Emaad Khwaja

Emaad Khwaja
Google Inc. | Google · Research Department

Doctor of Philosophy
🤖🔬🧬 Multimodal Generative AI Expert

About

15
Publications
1,552
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
152
Citations
Introduction
I am interested in utilizing physical principles and biological knowledge to inform machine learning within microscopy and medical imaging contexts. I have a special place in my heart for transformer models.

Publications

Publications (15)
Preprint
Full-text available
This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state of the art on generalized time series benchmarks in domains such as electricity and weather, this model is the first general-purp...
Preprint
Full-text available
We present a one-shot text-to-image diffusion model that can generate high-resolution images from natural language descriptions. Our model employs a layered U-Net architecture that simultaneously synthesizes images at multiple resolution scales. We show that this method outperforms the baseline of synthesizing images only at the target resolution,...
Preprint
Full-text available
We present CELL-E 2, a novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and vice versa). Protein localization is a challenging problem that requires integrating sequence and image information, which most existing methods ignore. CELL-E 2 extends the work of CELL-E, no...
Preprint
Full-text available
Accurately predicting cellular activities of proteins based on their primary amino acid sequences would greatly improve our understanding of the proteome. In this paper, we present CELL-E, a text-to-image transformer model that generates 2D probability density images describing the spatial distribution of proteins within cells. Given an amino acid...
Preprint
Full-text available
Predicting the cellular activities of proteins from their primary amino acid sequences is a highly desirable capability that could greatly enhance our functional understanding of the proteome. Here, we demonstrate CELL-E, a text-to-image transformer architecture, which given a protein sequence and a reference image for cell (or nucleus) morphology,...
Article
Full-text available
When using fluorescent microscopy to study cellular dynamics, trade-offs typically have to be made between light exposure and quality of recorded image to balance the phototoxicity and image signal-to-noise ratio. Image denoising is an important tool for retrieving information from dim cell images. Recently, deep learning based image denoising is b...
Preprint
Full-text available
When using fluorescent microscopy to study cellular dynamics, trade-off typically has to be made between light exposure and quality of recorded image to balance phototoxicity and image signal-to-noise ratio. Image denoising is an important tool for retrieving information from dim live cell images. Recently, deep learning based image denoising is be...
Article
Luminescence arising from β decay of radiotracers has attracted much interest recently as a viable in vivo imaging technique. The emitted Cerenkov radiation can be directly detected by high-sensitivity cameras or used to excite highly efficient fluorescent dyes. Here we investigate the enhancement of visible and infrared emission driven by β decay...
Article
Full-text available
Distortion of nominally planar phthalocyanine macrocycles affects the excited state dynamics in that most of the excited‐state energy decays through internal conversion. A click‐type annulation reaction on a perfluorophthalocyanine platform appending a seven‐membered ring to the β‐positions on one or more of the isoindoles distorts the macrocycle a...
Article
The control and enhancement of resonance energy transfer is highly desirable for a variety of applications ranging from solar cells to spectroscopic rulers. However the process of direct resonance energy transfer is distance dependent and limited to ~ 10nm for typical donor-acceptor pairs. Here we demonstrate long range (~ 160nm) direct energy tran...
Article
A physical organic chemistry experiment is described for second-year college students. Students performed nucleophilic aromatic substitution (NAS) reactions on 5,10,15,20-tetrakis(2,3,4,5,6-pentafluorophenyl)porphyrin (TPPF20) using three different nucleophiles. Substitution occurs preferentially at the 4-position (para) because it is thermodynamic...
Conference Paper
We experimentally demonstrate long range (~160 nm) energy transfer in a donor-acceptor pair across a metamaterial designed such that the epsilon-near-zero regime coincided with the donor emission.
Article
Nanoparticles labeled with radiometals enable whole-body nuclear imaging and therapy. While chelating agents are commonly used to radiolabel biomolecules, nanoparticles offer the advantage of attaching a radiometal directly to the nanoparticle itself without the need of such agents. We previously demonstrated that direct radiolabeling of silica nan...

Network

Cited By