High-Performance Deep Learning Toolbox for Genome-Scale Prediction of Protein Structure and Function
Year: 2021
Type: conference-paper
Abstract: Computational biology is one of many scientific disciplines ripe for innovation and acceleration with the advent of high-performance computing (HPC). In recent years, the field of machine learning has also seen significant benefits from adopting HPC practices. In this work, we present a novel HPC pipeline that incorporates various machine-learning approaches for structure-based functional annotation of proteins on the scale of whole genomes. Our pipeline makes extensive use of deep learning and provides computational insights into best practices for training advanced deep-learning models for high-throughput data such as proteomics data. We showcase methodologies our pipeline currently supports and detail future tasks for our pipeline to envelop, including large-scale sequence comparison using SAdLSA and prediction of protein tertiary structures using AlphaFold2.
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
Awards: G121915436, UNIVERSITY OF MISSOURI - NEW AWARD
CONTROL NUMBER: 2107-1570
PROJECT TITLE: DEEP LEARNING PREDICTION OF PROTEIN COMPLEX STRUCTURES
PROJECT DESCRIPTION: THIS COOPERATIVE AGREEMENT IS HEREBY AWARDED TO THE CURATORS OF THE UNIVERSITY OF MISSOURI WHO PROPOSES TO DEVELOP NOVEL DEEP LEARNING METHODS TO PREDICT INTER-PROTEIN AMINO ACID INTERACTIONS (CONTACTS) AND BUILD THREE-DIMENSIONAL STRUCTURES OF PROTEIN COMPLEXES., G1645119126, HIGH THROUGHPUT, ACCURATE GENE ANNOTATION THROUGH AI AND HPC-ENABLED STRUCTURAL ANALYSIS, G203625172, G2411683797, III: Medium: Collaborative Research: Guiding Exploration of Protein Structure Spaces with Deep Learning, G2584197162, G2988778103, G4370606643, G4423657506, ABI Innovation: Deep learning methods for protein bioinformatics, G675320460, Distance-based ab initio protein structure prediction, G8269158468, DEEP GREEN: STRUCTURAL AND FUNCTIONAL GENOMIC CHARACTERIZATION OF CONSERVED UNANNOTATED GREEN LINEAGE PROTEINS, G8906985441, Interplay of inherent promiscuity and specificity in protein biochemical function with applications to drug discovery and exome analysis
OpenAlex ID: W4200213155