Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “protein function prediction”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

PersGNN: Applying Topological Data Analysis and Geometric Deep Learning to Structure-Based Protein Function Prediction

Understanding protein structure-function relationships is a key challenge in computational biology, with applications across the biotechnology and pharmaceutical industries. While it is known that protein structure directly impacts protein function, many functional prediction tasks use only protein sequence. In this work, we isolate protein structure to make functional annotations for proteins in the Protein Data Bank in order to study the expressiveness of different structure-based prediction schemes. We present PersGNN - an end-to-end trainable deep learning model that combines graph representation learning with topological data analysis to capture a complex set of both local and global structural features. While variations of these techniques have been successfully applied to proteins before, we demonstrate that our hybridized approach, PersGNN, outperforms either method on its own as well as a baseline neural network that learns from the same information. PersGNN achieves a 9.3% boost in area under the precision recall curve (AUPR) compared to the best individual model, as well as high F1 scores across different gene ontology categories, indicating the transferability of this approach.

Swenson, Nicolas↗
DOE OSTI2023

Combining protein sequences and structures with transformers and equivariant graph neural networks to predict protein function

Abstract Motivation Millions of protein sequences have been generated by numerous genome and transcriptome sequencing projects. However, experimentally determining the function of the proteins is still a time consuming, low-throughput, and expensive process, leading to a large protein sequence-function gap. Therefore, it is important to develop computational methods to accurately predict protein function to fill the gap. Even though many methods have been developed to use protein sequences as input to predict function, much fewer methods leverage protein structures in protein function prediction because there was lack of accurate protein structures for most proteins until recently. Results We developed TransFun—a method using a transformer-based protein language model and 3D-equivariant graph neural networks to distill information from both protein sequences and structures to predict protein function. It extracts feature embeddings from protein sequences using a pre-trained protein language model (ESM) via transfer learning and combines them with 3D structures of proteins predicted by AlphaFold2 through equivariant graph neural networks. Benchmarked on the CAFA3 test dataset and a new test dataset, TransFun outperforms several state-of-the-art methods, indicating that the language model and 3D-equivariant graph neural networks are effective methods to leverage protein sequences and structures to improve protein function prediction. Combining TransFun predictions and sequence similarity-based predictions can further increase prediction accuracy. Availability and implementation The source code of TransFun is available at https://github.com/jianlin-cheng/TransFun.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Structural- and Functional-Informed Machine Learning for Protein Function Prediction

In this project we aimed to extend methods for protein function prediction to include structural prediction data, and benchmark methods against existing tools. We proposed to apply the method to large metagenome datasets, and develop approaches to examine activity-based protein profiling results for protein function-structure patterns. Nitrogen cycle protein families were previously identified and are used here to provide a proof-of-principle for use of structure prediction in protein function classification.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2003

Predicting protein functions from redundancies in large-scale protein interaction networks

Interpreting data from large-scale protein interaction experiments has been a challenging task because of the widespread presence of random false positives. Here, we present a network-based statistical algorithm that overcomes this difficulty and allows us to derive functions of unannotated proteins from large-scale interaction data. Our algorithm uses the insight that if two proteins share significantly larger number of common interaction partners than random, they have close functional associations. Analysis of publicly available data from Saccharomyces cerevisiae reveals >2,800 reliable functional associations, 29% of which involve at least one unannotated protein. By further analyzing these associations, we derive tentative functions for 81 unannotated proteins with high certainty. Our method is not overly sensitive to the false positives present in the data. Even after adding 50% randomly generated interactions to the measured data set, we are able to recover almost all (approximately 89%) of the original associations.

Proteins/chemistry/metabolism↗
DOE OSTI2024

Harnessing the predicted maize pan-interactome for putative gene function prediction and prioritization of candidate genes for important traits

Abstract The recent assembly and annotation of the 26 maize nested association mapping population founder inbreds have enabled large-scale pan-genomic comparative studies. These studies have expanded our understanding of agronomically important traits by integrating pan-transcriptomic data with trait-specific gene candidates from previous association mapping results. In contrast to the availability of pan-transcriptomic data, obtaining reliable protein–protein interaction (PPI) data has remained a challenge due to its high cost and complexity. We generated predicted PPI networks for each of the 26 genomes using the established STRING database. The individual genome-interactomes were then integrated to generate core- and pan-interactomes. We deployed the PPI clustering algorithm ClusterONE to identify numerous PPI clusters that were functionally annotated using gene ontology (GO) functional enrichment, demonstrating a diverse range of enriched GO terms across different clusters. Additional cluster annotations were generated by integrating gene coexpression data and gene description annotations, providing additional useful information. We show that the functionally annotated PPI clusters establish a useful framework for protein function prediction and prioritization of candidate genes of interest. Our study not only provides a comprehensive resource of predicted PPI networks for 26 maize genomes but also offers annotated interactome clusters for predicting protein functions and prioritizing gene candidates. The source code for the Python implementation of the analysis workflow and a standalone web application for accessing the analysis results are available at https://github.com/eporetsky/PanPPI.

Genetics & Heredity↗
DOE OSTI2024

Multi-Omics integration can be used to rescue metabolic information for some of the dark region of the Pseudomonas putida proteome

In every omics experiment, genes or their products are identified for which even state of the art tools are unable to assign a function. In the biotechnology chassis organism Pseudomonas putida, these proteins of unknown function make up 14% of the proteome. This missing information can bias analyses since these proteins can carry out functions which impact the engineering of organisms. As a consequence of predicting protein function across all organisms, function prediction tools generally fail to use all of the types of data available for any specific organism, including protein and transcript expression information. Additionally, the release of Alphafold predictions for all Uniprot proteins provides a novel opportunity for leveraging structural information. We constructed a bespoke machine learning model to predict the function of recalcitrant proteins of unknown function in Pseudomonas putida based on these sources of data, which annotated 1079 terms to 213 proteins. Among the predicted functions supplied by the model, we found evidence for a significant overrepresentation of nitrogen metabolism and macromolecule processing proteins. These findings were corroborated by manual analyses of selected proteins which identified, among others, a functionally unannotated operon that likely encodes a branch of the shikimate pathway.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2019

Unified rational protein engineering with sequence-based deep representation learning

Rational protein engineering requires a holistic understanding of protein function. Here, we apply deep learning to unlabeled amino-acid sequences to distill the fundamental features of a protein into a statistical representation that is semantically rich and structurally, evolutionarily and biophysically grounded. We show that the simplest models built on top of this unified representation (UniRep) are broadly applicable and generalize to unseen regions of sequence space. Our data-driven approach predicts the stability of natural and de novo designed proteins, and the quantitative function of molecularly diverse mutants, competitively with the state-of-the-art methods. UniRep further enables two orders of magnitude efficiency improvement in a protein engineering task. Lastly, UniRep is a versatile summary of fundamental protein features that can be applied across protein engineering informatics.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Herbivorous Fish Microbiome Adaptations to Sulfated Dietary Polysaccharides

Marine herbivorous fish that feed primarily on macroalgae, such as those from the genus Kyphosus, are essential for maintaining coral health and abundance on tropical reefs. Here, deep metagenomic sequencing and assembly of gut compartment-specific samples from three sympatric, macroalgivorous Hawaiian kyphosid species have been used to connect host gut microbial taxa with predicted protein functional capacities likely to contribute to efficient macroalgal digestion. Bacterial community compositions, algal dietary sources, and predicted enzyme functionalities were analyzed in parallel for 16 metagenomes spanning the mid- and hindgut digestive regions of wild-caught fishes. Gene colocalization patterns of expanded carbohydrate (CAZy) and sulfatase (SulfAtlas) digestive enzyme families on assembled contigs were used to identify likely polysaccharide utilization locus associations and to visualize potential cooperative networks of extracellularly exported proteins targeting complex sulfated polysaccharides. These insights into the gut microbiota of herbivorous marine fish and their functional capabilities improve our understanding of the enzymes and microorganisms involved in digesting complex macroalgal sulfated polysaccharides.

09 BIOMASS FUELS↗
DOE OSTI2023

Plug & play directed evolution of proteins with gradient-based discrete MCMC

Abstract A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations that improve the function of a known protein. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins. Our framework achieves this without any model fine-tuning or re-training by constructing a product of experts distribution directly in discrete protein space. Instead of resorting to brute force search or random sampling, which is typical of classic directed evolution, we introduce a fast Markov chain Monte Carlo sampler that uses gradients to propose promising mutations. We conduct in silico directed evolution experiments on wide fitness landscapes and across a range of different pre-trained unsupervised models, including a 650 M parameter protein language model. Our results demonstrate an ability to efficiently discover variants with high evolutionary likelihood as well as estimated activity multiple mutations away from a wild type protein, suggesting our sampler provides a practical and effective new paradigm for machine-learning-based protein engineering.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

A large-scale screening campaign of putative carbohydrate-active enzymes reveals a novel xylanase from anaerobic gut fungi

The genomes of anaerobic gut fungi (AGF) encode a diverse array of carbohydrate-active enzymes (CAZymes), yet exceedingly few of these enzymes have been experimentally validated or expressed in heterologous systems. Here, we developed a predictive bioinformatic pipeline to annotate novel putative CAZymes from anaerobic fungi and validate their activity through large-scale heterologous expression in Escherichia coli. A total of 173 fungal proteins from Piromyces finnis associated with biomass degradation were synthesized and expressed in E. coli, and 9.8% were soluble with expression levels exceeding 5% of the total proteome using high-throughput proteomic screening. Among these 17 heterologously expressed proteins, analysis with AlphaFold and FoldSeek predicted 13 multi-functional proteins containing catalytic domains fused with repetitive fungal dockerins, and half of the substrate predictions were experimentally validated. One promising enzyme, celsome_012, exhibited robust and specific activity against beechwood xylan at 37°C and pH 6.4, with titers that were also fivefold higher than those of other recombinant proteins screened here. Both Michaelis-Menten kinetics and the linearized Lineweaver-Burk equation yielded consistent values for K m , and its activation energy was estimated at 51.9 kJ/mol based on the Arrhenius model. This work supports the industrial translation of anaerobic fungal CAZymes due to their robust lignocellulolytic activity and provides a framework for prioritizing AGF proteins for efficient E. coli heterologous expression.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2002

Predicting functional divergence in protein evolution by site-specific rate shifts

Most modern tools that analyze protein evolution allow individual sites to mutate at constant rates over the history of the protein family. However, Walter Fitch observed in the 1970s that, if a protein changes its function, the mutability of individual sites might also change. This observation is captured in the "non-homogeneous gamma model", which extracts functional information from gene families by examining the different rates at which individual sites evolve. This model has recently been coupled with structural and molecular biology to identify sites that are likely to be involved in changing function within the gene family. Applying this to multiple gene families highlights the widespread divergence of functional behavior among proteins to generate paralogs and orthologs.

Review↗
NASA NTRS1996

Single residue substitutions that change the gating properties of a mechanosensitive channel in Escherichia coli

MscL is a channel that opens a large pore in the Escherichia coli cytoplasmic membrane in response to mechanical stress. Previously, we highly enriched the MscL protein by using patch clamp as a functional assay and cloned the corresponding gene. The predicted protein contains a largely hydrophobic core spanning two-thirds of the molecule and a more hydrophilic carboxyl terminal tail. Because MscL had no homology to characterized proteins, it was impossible to predict functional regions of the protein by simple inspection. Here, by mutagenesis, we have searched for functionally important regions of this molecule. We show that a short deletion from the amino terminus (3 amino acids), and a larger deletion of 27 amino acids from the carboxyl terminus of this protein, had little if any effect in channel properties. We have thus narrowed the search of the core mechanosensitive mechanism to 106 residues of this 136-amino acid protein. In contrast, single residue substitutions of a lysine in the putative first transmembrane domain or a glutamine in the periplasmic loop caused pronounced shifts in the mechano-sensitivity curves and/or large changes in the kinetics of channel gating, suggesting that the conformational structure in these regions is critical for normal mechanosensitive channel gating.

Non-NASA Center↗
DOE OSTI2021

High-Performance Deep Learning Toolbox for Genome-Scale Prediction of Protein Structure and Function

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.

Gao, Mu↗
NASA NTRS2021

Predicting the Functional State of Protein Kinases Using Interpretable Graph Neural Networks

Kinases are a family of proteins that function as molecular switches, regulating several essential cellular activities such as cell proliferation. Dysfunctional kinases are implicated in several types of cancers and hence they are actively pursued as drug targets. Given the vast number of complex kinase structures that are available in the protein data bank (PDB), there is a necessity to develop methodologies that can identify structurally important moieties of the kinases in an automated fashion, for such techniques can be instrumental in identifying novel drug targets. In this work, we develop a graph neural network (GNN) based deep learning framework for classifying the functionally active and inactive states of a large set of eukaryotic protein kinases, making use of their 3D structure from the PDB. We show that GNN based machine learning models can classify protein states with an accuracy greater than 97%. We further use the GNN models to automatically identify regions of the kinases that are important for its function. For this purpose, Gradient-weighted Class Activation Mapping (Grad-CAM) was implemented on the protein graphs. Remarkably, Grad-CAM consistently identifies the highly conserved DFG motif as the most important part of the protein across the entire kinome, without any prior input. Other regions of the hydrophobic core such as the HRD motif were also identified by the interpretable GNN framework, consistent with the literature. We discuss the significance of each of these regions in detail.

Ashwin Ravichandran↗
DOE OSTI2026

EC-Bench: A Benchmark for Enzyme Commission Number Prediction

Enzymes are proteins that catalyze specific biochemical reactions in cells. Enzyme Commission (EC) numbers are used to annotate enzymes in a four-level hierarchy that classifies enzymes based on the specific chemical reactions they catalyze. Accurate EC number prediction is essential for understanding enzyme functions. Despite the availability of numerous methods for predicting EC numbers from protein sequences, there is no unified framework for evaluating and studying such methods systematically. This gap limits the ability of the community to identify the most effective approaches for enzyme annotation. We introduce EC-Bench, a benchmark for EC number prediction, consisting of 1) an initial representative set of existing methods (including homology-based, deep learning, contrastive learning, and language model methods), 2) existing and novel accuracy and efficiency performance metrics, and 3) selected datasets to allow for comprehensive comparative study. EC-Bench is open-source and provides a framework for researchers to not only compare among existing methods objectively under uniform conditions, but also to introduce and effectively evaluate performance of new methods in a comparative framework. To demonstrate the utility of EC-Bench, we perform extensive experimentation to compare the existing EC number prediction methods and establish their advantages and disadvantages in a variety of prediction tasks, namely “exact EC number prediction”, “EC number completion” and (partial or additional) “EC number recommendation”. We find wide variation in the performance of different methods, but also subtle but potentially useful differences in the performance of different methods across tasks and for different parts of the EC hierarchy.

59 BASIC BIOLOGICAL SCIENCES↗