying indirect FXS effects ↔ utils/enrichment.Rmd, lines 6 to 78 · score 0.80 · chromatin binding, RNA binding, transcription regulators, TDRD3, FIZ1, SMG5 · block oscr:b:GSR8GV3JDCRMT-D · Report a mismatch
  4. [4] § Materials and methods › Benchmarking ↔ main.py, lines 211 to 287 · score 0.67 · OmiEmbed, DeepIMV, MCVAE training, pipeline, Enrichment, Benchmarking · block oscr:b:TAC22B4V3AYWH-Y · Report a mismatch
  5. [5] § Materials and methods › Data Integration Analysis for Biomarker discovery using Latent cOmponents (DIABLO) › Leave-one-out cross-validation (LOOCV) to compare benchmarked methods ↔ utils/DIABLO.py, lines 310 to 368 · score 0.65 · WeightedPredict.class, F1 score, recall, precision, accuracy, DIABLO · block oscr:b:THRM39XGTBFT0-B · Report a mismatch
  6. [6] § Materials and methods › Data collection and pre-processing ↔ pre-processing/DESeq.Rmd, lines 160 to 213 · score 0.64 · DESeq2, Rlog transformation, pre processing, covariances, batch, validation · block oscr:b:WXFPNHNG14830-W · Report a mismatch
  7. [7] § Results › Benchmarking ↔ main.py, lines 211 to 287 · score 0.57 · OmiEmbed, DeepIMV, benchmarked, CCA, PLS, linear · block oscr:b:TAC22B4V3AYWH-Y · Report a mismatch
  8. [8] § Results › MCVAE identifies a multi-omic anomaly signature separating WT and Fmr1-KO samples ↔ utils/PCA.py, lines 275 to 336 · score 0.56 · neural stem cells, adult, hippocampus, cortex, GSE112502, Fmr1 · block oscr:b:GDPH5EZPCJTMF-M · Report a mismatch
  9. [9] § Materials and methods › Anomaly detection ↔ models/VAE/error_analysis_vae.py, lines 20 to 93 · score 0.56 · Brunner Munzel, Reconstruction error, model · block oscr:b:PF0TJT3NW51J2-G · Report a mismatch
  10. [10] § Materials and methods › MCVAE model training ↔ models/MCVAE/MCVAE.py, lines 52 to 129 · score 0.55 · Kullback Leibler, dimensional, latent, layers, MCVAE, model · block oscr:b:KTDBDCKTJRTK6-W · Report a mismatch
  11. [11] § Materials and methods › Anomaly detection ↔ models/Linear/CCA.py, lines 216 to 272 · score 0.55 · Brunner Munzel, statsmodels · block oscr:b:8AXT6G4J0CN08-Q · Report a mismatch
  12. [12] § Results › Involvement of translatomic anomalies in brain physiology, FXS, and other neurodevelopmental disorders ↔ utils/PCA.py, lines 275 to 336 · score 0.52 · neural stem cells, Fmr1 KO, embryonic, cortex, brain · block oscr:b:GDPH5EZPCJTMF-M · Report a mismatch
  13. [13] § Materials and methods › Annotation analysis of anomalies ↔ utils/enrichment.Rmd, lines 185 to 260 · score 0.52 · chromatin binding, Tmem47, DNA, STAG2, RNA, Stox2 · block oscr:b:Y5CZ6HQ3NG1NV-X · Report a mismatch
  14. [14] § Materials and methods › Enrichment score for consensus FMRP mRNA targets ↔ utils/CLIP_enrichment.py, lines 119 to 201 · score 0.50 · enrichment score, overlapping, CLIP, genes · block oscr:b:BC45XPBEZBC15-2 · Report a mismatch

Paper

Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

R Markdown · 265 lines · 8.5 KB · no license · 3 matches

  1. ---
  2. title: "R Notebook"
  3. output: html_notebook
  4. ---
  5. This is an [R Markdown](http://rmarkdown.rstudio.com) Notebook. When you execute code within the notebook, the results appear beneath the code.
  6. Try executing this chunk by clicking the *Run* button within the chunk or by placing your cursor inside it and pressing *Ctrl+Shift+Enter*.
  7. ```{r}
  8. library(dplyr)
  9. library(tidyr)
  10. library(ggplot2)
  11. library(readr)
  12. library(scales)
  13. library(stringr)
  14. allowed_terms_path <- "../data/clusters_annotations.csv"
  15. bp_data_path <- "../data/annotations.csv"
  16. allowed_terms_df <- read_csv(allowed_terms_path) %>%
  17. mutate(Term = str_squish(Term),
  18. CLUSTER_NAME = str_squish(CLUSTER_NAME))
  19. bp_data <- read_delim(bp_data_path, delim = ",", quote = "\"") %>%
  20. mutate(Term = str_squish(Term),
  21. Genes = str_squish(Genes)) %>%
  22. separate_rows(Genes, sep = ",\\s*") %>%
  23. mutate(Genes = str_remove_all(Genes, '"|\\s+'),
  24. Genes = str_squish(Genes))
  25. cluster_order <- c(
  26. "mRNA biogenesis", "Pscychiatric disorder", "FXS",
  27. "Intelectual disability", "Cognition", "Neurodegeneration",
  28. "Neuropathy/Ataxia", "Epilepsy", "Synapse",
  29. "Neurotransmitter Signaling", "Neurotransmitter signaling by GPCR",
  30. "GPCR & G-Protein Signaling", "Small GTPase / Rho GTPase Signaling",
  31. "Second Messenger & Kinase Pathways", "General & Broad Signal Transduction",
  32. "Receptor Tyrosine Kinase (RTK) Signaling", "Hormone&Nuclear Receptor",
  33. "Neurotrophic and Growth Factor mediated neurodevelopment and brain function",
  34. "Development and function of the CNS", "Neurodeveloppement/Neurogenesis",
  35. "Neurodevelopment, Axon guidance, Axon regeneration", "Cytoskeleton",
  36. "Mechanotransduction & Specialized Cellular Signaling",
  37. "Immune response/Inflammation/Neuroinflammation", "Neuro-inflammation"
  38. )
  39. gene_order <- rev(c(
  40. 'PKP4', 'STOX2', 'NEDD4', 'PUM1', 'STAG2', 'FMR1', 'ZNF207','CLIC4', 'LPGAT1',
  41. 'SMG5', 'ARC', 'FIZ1', 'LONP1', 'TMEM47', 'VPS4B', 'TDRD3','ASCL1','SNX6',
  42. 'NSMCE2','SHB','PRKAR2A','TMOD3','KLC2'
  43. ))
  44. bp_filtered <- bp_data %>%
  45. filter(Term %in% allowed_terms_df$Term) %>%
  46. left_join(allowed_terms_df %>% select(Term, CLUSTER_NAME), by = "Term") %>%
  47. mutate(
  48. Category = case_when(
  49. Category == 1 ~ "RNA binding/translation regulator",
  50. Category == 2 ~ "DNA/chromatin binding",
  51. Category == 3 ~ "Transcription regulator",
  52. Category == 4 ~ "Pathways",
  53. Category == 5 ~ "FXS phenotype-associated",
  54. TRUE ~ as.character(Category)
  55. ),
  56. CLUSTER_NAME = factor(CLUSTER_NAME, levels = cluster_order),
  57. Genes = factor(Genes, levels = gene_order)
  58. ) %>%
  59. # Remove any rows that failed to match a cluster in your list
  60. filter(!is.na(CLUSTER_NAME)) %>%
  61. distinct()
  62. create_dotplot <- function(df, keep_categories, title, row_expand = 1) {
  63. # Filter data for specific categories (Pathways & FXS)
  64. df_plot <- df %>% filter(Category %in% keep_categories)
  65. # CRITICAL: Force Term order to follow Cluster order
  66. term_order_levels <- df_plot %>%
  67. arrange(CLUSTER_NAME, Term) %>%
  68. pull(Term) %>%
  69. unique()
  70. df_plot <- df_plot %>%
  71. mutate(Term = factor(Term, levels = term_order_levels))
  72. # Generate colors for the bottom bars
  73. cluster_colors <- scales::hue_pal()(length(cluster_order))
  74. names(cluster_colors) <- cluster_order
  75. # Calculate positions for the rectangles
  76. gap <- 0.5
  77. cluster_blocks <- df_plot %>%
  78. group_by(CLUSTER_NAME) %>%
  79. summarise(
  80. xmin = min(as.numeric(Term)) - 0.5 + gap/2,
  81. xmax = max(as.numeric(Term)) + 0.5 - gap/2,
  82. ymin = -0.5,
  83. ymax = -0.2,
  84. .groups = "drop"
  85. )
  86. # Build the plot
  87. p <- ggplot(df_plot, aes(x = Term, y = Genes)) +
  88. # Grid lines
  89. geom_hline(yintercept = seq_along(levels(df_plot$Genes)),
  90. color = "lightgrey", size = 0.3) +
  91. # THE DOTS: All grey, black outline, no mapping to Category
  92. geom_point(fill = "grey70", shape = 21, color = "black", size = 3) +
  93. scale_y_discrete(drop = FALSE, expand = expansion(add = c(0.5 * row_expand, 0.5 * row_expand))) +
  94. coord_cartesian(clip = "off") +
  95. theme_minimal(base_size = 10) +
  96. theme(
  97. axis.text.x = element_blank(),
  98. axis.text.y = element_text(size = 7, face = "bold"),
  99. axis.title = element_blank(),
  100. panel.grid.major = element_blank(),
  101. legend.position = "none",
  102. plot.margin = margin(t = 10, r = 10, b = 150, l = 10) # Space for labels
  103. ) +
  104. labs(title = title)
  105. # Add the color bars for clusters
  106. for(cluster in unique(cluster_blocks$CLUSTER_NAME)){
  107. cluster_data <- cluster_blocks %>% filter(CLUSTER_NAME == cluster)
  108. p <- p + geom_rect(
  109. data = cluster_data,
  110. aes(xmin = xmin, xmax = xmax, ymin = ymin, ymax = ymax),
  111. fill = cluster_colors[as.character(cluster)],
  112. inherit.aes = FALSE
  113. )
  114. }
  115. # Add vertical separators between clusters
  116. if(nrow(cluster_blocks) > 1){
  117. for(i in 2:nrow(cluster_blocks)){
  118. line_x <- cluster_blocks$xmin[i] - gap/2
  119. p <- p + geom_segment(
  120. x = line_x, xend = line_x,
  121. y = -0.2,
  122. yend = length(levels(df_plot$Genes)),
  123. color = "lightgrey", size = 0.4, inherit.aes = FALSE
  124. )
  125. }
  126. }
  127. # Add rotated labels
  128. cluster_labels <- cluster_blocks %>%
  129. mutate(x = (xmin + xmax)/2,
  130. y = -1.2, # Vertical offset
  131. label = stringr::str_wrap(CLUSTER_NAME, width = 40))
  132. p <- p + geom_text(data = cluster_labels,
  133. aes(x = x, y = y, label = label),
  134. angle = 90, hjust = 1, vjust = 0.5, size = 3,
  135. fontface = "bold", inherit.aes = FALSE)
  136. return(p)
  137. }
  138. dotplot_final <- create_dotplot(
  139. bp_filtered,
  140. keep_categories = c("Pathways", "FXS phenotype-associated"),
  141. title = "Final Analysis",
  142. row_expand = 50
  143. )
  144. print(dotplot_final)
  145. #ggsave("plots/dotplot_pathways.png", dotplot_pathways, width = 12, height = 10, dpi = 1200)
  146. #ggsave("plots/dotplot_pathways.pdf", dotplot_final, width = 12, height = 8)
  147. ```
  148. ```{r}
  149. library(dplyr)
  150. library(tidyr)
  151. library(ggplot2)
  152. library(readr)
  153. library(stringr)
  154. setwd("..")
  155. getwd()
  156. bp_data_path <- "data/annotations.csv"
  157. # --- Load MF data, split Genes, remove quotes ---
  158. bp_data <- read_delim(bp_data_path, delim = ",", quote = "\"") %>%
  159. mutate(
  160. Term = trimws(Term),
  161. Genes = trimws(Genes)
  162. ) %>%
  163. separate_rows(Genes, sep = ",\\s*") %>%
  164. mutate(Genes = str_remove_all(Genes,'"|\\s+'),
  165. Genes = trimws(Genes)) %>%
  166. filter(GROUP == "MF") # Keep only MF
  167. bp_data <- bp_data %>%
  168. mutate(Term_short = str_replace(Term, "~.*$", "") %>% str_trim())
  169. #write.csv(bp_data , "bp_expanded_MF.csv", row.names = FALSE)
  170. # --- Define group color mapping ---
  171. group_colors <- c(
  172. "1" = "#F0E2B6", # RNA binding/translation regulator
  173. "2" = "#D3EEEA", # DNA/chromatin binding
  174. "3" = "#CFD5E8" # Transcription regulator
  175. )
  176. # --- Order terms by Category, then Term_short ---
  177. term_order <- bp_data %>%
  178. group_by(Category, Term_short) %>%
  179. summarise(n = n(), .groups = "drop") %>%
  180. arrange(Category, Term_short) %>%
  181. pull(Term_short) %>% unique()
  182. bp_data <- bp_data %>%
  183. mutate(Term_short = factor(Term_short, levels = term_order),
  184. Category = factor(Category, levels = c(1,2,3)))
  185. selected_genes <- c('PKP4', 'STOX2', 'NEDD4', 'PUM1', 'STAG2', 'ZNF207',
  186. 'FMR1', 'CLIC4', 'SMG5', 'LPGAT1', 'ARC', 'LONP1',
  187. 'FIZ1', 'TMEM47', 'VPS4B')
  188. all_genes <- unique(bp_data$Genes)
  189. gene_levels <- c(setdiff(all_genes, selected_genes), rev(selected_genes))
  190. bp_data <- bp_data %>%
  191. mutate(Genes = factor(Genes, levels = gene_levels))
  192. p <- ggplot(bp_data, aes(x = Term_short, y = Genes)) +
  193. geom_point(aes(color = Category), size = 3) +
  194. scale_color_manual(values = group_colors, name = "MF Group") +
  195. geom_tile(aes(y = -0.5, fill = Category), height = 0.3) +
  196. scale_fill_manual(values = group_colors, guide = "none") +
  197. theme_minimal(base_size = 10) +
  198. theme(
  199. axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5),
  200. axis.title = element_blank(),
  201. legend.position = "right",
  202. panel.grid.major = element_blank()
  203. ) +
  204. labs(title = "MF Terms - Colored by Group (1,2,3)")
  205. print(p)
  206. ```
  207. Add a new chunk by clicking the *Insert Chunk* button on the toolbar or by pressing *Ctrl+Alt+I*.
  208. When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the *Preview* button or press *Ctrl+Shift+K* to preview the HTML file).
  209. The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike *Knit*, *Preview* does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

enrichment.Rmd at commit 31d52c6, no license · at the source

Overview

Authors: Wassila Khatir1,2, Marco Lorenzi1, Irene Balelli1, Carole Gwizdek2
ORCID iDs: Wassila Khatir
  1. INRIA Center at Université Côte d’Azur, Epione Team, 2004 Rte des Lucioles, 06560 Valbonne, France
  2. IPMC, CNRS, Université Côte d’Azur, 660 Rte des Lucioles, 06560 Valbonne, France
Journal: NAR molecular medicine, volume 3, issue 2, article ugag028
Dates: received 8 January 2026; accepted 13 May 2026; published online 3 June 2026
Type: Research article · Language: English
License: CC BY-NC
Identifiers: DOI 10.1093/narmme/ugag028 · PMID 42266503 · PMCID PMC13245416 · OpenAlex W7163537245
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: genetics / omics (modality), other condition (population), cellular / molecular (subfield)
Methods: Statistics, Smoothing, state filtering, decompositions, Machine learning
Topic: Genetics and Neurodevelopmental Disorders (Genetics, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: Agence Nationale de la Recherche (ANR-19-P3IA-0002, ANR‐15‐IDEX‐01)
Citations: not cited yet (Europe PMC); 84 references in the paper

Abstract

Fragile X Syndrome (FXS) is a neurodevelopmental disorder caused by mutations in the FMR1 gene, resulting in the loss of FMRP, an RNA-binding protein regulating translation of hundreds of mRNAs. The Fmr1 knock-out mouse models this deficiency and is used to study molecular perturbations in the FXS brain. Omics analysis shows that FMRP loss disrupts coordination between transcriptomic and translatomic layers. But limited sample availability and dataset heterogeneity hinder detection of subtle, coordinated multi-omic dysregulations. To address this, we trained a Multi-Channel Variational Autoencoder (MCVAE) on wild-type samples to learn a shared latent representation of transcriptomic and translatomic modalities via cross-modal reconstruction. Testing MCVAE on Fmr1-knock-out samples revealed deviations from wild-type as anomalies, uncovering known and novel perturbations. Compared to alternative methods, MCVAE shows stronger enrichment for FMRP mRNA targets and improved genotype discriminative power in post-hoc tests. Translatomic anomalies exhibited coordinated relationships with transcriptomic anomalies, as supported by publicly available databases exploration. Moreover, these anomalies mapped to validated FMRP regulators and neurodevelopmental pathways, establishing MCVAE as a framework to uncover coordinated molecular perturbations underlying the FXS pathophysiology and guide biomarker and therapeutic target identification.

Reproduced under the paper's license (CC BY-NC), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above, with 14 matches between paragraphs and lines of code.

gitlab.inria.fr/wkhatir/mcvae_anomaly_detection

License: none: the authors keep all their rights
State: the link answers, verified on 28 September 2026
Evidence: files inventoried
Commit: 31d52c607466bac22b69b40810cee3037017ff81, 21 September 2026
Languages: Python (36), R (4), Jupyter (1)
Size: 4,007 files, 41 scripts
Software Heritage: not archived
Found in: “Data availability”
Holds: README, 2 notebooks
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (26 files), pandas (26 files), Matplotlib (22 files), PyTorch (14 files), scikit-learn (13 files), seaborn (13 files), SciPy (10 files), statsmodels (8 files), rpy2 (5 files), TensorFlow (3 files), tidyverse (3 files), ggplot2 (2 files), clusterProfiler (1 file), DESeq2 (1 file)
Availability: 1 check, the latest on 28 September 2026: the link answers
  • 28 September 2026: the link answers
42 files

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 41 scripts, each with its path and the digest of its content;
  • 14 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

Datasets cited

Data availability

All transcriptomic () and translatomic () datasets analyzed in this study are publicly available through the Gene Expression Omnibus (GEO) repository. The study utilized a total of 35 unique GEO accession codes, which include: GSE140565 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE140565), GSE127845 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE127845), GSE143330 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE143330), GSE174303 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE174303), GSE112502 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112502), GSE165872 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE165872), GSE119681 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE119681), GSE145102 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE145102), GSE121162 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE121162), GSE227891 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE227891), GSE158881 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE158881), GSE144539 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE144539), GSE82068 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE82068), GSE254224 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE254224), GSE156414 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE156414), GSE147830 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE147830), GSE137283 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE137283), GSE180766 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE180766), GSE51424 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51424), GSE141204 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141204), GSE141624 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141624), GSE141899 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141899), GSE141979 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141979), GSE209902 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE209902), GSE242245 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE242245), GSE153872 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE153872), GSE108371 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE108371), GSE108372 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE108372), GSE248013 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE248013), GSE51619 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE51619), GSE131536 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE131536), GSE143659 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE143659), GSE114064 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE114064), GSE201239 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE201239), and GSE101823 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE101823). A complete categorization of these accession numbers is detailed in Table 1 of the manuscript.

The source code used for this analysis is publicly available at https://gitlab.inria.fr/wkhatir/MCVAE_anomaly_detection.

Reproduced under the paper's license (CC BY-NC), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 2, 28 September 2026

  • Funding: added Agence Nationale de la Recherche: ANR-19-P3IA-0002, ANR‐15‐IDEX‐01

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 79 references.

Cite

This paper

Khatir, W., Lorenzi, M., Balelli, I., & Gwizdek, C. (2026). MCVAE-based multi-omic anomaly detection in Fragile X Syndrome. NAR molecular medicine, 3(2), ugag028. https://doi.org/10.1093/narmme/ugag028

BibTeX

@article{khatir2026mcvae,
author = {Khatir, Wassila and Lorenzi, Marco and Balelli, Irene and Gwizdek, Carole},
title = {{MCVAE-based multi-omic anomaly detection in Fragile X Syndrome}},
journal = {NAR molecular medicine},
year = {2026},
month = apr,
volume = {3},
number = {2},
pages = {ugag028},
publisher = {Oxford University Press},
issn = {2976-856X},
doi = {10.1093/narmme/ugag028},
url = {https://doi.org/10.1093/narmme/ugag028},
pmid = {42266503},
pmcid = {PMC13245416}
}

RIS

TY - JOUR
AU - Khatir, Wassila
AU - Lorenzi, Marco
AU - Balelli, Irene
AU - Gwizdek, Carole
TI - MCVAE-based multi-omic anomaly detection in Fragile X Syndrome
T2 - NAR molecular medicine
J2 - NAR Mol Med
PY - 2026
DA - 2026/04/01
VL - 3
IS - 2
SP - ugag028
SN - 2976-856X
PB - Oxford University Press
DO - 10.1093/narmme/ugag028
UR - https://doi.org/10.1093/narmme/ugag028
LA - en
ER -

CSL-JSON

{
"id": "10.1093/narmme/ugag028",
"type": "article-journal",
"title": "MCVAE-based multi-omic anomaly detection in Fragile X Syndrome",
"container-title": "NAR molecular medicine",
"author": [
{
"family": "Khatir",
"given": "Wassila"
},
{
"family": "Lorenzi",
"given": "Marco"
},
{
"family": "Balelli",
"given": "Irene"
},
{
"family": "Gwizdek",
"given": "Carole"
}
],
"container-title-short": "NAR Mol Med",
"volume": "3",
"issue": "2",
"page": "ugag028",
"DOI": "10.1093/narmme/ugag028",
"PMID": "42266503",
"PMCID": "PMC13245416",
"ISSN": "2976-856X",
"publisher": "Oxford University Press",
"URL": "https://doi.org/10.1093/narmme/ugag028",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
1
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1101/gr.276477.121 [code]
A model-based constrained deep learning clustering approach for spatially resolved single-cell data.
Journal: Genome research
In common: rpy2, clusterProfiler, statsmodels, 9 other tools, genetics / omics, cellular / molecular, 1 reference
[2] doi:10.1186/s12864-025-11946-7 [code]
GNODEVAE: a graph-based ODE-VAE enhances clustering for single-cell data.
Journal: BMC genomics
In common: rpy2, clusterProfiler, TensorFlow, 10 other tools, genetics / omics
[3] doi:10.1016/j.xcrm.2026.102766 [code]
A longitudinal single-cell and spatial multiomic atlas of pediatric high-grade glioma.
Journal: Cell reports. Medicine
In common: rpy2, clusterProfiler, DESeq2, 9 other tools, genetics / omics, other condition, cellular / molecular
[4] doi:10.1016/j.isci.2026.114674 [code]
Single-cell transcriptomics revealed molecular vulnerability in a human midbrain-like organoid model of Parkinson's disease.
Journal: iScience
In common: rpy2, clusterProfiler, DESeq2, 9 other tools, genetics / omics, cellular / molecular
[5] doi:10.1016/j.jbc.2024.107540
Characterization of ribosome stalling and no-go mRNA decay stimulated by the fragile X protein, FMRP.
Journal: The Journal of biological chemistry
In common: other condition, cellular / molecular, 8 references
[6] doi:10.1038/s41591-024-03150-z [code]
A brain cell atlas integrating single-cell transcriptomes across human brain regions.
Journal: Nature medicine
In common: rpy2, clusterProfiler, PyTorch, 8 other tools, genetics / omics, 1 reference
[7] doi:10.1093/bib/bbaf657 [code]
SpaTM: topic models for inferring spatially informed transcriptional programs.
Journal: Briefings in bioinformatics
In common: rpy2, DESeq2, TensorFlow, 9 other tools, genetics / omics
[8] doi:10.1093/bib/bbag485 [code]
Single-cell-level perturbation-induced and condition-related signal estimation with batch effect removal using NDreamer.
Journal: Briefings in bioinformatics
In common: rpy2, clusterProfiler, statsmodels, 9 other tools, genetics / omics
[9] doi:10.1093/neuped/wuag009 [code]
Alternative splicing in pediatric central nervous system tumors highlights oncofetal candidate &lt;i&gt;CLK1&lt;/i&gt; exon 4.
Journal: Neuro-oncology pediatrics
In common: rpy2, clusterProfiler, DESeq2, 8 other tools, other condition
[10] doi:10.1038/s41467-025-67779-1 [code]
An in vivo and in vitro spatiotemporal profile of human midbrain development.
Journal: Nature communications
In common: rpy2, DESeq2, statsmodels, 8 other tools, genetics / omics, cellular / molecular

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Add the badge to the code's README

OSCR: the badge of this paper

If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.

Markdown
<!-- oscr-badge:start -->
[![OSCR](https://openscicode.org/badge/doi/10.1093/narmme/ugag028.svg)](https://openscicode.org/badge/doi/10.1093/narmme/ugag028)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.1093/narmme/ugag028.svg
   :target: https://openscicode.org/badge/doi/10.1093/narmme/ugag028
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1093/narmme/ugag028"><img src="https://openscicode.org/badge/doi/10.1093/narmme/ugag028.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->

If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Report a mismatch between the code and the paper · Report a code error (signed in)

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Report a reproduction failure (signed in)

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.