Predicting the Risk Genes of Autism Spectrum Disorders

Lin, Yen-Ching; Sathipati, Srinivasulu Yerukala; Ho, Shinn-Ying

doi:10.3389/fgene.2021.665469

Cited by 10 publications

(8 citation statements)

References 72 publications

(83 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…12, indicates that high specificity refers to a lower error rate. (12) specificity = number of TN number of TN + number of FP Fig. 6 The performance of different classifiers evaluated on SFARI dataset using different semantic similarity measures in terms of precision Fig.…”

Section: Performance Measuresmentioning

confidence: 99%

“…A support vector machine model was built in [ 12 ] to identify ASD risk genes and their influence on the temporospatial areas in the brain at different times using gene expression. Some researchers utilized deep learning techniques in gene prediction models [ 13 ], the DeepHE model was proposed to train a multilayer network using DNA sequence data and the data from the protein-to-protein network (PPI).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HEC-ASD: a hybrid ensemble-based classification model for predicting autism spectrum disorder disease genes

2022

View full text Add to dashboard Cite

Purpose Autism spectrum disorder (ASD) is the most prevalent disease today. The causes of its infection may be attributed to genetic causes by 80% and environmental causes by 20%. In spite of this, the majority of the current research is concerned with environmental causes, and the least proportion with the genetic causes of the disease. Autism is a complex disease, which makes it difficult to identify the genes that cause the disease. Methods Hybrid ensemble-based classification (HEC-ASD) model for predicting ASD genes using gradient boosting machines is proposed. The proposed model utilizes gene ontology (GO) to construct a gene functional similarity matrix using hybrid gene similarity (HGS) method. HGS measures the semantic similarity between genes effectively. It combines the graph-based method, such as Wang method with the number of directed children’s nodes of gene term from GO. Moreover, an ensemble gradient boosting classifier is adapted to enhance the prediction of genes forming a robust classification model. Results The proposed model is evaluated using the Simons Foundation Autism Research Initiative (SFARI) gene database. The experimental results are promising as they improve the classification performance for predicting ASD genes. The results are compared with other approaches that used gene regulatory network (GRN), protein to protein interaction network (PPI), or GO. The HEC-ASD model reaches the highest prediction accuracy of 0.88% using ensemble learning classifiers. Conclusion The proposed model demonstrates that ensemble learning technique using gradient boosting is effective in predicting autism spectrum disorder genes. Moreover, the HEC-ASD model utilized GO rather than using PPI network and GRN.

show abstract

Section: Performance Measuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HEC-ASD: a hybrid ensemble-based classification model for predicting autism spectrum disorder disease genes

2022

View full text Add to dashboard Cite

show abstract

“…The main limitation of this approach is the significant clinical and biological heterogeneity of subjects with ASD [ 69 , 70 ]. Molecular genetics studies have identified a few hundred ASD risk genes [ 71 , 72 ] that may significantly amplify the difficulties in identifying reliable biomarkers for the disorder. ASD susceptibility genes, however, appear to converge in a discrete number of biological pathways [ 72 ]: several lines of evidence suggest that many of these biological pathways (and thus many genes) are shared, at least in children and adolescents, among different psychiatric disorders [ 73 , 74 , 75 , 76 ].…”

Section: Conclusion and Limitations Of The Studymentioning

confidence: 99%

1H-NMR-Based Metabolomics in Autism Spectrum Disorder and Pediatric Acute-Onset Neuropsychiatric Syndrome

Gagliano

Murgia

Capodiferro

et al. 2022

JCM

View full text Add to dashboard Cite

We recently described a unique plasma metabolite profile in subjects with pediatric acute-onset neuropsychiatric syndrome (PANS), suggesting pathogenic models involving specific patterns of neurotransmission, neuroinflammation, and oxidative stress. Here, we extend the analysis to a group of patients with autism spectrum disorder (ASD), as a consensus has recently emerged around its immune-mediated pathophysiology with a widespread involvement of brain networks. This observational case-control study enrolled patients referred for PANS and ASD from June 2019 to May 2020, as well as neurotypical age and gender-matched control subjects. Thirty-four PANS outpatients, fifteen ASD outpatients, and twenty-five neurotypical subjects underwent physical and neuropsychiatric evaluations, alongside serum metabolomic analysis with 1H-NMR. In supervised models, the metabolomic profile of ASD was significantly different from controls (p = 0.0001), with skewed concentrations of asparagine, aspartate, betaine, glycine, lactate, glucose, and pyruvate. Metabolomic separation was also observed between PANS and ASD subjects (p = 0.02), with differences in the concentrations of arginine, aspartate, betaine, choline, creatine phosphate, glycine, pyruvate, and tryptophan. We confirmed a unique serum metabolomic profile of PANS compared with both ASD and neurotypical subjects, distinguishing PANS as a pathophysiological entity per se. Tryptophan and glycine appear as neuroinflammatory fingerprints of PANS and ASD, respectively. In particular, a reduction in glycine would primarily affect NMDA-R excitatory tone, overall impairing downstream glutamatergic, dopaminergic, and GABAergic transmissions. Nonetheless, we found metabolomic similarities between PANS and ASD that suggest a putative role of N-methyl-D-aspartate receptor (NMDA-R) dysfunction in both disorders. Metabolomics-based approaches could contribute to the identification of novel ASD and PANS biomarkers.

show abstract

“…In the largest study to date, researchers analysed multiple generations from over two million families located in Denmark, Finland, Sweden, Israel, and Western Australia, and found the occurrence of ASD could mainly be attributed to genetic factors, that is about 80% of the time (Bai et al, 2019). There are currently no definitive genetic markers identified, but the online human gene database, GeneCards, lists 7,211 genes potentially related to ASD (GeneCards, 2021;Lin et al, 2021). The most frequent mutation associated with the neuropathology of ASD involves a mutation in the SHANK3 protein that encodes for signalling molecules present in postsynaptic receptors (Jaramillo et al, 2020).…”

Section: Aetiologymentioning

confidence: 99%

“…The most frequent mutation associated with the neuropathology of ASD involves a mutation in the SHANK3 protein that encodes for signalling molecules present in postsynaptic receptors (Jaramillo et al, 2020). A mutation of this protein inhibits proper signalling between neurons, leading to atypical structural development and functioning of neurons (Amaral, 2017;Lin et al, 2021;Lutz et al, 2020).…”

Section: Aetiologymentioning

confidence: 99%

Using an Antecedent Prompting Method to Teach an Extended Communication Sequence to Children with Autism Using a Speech Generating Device

Sawchak¹

View full text Add to dashboard Cite

<p>Children with autism spectrum disorder often have severely limited speech and language development and these children might therefore benefit from alternative and augmentative communication (AAC) intervention. While there is an extensive literature demonstrating effective procedures for teaching children with developmental disabilities and severe communication to use AAC, studies in this area have mainly focused on teaching relatively short and single-function communicative exchanges, such as teaching the person to request access to a preferred object by producing one communication act, such as by selecting a single symbol on a speech-generating device. While requesting access to a preferred object is useful, it would also seem important for children to be able to engage in more extended and multi-functional communication exchanges. However, there is little research into the development and evaluation of procedures for teaching more extended, multi-function communication sequences, such as teaching the child to (a) first greet his or her listener, (b) then make a request for a general object (“I want a snack.”), (c) then make a request for a specific object (“I want popcorn.”), and (d) then thank the listener for providing the requesting item. Furthermore, there is no published literature teaching communicative behaviours on a speech-generating device using the antecedent prompting procedure. The aim of this research is to determine whether children with developmental disabilities and severe communication impairment can learn to produce such extended and multi-functional communication sequences by systematically implementing the antecedent prompting procedure with an iPad-based speech-generating device. Study 1 used a multiple baseline design to evaluate the effectiveness of the antecedent prompt to teach a 4-step communicative exchange on an iPad®-based speech-generating device set with a progressive display. Participants were required to discriminate between two icons at a time, and the progressive display guided them through four screens, or the four steps, of the communicative exchange. All five participants (4 boys, 1 girl, aged 6 to 10 years) who participated in this study mastered the 4-step communicative exchange in four sessions on average. Study 2 was identical to Study 1, except the iPad®-based speech-generating device was set with a static screen. Participants (4 boys, aged 6 to 10 years) were required to discriminate between 12 icons simultaneously and select the appropriate icon for each step of the exchange. Of the participants, three were performing the sequence correctly after one session on average, one student did not reach mastery criteria but the average number of his communicative exchanges per interaction increased. Considering the positive outcomes and rapid rate of acquisition from both studies, future research should consider implementing the antecedent prompt when teaching communication interventions to minimally verbal children with autism on a speech-generating device.</p>

show abstract

Predicting the Risk Genes of Autism Spectrum Disorders

Cited by 10 publications

References 72 publications

HEC-ASD: a hybrid ensemble-based classification model for predicting autism spectrum disorder disease genes

HEC-ASD: a hybrid ensemble-based classification model for predicting autism spectrum disorder disease genes

1H-NMR-Based Metabolomics in Autism Spectrum Disorder and Pediatric Acute-Onset Neuropsychiatric Syndrome

Using an Antecedent Prompting Method to Teach an Extended Communication Sequence to Children with Autism Using a Speech Generating Device

Contact Info

Product

Resources

About