A multidimensional precision medicine approach identifies an autism subtype characterized by dyslipidemia

Characterization of a Clinically and Biologically Defined Subgroup of Patients with Autism Spectrum Disorder and Identification of a Tailored Combination Treatment

Autism spectrum disorder (ASD) is a heterogeneous group of neurodevelopmental disorders (NDDs) with a high unmet medical need. The diagnosis of ASD is currently based on behavior criteria, which overlooks the diversity of genetic, neurophysiological, and clinical manifestations. Failure to acknowledge such heterogeneity has hindered the development of efficient drug treatments for ASD and other NDDs. DEPI® (Databased Endophenotyping Patient Identification) is a systems biology, multi-omics, and machine learning-driven platform enabling the identification of subgroups of patients with NDDs and the development of patient-tailored treatments. In this study, we provide evidence for the validation of a first clinically and biologically defined subgroup of patients with ASD identified by DEPI, ASD Phenotype 1 (ASD-Phen1). Among 313 screened patients with idiopathic ASD, the prevalence of ASD-Phen1 was observed to be ~24% in 84 patients who qualified to be enrolled in the study. Metabolic and transcriptomic alterations differentiating patients with ASD-Phen1 were consistent with an over-activation of NF-κB and NRF2 transcription factors, as predicted by DEPI. Finally, the suitability of STP1 combination treatment to revert such observed molecular alterations in patients with ASD-Phen1 was determined. Overall, our results support the development of precision medicine-based treatments for patients diagnosed with ASD.

The genetic landscape of autism spectrum disorder in the Middle Eastern population

Introduction: Autism spectrum disorder (ASD) is characterized by aberrations in social interaction and communication associated with repetitive behaviors and interests, with strong clinical heterogeneity. Genetic factors play an important role in ASD, but about 75% of ASD cases have an undetermined genetic risk. Methods: We extensively investigated an ASD cohort made of 102 families from the Middle Eastern population of Qatar. First, we investigated the copy number variations (CNV) contribution using genome-wide SNP arrays. Next, we employed Next Generation Sequencing (NGS) to identify de novo or inherited variants contributing to the ASD etiology and its associated comorbid conditions in families with complete trios (affected child and the parents). Results: Our analysis revealed 16 CNV regions located in genomic regions implicated in ASD. The analysis of the 88 ASD cases identified 41 genes in 39 ASD subjects with de novo (n = 24) or inherited variants (n = 22). We identified three novel de novo variants in new candidate genes for ASD (DTX4, ARMC6, and B3GNT3). Also, we have identified 15 de novo variants in genes that were previously implicated in ASD or related neurodevelopmental disorders (PHF21A, WASF1, TCF20, DEAF1, MED13, CREBBP, KDM6B, SMURF1, ADNP, CACNA1G, MYT1L, KIF13B, GRIA2, CHM, and KCNK9). Additionally, we defined eight novel recessive variants (RYR2, DNAH3, TSPYL2, UPF3B KDM5C, LYST, and WNK3), four of which were X-linked. Conclusion: Despite the ASD multifactorial etiology that hinders ASD genetic risk discovery, the number of identified novel or known putative ASD genetic variants was appreciable. Nevertheless, this study represents the first comprehensive characterization of ASD genetic risk in Qatar's Middle Eastern population.

Spatiotemporal expression patterns of anxiety disorder-associated genes

Anxiety disorders (ADs) are the most common form of mental disorder that affects millions of individuals worldwide. Although physiological studies have revealed the neural circuits related to AD symptoms, how AD-associated genes are spatiotemporally expressed in the human brain still remains unclear. In this study, we integrated genome-wide association studies of four human AD subtypes-generalized anxiety disorder, social anxiety disorder, panic disorder, and obsessive-compulsive disorder-with spatial gene expression patterns. Our investigation uncovered a novel division among AD-associated genes, marked by significant and distinct expression enrichments in the cerebral nuclei, limbic, and midbrain regions. Each gene cluster was associated with specific anxiety-related behaviors, signaling pathways, region-specific gene networks, and cell types. Notably, we observed a significant negative correlation in the temporal expression patterns of these gene clusters during various developmental stages. Moreover, the specific brain regions enriched in each gene group aligned with neural circuits previously associated with negative decision-making and anxious temperament. These results suggest that the two distinct gene clusters may underlie separate neural systems involved in anxiety. As a result, our findings bridge the gap between genes and neural circuitry, shedding light on the mechanisms underlying AD-associated behaviors.

Role of the Autism Risk Gene Shank3 in the Development of Atherosclerosis: Insights from Big Data and Mechanistic Analyses

Increased medical attention is needed as the prevalence of autism spectrum disorder (ASD) rises. Both cardiovascular disorder (CVD) and hyperlipidemia are closely associated with adult ASD. Shank3 plays a key genetic role in ASD. We hypothesized that Shank3 contributes to CVD development in young adults with ASD. In this study, we investigated whether Shank3 facilitates the development of atherosclerosis. Using Gene Set Enrichment Analysis software (Version No.: GSEA-4.0.3), we analyzed the data obtained from Shank3 knockout mice (Gene Expression Omnibus database), a human population-based study cohort (from Taiwan's National Health Insurance Research Database), and a Shank3 knockdown cellular model. Shank3 knockout upregulated the expression of genes of cholesterol homeostasis and fatty acid metabolism but downregulated the expression of genes associated with inflammatory responses. Individuals with autism had higher risks of hyperlipidemia (adjusted hazard ratio (aHR): 1.39; p < 0.001), major adverse cardiac events (aHR: 2.67; p < 0.001), and stroke (aHR: 3.55; p < 0.001) than age- and sex-matched individuals without autism did. Shank3 downregulation suppressed tumor necrosis factor-α-induced fatty acid synthase expression; vascular cell adhesion molecule 1 expression; and downstream signaling pathways involving p38, Jun N-terminal kinase, and nuclear factor-κB. Thus, Shank3 may influence the development of early-onset atherosclerosis and CVD in ASD. Furthermore, regulating Shank3 expression may reduce inflammation-related disorders, such as atherosclerosis, by inhibiting tumor necrosis factor-alpha-mediated inflammatory cascades.

The Potential Usefulness of the Expanded Carrier Screening to Identify Hereditary Genetic Diseases: A Case Report from Real-World Data

Expanded carrier screening (ECS) means a comprehensive genetic analysis to evaluate an individual's carrier status. ECS is becoming more frequently used, thanks to the availability of techniques such as next generation sequencing (NGS) and array comparative genomic hybridization (aCGH), allowing for extensive genome-scale analyses. Here, we report the case of a couple who underwent ECS for a case of autism spectrum disorder in the male partner family. aCGH and whole-exome sequencing (WES) were performed in the couple. aCGH analysis identified in the female partner two deletions involving genes associated to behavioral and neurodevelopment disorders. No clinically relevant alterations were identified in the husband. Interestingly, WES analysis identified in the male partner a pathogenic variant in the LPL gene that is emerging as a novel candidate gene for autism. This case shows that ECS may be useful in clinical contexts, especially when both the partners are analyzed before conception, thus allowing the estimation of their risk to transmit an inherited condition. On the other side, there are several concerns related to possible incidental findings and difficult-to-interpret results. Once these limits are defined by the establishment of specific guidelines, ECS may have a greater diffusion.

Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction

Recent advances and achievements of artificial intelligence (AI) as well as deep and graph learning models have established their usefulness in biomedical applications, especially in drug-drug interactions (DDIs). DDIs refer to a change in the effect of one drug to the presence of another drug in the human body, which plays an essential role in drug discovery and clinical research. DDIs prediction through traditional clinical trials and experiments is an expensive and time-consuming process. To correctly apply the advanced AI and deep learning, the developer and user meet various challenges such as the availability and encoding of data resources, and the design of computational methods. This review summarizes chemical structure based, network based, natural language processing based and hybrid methods, providing an updated and accessible guide to the broad researchers and development community with different domain knowledge. We introduce widely used molecular representation and describe the theoretical frameworks of graph neural network models for representing molecular structures. We present the advantages and disadvantages of deep and graph learning methods by performing comparative experiments. We discuss the potential technical challenges and highlight future directions of deep and graph learning models for accelerating DDIs prediction.

Screening autism-associated environmental factors in differentiating human neural progenitors with fractional factorial design-based transcriptomics

Research continues to identify genetic variation, environmental exposures, and their mixtures underlying different diseases and conditions. There is a need for screening methods to understand the molecular outcomes of such factors. Here, we investigate a highly efficient and multiplexable, fractional factorial experimental design (FFED) to study six environmental factors (lead, valproic acid, bisphenol A, ethanol, fluoxetine hydrochloride and zinc deficiency) and four human induced pluripotent stem cell line derived differentiating human neural progenitors. We showcase the FFED coupled with RNA-sequencing to identify the effects of low-grade exposures to these environmental factors and analyse the results in the context of autism spectrum disorder (ASD). We performed this after 5-day exposures on differentiating human neural progenitors accompanied by a layered analytical approach and detected several convergent and divergent, gene and pathway level responses. We revealed significant upregulation of pathways related to synaptic function and lipid metabolism following lead and fluoxetine exposure, respectively. Moreover, fluoxetine exposure elevated several fatty acids when validated using mass spectrometry-based metabolomics. Our study demonstrates that the FFED can be used for multiplexed transcriptomic analyses to detect relevant pathway-level changes in human neural development caused by low-grade environmental risk factors. Future studies will require multiple cell lines with different genetic backgrounds for characterising the effects of environmental exposures in ASD.

DNA-framework-based multidimensional molecular classifiers for cancer diagnosis

A molecular classification of diseases that accurately reflects clinical behaviour lays the foundation of precision medicine. The development of in silico classifiers coupled with molecular implementation based on DNA reactions marks a key advance in more powerful molecular classification, but it nevertheless remains a challenge to process multiple molecular datatypes. Here we introduce a DNA-encoded molecular classifier that can physically implement the computational classification of multidimensional molecular clinical data. To produce unified electrochemical sensing signals across heterogeneous molecular binding events, we exploit DNA-framework-based programmable atom-like nanoparticles with n valence to develop valence-encoded signal reporters that enable linearity in translating virtually any biomolecular binding events to signal gains. Multidimensional molecular information in computational classification is thus precisely assigned weights for bioanalysis. We demonstrate the implementation of a molecular classifier based on programmable atom-like nanoparticles to perform biomarker panel screening and analyse a panel of six biomarkers across three-dimensional datatypes for a near-deterministic molecular taxonomy of prostate cancer patients.

Interactions between the lipidome and genetic and environmental factors in autism

Autism omics research has historically been reductionist and diagnosis centric, with little attention paid to common co-occurring conditions (for example, sleep and feeding disorders) and the complex interplay between molecular profiles and neurodevelopment, genetics, environmental factors and health. Here we explored the plasma lipidome (783 lipid species) in 765 children (485 diagnosed with autism spectrum disorder (ASD)) within the Australian Autism Biobank. We identified lipids associated with ASD diagnosis (n = 8), sleep disturbances (n = 20) and cognitive function (n = 8) and found that long-chain polyunsaturated fatty acids may causally contribute to sleep disturbances mediated by the FADS gene cluster. We explored the interplay of environmental factors with neurodevelopment and the lipidome, finding that sleep disturbances and unhealthy diet have a convergent lipidome profile (with potential mediation by the microbiome) that is also independently associated with poorer adaptive function. In contrast, ASD lipidome differences were accounted for by dietary differences and sleep disturbances. We identified a large chr19p13.2 copy number variant genetic deletion spanning the LDLR gene and two high-confidence ASD genes (ELAVL3 and SMARCA4) in one child with an ASD diagnosis and widespread low-density lipoprotein-related lipidome derangements. Lipidomics captures the complexity of neurodevelopment, as well as the biological effects of conditions that commonly affect quality of life among autistic people.

A computational framework of routine test data for the cost-effective chronic disease prediction

Chronic diseases, because of insidious onset and long latent period, have become the major global disease burden. However, the current chronic disease diagnosis methods based on genetic markers or imaging analysis are challenging to promote completely due to high costs and cannot reach universality and popularization. This study analyzed massive data from routine blood and biochemical test of 32 448 patients and developed a novel framework for cost-effective chronic disease prediction with high accuracy (AUC 87.32%). Based on the best-performing XGBoost algorithm, 20 classification models were further constructed for 17 types of chronic diseases, including 9 types of cancers, 5 types of cardiovascular diseases and 3 types of mental illness. The highest accuracy of the model was 90.13% for cardia cancer, and the lowest was 76.38% for rectal cancer. The model interpretation with the SHAP algorithm showed that CREA, R-CV, GLU and NEUT% might be important indices to identify the most chronic diseases. PDW and R-CV are also discovered to be crucial indices in classifying the three types of chronic diseases (cardiovascular disease, cancer and mental illness). In addition, R-CV has a higher specificity for cancer, ALP for cardiovascular disease and GLU for mental illness. The association between chronic diseases was further revealed. At last, we build a user-friendly explainable machine-learning-based clinical decision support system (DisPioneer: http://bioinfor.imu.edu.cn/dispioneer) to assist in predicting, classifying and treating chronic diseases. This cost-effective work with simple blood tests will benefit more people and motivate clinical implementation and further investigation of chronic diseases prevention and surveillance program.

Differentiated Approach to Pharmacotherapy of Autism Spectrum Disorders: Biochemical Aspects

Autism Spectrum Disorders (ASD) are highly heterogeneous neurodevelopmental disorders caused by a complex interaction of numerous genetic and environmental factors and leading to deviations in the nervous system formation at the very early developmental stages. Currently, there are no accepted pharmacological treatments for the so-called core symptoms of ASD, such as social communication disorders and restricted and repetitive behavior patterns. Lack of knowledge about biological basis of ASD, absence of the clinically significant biochemical parameters reflecting abnormalities in the signaling cascades controlling the nervous system development and functioning, and lack of methods for selection of clinically and biologically homogeneous subgroups are considered as causes for the failure of clinical trials of ASD pharmacotherapy. This review considers the possibilities of applying differentiated clinical and biological approaches to the targeted search for ASD pharmacotherapy with emphasis on biochemical markers associated with ASD and attempts to stratify patients by biochemical parameters. The use of such approach as "the target-oriented therapy and assessment of the target status before and during the treatment to identify patients with a positive response to treatment" is discussed using the published results of clinical trials as examples. It is concluded that identification of biochemical parameters for selection of the distinct subgroups among the ASD patients requires research on large samples reflecting clinical and biological diversity of the patients with ASD, and use of unified approaches for such studies. An integrated approach, including clinical observation, clinical-psychological assessment of the patient behavior, study of medical history and description of individual molecular profiles should become a new strategy for stratifying patients with ASD for clinical pharmacotherapeutic trials, as well as for evaluating their efficiency.

Translating precision medicine for autism spectrum disorder: A pressing need

Autism spectrum disorder (ASD) is a heterogenous group of neurodevelopmental disorders (NDDs) with a high unmet medical need. Currently, ASD is diagnosed according to behavior-based criteria that overlook clinical and genomic heterogeneity, thus repeatedly resulting in failed clinical trials. Here, we summarize the scientific evidence pointing to the pressing need to create a precision medicine framework for ASD and other NDDs. We discuss the role of omics and systems biology to characterize more homogeneous disease subtypes with different underlying pathophysiological mechanisms and to determine corresponding tailored treatments. Finally, we provide recent initiatives towards tackling the complexity in NDDs for precision medicine and cost-effective drug discovery.

Accelerating Food Allergy Research: Need for a Data Commons

Food allergy is a significant health problem affecting approximately 8% of children and 11% of adults in the United States. It exhibits all the characteristics of a "complex" genetic trait; therefore, it is necessary to look at very large numbers of patients, far more than exist at any single organization, to eliminate gaps in the current understanding of this complex chronic disorder. Advances may be achieved by bringing together food allergy data from large numbers of patients into a Data Commons, a secure and efficient platform for researchers, comprising standardized data, available in a common interface for download and/or analysis, in accordance with the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. Prior data commons initiatives indicate that research community consensus and support, formal food allergy ontology, data standards, an accepted platform and data management tools, an agreed upon infrastructure, and trusted governance are the foundation of any successful data commons. In this article, we will present the justification for the creation of a food allergy data commons and describe the core principles that can make it successful and sustainable.

Building a knowledge graph to enable precision medicine

Developing personalized diagnostic strategies and targeted treatments requires a deep understanding of disease biology and the ability to dissect the relationship between molecular and genetic factors and their phenotypic consequences. However, such knowledge is fragmented across publications, non-standardized repositories, and evolving ontologies describing various scales of biological organization between genotypes and clinical phenotypes. Here, we present PrimeKG, a multimodal knowledge graph for precision medicine analyses. PrimeKG integrates 20 high-quality resources to describe 17,080 diseases with 4,050,249 relationships representing ten major biological scales, including disease-associated protein perturbations, biological processes and pathways, anatomical and phenotypic scales, and the entire range of approved drugs with their therapeutic action, considerably expanding previous efforts in disease-rooted knowledge graphs. PrimeKG contains an abundance of 'indications', 'contradictions', and 'off-label use' drug-disease edges that lack in other knowledge graphs and can support AI analyses of how drugs affect disease-associated networks. We supplement PrimeKG's graph structure with language descriptions of clinical guidelines to enable multimodal analyses and provide instructions for continual updates of PrimeKG as new data become available.

A comprehensive SARS-CoV-2-human protein-protein interactome reveals COVID-19 pathobiology and potential host therapeutic targets

Studying viral-host protein-protein interactions can facilitate the discovery of therapies for viral infection. We use high-throughput yeast two-hybrid experiments and mass spectrometry to generate a comprehensive SARS-CoV-2-human protein-protein interactome network consisting of 739 high-confidence binary and co-complex interactions, validating 218 known SARS-CoV-2 host factors and revealing 361 novel ones. Our results show the highest overlap of interaction partners between published datasets and of genes differentially expressed in samples from COVID-19 patients. We identify an interaction between the viral protein ORF3a and the human transcription factor ZNF579, illustrating a direct viral impact on host transcription. We perform network-based screens of >2,900 FDA-approved or investigational drugs and identify 23 with significant network proximity to SARS-CoV-2 host factors. One of these drugs, carvedilol, shows clinical benefits for COVID-19 patients in an electronic health records analysis and antiviral properties in a human lung cell line infected with SARS-CoV-2. Our study demonstrates the value of network systems biology to understand human-virus interactions and provides hits for further research on COVID-19 therapeutics.

Inductively coupled plasma mass spectrometry based urine metallome to construct clinical decision models for autism spectrum disorder

BACKGROUND

The global prevalence of autism spectrum disorder (ASD) is on the rise, and high levels of exposure to toxic heavy metals may be associated with this increase. Urine analysis is a noninvasive method for investigating the accumulation and excretion of heavy metals. The aim of this study was to identify ASD-associated urinary metal markers.

METHODS

Overall, 70 children with ASD and 71 children with typical development (TD) were enrolled in this retrospective case-control study. In this metallomics investigation, inductively coupled plasma mass spectrometry was performed to obtain the urine profile of 27 metals.

RESULTS

Children with ASD could be distinguished from children with TD based on the urine metal profile, with ASD children showing an increased urine metal Shannon diversity. A metallome-wide association analysis was used to identify seven ASD-related metals in urine, with cobalt, aluminum, selenium, and lithium significantly higher, and manganese, mercury, and titanium significantly lower in the urine of children with ASD than in children with TD. The least absolute shrinkage and selection operator (LASSO) machine learning method was used to rank the seven urine metals in terms of their effect on ASD. On the basis of these seven urine metals, we constructed a LASSO regression model for ASD classification and found an area under the receiver operating characteristic curve of 0.913. We also constructed a clinical prediction model for ASD based on the seven metals that were different in the urine of children with ASD and found that the model would be useful for the clinical prediction of ASD risk.

CONCLUSIONS

The study findings suggest that altered urine metal concentrations may be an important risk factor for ASD, and we recommend further exploration of the mechanisms and clinical treatment measures for such alterations.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

Deep generative molecular design reshapes drug discovery

Recent advances and accomplishments of artificial intelligence (AI) and deep generative models have established their usefulness in medicinal applications, especially in drug discovery and development. To correctly apply AI, the developer and user face questions such as which protocols to consider, which factors to scrutinize, and how the deep generative models can integrate the relevant disciplines. This review summarizes classical and newly developed AI approaches, providing an updated and accessible guide to the broad computational drug discovery and development community. We introduce deep generative models from different standpoints and describe the theoretical frameworks for representing chemical and biological structures and their applications. We discuss the data and technical challenges and highlight future directions of multimodal deep generative models for accelerating drug discovery.

Machine Learning for Lung Cancer Diagnosis, Treatment, and Prognosis

The recent development of imaging and sequencing technologies enables systematic advances in the clinical study of lung cancer. Meanwhile, the human mind is limited in effectively handling and fully utilizing the accumulation of such enormous amounts of data. Machine learning-based approaches play a critical role in integrating and analyzing these large and complex datasets, which have extensively characterized lung cancer through the use of different perspectives from these accrued data. In this review, we provide an overview of machine learning-based approaches that strengthen the varying aspects of lung cancer diagnosis and therapy, including early detection, auxiliary diagnosis, prognosis prediction, and immunotherapy practice. Moreover, we highlight the challenges and opportunities for future applications of machine learning in lung cancer.

AGREEing on Clinical Practice Guidelines for Autism Spectrum Disorders in Children: A Systematic Review and Quality Assessment

Background: Autism spectrum disorder (ASD) is a multifaceted neurodevelopmental disorder requiring multimodal intervention and an army of multidisciplinary teams for a proper rehabilitation plan. Accordingly, multiple practice guidelines have been published for different disciplines. However, systematic evidence to detect and intervene must be updated regularly. Our main objective is to compare and summarize the recommendations made in the clinical practice guidelines (CPGs) for ASD in children released from November 2015 to March 2022. Methods: CPGs were subjected to a systematic review. We developed the inclusion and exclusion criteria and health-related questions, then searched and screened for CPGs utilizing bibliographic and CPG databases. Each of the CPGs used in the study were critically evaluated using the Appraisal of Guidelines for REsearch and Evaluation II (AGREE II) instrument. In a realistic comparison table, we summarized the recommendations. Results: Four eligible CPGs were appraised: Australian Autism CRC (ACRC); Ministry of Health New Zealand (NZ); National Institute for Health and Care Excellence (NICE); and Scottish Intercollegiate Guidelines Network, Healthcare Improvement Scotland (SIGN-HIS). The overall assessments of all four CPGs scored greater than 80%; these findings were consistent with the high scores in the six domains of AGREE II, including: (1) scope and purpose, (2) stakeholder involvement, (3) rigor of development, (4) clarity of presentation, (5) applicability, and (6) editorial independence domains. Domain (3) scored 84%, 93%, 86%, and 85%; domain (5) 92%, 89%, 54%, and 85%; and domain (6) 92%, 96%, 88%, and 92% for ACRC, NICE, NZ, and SIGN-HIS, respectively. Overall, there were no serious conflicts between the clinical recommendations of the four CPGs, but some were more comprehensive and elaborative than others. Conclusions: All four assessed evidence-based CPGs demonstrated high methodological quality and relevance for use in practice.

Factors associated with age of diagnosis of autism spectrum disorder among children in Saudi Arabia: new insights from a cross-sectional study

Objectives

Research examining the age of diagnosis of autism spectrum disorder (ASD) and its influencing factors mostly originate from developed Western countries, providing little to no systematic information about the understanding and management of ASD in the rest of the world. The present exploratory study examined the influence of child and family characteristics on the age of ASD diagnosis in Saudi Arabia.

Results

The median age at diagnosis was 3.0 years and was associated with some child and family characteristics. A 1 year increase in child’s age was associated with a 0.1 year increase in age of diagnosis (95% CI 0.05, 0.12). Children who did not respond to their name were diagnosed 0.3 years earlier than other children (95% CI − 0.60, − 0.05), and engaging in challenging behavior was associated with a 0.5 year increase in age of diagnosis (95% CI 0.20, 0.81). A lack of comorbidity was associated with a 0.6 year increase in the age of diagnosis compared to the diagnosis age of children with comorbidity (95% CI 0.13, 1.01). Finally, those residing outside of Saudi Arabia were diagnosed with ASD 0.9 years earlier than those residing in Saudi Arabia (95% CI − 0.171, − 0.11).

Supplementary Information

The online version contains supplementary material available at 10.1186/s13104-022-06035-x.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

C1q/TNF-related protein-1: Potential biomarker for early diagnosis of autism spectrum disorder

INTRODUCTION

Autism spectrum disorders (ASDs) are neurodevelopmental diseases characterized by communication inabilities, social interaction impairment, repetitive behavior, as well as learning problems. Although the exact mechanism underlying this disease is still obscure, researchers believe that several factors play a significant role in its development and pathogenesis. Some authors have reported an association between adipokines family and autism. C1q/TNF-related protein-1 (CTRP1) is a member of the adipokines family, and we hypothesized that this adipokine might have an influential role in the pathogenesis of ASDs. Since there is no specific marker for screening the disease, we evaluated CTRP1 as a potential marker for achieving this purpose.

METHODS

Blood samples were collected from 82 (41 ASDs boys, 41 healthy boys as controls) children aged 5-7 years old. CTRP1 gene expression and CTRP1 serum level were measured by quantitative realtime-PCR and enzyme-linked immunosorbent assay methods, respectively.

RESULTS

It was found that CTRP1 is significantly elevated in autistic children in comparison to healthy controls, both at the gene expression level, as well as at the serum level; demonstrating a good diagnostic value with a good range of sensitivity and specificity for detecting ASDs.

CONCLUSION

CTRP1 expression is elevated in ASDs boys aged 5-7 years old, suggesting a role for this adipokine in ASDs pathophysiology. Also, receiver operating characteristic curve analyses revealed that this adipokine could be utilized as a diagnostic biomarker for differentiating ASDs patients from healthy individuals along with other recently proposed biomarkers.

CTRP3 as a novel biomarker in the plasma of Saudi children with autism

BACKGROUND

C1q/tumor necrosis factor-related protein-3 (CTRP3) has diverse functions: anti-inflammation, metabolic regulation, and protection against endothelial dysfunction.

METHODS

The plasma level of CTRP3 in autistic patients (n = 32) was compared to that in controls (n = 37) using ELISA.

RESULTS

CTRP3 was higher (24.7% with P < 0.05) in autistic patients than in controls. No association was observed between CTRP3 and the severity of the disorder using the Childhood Autism Rating Scale (CARS). A positive correlation between CARs and the age of patients was reported. Receiver operating characteristic (ROC) analysis demonstrated a low area under the curve (AUC) for all patients (0.636). Low AUCs were also found in the case of severe patients (0.659) compared to controls, but both values were statistically significant (P ≤ 0.05). Despite the small sample size, we are the first to find an association between CTRP3 and autism spectrum disorder (ASD).

Diagnostic shifts in autism spectrum disorder can be linked to the fuzzy nature of the diagnostic boundary: a data-driven approach

BACKGROUND

Diagnostic shifts at early ages may provide invaluable insights into the nature of separation between autism spectrum disorder (ASD) and typical development. Recent conceptualizations of ASD suggest the condition is only fuzzily separated from non-ASD, with intermediate cases between the two. These intermediate cases may shift along a transition region over time, leading to apparent instability of diagnosis.

METHODS

We used a cohort of children with high ASD risk, by virtue of having an older sibling with ASD, assessed at 24 months (N = 212) and 36 months (N = 191). We applied machine learning to empirically characterize the classification boundary between ASD and non-ASD, using variables quantifying developmental and adaptive skills. We computed the distance of children to the classification boundary.

RESULTS

Children who switched diagnostic labels from 24 to 36 months, in both directions, (dynamic group) had intermediate phenotypic profiles. They were closer to the classification boundary compared to children who had stable diagnoses, both at 24 months (Cohen's d = .52) and at 36 months (d = .75). The magnitude of change in distance between the two time points was similar for the dynamic and stable groups (Cohen's d = .06), and diagnostic shifts were not associated with a large change. At the individual level, a few children in the dynamic group showed substantial change.

CONCLUSIONS

Our results suggested that a diagnostic shift was largely due to a slight movement within a transition region between ASD and non-ASD. This fact highlights the need for more vigilant surveillance and intervention strategies. Young children with intermediate phenotypes may have an increased susceptibility to gain or lose their diagnosis at later ages, calling attention to the inherently dynamic nature of early ASD diagnoses.

Sterol and lipid analyses identifies hypolipidemia and apolipoprotein disorders in autism associated with adaptive functioning deficits

An improved understanding of sterol and lipid abnormalities in individuals with autism spectrum disorder (ASD) could lead to personalized treatment approaches. Toward this end, in blood, we identified reduced synthesis of cholesterol in families with ≥2 children with ASD participating with the Autism Genetic Resource Exchange (AGRE), as well as reduced amounts of high-density lipoprotein cholesterol (HDL), apolipoprotein A1 (ApoA1) and apolipoprotein B (ApoB), with 19.9% of the subjects presenting with apolipoprotein patterns similar to hypolipidemic clinical syndromes and 30% with either or both ApoA1 and ApoB less than the fifth centile. Subjects with levels less than the fifth centile of HDL or ApoA1 or ApoA1 + ApoB had lower adaptive functioning than other individuals with ASD, and hypocholesterolemic subjects had apolipoprotein deficits significantly divergent from either typically developing individuals participating in National Institutes of Health or the National Health and Nutrition Examination Survey III.

The promise of precision medicine in autism

Autism spectrum disorder (ASD) is a clinically and etiologically diverse developmental condition characterized by diminished social interactions, impaired communication, and repetitive and/or restrictive behaviors. Recent advances in ASD genetics pave the way for implementation of precision medicine in clinical management of autism.

Finding a new balance between a genetics-first or phenotype-first approach to the study of disease

Successes in neuroscience using a genetics-first approach to characterizing disorders such as autism have eclipsed the scientific and clinical value of a comprehensive phenotype-first-clinical or molecular-approach. Recent high-throughput phenotyping techniques using machine learning, electronic medical records, and even administrative databases show the value of a synthesis between the two approaches.

Unveiling the Pathogenesis of Psychiatric Disorders Using Network Models

Psychiatric disorders are complex brain disorders with a high degree of genetic heterogeneity, affecting millions of people worldwide. Despite advances in psychiatric genetics, the underlying pathogenic mechanisms of psychiatric disorders are still largely elusive, which impedes the development of novel rational therapies. There has been accumulating evidence suggesting that the genetics of complex disorders can be viewed through an omnigenic lens, which involves contextualizing genes in highly interconnected networks. Thus, applying network-based multi-omics integration methods could cast new light on the pathophysiology of psychiatric disorders. In this review, we first provide an overview of the recent advances in psychiatric genetics and highlight gaps in translating molecular associations into mechanistic insights. We then present an overview of network methodologies and review previous applications of network methods in the study of psychiatric disorders. Lastly, we describe the potential of such methodologies within a multi-tissue, multi-omics approach, and summarize the future directions in adopting diverse network approaches.

Paving the Way toward Personalized Medicine: Current Advances and Challenges in Multi-OMICS Approach in Autism Spectrum Disorder for Biomarkers Discovery and Patient Stratification

Autism spectrum disorder (ASD) is a multifactorial neurodevelopmental disorder characterized by impairments in two main areas: social/communication skills and repetitive behavioral patterns. The prevalence of ASD has increased in the past two decades, however, it is not known whether the evident rise in ASD prevalence is due to changes in diagnostic criteria or an actual increase in ASD cases. Due to the complexity and heterogeneity of ASD, symptoms vary in severity and may be accompanied by comorbidities such as epilepsy, attention deficit hyperactivity disorder (ADHD), and gastrointestinal (GI) disorders. Identifying biomarkers of ASD is not only crucial to understanding the biological characteristics of the disorder, but also as a detection tool for its early screening. Hence, this review gives an insight into the main areas of ASD biomarker research that show promising findings. Finally, it covers success stories that highlight the importance of precision medicine and the current challenges in ASD biomarker discovery studies.

Identifying Subgroups of Patients With Autism by Gene Expression Profiles Using Machine Learning Algorithms

Objectives: The identification of subgroups of autism spectrum disorder (ASD) may partially remedy the problems of clinical heterogeneity to facilitate the improvement of clinical management. The current study aims to use machine learning algorithms to analyze microarray data to identify clusters with relatively homogeneous clinical features. Methods: The whole-genome gene expression microarray data were used to predict communication quotient (SCQ) scores against all probes to select differential expression regions (DERs). Gene set enrichment analysis was performed for DERs with a fold-change >2 to identify hub pathways that play a role in the severity of social communication deficits inherent to ASD. We then used two machine learning methods, random forest classification (RF) and support vector machine (SVM), to identify two clusters using DERs. Finally, we evaluated how accurately the clusters predicted language impairment. Results: A total of 191 DERs were initially identified, and 54 of them with a fold-change >2 were selected for the pathway analysis. Cholesterol biosynthesis and metabolisms pathways appear to act as hubs that connect other trait-associated pathways to influence the severity of social communication deficits inherent to ASD. Both RF and SVM algorithms can yield a classification accuracy level >90% when all 191 DERs were analyzed. The ASD subtypes defined by the presence of language impairment, a strong indicator for prognosis, can be predicted by transcriptomic profiles associated with social communication deficits and cholesterol biosynthesis and metabolism. Conclusion: The results suggest that both RF and SVM are acceptable options for machine learning algorithms to identify AD subgroups characterized by clinical homogeneity related to prognosis.

Developmental and social deficits and enhanced sensitivity to prenatal chlorpyrifos in PON1-/- mouse pups and adults

The levels and activity of the enzyme paraoxonase 1 affect the vulnerability to the teratogenic effects of organophosphate pesticides. Mutant mice lacking the gene for paraoxonase1 (PON1^-/-) are more susceptible to the toxic effects of chlorpyrifos, and were hypothesized to be more vulnerable to social behavior deficits induced by exposure to chlorpyrifos during gestation. Three experiments were performed comparing PON1^-/- mice to PON1^+/+ mice born to dams treated with 0.5 mg/kg chlorpyrifos or cornoil vehicle on gestational days 12–15. Chlofpyrifos-exposed male PON1^-/- mouse pups had delayed development of reflexes in in the first experiment. In the second experiment, adult male and female PON1^-/- mice and the female PON1^+/+ mice all displayed lower social preference than the male vehicle-treated PON1^+/+ mice. The PON1^-/- mice and the female PON1^+/+ mice displayed lower social preference compared to the PON1^+/+ male mice. Male adult mice that had been exposed in utero to chlorpyrifos showed less conditioned social preference regardless of genotype. In the third study, the delayed reflex development was replicated in male and female PON1^-/- mice, but chlorpyrifos did not augment this effect. Nest Odor Preference, a test of early social attachment to dam and siblings, was lower in PON1^-/- mouse pups compared to PON1^+/+ pups. This study shows for the first time that PON1^-/- mice have a behavioral phenotype that indicates impaired reflex development and social behavior. Chlorpyrifos exposure during gestation tended to augment some of these effects.