Search

The size of the human head is highly heritable, but genetic drivers of its variation within the general population remain unmapped. We perform a genome-wide association study on head size (N = 80,890) and identify 67 genetic loci, of which 50 are novel. Neuroimaging studies show that 17 variants affect specific brain areas, but most have widespread effects. Gene set enrichment is observed for various cancers and the p53, Wnt, and ErbB signaling pathways. Genes harboring lead variants are enriched for macrocephaly syndrome genes (37-fold) and high-fidelity cancer genes (9-fold), which is not seen for human height variants. Head size variants are also near genes preferentially expressed in intermediate progenitor cells, neural cells linked to evolutionary brain expansion. Our results indicate that genes regulating early brain and cranial growth incline to neoplasia later in life, irrespective of height. This warrants investigation of clinical implications of the link between head size and cancer.

Deep learning applications have had a profound impact on many scientific fields, including functional genomics. Deep learning models can learn complex interactions between and within omics data; however, interpreting and explaining these models can be challenging. Interpretability is essential not only to help progress our understanding of the biological mechanisms underlying traits and diseases but also for establishing trust in these model's efficacy for healthcare applications. Recognizing this importance, recent years have seen the development of numerous diverse interpretability strategies, making it increasingly difficult to navigate the field. In this review, we present a quantitative analysis of the challenges arising when designing interpretable deep learning solutions in functional genomics. We explore design choices related to the characteristics of genomics data, the neural network architectures applied, and strategies for interpretation. By quantifying the current state of the field with a predefined set of criteria, we find the most frequent solutions, highlight exceptional examples, and identify unexplored opportunities for developing interpretable deep learning models in genomics. [ABSTRACT FROM AUTHOR]

Background Methods Results Conclusion Craniosynostosis, a congenital condition characterized by the premature fusion of cranial sutures, necessitates objective methods for evaluating cranial morphology to enhance patient treatment. Current subjective assessments often lead to inconsistent outcomes. This study introduces a novel, quantitative approach to classify craniosynostosis and measure its severity.An artificial neural network was trained to classify normocephalic, trigonocephalic, and scaphocephalic head shapes based on a publicly available dataset of synthetic 3D head models. Each 3D model was converted into a low‐dimensional shape representation based on the distribution of normal vectors, which served as the input for the neural network, ensuring complete patient anonymity and invariance to geometric size and orientation. Explainable AI methods were utilized to highlight significant features when making predictions. Additionally, the Feature Prominence (FP) score was introduced, a novel metric that captures the prominence of distinct shape characteristics associated with a given class. Its relationship with clinical severity scores was examined using the Spearman Rank Correlation Coefficient.The final model achieved excellent test accuracy in classifying the different cranial shapes from their low‐dimensional representation. Attention maps indicated that the network's attention was predominantly directed toward the parietal and temporal regions, as well as toward the region signifying vertex depression in scaphocephaly. In trigonocephaly, features around the temples were most pronounced. The FP score showed a strong positive monotonic relationship with clinical severity scores in both scaphocephalic (ρ = 0.83, p < 0.001) and trigonocephalic (ρ = 0.64, p < 0.001) models. Visual assessments further confirmed that as FP values rose, phenotypic severity became increasingly evident.This study presents an innovative and accessible AI‐based method for quantifying cranial shape that mitigates the need for adjustments due to age‐specific size variations or differences in the spatial orientation of the 3D images, while ensuring complete patient privacy. The proposed FP score strongly correlates with clinical severity scores and has the potential to aid in clinical decision‐making and facilitate multi‐center collaborations. Future work will focus on validating the model with larger patient datasets and exploring the potential of the FP score for broader applications. The publicly available source code facilitates easy implementation, aiming to advance craniofacial care and research. [ABSTRACT FROM AUTHOR]

Subcortical brain structures are involved in developmental, psychiatric and neurological disorders. We performed GWAS meta-analyses of intracranial and nine subcortical brain volumes (brainstem, caudate nucleus, putamen, hippocampus, globus pallidus, thalamus, nucleus accumbens, amygdala and, for the first time, the ventral diencephalon) in 74,898 participants of European ancestry. We identified 254 independent loci associated with these brain volumes, explaining up to 35% of phenotypic variance. We observed gene expression in specific neural cell types across differentiation time points, including genes involved in intracellular signalling and brain ageing-related processes. Polygenic scores for brain volumes showed predictive ability when applied to individuals of diverse ancestries. We observed causal genetic effects of brain volumes with Parkinson's disease and ADHD. Findings implicate specific gene expression patterns in brain development and genetic variants in comorbid neuropsychiatric disorders, which could point to a brain substrate and region of action for risk genes implicated in brain diseases., Competing Interests: IA received speaker’s honorarium Lundbeck; OAA is a consultant to Cortechs.ai and Precision Health, speaker’s honorarium from Lundbeck, Janssen, Otsuka, Sunovion; HB is an Advisory Board Member or Consultant to Biogen, Eisai, Eli Lilly, Roche, Skin2Neuron, Cranbrook Care and Montefiore Homes; CRKC has received past partial research support from Biogen, Inc. (Boston, USA) for work unrelated to the topic of this manuscript; AMD is the Principal Investigator of a research agreement between General Electric Healthcare and the University of California, San Diego (UCSD); he is a Founder of and hold equity in CorTechs Labs, Inc. I am a member of the Scientific Advisory Board of Human Longevity, Inc., and the Mohn Medical Imaging and Visualization Center in Bergen, Norway. The terms of these arrangements have been reviewed and approved by UCSD in accordance with its conflict-of-interest policies; BF has received educational speaking fees from Medice; HJG has received travel grants and speakers honoraria from Fresenius Medical Care, Neuraxpharm, Servier and Janssen Cilag as well as research funding from Fresenius Medical Care; DPH is a full time employee of Genentech, Inc; NH is a shareholder various manufacturers of medical technology; AM-L has received consultant fees from Daimler und Benz Stiftung, EPFL Brain Mind Institute, Fondation FondaMental, Hector Stiftung II, Invisio, Janssen-Cilag GmbH, Lundbeck A/S, Lundbeckfonden, Lundbeck Int. Neuroscience Foundation, Neurotorium, MedinCell, The LOOP Zürich, University Medical Center Utrecht, University of Washington, Verein für Mentales Wohlbefinden, von Behring-Röntgen-Stiftung; speaker fees from Ärztekammer Nordrhein, Caritas, Clarivate, Dt. Gesellschaft für Neurowissenschaftliche Begutachtung, Gentner Verlag, Landesärztekammer Baden-Württemberg, LWL Bochum, Northwell Health, Ruhr University Bochum, Penn State University, Society of Biological Psychiatry, University Prague, Vitos Klinik Rheingau and editorial and/or author fees fromAmerican Association for the Advancement of Science, ECNP, Servier Int., Thieme Verlag; WN is founder of Quantib BV and was scientific lead of Quantib BV until Jan 31, 2023; MMN has received fees for membership in an advisory board from HMG Systems Engineering GmbH (Fürth, Germany), for membership in the Medical-Scientific Editorial Office of the Deutsches Ärzteblatt, and for serving as a consultant for EVERIS Belgique SPRL in a project of the European Commission (REFORM/SC2020/029). MMN receives salary payments from Life & Brain GmbH and holds shares in Life & Brain GmbH. All these concerned activities outside the submitted work; BMP serves on the Steering Committee of the Yale Open Data Access Project funded by Johnson & Johnson; AJS receives support from multiple NIH grants (P30 AG010133, P30 AG072976, R01 AG019771, R01 AG057739, U19 AG024904, R01 LM013463, R01 AG068193, T32 AG071444, U01 AG068057, U01 AG072177, and U19 AG074879). He has also received support from Avid Radiopharmaceuticals, a subsidiary of Eli Lilly (in kind contribution of PET tracer precursor); Bayer Oncology (Scientific Advisory Board); Eisai (Scientific Advisory Board); Siemens Medical Solutions USA, Inc. (Dementia Advisory Board); NIH NHLBI (MESA Observational Study Monitoring Board); Springer-Nature Publishing (Editorial Office Support as Editor-in-Chief, Brain Imaging and Behavior); MSreceived funding from Pfizer Inc. for a project not related to this research; ES received speaker fees from bfd buchholz fachinformationsdienst gmbh; PMT receives partial research support from Biogen, Inc., for research unrelated to this manuscript; MWW serves on Editorial Boards for Alzheimer’s & Dementia, and the Journal for Prevention of Alzheimer’s disease. He has served on Advisory Boards for Acumen Pharmaceutical, Alzheon, Inc., Cerecin, Merck Sharp & Dohme Corp., and NC Registry for Brain Health. He also serves on the USC ACTC grant which receives funding from Eisai for the AHEAD study. MWW has provided consulting to Boxer Capital, LLC, Cerecin, Inc., Clario, Dementia Society of Japan, Eisai, Guidepoint, Health and Wellness Partners, Indiana University, LCN Consulting, Merck Sharp & Dohme Corp., NC Registry for Brain Health, Prova Education, T3D Therapeutics, University of Southern California (USC), and WebMD. MWW has acted as a speaker/lecturer for China Association for Alzheimer’s Disease (CAAD) and Taipei Medical University, as well as a speaker/lecturer with academic travel funding provided by: AD/PD Congress, Cleveland Clinic, CTAD Congress, Foundation of Learning; Health Society (Japan), INSPIRE Project; U. Toulouse, Japan Society for Dementia Research, and Korean Dementia Society, Merck Sharp & Dohme Corp., National Center for Geriatrics and Gerontology (NCGG; Japan), University of Southern California (USC). MWW holds stock options with Alzeca, Alzheon, Inc., ALZPath, Inc., and Anven. MWW received support for his research from the following funding sources: National Institutes of Health (NIH)/NINDS/National Institute on Aging (NIA), Department of Defense (DOD), California Department of Public Health (CDPH), University of Michigan, Siemens, Biogen, Hillblom Foundation, Alzheimer’s Association, Johnson & Johnson, Kevin and Connie Shanahan, GE, VUmc, Australian Catholic University (HBI-BHR), The Stroke Foundation, and the Veterans Administration; AIC is currently employed by the Regeneron Genetics Center, a wholly-owned subsidiary of Regeneron Pharmaceuticals, Inc., and may hold Regeneron stock or stock options. All other authors declare no competing interests.

Integrating multi-omics data into predictive models has the potential to enhance accuracy, which is essential for precision medicine. In this study, we developed interpretable predictive models for multi-omics data by employing neural networks informed by prior biological knowledge, referred to as visible networks. These neural networks offer insights into the decision-making process and can unveil novel perspectives on the underlying biological mechanisms associated with traits and complex diseases. We tested the performance, interpretability and generalizability for inferring smoking status, subject age and LDL levels using genome-wide RNA expression and CpG methylation data from the blood of the BIOS consortium (four population cohorts, N total  = 2940). In a cohort-wise cross-validation setting, the consistency of the diagnostic performance and interpretation was assessed. Performance was consistently high for predicting smoking status with an overall mean AUC of 0.95 (95% CI: 0.90-1.00) and interpretation revealed the involvement of well-replicated genes such as AHRR, GPR15 and LRRN3. LDL-level predictions were only generalized in a single cohort with an R 2 of 0.07 (95% CI: 0.05-0.08). Age was inferred with a mean error of 5.16 (95% CI: 3.97-6.35) years with the genes COL11A2, AFAP1, OTUD7A, PTPRN2, ADARB2 and CD34 consistently predictive. For both regression tasks, we found that using multi-omics networks improved performance, stability and generalizability compared to interpretable single omic networks. We believe that visible neural networks have great potential for multi-omics analysis; they combine multi-omic data elegantly, are interpretable, and generalize well to data from different cohorts., (© 2024. The Author(s).)

Deep learning applications have had a profound impact on many scientific fields, including functional genomics. Deep learning models can learn complex interactions between and within omics data; however, interpreting and explaining these models can be challenging. Interpretability is essential not only to help progress our understanding of the biological mechanisms underlying traits and diseases but also for establishing trust in these model's efficacy for healthcare applications. Recognizing this importance, recent years have seen the development of numerous diverse interpretability strategies, making it increasingly difficult to navigate the field. In this review, we present a quantitative analysis of the challenges arising when designing interpretable deep learning solutions in functional genomics. We explore design choices related to the characteristics of genomics data, the neural network architectures applied, and strategies for interpretation. By quantifying the current state of the field with a predefined set of criteria, we find the most frequent solutions, highlight exceptional examples, and identify unexplored opportunities for developing interpretable deep learning models in genomics., (© The Author(s) 2024. Published by Oxford University Press.)