Johannes Birgmeier

Johannes Birgmeier

Auto-generated profile, based on publicly available information

Johannes Birgmeier

Stanford University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 May 2020 in Science Translational Medicine
Verified
Journal Article
Closed access
PDF file
JBJohannes Birgmeier
Johannes Birgmeier
MHMaximilian Haeussler
Maximilian Haeussler
CDCole A. Deisseroth
Cole A. Deisseroth
ESEthan H. Steinberg
Ethan H. Steinberg
KJKarthik A. Jagadeesh
Karthik A. Jagadeesh
GBGill Bejerano
Gill Bejerano
An automated pipeline parses primary literature about Mendelian diseases to rank patient candidate causative genes, thereby accelerating diagnosis.

2 August 2017 in bioRxiv
Verified
Preprint
Open access
PDF file
JBJohannes Birgmeier
Johannes Birgmeier
MHMaximilian Haeussler
Maximilian Haeussler
CDCole A. Deisseroth
Cole A. Deisseroth
KJKarthik A. Jagadeesh
Karthik A. Jagadeesh
ARAlexander J. Ratner
Alexander J. Ratner
GBGill Bejerano
Gill Bejerano
The diagnosis of Mendelian disorders requires labor-intensive literature research. Our software system AMELIE ( A utomatic M endelian L iterature E valuation) greatly automates this process. AMELIE parses hundreds of thousands of full text articles to find an underlying diagnosis to explain a patient’s phenotypes given the patient’s exome. AMELIE prioritizes patient candidate genes for their likelihood of causing the patient’s phenotypes. Diagnosis of singleton patients (without relatives’ exomes) is the most time-consuming scenario. AMELIE’s gene ranking method was tested on 215 singleton Mendelian patients with a clinical diagnosis. AMELIE ranked the causal gene among the top 2 in the majority (63%) of cases. Examining AMELIE’s top 10 genes, amounting to 8% of 124 candidate genes with rare functional variants per patient, results in diagnosis for 95% of cases. Strikingly, training only on gene pathogenicity knowledge from 2011 leads to identical performance compared to training on current data. An accompanying analysis web portal has launched at AMELIE.stanford.edu .

2 April 2018 in bioRxiv
Verified
Preprint
Open access
PDF file
KJKarthik A. Jagadeesh
Karthik A. Jagadeesh
JBJohannes Birgmeier
Johannes Birgmeier
HGHarendra Guturu
Harendra Guturu
CDCole A. Deisseroth
Cole A. Deisseroth
AWAaron M. Wenger
Aaron M. Wenger
GBGill Bejerano
Gill Bejerano
Purpose: Exome sequencing and diagnosis is beginning to spread across the medical establishment. The most time-consuming part of genome based diagnosis is the manual step of matching the potentially long list of patient candidate genes to patient phenotypes to identify the causative disease. Methods: We introduce Phrank (for phenotype ranking), an information-theory inspired method that utilizes a Bayesian Network to prioritize candidate diseases or genes, as a stand-alone module that can be run with any underlying knowledgebase and any variant filtering scheme. Results: Phrank outperforms existing methods at ranking the causative disease or gene when applied to 169 real patient exomes with Mendelian diagnoses. Phrank’s greatest improvement is in disease space, where across all 169 patients it ranks only 3 diseases on average ahead of the true diagnosis, whereas Phenomizer ranks 32 diseases ahead of the causal one. Conclusion: Using Phrank to rank all patient candidate genes or diseases, as they start working through a new case, will save the busy clinician much time in deriving a genetic diagnosis.

4 July 2018 in bioRxiv
Verified
Preprint
Open access
PDF file
CDCole A. Deisseroth
Cole A. Deisseroth
JBJohannes Birgmeier
Johannes Birgmeier
EBEthan E. Bodle
Ethan E. Bodle
JBJonathan A. Bernstein
Jonathan A. Bernstein
GBGill Bejerano
Gill Bejerano
Purpose: Severe genetic diseases affect 7 million births per year, worldwide. Diagnosing these diseases is necessary for optimal care, but it can involve the manual evaluation of hundreds of genetic variants per case, with many variants taking an hour to evaluate. Automatic gene-ranking approaches shorten this process by reporting which of the genes containing variants are most likely to be causing the patient’s symptoms. To use these tools, busy clinicians must manually encode patient phenotypes, which is a cumbersome and imprecise process. With 60 million patients expected to be sequenced in the next 7 years, a fast alternative to manual phenotype extraction from the clinical notes in patients’ medical records will become necessary. Methods: We introduce ClinPhen: a fast, high-accuracy tool that automatically converts the clinical notes into a prioritized list of patient symptoms using HPO terms. Results: ClinPhen shows superior accuracy to existing phenotype extractors, and when paired with a gene-ranking tool it significantly improve the latter’s performance. Conclusion: Compared to manual phenotype extraction, ClinPhen saves more than 5 hours per case in Mendelian diagnosis alone. Summing over millions of forthcoming cases whose medical notes await phenotype encoding, ClinPhen makes a substantial contribution towards ending all patients’ diagnostic odyssey.

27 January 2017 in bioRxiv
Verified
Preprint
Open access
PDF file
KJKarthik A. Jagadeesh
Karthik A. Jagadeesh
DWDavid J. Wu
David J. Wu
JBJohannes A. Birgmeier
Johannes A. Birgmeier
DBDan Boneh
Dan Boneh
GBGill Bejerano
Gill Bejerano
Given the rapidly growing utility of critical health information revealed in the human genome, secure genomic computation is essential to moving forward, especially as genome sequencing becomes commonplace. We devise and implement proof-of-principle computational operations for precisely identifying causal variants in Mendelian patients using secure multiparty computation methods based on Yao’s protocol. We show multiple real scenarios (small patient cohorts, trio analysis, two hospital collaboration) where the causal variant is discovered jointly, while keeping up to 99.7% of all participants’ most sensitive genomic information private. All similar operations performed today to diagnose such cases are done openly, keeping 0% of participants’ genomic information private. Our work will help usher in an era where genomes can be both utilized and truly protected.

4 November 2018 in bioRxiv
Verified
Preprint
Open access
PDF file
JBJohannes Birgmeier
Johannes Birgmeier
ATAndrew P. Tierno
Andrew P. Tierno
PSPeter D. Stenson
Peter D. Stenson
CDCole A. Deisseroth
Cole A. Deisseroth
KJKarthik A. Jagadeesh
Karthik A. Jagadeesh
GBGill Bejerano
Gill Bejerano
Purpose: The primary literature on human genetic diseases includes descriptions of pathogenic variants that are essential for clinical diagnosis. Variant databases such as ClinVar and HGMD collect pathogenic variants by manual curation. We aimed to automatically construct a freely accessible database of pathogenic variants directly from full-text articles about genetic disease. Methods: AVADA (Automatically curated VAriant DAtabase) is a novel machine learning tool that uses natural language processing to automatically identify pathogenic variants and genes in full text of primary literature and converts them to genomic coordinates for rapid downstream use. Results: AVADA automatically curated almost 60% of pathogenic variants deposited in HGMD, a 4.4-fold improvement over the current state of the art in automated variant extraction. AVADA also contains more than 60,000 pathogenic variants that are in HGMD, but not in ClinVar. In a cohort of 245 diagnosed patients, AVADA correctly annotated 38 previously described diagnostic variants, compared to 43 using HGMD, 20 using ClinVar and only 13 (wholly subsumed by AVADA and ClinVar’s) using the best automated abstracts-only based approach. Conclusion: AVADA is the first machine learning tool that automatically curates a variants database directly from full text literature. AVADA is available upon publication at http://bejerano.stanford.edu/AVADA .