Exploring the Use of Dataflow Architectures for Graph Neural Network Workloads

Hosseini, Ryien; Simini, Filippo; Vishwanath, Venkatram; Sivakumar, Ramakrishnan; Shanmugavelu, Sanjif; Chen, Zhengyu; Zlotnik, Lev; Wang, Mingran; Colangelo, Philip; Deng, Andrew; Lassen, Philip; Pathan, Shukur

doi:10.1007/978-3-031-40843-4_48

Cited by 1 publication

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A crucial advantage of GNNs is their ability to be customized to display either invariance or equivariance to SE(3) transformations, thereby making them ideal for learning molecular properties. Over time, there have been improvements and variations in GNNs, including graph convolutional networks (GCNs), graph attention networks (GATs), and graph recurrent networks (GRNs), which have demonstrated remarkable performance in different deep learning tasks. − Geometric deep learning has far-reaching implications in various biotechnological domains, , such as protein docking, − molecule design, − and property prediction. ,− Its advancements have revolutionized the field of protein structure determination, bringing about a paradigm shift and creating new prospects for progress in biotechnology and pharmaceuticals.…”

Section: Introductionmentioning

confidence: 99%

RhoMax: Computational Prediction of Rhodopsin Absorption Maxima Using Geometric Deep Learning

Sela,

Church,

Schapiro

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Microbial rhodopsins (MRs) are a diverse and abundant family of photoactive membrane proteins that serve as model systems for biophysical techniques. Optogenetics utilizes genetic engineering to insert specialized proteins into specific neurons or brain regions, allowing for manipulation of their activity through light and enabling the mapping and control of specific brain areas in living organisms. The obstacle of optogenetics lies in the fact that light has a limited ability to penetrate biological tissues, particularly blue light in the visible spectrum. Despite this challenge, most optogenetic systems rely on blue light due to the scarcity of red-shifted opsins. Finding additional red-shifted rhodopsins would represent a major breakthrough in overcoming the challenge of limited light penetration in optogenetics. However, determining the wavelength absorption maxima for rhodopsins based on their protein sequence is a significant hurdle. Current experimental methods are time-consuming, while computational methods lack accuracy. The paper introduces a new computational approach called RhoMax that utilizes structure-based geometric deep learning to predict the absorption wavelength of rhodopsins solely based on their sequences. The method takes advantage of AlphaFold2 for accurate modeling of rhodopsin structures. Once trained on a balanced train set, RhoMax rapidly and precisely predicted the maximum absorption wavelength of more than half of the sequences in our test set with an accuracy of 0.03 eV. By leveraging computational methods for absorption maxima determination, we can drastically reduce the time needed for designing new red-shifted microbial rhodopsins, thereby facilitating advances in the field of optogenetics.

show abstract