This preprint is under consideration at Human Genomics. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Primary research
Christopher Toh
University of California Irvine
Corresponding Author
ORCiD: https://orcid.org/0000-0003-3298-9055
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Introduction
Schizophrenia is a neurological disorder that often manifests itself as a combination of psychotic symptoms such as delusions, hallucinations, and disorganized cognitive functions. Several lines of evidence indicate that schizophrenia has a genetic component, however it cannot be isolated to a single gene. We set out to determine how well one could predict that a person will develop schizophrenia based on their germ line DNA.
Methods
We compared 1129 people from the UK Biobank dataset who had a diagnosis of schizophrenia to an equal number of age matched people drawn from the general UK Biobank population. For each person, we constructed a profile consisting of a sequence of numbers. Each number characterized the length of a segment of one of their chromosomes. We tested several machine learning algorithms using the h2o.ai framework to determine which was most effective in predicting schizophrenia. We also tested whether there was any improvement in prediction by breaking the chromosomes into smaller chunks. We used SHAP values to better understand features important to the predictive model.
Results
We found that the stacked ensemble, a combination of four different machine learning algorithms, performed best with an area under the receiver operating characteristic curve (AUC) of 0.583 (95% CI 0.581-0.586). We noted an increase in the AUC by breaking the chromosomes into smaller chunks for analysis. Using SHAP values, we identified the X chromosome as the most important contributor to the predictive model.
Conclusion
We conclude that germ line chromosomal scale length variation data can provide an effective genetic risk score for schizophrenia. Length variations of several regions of the X Chromosome are the greatest contributing factor.
Keywords
Predicting Schizophrenia, Chromosomal-Scale, Biobank dataset
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
This is a list of supplementary files associated with this preprint. Click to download.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Revision
Version 1
Posted 04 Mar, 2021
No community comments so far
Editorial decision: Major revision
On 01 Apr, 2021
Review #2 received
Received 30 Mar, 2021
Review #1 received
Received 29 Mar, 2021
Reviewer #2 agreed
On 15 Mar, 2021
Review #? received
Received 15 Mar, 2021
Reviewer #1 agreed
On 14 Mar, 2021
Reviewers invited
Invitations sent on 07 Mar, 2021
Editor assigned
On 23 Feb, 2021
Submission checks complete
On 23 Feb, 2021
Editor invited
On 23 Feb, 2021
First submitted
On 22 Feb, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Epigenetics & Genomics
Learn more about our company.
This preprint is under consideration at Human Genomics. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Primary research
Christopher Toh
University of California Irvine
Corresponding Author
ORCiD: https://orcid.org/0000-0003-3298-9055
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Revision
Version 1
Posted 04 Mar, 2021
No community comments so far
Editorial decision: Major revision
On 01 Apr, 2021
Review #2 received
Received 30 Mar, 2021
Review #1 received
Received 29 Mar, 2021
Reviewer #2 agreed
On 15 Mar, 2021
Review #? received
Received 15 Mar, 2021
Reviewer #1 agreed
On 14 Mar, 2021
Reviewers invited
Invitations sent on 07 Mar, 2021
Editor assigned
On 23 Feb, 2021
Submission checks complete
On 23 Feb, 2021
Editor invited
On 23 Feb, 2021
First submitted
On 22 Feb, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Epigenetics & Genomics
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Introduction
Schizophrenia is a neurological disorder that often manifests itself as a combination of psychotic symptoms such as delusions, hallucinations, and disorganized cognitive functions. Several lines of evidence indicate that schizophrenia has a genetic component, however it cannot be isolated to a single gene. We set out to determine how well one could predict that a person will develop schizophrenia based on their germ line DNA.
Methods
We compared 1129 people from the UK Biobank dataset who had a diagnosis of schizophrenia to an equal number of age matched people drawn from the general UK Biobank population. For each person, we constructed a profile consisting of a sequence of numbers. Each number characterized the length of a segment of one of their chromosomes. We tested several machine learning algorithms using the h2o.ai framework to determine which was most effective in predicting schizophrenia. We also tested whether there was any improvement in prediction by breaking the chromosomes into smaller chunks. We used SHAP values to better understand features important to the predictive model.
Results
We found that the stacked ensemble, a combination of four different machine learning algorithms, performed best with an area under the receiver operating characteristic curve (AUC) of 0.583 (95% CI 0.581-0.586). We noted an increase in the AUC by breaking the chromosomes into smaller chunks for analysis. Using SHAP values, we identified the X chromosome as the most important contributor to the predictive model.
Conclusion
We conclude that germ line chromosomal scale length variation data can provide an effective genetic risk score for schizophrenia. Length variations of several regions of the X Chromosome are the greatest contributing factor.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Loading...