Shantanu Singh

Shantanu Singh

Auto-generated profile, based on publicly available information

Shantanu Singh

Imaging Platform, Broad Institute of MIT and Harvard, Cambridge, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
25 August 2016 in Nature Protocols
Verified
Journal Article
Closed access
PDF file
MBMark-Anthony Bray
Mark-Anthony Bray
SSShantanu Singh
Shantanu Singh
HHHan Han
Han Han
CDChadwick T Davis
Chadwick T Davis
BBBlake Borgeson
Blake Borgeson
ACAnne E Carpenter
Anne E Carpenter

21 October 2019 in Nature Methods
Verified
Journal Article
Open access
PDF file
JCJuan C. Caicedo
Juan C. Caicedo
AGAllen Goodman
Allen Goodman
KKKyle W. Karhohs
Kyle W. Karhohs
BCBeth A. Cimini
Beth A. Cimini
JAJeanelle Ackerman
Jeanelle Ackerman
ACAnne E. Carpenter
Anne E. Carpenter
Segmenting the nuclei of cells in microscopy images is often the first step in the quantitative analysis of imaging data for biological and biomedical applications. Many bioimage analysis tools can segment nuclei in images but need to be selected and configured for every experiment. The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction. Top participants in the challenge succeeded in this task, developing deep-learning-based models that identified cell nuclei across many image types and experimental conditions without the need to manually adjust segmentation parameters. This represents an important step toward configuration-free bioimage analysis software tools.

16 July 2019 in Cytometry Part A
Verified
Journal Article
Open access
PDF file
JCJuan C. Caicedo
Juan C. Caicedo
JRJonathan Roth
Jonathan Roth
AGAllen Goodman
Allen Goodman
TBTim Becker
Tim Becker
KKKyle W. Karhohs
Kyle W. Karhohs
ACAnne E. Carpenter
Anne E. Carpenter
Identifying nuclei is often a critical first step in analyzing microscopy images of cells and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluation metrics for nucleus segmentation do not satisfactorily capture error modes that are relevant in cellular images. We present an evaluation framework to measure accuracy, types of errors, and computational efficiency; and use it to compare deep learning strategies and classical approaches. We publicly release a set of 23,165 manually annotated nuclei and source code to reproduce experiments and run the proposed evaluation methodology. Our evaluation framework shows that deep learning improves accuracy and can reduce the number of biologically relevant errors by half. © 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

9 April 2024 in Nature Methods
Verified
Journal Article
Open access
PDF file
SCSrinivas Niranj Chandrasekaran
Srinivas Niranj Chandrasekaran
BCBeth A. Cimini
Beth A. Cimini
AGAmy Goodale
Amy Goodale
LMLisa Miller
Lisa Miller
MKMaria Kost-Alimova
Maria Kost-Alimova
ACAnne E. Carpenter
Anne E. Carpenter
The identification of genetic and chemical perturbations with similar impacts on cell morphology can elucidate compounds’ mechanisms of action or novel regulators of genetic pathways. Research on methods for identifying such similarities has lagged due to a lack of carefully designed and well-annotated image sets of cells treated with chemical and genetic perturbations. Here we create such a Resource dataset, CPJUMP1, in which each perturbed gene’s product is a known target of at least two chemical compounds in the dataset. We systematically explore the directionality of correlations among perturbations that target the same protein encoded by a given gene, and we find that identifying matches between chemical and genetic perturbations is a challenging task. Our dataset and baseline analyses provide a benchmark for evaluating methods that measure perturbation similarities and impact, and more generally, learn effective representations of cellular state from microscopy images. Such advancements would accelerate the applications of image-based profiling of cellular states, such as uncovering drug mode of action or probing functional genomics.

21 June 2023 in Nature Protocols
Verified
Journal Article
Closed access
PDF file
BCBeth A. Cimini
Beth A. Cimini
SCSrinivas Niranj Chandrasekaran
Srinivas Niranj Chandrasekaran
MKMaria Kost-Alimova
Maria Kost-Alimova
LMLisa Miller
Lisa Miller
AGAmy Goodale
Amy Goodale
ACAnne E. Carpenter
Anne E. Carpenter

18 March 2017 in eLife
Verified
Journal Article
Open access
MRMohammad Hossein Rohban
Mohammad Hossein Rohban
SSShantanu Singh
Shantanu Singh
XWXiaoyun Wu
Xiaoyun Wu
JBJulia B Berthet
Julia B Berthet
MBMark-Anthony Bray
Mark-Anthony Bray
ACAnne E Carpenter
Anne E Carpenter
We hypothesized that human genes and disease-associated alleles might be systematically functionally annotated using morphological profiling of cDNA constructs, via a microscopy-based Cell Painting assay. Indeed, 50% of the 220 tested genes yielded detectable morphological profiles, which grouped into biologically meaningful gene clusters consistent with known functional annotation (e.g., the RAS-RAF-MEK-ERK cascade). We used novel subpopulation-based visualization methods to interpret the morphological changes for specific clusters. This unbiased morphologic map of gene function revealed TRAF2/c-REL negative regulation of YAP1/WWTR1-responsive pathways. We confirmed this discovery of functional connectivity between the NF-κB pathway and Hippo pathway effectors at the transcriptional level, thereby expanding knowledge of these two signaling pathways that critically regulate tumor initiation and progression. We make the images and raw data publicly available, providing an initial morphological map of major biological pathways for future study.