Putative synaptic genes defined from a Drosophila whole body developmental transcriptome by a machine learning approach

Obregón, Flavio Pazos; Papalardo, Cecilia; Castro, Sebastián; Guerberoff, Gustavo; Cantera, Rafael

doi:10.1186/s12864-015-1888-3

“…A catalogue obtained by training an ensemble machine-learning model that assigned each Drosophila protein-coding gene a probability of having synaptic function was published four years ago (6). Of note, the model was based exclusively on a whole-body temporal transcriptome.…”

Section: Discussionmentioning

confidence: 99%

“…We excluded 1,756 genes that show transcript levels above zero only during adult life and normalized each gene's temporal series dividing it by its maximum value, thus obtaining for each gene a series of 24 values oscillating between 0 and 1. More details in (6).…”

Section: Datamentioning

confidence: 99%

“…The top-performing algorithms, architectures and training schemes are function-specific and context-dependent (5). In a previous study (6), we implemented an ensemble machine learning model that assigned a probability of being a "synaptic gene" to each protein-coding gene of Drosophila melanogaster. The features to infer the synaptic function were the whole-body transcription levels of all protein-coding genes at 24 developmental stages, published by the modENCODE project (7).…”

Section: Introductionmentioning

confidence: 99%

“…After an exhaustive bibliographic review, a set of genes for which a function in synapse formation and/or maturation, and/or neurotransmission, and/or plasticity and/or maintenance had been experimentally demonstrated was selected as a positive example and included in the training set. Genes fulfilling any of two biological criteria defined ad hoc were selected as negatives examples (6). (Additional file 1).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An improved catalogue of putative synaptic genes defined exclusively by temporal transcription profiles through an ensemble machine learning approach

Obregón

¹

,

Palazzo²,

Soto

³

et al. 2019

Preprint

Self Cite

0

View full text Add to dashboard Cite

Background . Assembly and function of neuronal synapses require the coordinated expression of a yet undetermined set of genes. Previously, we had trained an ensemble machine learning model to assign a probability of having synaptic function to every protein-coding gene in Drosophila melanogaster. This approach resulted in the publication of a catalogue of 893 genes which we postulated to be very enriched in genes with a still undocumented synaptic function. Since then, the scientific community has experimentally identified 79 new synaptic genes. Here we use these new empirical data to evaluate our original prediction. We also implement a series of changes to the training scheme of our model and using the new data we demonstrate that this improves its predictive power. Finally, we added the new synaptic genes to the training set and trained a new model, obtaining a new, enhanced catalogue of putative synaptic genes. Results . The retrospective analysis demonstrate that our original catalogue was significantly enriched in new synaptic genes. When the changes to the training scheme were implemented using the original training set we obtained even higher enrichment. Finally, applying the new training scheme with a training set including the 79 new synaptic genes, resulted in an enhanced catalogue of putative synaptic genes. Here we present this new catalogue and announce that a regularly updated version will be available online at: http://synapticgenes.bnd.edu.uy Conclusions . We show that training an ensemble of machine learning classifiers solely with the whole-body temporal transcription profiles of known synaptic genes resulted in a catalogue with a significant enrichment in undiscovered synaptic genes. Using new empirical data provided by the scientific community, we validated our original approach, improved our model an obtained an arguably more precise prediction. This approach reduces the number of genes to be tested through hypothesis-driven experimentation and will facilitate our understanding of neuronal function. Availability : http://synapticgenes.bnd.edu.uy

show abstract

“…Since the biological roles of the vast majority of known amino acid sequences remain partly or are function-specific and context-dependent [5]. In a previous study [6], we implemented an ensemble machine learning model that assigned a probability of being a "synaptic gene" to each protein-coding gene of Drosophila melanogaster. The features to infer the synaptic function were the whole-body transcription levels of all protein-coding genes at 24 developmental stages, published by the modENCODE project [7].…”

Section: Introductionmentioning

confidence: 99%

An improved catalogue of putative synaptic genes defined exclusively by temporal transcription profiles through an ensemble machine learning approach

Obregón

¹

,

Palazzo²,

Soto

³

et al. 2019

Preprint

Self Cite

0

View full text Add to dashboard Cite

Background . Assembly and function of neuronal synapses require the coordinated expression of a yet undetermined set of genes. Previously, we had trained an ensemble machine learning model to assign a probability of having synaptic function to every protein-coding gene in Drosophila melanogaster. This approach resulted in the publication of a catalogue of 893 genes which we postulated to be very enriched in genes with a still undocumented synaptic function. Since then, the scientific community has experimentally identified 79 new synaptic genes. Here we use these new empirical data to evaluate our original prediction. We also implement a series of changes to the training scheme of our model and using the new data we demonstrate that this improves its predictive power. Finally, we added the new synaptic genes to the training set and trained a new model, obtaining a new, enhanced catalogue of putative synaptic genes. Results . The retrospective analysis demonstrate that our original catalogue was significantly enriched in new synaptic genes. When the changes to the training scheme were implemented using the original training set we obtained even higher enrichment. Finally, applying the new training scheme with a training set including the 79 new synaptic genes, resulted in an enhanced catalogue of putative synaptic genes. Here we present this new catalogue and announce that a regularly updated version will be available online at: http://synapticgenes.bnd.edu.uy Conclusions . We show that training an ensemble of machine learning classifiers solely with the whole-body temporal transcription profiles of known synaptic genes resulted in a catalogue with a significant enrichment in undiscovered synaptic genes. Using new empirical data provided by the scientific community, we validated our original approach, improved our model an obtained an arguably more precise prediction. This approach reduces the number of genes to be tested through hypothesis-driven experimentation and will facilitate our understanding of neuronal function. Availability : http://synapticgenes.bnd.edu.uy

show abstract

A novel microduplication in INPP5A segregates with schizophrenia spectrum disorder in the family of a patient with both childhood onset schizophrenia and autism spectrum disorder

Fernandez

¹

,

Drozd

²

,

Thümmler

³

et al. 2021

American J of Med Genetics Pt A

2

0

View full text Add to dashboard Cite

Childhood‐Onset Schizophrenia (COS) is a very rare and severe psychiatric disorder defined by adult schizophrenia symptoms occurring before the age of 13. We report a microduplication in the 10q26.3 region including part of the Inositol Polyphosphate‐5‐Phosphatase A (INPP5A) gene that segregates with Schizophrenia Spectrum Disorders (SSDs) in the family of a female patient affected by both COS and Autism Spectrum Disorder (ASD). Phenotyping and genotyping (including CGH‐array) were performed for mother, healthy sister, and affected child according to the GenAuDiss protocol (NCT02565524). The duplication size is 324 kb and is present in a patient with COS and in her mother with SSD, but not in the patient's healthy sister. INPP5A encodes a membrane‐associated 43 kDa type I inositol 1,4,5‐trisphosphate (InsP3) 5‐phosphatase. This protein is found both in mouse and human brains and we found that its Drosophila homologue 5PtaseI is specifically expressed in the central nervous system. Hydrolyzed products from InsP3 5‐phosphatases mobilize intracellular calcium, which is relevant for dendritic spine morphogenesis in neurons and altered in both schizophrenia and ASD. These may constitute arguments in favor of this gene alteration in the pathophysiology of COS.

show abstract

Putative synaptic genes defined from a Drosophila whole body developmental transcriptome by a machine learning approach

Cited by 19 publications

References 66 publications

An improved catalogue of putative synaptic genes defined exclusively by temporal transcription profiles through an ensemble machine learning approach

An improved catalogue of putative synaptic genes defined exclusively by temporal transcription profiles through an ensemble machine learning approach

An improved catalogue of putative synaptic genes defined exclusively by temporal transcription profiles through an ensemble machine learning approach

A novel microduplication in INPP5A segregates with schizophrenia spectrum disorder in the family of a patient with both childhood onset schizophrenia and autism spectrum disorder

Contact Info

Product

Resources

About