OSCR

Deep learning reveals a neurocomputational mechanism predicting depression risk in adolescents.

Code ↔ Paper

3 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.

The 3 matches
  1. [1] § MATERIALS AND METHODS › The analysis of visual anger code › Clustering analysis ↔ subgroup.R, lines 41–82 · score 0.67 · consensus matrix, silhouette score, distance, subgroups, clustering
  2. [2] § MATERIALS AND METHODS › Prediction models in early adulthood ↔ ANN_perturbation.R, lines 175–262 · score 0.65 · linear regression, baseline models, emotional symptoms, AIC, R2, predict
  3. [3] § RESULTS › Computational marker detected specifically in MDD patients ↔ stratify_val.R, lines 1–40 · score 0.52 · MDD control, STRATIFY, AUD, BN, activation, brain scores

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

R · 233 lines · 8.5 KB · CC-BY-4.0 · 1 match

  1. require('R.matlab')
  2. require(tidyverse)
  3. require(dplyr)
  4. require(ggplot2)
  5. require(rstatix)
  6. library(philentropy)
  7. library(cluster)
  8. library(jsonlite)
  10. ########################################################################
  11. ######################## K means clustering ###########################
  12. ########################################################################
  13. angry_neutral_occipital = readMat('data/ANN_mapping/angry_mu_seed100_occipital.mat')$angry.mu.seed100.occipital %>%
  14. as.data.frame # [1332, 256]
  16. ############# The optimal number of clusters #############
  17. #### elbow method ####
  18. set.seed(123)
  19. wcss <- numeric()
  20. for (k in 1:7) {
  21. kmeans_result <- kmeans(angry_neutral_occipital, centers=k, nstart=25, iter.max=20)
  22. wcss[k] <- kmeans_result$tot.withinss
  23. }
  24. ggplot() +
  25. geom_line(aes(x=1:7, y=wcss), color='blue', linewidth=1) +
  26. geom_point(aes(x=1:7, y=wcss), color='red', size=3) +
  27. labs(x='Number of clusters', y='WCSS') +
  28. scale_x_continuous(breaks=1:7) +
  29. theme_bw() + theme(panel.border = element_blank(), panel.grid.minor = element_blank(),
  30. panel.grid.major = element_blank(), axis.line = element_line(colour = "black"),
  31. text=element_text(size=13, family='Arial'))
  33. # ggsave(filename='elbow.tiff',
  34. # width=1300,
  35. # height=1000,
  36. # units='px',
  37. # bg = "white",
  38. # dpi=300)
  41. #### silhouette method ####
  42. silhouette_scores <- numeric()
  44. for (k in 2:7) {
  45. kmeans_result <- kmeans(angry_neutral_occipital, centers=k, nstart=25, iter.max=20)
  46. silhouette_obj <- silhouette(kmeans_result$cluster, dist(angry_neutral_occipital))
  47. silhouette_scores[k-1] <- mean(silhouette_obj[, "sil_width"])
  48. }
  50. ggplot() +
  51. geom_line(aes(x=2:7, y=silhouette_scores), color='blue', linewidth=1) +
  52. geom_point(aes(x=2:7, y=silhouette_scores), color='red', size=3) +
  53. labs(x='Number of clusters', y='Average silhouette width') +
  54. scale_x_continuous(breaks=2:7) +
  55. theme_bw() + theme(panel.border = element_blank(), panel.grid.minor = element_blank(),
  56. panel.grid.major = element_blank(), axis.line = element_line(colour = "black"),
  57. text=element_text(size=13, family='Arial'))
  59. # ggsave(filename='silhouette.tiff',
  60. # width=1300,
  61. # height=1000,
  62. # units='px',
  63. # bg = "white",
  64. # dpi=300)
  67. ###################### stability testing ##################
  68. num_clusters <- 2
  69. num_repeats <- 50
  71. consensus_matrix <- matrix(0, nrow = nrow(angry_neutral_occipital), ncol = nrow(angry_neutral_occipital))
  72. for (i in 1:num_repeats) {
  73. set.seed(i)
  74. cluster_result <- kmeans(angry_neutral_occipital, centers = num_clusters, nstart = 25)
  75. # Update consensus matrix
  76. for (j in 1:num_clusters) {
  77. cluster_members <- which(cluster_result$cluster == j)
  78. consensus_matrix[cluster_members, cluster_members] <- consensus_matrix[cluster_members, cluster_members] + 1
  79. }
  80. }
  82. consensus_matrix <- consensus_matrix / num_repeats
  84. ############ T-SNE for visualization ###########
  85. df_pca <- read_csv('data/tsne_cluster2.csv') %>%
  86. convert_as_factor(cluster)
  87. ggplot(df_pca, aes(x = PC1, y = PC2, color = as.factor(cluster))) +
  88. geom_point(alpha = 0.5) + xlab('') + ylab('') +
  89. scale_color_manual(values = c('1' = '#C4777D', '2' = '#809EC4')) +
  90. theme_minimal() + theme(panel.border = element_blank(), panel.grid.minor = element_blank(),
  91. panel.grid.major = element_blank(), axis.text = element_blank(),
  92. text=element_text(size=13, family='Arial'),
  93. legend.position = 'none')
  95. # ggsave(filename='vis2.tiff',
  96. # width=1300,
  97. # height=1300,
  98. # units='px',
  99. # bg = "white",
  100. # dpi=300)
  102. ##########################################################################
  103. ################ The demographic difference between two clusters ##############
  104. ##########################################################################
  105. data <- read_csv('data/IMAGEN_covariate/IMAGEN_data/score_symptom_dawba_adrs.csv') %>%
  106. convert_as_factor(id, cluster, sex, hand, site)
  108. data$cluster <- ifelse(data$cluster == 0, 1, 0)
  109. data$cluster <- as.factor(data$cluster)
  111. # chi square test for handedness, sex, site
  112. chi_table <- table(data$cluster, data$site)
  113. chisq.test(chi_table)
  115. # t test for ses
  116. t.test(ses ~ cluster, data = data)
  119. ##########################################################################
  120. ################ The symptom difference between two clusters ##############
  121. ##########################################################################
  122. # Load the symptom data
  123. data <- read_csv('data/IMAGEN_covariate/IMAGEN_data/score_symptom_dawba_adrs.csv') %>%
  124. convert_as_factor(id, cluster, sex, hand, site)
  126. data$cluster <- ifelse(data$cluster == 0, 1, 0)
  127. data$cluster <- as.factor(data$cluster)
  128. data <- as.data.frame(lapply(data, function(x) if(is.numeric(x)) scale(x) else x))
  130. model <- lm(adrs_sum ~ cluster + sex + ses + hand + site, data = data)
  131. summary(model)
  132. confint(model)
  134. ########### The proportion of case and control in two clusters ###########
  135. data <- read_csv('data/IMAGEN_covariate/IMAGEN_data/score_symptom_dawba_adrs.csv') %>%
  136. convert_as_factor(id, cluster, sex, hand, site)
  137. data %>%
  138. group_by(cluster) %>%
  139. summarise(mean=mean(dep, na.rm = TRUE), std=sd(dep, na.rm=TRUE), n= sum(!is.na(dep)))
  141. band <- read_csv('data/IMAGEN_covariate/IMAGEN_data/DAWBA_band.csv') %>%
  142. convert_as_factor(id)
  143. band <- band[,c(1, 2, 9, 11)]
  144. band$sp19_low <- ifelse(band$sspphband < 4, 0, 1)
  145. band$dep19_low <- ifelse(band$sdepband < 4, 0, 1)
  146. band$ep19_low <- ifelse(band$seatband < 4, 0, 1)
  148. band$internal19_low <- ifelse(band$sspphband >= 4 | band$sdepband >= 4 | band$seatband >= 4, 1, 0)
  151. data <- merge(data, band[,c(1,5,6,8)], by='id', all.x = TRUE)
  153. # The number of cases in low-efficiency group: control: 654, case: 51
  154. table(data[data$cluster==0,]$internal19_low)
  155. # The number of cases in high-efficiency group: control: 388, case: 9
  156. table(data[data$cluster==1,]$internal19_low)
  158. #### chi-squared test ####
  159. counts <- matrix(c(654, 51, 388, 9), nrow = 2, byrow = TRUE)
  160. colnames(counts) <- c("0", "1")
  161. rownames(counts) <- c("Cluster 0", "Cluster 1")
  163. chi_test <- chisq.test(counts)
  164. chi_test
  166. ##########################################################################
  167. ################ Information gain for two clusters ##############
  168. ##########################################################################
  169. InfoGain <- function(data, num_bins=40) {
  170. randomdis = log2(num_bins) # random distribution
  171. mean_data = 2 * (data - min(data)) / (max(data) - min(data)) - 1 # normalize to [-1, 1]
  172. bins = cut(mean_data, breaks = num_bins)
  173. counts = table(bins) # the number of data points in each bin
  174. probabilities = counts / sum(counts) # convert to probabilities
  176. entropy <- -sum(probabilities * log2(probabilities + 1e-10))
  177. gain <- randomdis - entropy
  178. return(gain)
  179. }
  181. # Compute the 95%CI for the difference in information gain between two groups
  182. InfoGain_twogroup <- function(data_C1, data_C2, n_iter = 1000){
  183. result <- data.frame(information1=numeric(1), information2=numeric(1), lower=numeric(1),
  184. upper=numeric(1), more=numeric(1))
  185. diffs = numeric(n_iter)
  186. info1_all = InfoGain(colMeans(data_C1))
  187. info2_all = InfoGain(colMeans(data_C2))
  189. for (j in 1:n_iter){
  190. # Sample with replacement
  191. idx1 = sample(nrow(data_C1), replace = TRUE)
  192. sample_C1 = data_C1[idx1, ]
  193. idx2 = sample(nrow(data_C2), replace = TRUE)
  194. sample_C2 = data_C2[idx2, ]
  196. info1_sample = InfoGain(colMeans(sample_C1))
  197. info2_sample = InfoGain(colMeans(sample_C2))
  199. diffs[j] = info2_sample - info1_sample # information
  201. }
  203. # 95%CI
  204. ci_p = quantile(diffs, c(0.025, 0.975))
  205. result[1,] <- c(info1_all, info2_all, ci_p[1], ci_p[2],
  206. ifelse(ci_p[1]>=0 & ci_p[2]>0, 2, ifelse(
  207. ci_p[1]<0 & ci_p[2]<=0, 1, 0)))
  208. result_info <- list(diffs, result)
  209. return(result_info)
  210. }
  213. set.seed(123)
  214. angry_neutral_occipital = readMat('data/ANN_mapping/angry_mu_seed100_occipital.mat')$angry.mu.seed100.occipital %>%
  215. as.data.frame # [1332, 256]
  216. kmeans_result <- kmeans(angry_neutral_occipital, centers=2, nstart=25, iter.max=20)
  217. id <- fromJSON('data/id_json/total_id_occipital.json')
  218. id_label <- data.frame(id=id, cluster=kmeans_result$cluster)
  219. id_label$id <- gsub('\\.npy$', '', id_label$id)
  220. data <- cbind(id_label$cluster, angry_neutral_occipital)
  221. colnames(data)[1] <- 'cluster'
  222. data_C1 <- filter(data, cluster == 1)
  223. data_C2 <- filter(data, cluster == 2)
  224. data_C1 <- data_C1[, -1]
  225. data_C2 <- data_C2[, -1]
  228. result_info <- InfoGain_twogroup(data_C1, data_C2)

subgroup.R, under CC-BY-4.0 · at the source

Overview

Authors: Han Lu1, Xiaoqian Yan2, Benjamin Becker3,4, Andreas Heinz5,6, Barbara J Sahakian7,8, Christelle Langley7,8, Zhaoyu Zuo2, Luolong Cao2, Zuo Zhang9,10, Lauren Robinson9,11, Nilakshi Vaidya12, Jeanne Winterer13,14, Sinead King9, Charlotte Walton15, Tobias Banaschewski16, Gareth J Barker17, Arun LW Bokde18, Rüdiger Brühl19, Herta Flor20,21, Hugh Garavan22
and 22 other authorsPenny Gowland23, Antoine Grigis24, Herve Lemaitre24,25, Jean-Luc Martinot26,27, Marie-Laure Paillère Martinot26,28, Eric Artiges26,27, Frauke Nees29, Dimitri Papadopoulos Orfanos21, Luise Poustka30,31, Hedi Kebir12, Ulrike Schmidt32,33, Julia Sinclair34, Michael N Smolka6, Sarah Hohmann16, Nathalie Holz16, Henrik Walter31,35, Robert Whelan36, Sylvane Desrivières9, Gunter Schumann2,12,31, Qiang Luo37,38, STRATIFY/ESTRA Consortium, IMAGEN Consortium
ORCID iDs: Han Lu, Xiaoqian Yan, Benjamin Becker, Andreas Heinz, Barbara J Sahakian, Christelle Langley, Luolong Cao, Zuo Zhang, Lauren Robinson, Nilakshi Vaidya, Jeanne Winterer, Sinead King, Charlotte Walton, Tobias Banaschewski, Gareth J Barker, Arun LW Bokde, Rüdiger Brühl, Herta Flor, Hugh Garavan, Penny Gowland, Herve Lemaitre, Jean-Luc Martinot, Marie-Laure Paillère Martinot, Eric Artiges, Frauke Nees, Dimitri Papadopoulos Orfanos, Luise Poustka, Ulrike Schmidt, Julia Sinclair, Michael N Smolka, Nathalie Holz, Henrik Walter, Robert Whelan, Sylvane Desrivières, Gunter Schumann, Qiang Luo
38 affiliations
  1. School of Artificial Intelligence, Shenzhen University, Shenzhen, China
  2. Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China
  3. MIND & AI Lab, Department of Psychology, The University of Hong Kong, Hong Kong SAR, China
  4. SRT AI, Society & Social Dynamics, Faculty of Social Sciences, The University of Hong Kong, Hong Kong SAR, China
  5. Department of Psychiatry and Psychotherapy, University of Tübingen and German Center for Mental Health (DZPG), Site Tübingen, Germany
  6. Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Dresden, Germany
  7. Department of Psychiatry, University of Cambridge, Cambridge CB2 0SZ, UK
  8. Behavioural and Clinical Neuroscience Institute, Department of Psychology, University of Cambridge, Cambridge CB2 3EB, UK
  9. Social Genetic and Developmental Psychiatry Centre, Institute of Psychiatry, Psychology, and Neuroscience, King’s College London, London SE5 8AF, UK
  10. School of Psychology, Institute for Mental Health, University of Birmingham, Birmingham, UK
  11. Oxford Institute of Clinical Psychology Training and Research, Oxford University, Oxford, UK
  12. Centre for Population Neuroscience and Stratified Medicine (PONS), Department of Psychiatry and Psychotherapy, Charité Universitätsmedizin Berlin, Germany
  13. Charité—Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Department of Psychiatry and Psychotherapy, Campus Charité Mitte, Charitéplatz 1, Berlin, Germany
  14. Department of Education and Psychology, Freie Universität Berlin, Berlin, Germany
  15. Psychology Department, B44 University Road, University of Southampton, Southampton SO17 1PS, UK
  16. Department of Child and Adolescent Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159 Mannheim, Germany; German Center for Mental Health (DZPG), partner site Mannheim-Heidelberg-Ulm
  17. Department of Neuroimaging, Institute of Psychiatry, Psychology, and Neuroscience, King’s College London, UK
  18. Discipline of Psychiatry, School of Medicine and Trinity College Institute of Neuroscience, Trinity College Dublin, Dublin, Ireland
  19. Physikalisch-Technische Bundesanstalt (PTB), Braunschweig and Berlin, Germany
  20. Institute of Cognitive and Clinical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, Mannheim, Germany
  21. Department of Psychology, School of Social Sciences, University of Mannheim, 68131 Mannheim, Germany
  22. Departments of Psychiatry and Psychology, University of Vermont, Burlington, VT 05405, USA
  23. Sir Peter Mansfield Imaging Centre School of Physics and Astronomy, University of Nottingham, University Park, Nottingham, UK
  24. NeuroSpin, CEA, Université Paris-Saclay, F-91191 Gif-sur-Yvette, France
  25. Institut des Maladies Neurodégénératives, UMR 5293, CNRS, CEA, Université de Bordeaux, 33076 Bordeaux, France
  26. Institut National de la Santé et de la Recherche Médicale, INSERM U1299 “Trajectoires développementales en psychiatrie”; Université Paris-Saclay, Ecole Normale supérieure Paris-Saclay, CNRS, Centre Borelli, Gif-sur-Yvette, France
  27. Research Department, LABD-PSY, Etablissement Public de Santé (EPS) Barthélemy Durand, 91700 Sainte-Geneviève-des-Bois, France
  28. AP-HP, Sorbonne Université, Department of Child and Adolescent Psychiatry, Pitié-Salpêtrière Hospital, Paris, France
  29. Institute of Medical Psychology, Ludwig-Maximilians-Universität (LMU) in Munich, Munich, Germany
  30. Department of Child and Adolescent Psychiatry, Center for Psychosocial Medicine, University Hospital Heidelberg, Heidelberg, Germany
  31. German Center for Mental Health (DZPG), Site Berlin-Potsdam, Germany
  32. Department of Psychological Medicine, Section for Eating Disorders, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London SE5 8AF, UK
  33. South London and Maudsley NHS Foundation Trust, London, UK
  34. Clinical and Experimental Sciences, Faculty of Medicine, University of Southampton, Southampton, UK
  35. Department of Psychiatry and Psychotherapy CCM, Charité—Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany
  36. School of Psychology and Global Brain Health Institute, Trinity College Dublin, Ireland
  37. Research Institute of Intelligent Complex Systems, Fudan University, Shanghai, China
  38. State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science, Institutes of Brain Science, Fudan University, Shanghai, China
Institutions: Shenzhen University (China); Shanghai Medical College of Fudan University (China); Fudan University (China); University of Hong Kong (Hong Kong SAR China); Deutsches Zentrum für Psychische Gesundheit (Germany); Technische Universität Dresden (Germany); University of Tübingen (Germany); University of Cambridge (United Kingdom); King's College London (United Kingdom); University of Birmingham (United Kingdom); University of Oxford (United Kingdom); Stiftung Charité; Charité - Universitätsmedizin Berlin (Germany); Humboldt-Universität zu Berlin (Germany); Freie Universität Berlin (Germany); University of Southampton (United Kingdom); Heidelberg University (Germany); Central Institute of Mental Health (Germany); Medizinische Fakultät Mannheim; Trinity College Dublin (Ireland); Physikalisch-Technische Bundesanstalt (Germany); University of Mannheim (Germany); University of Vermont (United States); University of Nottingham (United Kingdom); Commissariat à l'Énergie Atomique et aux Énergies Alternatives (France); Université Paris-Saclay (France); CEA Paris-Saclay - Etablissement de Saclay (France); CEA Paris-Saclay (France); Centre National de la Recherche Scientifique (France); Université de Bordeaux (France); Institut des Maladies Neurodégénératives (France); École Normale Supérieure Paris-Saclay (France); Inserm (France); Trajectoires développementales & psychiatrie; Centre Borelli (France); Sorbonne Université (France); Assistance Publique – Hôpitaux de Paris (France); Pitié-Salpêtrière Hospital (France); Institut für Medizinische Psychologie (Germany); Ludwig-Maximilians-Universität München (Germany); University Hospital Heidelberg (Germany); South London and Maudsley NHS Foundation Trust (United Kingdom); Berlin Institute of Health at Charité - Universitätsmedizin Berlin (Germany); State Key Laboratory of Medical Neurobiology; Frontiers Center for Brain Science of the Ministry of Education (China)
Journal: Science advances, volume 12, issue 32, article eaed0772
Dates: received 16 October 2025; accepted 2 July 2026; published online 7 August 2026; in print August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1126/sciadv.aed0772 · PMID 42566534 · PMCID PMC13450214 · OpenAlex W7201871593
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: human (organism), depression (population), developmental (subfield)
Methods: Connectivity, Statistics, Smoothing, state filtering, decompositions, Machine learning, Preprocessing, fMRI & imaging
MeSH: Deep Learning*, Depression*, Adolescent, Brain, Emotions, Female, Genetic Predisposition to Disease, Humans, Male, Risk Factors (* major topic)
Topic: Mental Health via Writing (Social Psychology, Psychology), according to OpenAlex
Funding: NIMH NIH HHS (R01 MH085772); European Research Council (695313); NIDA NIH HHS (R01 DA049238); NIA NIH HHS (R56 AG058854); NIBIB NIH HHS (U54 EB020403)
Citations: not cited yet (Europe PMC); 68 references in the paper

Abstract

Early detection and prevention of psychiatric disorders, particularly depression, remain as major global health challenges, yet reliable tools for identifying individuals before symptom onset are lacking. Here, we combine functional neuroimaging with computational modeling to identify a mechanistic biomarker of depression risk. In a population-based adolescent cohort (IMAGEN, N = 1332), we found that weakened neural representations of emotional signals were linked to depressive symptoms. Perturbation experiments in a brain-aligned deep learning model showed that this deficit reflects overregularized emotion perception, producing a negative perceptual bias. A neurocomputational signature of this mechanism predicted depression symptom onset up to 4 years later at the IMAGEN follow-up (N = 725), was associated with both a genetic-risk variant and polygenic risk for depression, and improved depression classification in a patient cohort (STRATIFY, N = 411). These findings suggest a possible mechanism linking genetic vulnerability to altered emotion perception and future depression, and propose a predictive computational marker with potential for early detection and prevention.

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

Repository

Its files are read in the Code ↔ Paper reader above, with 3 matches between paragraphs and lines of code.

Zenodo 18647146

License: CC-BY-4.0
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Languages: R (4)
Size: 7 files, 4 scripts
Software Heritage: not checked
Found in: “Data, code, and materials availability:”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: ggplot2 (4 files), rstatix (4 files), tidyverse (4 files)
Availability: 1 check, the latest on 27 September 2026: the link answers (HTTP 200)
  • 27 September 2026: the link answers (HTTP 200)
5 files
At the source: zenodo.org/records/18647146

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;
  • 4 scripts, each with its path and the digest of its content;
  • 3 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

No dataset and no data link were found in the paper.

Data, code, and materials availability

Data from the IMAGEN study are available upon application: https://imagen2.cea.fr. STRATIFY/ESTRA data are available at www.stratify-project.org/data-access. For further information about the IMAGEN and STRATIFY/ESTRA consortia, please contact. The data and code used by the current study could be found at https://zenodo.org/records/18647146. All data and code needed to evaluate and reproduce the results in the paper are present in the paper and/or the Supplementary Materials. Materials used during this study can be made available upon request via the corresponding author.

Reproduced under the paper's license (CC BY), 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 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 42 authors, 10 MeSH terms, 5 funders, 59 references.

Cite

This paper

Lu, H., Yan, X., Becker, B., Heinz, A., Sahakian, B. J., Langley, C., Zuo, Z., Cao, L., Zhang, Z., Robinson, L., Vaidya, N., Winterer, J., King, S., Walton, C., Banaschewski, T., Barker, G. J., Bokde, A. L., Brühl, R., Flor, H., . . . IMAGEN Consortium. (2026). Deep learning reveals a neurocomputational mechanism predicting depression risk in adolescents. Science advances, 12(32), eaed0772. https://doi.org/10.1126/sciadv.aed0772

BibTeX

@article{lu2026deep,
author = {Lu, Han and Yan, Xiaoqian and Becker, Benjamin and Heinz, Andreas and Sahakian, Barbara J and Langley, Christelle and Zuo, Zhaoyu and Cao, Luolong and Zhang, Zuo and Robinson, Lauren and Vaidya, Nilakshi and Winterer, Jeanne and King, Sinead and Walton, Charlotte and Banaschewski, Tobias and Barker, Gareth J and Bokde, Arun LW and Brühl, Rüdiger and Flor, Herta and Garavan, Hugh and Gowland, Penny and Grigis, Antoine and Lemaitre, Herve and Martinot, Jean-Luc and Martinot, Marie-Laure Paillère and Artiges, Eric and Nees, Frauke and Orfanos, Dimitri Papadopoulos and Poustka, Luise and Kebir, Hedi and Schmidt, Ulrike and Sinclair, Julia and Smolka, Michael N and Hohmann, Sarah and Holz, Nathalie and Walter, Henrik and Whelan, Robert and Desrivières, Sylvane and Schumann, Gunter and Luo, Qiang and {STRATIFY/ESTRA Consortium} and {IMAGEN Consortium}},
title = {{Deep learning reveals a neurocomputational mechanism predicting depression risk in adolescents}},
journal = {Science advances},
year = {2026},
month = aug,
volume = {12},
number = {32},
pages = {eaed0772},
publisher = {American Association for the Advancement of Science},
issn = {2375-2548},
doi = {10.1126/sciadv.aed0772},
url = {https://doi.org/10.1126/sciadv.aed0772},
pmid = {42566534},
pmcid = {PMC13450214}
}

RIS

TY - JOUR
AU - Lu, Han
AU - Yan, Xiaoqian
AU - Becker, Benjamin
AU - Heinz, Andreas
AU - Sahakian, Barbara J
AU - Langley, Christelle
AU - Zuo, Zhaoyu
AU - Cao, Luolong
AU - Zhang, Zuo
AU - Robinson, Lauren
AU - Vaidya, Nilakshi
AU - Winterer, Jeanne
AU - King, Sinead
AU - Walton, Charlotte
AU - Banaschewski, Tobias
AU - Barker, Gareth J
AU - Bokde, Arun LW
AU - Brühl, Rüdiger
AU - Flor, Herta
AU - Garavan, Hugh
AU - Gowland, Penny
AU - Grigis, Antoine
AU - Lemaitre, Herve
AU - Martinot, Jean-Luc
AU - Martinot, Marie-Laure Paillère
AU - Artiges, Eric
AU - Nees, Frauke
AU - Orfanos, Dimitri Papadopoulos
AU - Poustka, Luise
AU - Kebir, Hedi
AU - Schmidt, Ulrike
AU - Sinclair, Julia
AU - Smolka, Michael N
AU - Hohmann, Sarah
AU - Holz, Nathalie
AU - Walter, Henrik
AU - Whelan, Robert
AU - Desrivières, Sylvane
AU - Schumann, Gunter
AU - Luo, Qiang
AU - STRATIFY/ESTRA Consortium
AU - IMAGEN Consortium
TI - Deep learning reveals a neurocomputational mechanism predicting depression risk in adolescents
T2 - Science advances
J2 - Sci Adv
PY - 2026
DA - 2026/08/07
VL - 12
IS - 32
SP - eaed0772
SN - 2375-2548
PB - American Association for the Advancement of Science
DO - 10.1126/sciadv.aed0772
UR - https://doi.org/10.1126/sciadv.aed0772
LA - en
ER -

CSL-JSON

{
"id": "10.1126/sciadv.aed0772",
"type": "article-journal",
"title": "Deep learning reveals a neurocomputational mechanism predicting depression risk in adolescents",
"container-title": "Science advances",
"author": [
{
"family": "Lu",
"given": "Han"
},
{
"family": "Yan",
"given": "Xiaoqian"
},
{
"family": "Becker",
"given": "Benjamin"
},
{
"family": "Heinz",
"given": "Andreas"
},
{
"family": "Sahakian",
"given": "Barbara J"
},
{
"family": "Langley",
"given": "Christelle"
},
{
"family": "Zuo",
"given": "Zhaoyu"
},
{
"family": "Cao",
"given": "Luolong"
},
{
"family": "Zhang",
"given": "Zuo"
},
{
"family": "Robinson",
"given": "Lauren"
},
{
"family": "Vaidya",
"given": "Nilakshi"
},
{
"family": "Winterer",
"given": "Jeanne"
},
{
"family": "King",
"given": "Sinead"
},
{
"family": "Walton",
"given": "Charlotte"
},
{
"family": "Banaschewski",
"given": "Tobias"
},
{
"family": "Barker",
"given": "Gareth J"
},
{
"family": "Bokde",
"given": "Arun LW"
},
{
"family": "Brühl",
"given": "Rüdiger"
},
{
"family": "Flor",
"given": "Herta"
},
{
"family": "Garavan",
"given": "Hugh"
},
{
"family": "Gowland",
"given": "Penny"
},
{
"family": "Grigis",
"given": "Antoine"
},
{
"family": "Lemaitre",
"given": "Herve"
},
{
"family": "Martinot",
"given": "Jean-Luc"
},
{
"family": "Martinot",
"given": "Marie-Laure Paillère"
},
{
"family": "Artiges",
"given": "Eric"
},
{
"family": "Nees",
"given": "Frauke"
},
{
"family": "Orfanos",
"given": "Dimitri Papadopoulos"
},
{
"family": "Poustka",
"given": "Luise"
},
{
"family": "Kebir",
"given": "Hedi"
},
{
"family": "Schmidt",
"given": "Ulrike"
},
{
"family": "Sinclair",
"given": "Julia"
},
{
"family": "Smolka",
"given": "Michael N"
},
{
"family": "Hohmann",
"given": "Sarah"
},
{
"family": "Holz",
"given": "Nathalie"
},
{
"family": "Walter",
"given": "Henrik"
},
{
"family": "Whelan",
"given": "Robert"
},
{
"family": "Desrivières",
"given": "Sylvane"
},
{
"family": "Schumann",
"given": "Gunter"
},
{
"family": "Luo",
"given": "Qiang"
},
{
"literal": "STRATIFY/ESTRA Consortium"
},
{
"literal": "IMAGEN Consortium"
}
],
"container-title-short": "Sci Adv",
"volume": "12",
"issue": "32",
"page": "eaed0772",
"DOI": "10.1126/sciadv.aed0772",
"PMID": "42566534",
"PMCID": "PMC13450214",
"ISSN": "2375-2548",
"publisher": "American Association for the Advancement of Science",
"URL": "https://doi.org/10.1126/sciadv.aed0772",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
7
]
]
}
}

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:10.1038/s41398-026-04010-9 [code]
Bullying victimization and brain development: a longitudinal structural magnetic resonance imaging study from adolescence to early adulthood.
Journal: Translational psychiatry
In common: rstatix, ggplot2, tidyverse, developmental, 1 reference, 20 authors
[2] doi:10.1038/s41386-026-02401-6 [code]
Model-based analysis of stop-signal data reveals robust neural and clinical correlates of evidence accumulation but not inhibition.
Journal: Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology
In common: ggplot2, tidyverse, 16 authors
[3] doi:10.1038/s41398-026-04114-2 [code]
Plasma Glial Fibrillary Acidic Protein (GFAP) shows age-dependent associations with externalizing psychopathology and atypical brain connectivity.
Journal: Translational psychiatry
In common: ggplot2, tidyverse, 5 authors
[4] doi:10.1016/j.nicl.2026.104025
Functional brain biomarkers of self-referential bias in remitted depressed outpatients: a randomized controlled trial.
Journal: NeuroImage. Clinical
In common: depression, 4 references
[5] doi:10.1038/s41398-026-04131-1 [code]
Multimodal phenotypic classification of generalized anxiety and panic using structural MRI data and psychosocial factors: machine learning results from the German National Cohort (NAKO) study.
Journal: Translational psychiatry
In common: rstatix, ggplot2, tidyverse, 2 references
[6] doi:10.1038/s41398-026-04100-8 [code]
Bridging molecules and connectome: network biomarkers guided by neurotransmitter architecture in major depressive disorder.
Journal: Translational psychiatry
In common: tidyverse, depression, author Qiang Luo
[7] doi:10.1093/cercor/bhag067 [code]
Language laterality and cognitive skills: does anatomy matter?
Journal: Cerebral cortex (New York, N.Y. : 1991)
In common: ggplot2, tidyverse, author Herve Lemaitre
[8] doi:10.1192/bjp.2026.10664 [code]
Early effects of a novel 5-HT&lt;sub&gt;4&lt;/sub&gt;R agonist (PF-04995274) and the SSRI citalopram on emotional cognition in unmedicated depression: RESTAND study.
Journal: The British journal of psychiatry : the journal of mental science
In common: rstatix, ggplot2, tidyverse, depression, 1 reference
[9] doi:10.1038/s41467-026-73366-9 [code]
Cortical and white matter myelination proceed in concert during early infancy.
Journal: Nature communications
In common: developmental, author Xiaoqian Yan
[10] doi:10.1038/s41467-026-73153-6 [code]
Latent neural architecture organising shared aesthetic evaluations of visual artworks.
Journal: Nature communications
In common: 1 reference, author Benjamin Becker

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.

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: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

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