Pranik Chainani

Pranik Chainani

Statistics and Applied Mathematics at Yale University

New York City Metropolitan Area
1K followers 500+ connections

Join to view profile
Flatiron Institute

Activity

Join now to see all activity

Experience

  • Guest Researcher

    Flatiron Institute

    - Present 2 months

    New York, New York, United States

    Center for Computational Mathematics
    The mission of the Flatiron Institute is to advance scientific research through computational methods, including data analysis, theory, modeling and simulation.

  • Yale Helix Graphic

    Fellow

    Yale Helix

    - Present 3 years 9 months

    Yale Helix is the only undergraduate healthcare startup incubator at Yale University.

  • Teamworthy Ventures Graphic

    Summer Associate

    Teamworthy Ventures

    - 1 year

    Greenwich, Connecticut, United States

    Early investors in Toast, Carta, SeatGeek, Greenhouse, Zocdoc, iBotta, OpenGov, G2, Lithic, Vetcove and many others

  • Bioinformatics Researcher

    Azizi Lab @ Columbia University

    - 1 year 4 months

    New York, United States

    Interdisciplinary research, developing novel machine learning techniques and utilizing cutting-edge genomic and imaging technologies, to characterize complex populations of interacting cells in the tumor microenvironment, as well as their spatial and temporal dynamics and underlying circuitry.

  • Computer Vision Researcher

    Krishnaswamy Lab

    - 2 years 5 months

    New Haven, CT, United States

    The focus of our group is developing machine learning and applied mathematical techniques for extracting structure and patterns in high-dimensional and high-throughput biomedical data. The lab maintains active collaborations with research groups in the Departments of Immunology, Neuroscience, Genetics, Neurology, Radiation Oncology, and Endocrinology as well as outside institutions like Weill Cornell and the Salk Institute.

  • Deep Learning Researcher

    Gerstein Lab

    - 3 years 1 month

    New Haven, Connecticut, United States

    We focus on approaches that are “interpretable” in that they have a clear biological or physical basis. Our tools process large-scale datasets to, for instance, functionally prioritize genomic variants with respect to their biological function or potential contribution to disease or predict protein binding.

  • Yale Entrepreneurial Society Graphic

    Data Scientist

    Yale Entrepreneurial Society

    - 1 year

    Matching algorithm between applicants and startups

  • University of Houston-Downtown Graphic

    Researcher

    University of Houston-Downtown

    - 1 year 11 months

    Houston, Texas Area

    Bioinformatics Deep Learning
    2 publications
    https://www.semanticscholar.org/author/Pranik-Chainani/52108893

  • Joy Lutheran Church Graphic

    Organist

    Joy Lutheran Church

    - 9 months

    Richmond, Texas

    Leading the Congregation every Sunday

Education

Licenses & Certifications

Volunteer Experience

  • NEW HOPE LUTHERAN CHURCH Graphic

    Assistant Organist

    NEW HOPE LUTHERAN CHURCH

    - 4 years

    Social Services

  • Bassist for Upper School Musicals

    The John Cooper School

    - 3 years 5 months

    Arts and Culture

  • Mathematics Tutor

    Opal Hamilton Middle School

    - 8 months

    Education

Publications

  • Accurate prediction of boundaries of high resolution topologically associated domains (TADs) in fruit flies using deep learning

    Nucleic Acids Research (Oxford)

    Abstract Genomes are organized into self-interacting chromatin regions called topologically associated domains (TADs). A significant number of TAD boundaries are shared across multiple cell types and conserved across species. Disruption of TAD boundaries may affect the expression of nearby genes and could lead to several diseases. Even though detection of TAD boundaries is important and useful, there are experimental challenges in obtaining high resolution TAD locations. Here, we present…

    Abstract Genomes are organized into self-interacting chromatin regions called topologically associated domains (TADs). A significant number of TAD boundaries are shared across multiple cell types and conserved across species. Disruption of TAD boundaries may affect the expression of nearby genes and could lead to several diseases. Even though detection of TAD boundaries is important and useful, there are experimental challenges in obtaining high resolution TAD locations. Here, we present computational prediction of TAD boundaries from high resolution Hi-C data in fruit flies. By extensive exploration and testing of several deep learning model architectures with hyperparameter optimization, we show that a unique deep learning model consisting of three convolution layers followed by a long short-term-memory layer achieves an accuracy of 96%. This outperforms feature-based models’ accuracy of 91% and an existing method's accuracy of 73–78% based on motif TRAP scores. Our method also detects previously reported motifs such as Beaf-32 that are enriched in TAD boundaries in fruit flies and also several unreported motifs.

  • Deep learning identifies genome-wide DNA binding sites of long noncoding RNAs

    RNA biology (Taylor & Francis)

    ABSTRACT Long noncoding RNAs (lncRNAs) can exert their function by interacting with the DNA via triplex structure formation. Even though this has been validated with a handful of experiments, a genome-wide analysis of lncRNA-DNA binding is needed. In this paper, we develop and interpret deep learning models that predict the genome-wide binding sites deciphered by ChIRP-Seq experiments of 12 different lncRNAs. Among the several deep learning architectures tested, a simple architecture consisting…

    ABSTRACT Long noncoding RNAs (lncRNAs) can exert their function by interacting with the DNA via triplex structure formation. Even though this has been validated with a handful of experiments, a genome-wide analysis of lncRNA-DNA binding is needed. In this paper, we develop and interpret deep learning models that predict the genome-wide binding sites deciphered by ChIRP-Seq experiments of 12 different lncRNAs. Among the several deep learning architectures tested, a simple architecture consisting of two convolutional neural network layers performed the best suggesting local sequence patterns as determinants of the interaction. Further interpretation of the kernels in the model revealed that these local sequence patterns form triplex structures with the corresponding lncRNAs. We uncovered several novel triplexes forming domains (TFDs) of these 12 lncRNAs and previously experimentally verified TFDs of lncRNAs HOTAIR and MEG3. We experimentally verified such two novel TFDs of lncRNAs HOTAIR and TUG1 predicted by our method (but previously unreported) using Electrophoretic mobility shift assays. In conclusion, we show that simple deep learning architecture can accurately predict genome-wide binding sites of lncRNAs and interpretation of the models suggest RNA:DNA:DNA triplex formation as a viable mechanism underlying lncRNA-DNA interactions at genome-wide level. 

Test Scores

  • SAT

    Score: 1580/1600

  • AP US History

    Score: 5/5

  • AP Computer Science A

    Score: 5/5

  • AP Statistics

    Score: 5/5

  • AP Calculus BC

    Score: 5/5

    Associated with Opal Hamilton Middle School

Languages

  • German

    Full professional proficiency

  • Sindhi

    Native or bilingual proficiency

  • Chinese (Simplified)

    Elementary proficiency

  • French

    Limited working proficiency

More activity by Pranik

View Pranik’s full profile

  • See who you know in common
  • Get introduced
  • Contact Pranik directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Add new skills with these courses

See all courses