Andreas A. Werdich

Andreas A. Werdich

Auto-generated profile, based on publicly available information

Andreas A. Werdich

Core for Computational Biomedicine, Department for Biomedical Informatics, Blavatnik Institute Harvard Medical School Boston Massachusetts USA

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
1 January 2017 in Development
Verified
Journal Article
Closed access
PDF file
SCSophie Colombo
Sophie Colombo
CSCarmen de Sena-Tomás
Carmen de Sena-Tomás
VGVanessa George
Vanessa George
AWAndreas A. Werdich
Andreas A. Werdich
SKSunil Kapur
Sunil Kapur
KTKimara L. Targoff
Kimara L. Targoff
NKX2-5 is the most commonly mutated gene associated with human congenital heart defects (CHDs), with a predilection for cardiac pole abnormalities. This homeodomain transcription factor is a central regulator of cardiac development and is expressed in both the first and second heart fields (FHF and SHF). We have previously revealed essential functions of nkx2.5 and nkx2.7, two Nkx2-5 homologs expressed in zebrafish cardiomyocytes, in maintaining ventricular identity. However, the differential roles of these genes in the specific subpopulations of the anterior (aSHF) and posterior (pSHF) SHFs have yet to be fully defined. Here, we show that Nkx genes regulate aSHF and pSHF progenitors through independent mechanisms. We demonstrate that Nkx genes restrict proliferation of aSHF progenitors in the outflow tract, delimit the number of pSHF progenitors at the venous pole and pattern the sinoatrial node acting through Isl1 repression. Moreover, optical mapping highlights the requirement for Nkx gene dose in establishing electrophysiological chamber identity and in integrating the physiological connectivity of FHF and SHF cardiomyocytes. Ultimately, our results may shed light on the discrete errors responsible for NKX2-5-dependent human CHDs of the cardiac outflow and inflow tracts.

10 September 2024 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
JTJames Truslow
James Truslow
ASAngela Spillane
Angela Spillane
HLHuiming Lin
Huiming Lin
KCKatherine Cyr
Katherine Cyr
AUAdeeti Ullal
Adeeti Ullal
CMCalum A. MacRae
Calum A. MacRae
Physical activity or structured exercise is beneficial in a wide range of circumstances. Nevertheless, individual-level data on differential responses to various types of activity are not yet sufficient in scale, duration or level of annotation to understand the mechanisms of discrete outcomes nor to support personalized recommendations. The Apple Heart & Movement Study was designed to passively collect the dense physiologic data accessible on Apple Watch and iPhone from a large real-world cohort distributed across the US in order to address these knowledge gaps.

20 April 2025 in Journal of Periodontology
Verified
Journal Article
Open access
BFBalazs Feher
Balazs Feher
EOEduardo H. de Souza Oliveira
Eduardo H. de Souza Oliveira
Poliana Mendes DuartePoliana Mendes Duarte
Poliana Mendes Duarte
AWAndreas A. Werdich
Andreas A. Werdich
WGWilliam V. Giannobile
William V. Giannobile
MFMagda Feres
Magda Feres
Background: Periodontitis is among the most prevalent chronic inflammatory conditions globally, and is associated with bone resorption, tooth loss, and systemic complications. While its treatment is largely standardized, individual outcomes vary, with some patients experiencing further disease progression despite adherence. Methods: We developed a machine learning (ML) approach to predict individual outcomes 1 year post‐treatment using retrospectively assessed baseline parameters. We trained a Random Forest model on 18 demographic, clinical, microbiological, and treatment‐related features of 414 patients from randomized clinical trials (RCTs) in South America. We subsequently performed internal testing, interpretability analysis, and external testing on a second dataset of 78 patients from previous RCTs in North America and Europe exhibiting less severe disease. Results: In internal testing, the ML model achieved an area under the receiver operator characteristics curve (AUROC) of 0.93, an area under the precision‐recall curve (AUPRC) of 0.90, an F 1 ‐score of 0.82, and an out‐of‐bag score of 0.71. Relative importances were 0.42 for clinical, 0.33 for treatment‐related, 0.21 for microbiological, and 0.04 for demographic features. In external testing, the ML model achieved an AUROC of 0.76, an AUPRC of 0.69, and an F 1 ‐score of 0.71. Conclusions: Our study indicates that an ML‐based approach can assist in predicting individual responses to periodontal treatment. Prospective validation is needed for clinical application. Plain language summary: Using comprehensive data from patients with periodontitis, an inflammatory condition of the tooth‐supporting tissues, a machine learning model was trained to predict how well patients might respond to different treatments after 1 year. The model was externally tested in patient populations from 2 continents different from the training dataset. The results suggest that with further research and refinement, this tool could eventually become a valuable asset in personalizing treatment plans for improved patient outcomes.

16 March 2025 in Journal of Dental Research
Verified
Journal Article
Closed access
BFBalazs Feher
Balazs Feher
AWA.A. Werdich
A.A. Werdich
CCC.-Y. Chen
C.-Y. Chen
JBJane Barrow
Jane Barrow
SLS.J. Lee
S.J. Lee
MFMagda Feres
Magda Feres
Periodontitis is a severe infection affecting oral and systemic health and is traditionally diagnosed through clinical probing—a process that is time-consuming, uncomfortable for patients, and subject to variability based on the operator’s skill. We hypothesized that computer vision can be used to estimate periodontal stability from radiographs alone. At the tooth level, we used intraoral radiographs to detect and categorize individual teeth according to their periodontal stability and corresponding treatment needs: healthy (prevention), stable (maintenance), and unstable (active treatment). At the patient level, we assessed full-mouth series and classified patients as stable or unstable by the presence of at least 1 unstable tooth. Our 3-way tooth classification model achieved an area under the receiver operating characteristic curve of 0.71 for healthy teeth, 0.56 for stable, and 0.67 for unstable. The model achieved an F 1 score of 0.45 for healthy teeth, 0.57 for stable, and 0.54 for unstable (recall, 0.70). Saliency maps generated by gradient-weighted class activation mapping primarily showed highly activated areas corresponding to clinically probed regions around teeth. Our binary patient classifier achieved an area under the receiver operating characteristic curve of 0.68 and an F 1 score of 0.74 (recall, 0.70). Taken together, our results suggest that it is feasible to estimate periodontal stability, which traditionally requires clinical and radiographic examination, from radiographic signal alone using computer vision. Variations in model performance across different classes at the tooth level indicate the necessity of further refinement.

1 August 2022 in Circulation: Genomic and Precision Medicine
Verified
Journal Article
Closed access
PDF file
HJHannah N. De Jong
Hannah N. De Jong
FDFrederick E. Dewey
Frederick E. Dewey
PCPablo Cordero
Pablo Cordero
RVRachelle A. Victorio
Rachelle A. Victorio
AKAnna Kirillova
Anna Kirillova
EAEuan A. Ashley
Euan A. Ashley
Background: The study of hypertrophic cardiomyopathy (HCM) can yield insight into the mechanisms underlying the complex trait of cardiac hypertrophy. To date, most genetic variants associated with HCM have been found in sarcomeric genes. Here, we describe a novel HCM-associated variant in the noncanonical Wnt signaling interactor WTIP (Wilms tumor interacting protein) and provide evidence of a role for WTIP in complex disease. Methods: In a family affected by HCM, we used exome sequencing and identity-by-descent analysis to identify a novel variant in WTIP (p.Y233F). We knocked down WTIP in isolated neonatal rat ventricular myocytes with lentivirally delivered short hairpin ribonucleic acids and in Danio rerio via morpholino injection. We performed weighted gene coexpression network analysis for WTIP in human cardiac tissue, as well as association analysis for WTIP variation and left ventricular hypertrophy. Finally, we generated induced pluripotent stem cell–derived cardiomyocytes from patient tissue, characterized size and calcium cycling, and determined the effect of verapamil treatment on calcium dynamics. Results: WTIP knockdown caused hypertrophy in neonatal rat ventricular myocytes and increased cardiac hypertrophy, peak calcium, and resting calcium in D rerio . Network analysis of human cardiac tissue indicated WTIP as a central coordinator of prohypertrophic networks, while common variation at the WTIP locus was associated with human left ventricular hypertrophy. Patient-derived WTIP p.Y233F-induced pluripotent stem cell–derived cardiomyocytes recapitulated cellular hypertrophy and increased resting calcium, which was ameliorated by verapamil. Conclusions: We demonstrate that a novel genetic variant found in a family with HCM disrupts binding to a known Wnt signaling protein, misregulating cardiomyocyte calcium dynamics. Further, in orthogonal model systems, we show that expression of the gene WTIP is important in complex cardiac hypertrophy phenotypes. These findings, derived from the observation of a rare Mendelian disease variant, uncover a novel disease mechanism with implications across diverse forms of cardiac hypertrophy.