Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

NeoMUST: an accurate and efficient multi-task learning model for neoantigen presentation.

ABSTRACT: Accurate identification of neoantigens is important for advancing cancer immunotherapies. This study introduces Neoantigen MUlti-taSk Tower (NeoMUST), a model employing multi-task learning to effectively capture task-specific information across related tasks. Our results show that NeoMUST rivals existing algorithms in predicting the presentation of neoantigens via MHC-I molecules, while demonstrating a significantly shorter training time for enhanced computational efficiency. The use of multi-task learning enables NeoMUST to leverage shared knowledge and task dependencies, leading to improved performance metrics and a significant reduction in the training time. NeoMUST, implemented in Python, is freely accessible at the GitHub repository. Our model will facilitate neoantigen prediction and empower the development of effective cancer immunotherapeutic approaches.

SUBMITTER: Ma W

PROVIDER: S-EPMC10828515 | biostudies-literature | 2024 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

NeoMUST: an accurate and efficient multi-task learning model for neoantigen presentation.

Ma Wang W Zhang Jiawei J Yao Hui H

Life science alliance 20240130 4

Accurate identification of neoantigens is important for advancing cancer immunotherapies. This study introduces Neoantigen MUlti-taSk Tower (NeoMUST), a model employing multi-task learning to effectively capture task-specific information across related tasks. Our results show that NeoMUST rivals existing algorithms in predicting the presentation of neoantigens via MHC-I molecules, while demonstrating a significantly shorter training time for enhanced computational efficiency. The use of multi-ta ...[more]

PMID: 38290755

Similar Datasets

Model-Protected Multi-Task Learning.

Project description:Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together. In contrast, in single-task learning (STL) each individual task is learned independently. MTL often leads to better trained models because they can leverage the commonalities among related tasks. However, because MTL algorithms can "leak" information from different models across different tasks, MTL poses a potential security risk. Specifically, an adversary may participate in the MTL process through one task and thereby acquire the model information for another task. The previously proposed privacy-preserving MTL methods protect data instances rather than models, and some of them may underperform in comparison with STL methods. In this paper, we propose a privacy-preserving MTL framework to prevent information from each model leaking to other models based on a perturbation of the covariance matrix of the model matrix. We study two popular MTL approaches for instantiation, namely, learning the low-rank and group-sparse patterns of the model matrix. Our algorithms can be guaranteed not to underperform compared with STL methods. We build our methods based upon tools for differential privacy, and privacy guarantees, utility bounds are provided, and heterogeneous privacy budgets are considered. The experiments demonstrate that our algorithms outperform the baseline methods constructed by existing privacy-preserving MTL methods on the proposed model-protection problem.

| S-EPMC8828679 | biostudies-literature

Multi-task learning uncovers robust translation cis-regulatory features

Project description:To validate the sequence motifs identified by our multi-task learning model MTtrans, a new 5' UTR library with around 8,000 synthetic 5'UTRs was built to express EGFP. The reads count was used as a proxy of translation rate here to validate the estimated regulatory effect of motifs that we inferred from multiple datasets, proving the robustness of the sequence motifs.

2022-04-28 | GSE201766 | GEO

Accurate and efficient protein embedding using multi-teacher distillation learning.

Project description:MotivationProtein embedding, which represents proteins as numerical vectors, is a crucial step in various learning-based protein annotation/classification problems, including gene ontology prediction, protein-protein interaction prediction, and protein structure prediction. However, existing protein embedding methods are often computationally expensive due to their large number of parameters, which can reach millions or even billions. The growing availability of large-scale protein datasets and the need for efficient analysis tools have created a pressing demand for efficient protein embedding methods.ResultsWe propose a novel protein embedding approach based on multi-teacher distillation learning, which leverages the knowledge of multiple pre-trained protein embedding models to learn a compact and informative representation of proteins. Our method achieves comparable performance to state-of-the-art methods while significantly reducing computational costs and resource requirements. Specifically, our approach reduces computational time by ∼70% and maintains ±1.5% accuracy as the original large models. This makes our method well-suited for large-scale protein analysis and enables the bioinformatics community to perform protein embedding tasks more efficiently.Availability and implementationThe source code of MTDP is available via https://github.com/KennthShang/MTDP.

| S-EPMC11441318 | biostudies-literature

Genotype-phenotype association study via new multi-task learning model.

Project description:Research on the associations between genetic variations and imaging phenotypes is developing with the advance in high-throughput genotype and brain image techniques. Regression analysis of single nucleotide polymorphisms (SNPs) and imaging measures as quantitative traits (QTs) has been proposed to identify the quantitative trait loci (QTL) via multi-task learning models. Recent studies consider the interlinked structures within SNPs and imaging QTs through group lasso, e.g. ℓ2, 1-norm, leading to better predictive results and insights of SNPs. However, group sparsity is not enough for representing the correlation between multiple tasks and ℓ2, 1-norm regularization is not robust either. In this paper, we propose a new multi-task learning model to analyze the associations between SNPs and QTs. We suppose that low-rank structure is also beneficial to uncover the correlation between genetic variations and imaging phenotypes. Finally, we conduct regression analysis of SNPs and QTs. Experimental results show that our model is more accurate in prediction than compared methods and presents new insights of SNPs.

| S-EPMC5890010 | biostudies-literature

Multi-modal deep learning enables efficient and accurate annotation of enzymatic active sites.

Project description:Annotating active sites in enzymes is crucial for advancing multiple fields including drug discovery, disease research, enzyme engineering, and synthetic biology. Despite the development of numerous automated annotation algorithms, a significant trade-off between speed and accuracy limits their large-scale practical applications. We introduce EasIFA, an enzyme active site annotation algorithm that fuses latent enzyme representations from the Protein Language Model and 3D structural encoder, and then aligns protein-level information with the knowledge of enzymatic reactions using a multi-modal cross-attention framework. EasIFA outperforms BLASTp with a 10-fold speed increase and improved recall, precision, f1 score, and MCC by 7.57%, 13.08%, 9.68%, and 0.1012, respectively. It also surpasses empirical-rule-based algorithm and other state-of-the-art deep learning annotation method based on PSSM features, achieving a speed increase ranging from 650 to 1400 times while enhancing annotation quality. This makes EasIFA a suitable replacement for conventional tools in both industrial and academic settings. EasIFA can also effectively transfer knowledge gained from coarsely annotated enzyme databases to smaller, high-precision datasets, highlighting its ability to model sparse and high-quality databases. Additionally, EasIFA shows potential as a catalytic site monitoring tool for designing enzymes with desired functions beyond their natural distribution.

| S-EPMC11347633 | biostudies-literature

YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting.

Project description:BackgroundThe number of soybean pods is one of the most important indicators of soybean yield, pod counting is crucial for yield estimation, cultivation management, and variety breeding. Counting pods manually is slow and laborious. For crop counting, using object detection network is a common practice, but the scattered and overlapped pods make the detection and counting of the pods difficult.ResultsWe propose an approach that we named YOLO POD, based on the YOLO X framework. On top of YOLO X, we added a block for predicting the number of pods, modified the loss function, thus constructing a multi-task model, and introduced the Convolutional Block Attention Module (CBAM). We achieve accurate identification and counting of pods without reducing the speed of inference. The results showed that the R2 between the number predicted by YOLO POD and the ground truth reached 0.967, which is improved by 0.049 compared to YOLO X, while the inference time only increased by 0.08 s. Moreover, MAE, MAPE, RMSE are only 4.18, 10.0%, 6.48 respectively, the deviation is very small.ConclusionsWe have achieved the first accurate counting of soybean pods and proposed a new solution for the detection and counting of dense objects.

| S-EPMC9883929 | biostudies-literature

Multi-PLI: interpretable multi-task deep learning model for unifying protein-ligand interaction datasets.

Project description:The assessment of protein-ligand interactions is critical at early stage of drug discovery. Computational approaches for efficiently predicting such interactions facilitate drug development. Recently, methods based on deep learning, including structure- and sequence-based models, have achieved impressive performance on several different datasets. However, their application still suffers from a generalizability issue because of insufficient data, especially for structure based models, as well as a heterogeneity problem because of different label measurements and varying proteins across datasets. Here, we present an interpretable multi-task model to evaluate protein-ligand interaction (Multi-PLI). The model can run classification (binding or not) and regression (binding affinity) tasks concurrently by unifying different datasets. The model outperforms traditional docking and machine learning on both binary classification and regression tasks and achieves competitive results compared with some structure-based deep learning methods, even with the same training set size. Furthermore, combined with the proposed occlusion algorithm, the model can predict the important amino acids of proteins that are crucial for binding, thus providing a biological interpretation.

| S-EPMC8051026 | biostudies-literature

Alanine-based spacers promote an efficient antigen processing and presentation in neoantigen polypeptide vaccines.

Project description:Neoantigens are tumor-specific antigens that are mostly particular for each patient. Since the immune system is able to mount a specific immune response against these neoantigens, they are a promising tool for the development of therapeutic personalized cancer vaccines. Neoantigens must be presented to T cells by antigen presenting cells (APC) in the context of MHC-I or MHC-II molecules. Therefore, the strategy of vaccine delivery may have a major impact on the magnitude and quality of T cell responses. Neoantigen-based vaccines are frequently administered as a pool of individual synthetic peptides that induce mainly CD4+ T cell responses. MHC-I-mediated presentation and the elicitation of CD8+ T cell responses may be improved using DNA or RNA sequences that code for a unique long polypeptide that concatenates the different neoantigens spaced by linker sequences. When administered this way, the selection of the spacer between neoantigens is of special interest, as it might influence the processing and presentation of the right peptides by APCs. Here, we evaluate the impact of such linker regions on the MHC-I-dependent antigen presentation using an in vitro assay that assesses the MHC-I presentation of SIINFEKL, a H-2 Kb-restricted OVA peptide. Our results show that spacers used to generate epitope concatenates have a large impact on the efficiency of neoantigen processing and presentation by MHC-I molecules; in contrast, the peptide position and the flanking regions have a minimal impact. Moreover, linkers based on alanine residues promote a more efficient peptide presentation than the commonly used GGGS linker.

| S-EPMC10264286 | biostudies-literature

A multi-task CNN learning model for taxonomic assignment of human viruses.

Project description:BackgroundTaxonomic assignment is a key step in the identification of human viral pathogens. Current tools for taxonomic assignment from sequencing reads based on alignment or alignment-free k-mer approaches may not perform optimally in cases where the sequences diverge significantly from the reference sequences. Furthermore, many tools may not incorporate the genomic coverage of assigned reads as part of overall likelihood of a correct taxonomic assignment for a sample.ResultsIn this paper, we describe the development of a pipeline that incorporates a multi-task learning model based on convolutional neural network (MT-CNN) and a Bayesian ranking approach to identify and rank the most likely human virus from sequence reads. For taxonomic assignment of reads, the MT-CNN model outperformed Kraken 2, Centrifuge, and Bowtie 2 on reads generated from simulated divergent HIV-1 genomes and was more sensitive in identifying SARS as the closest relation in four RNA sequencing datasets for SARS-CoV-2 virus. For genomic region assignment of assigned reads, the MT-CNN model performed competitively compared with Bowtie 2 and the region assignments were used for estimation of genomic coverage that was incorporated into a naïve Bayesian network together with the proportion of taxonomic assignments to rank the likelihood of candidate human viruses from sequence data.ConclusionsWe have developed a pipeline that combines a novel MT-CNN model that is able to identify viruses with divergent sequences together with assignment of the genomic region, with a Bayesian approach to ranking of taxonomic assignments by taking into account both the number of assigned reads and genomic coverage. The pipeline is available at GitHub via https://github.com/MaHaoran627/CNN_Virus .

| S-EPMC8170063 | biostudies-literature

An efficient and accurate distributed learning algorithm for modeling multi-site zero-inflated count outcomes.

Project description:Clinical research networks (CRNs), made up of multiple healthcare systems each with patient data from several care sites, are beneficial for studying rare outcomes and increasing generalizability of results. While CRNs encourage sharing aggregate data across healthcare systems, individual systems within CRNs often cannot share patient-level data due to privacy regulations, prohibiting multi-site regression which requires an analyst to access all individual patient data pooled together. Meta-analysis is commonly used to model data stored at multiple institutions within a CRN but can result in biased estimation, most notably in rare-event contexts. We present a communication-efficient, privacy-preserving algorithm for modeling multi-site zero-inflated count outcomes within a CRN. Our method, a one-shot distributed algorithm for performing hurdle regression (ODAH), models zero-inflated count data stored in multiple sites without sharing patient-level data across sites, resulting in estimates closely approximating those that would be obtained in a pooled patient-level data analysis. We evaluate our method through extensive simulations and two real-world data applications using electronic health records: examining risk factors associated with pediatric avoidable hospitalization and modeling serious adverse event frequency associated with a colorectal cancer therapy. In simulations, ODAH produced bias less than 0.1% across all settings explored while meta-analysis estimates exhibited bias up to 12.7%, with meta-analysis performing worst in settings with high zero-inflation or low event rates. Across both applied analyses, ODAH estimates had less than 10% bias for 18 of 20 coefficients estimated, while meta-analysis estimates exhibited substantially higher bias. Relative to existing methods for distributed data analysis, ODAH offers a highly accurate, computationally efficient method for modeling multi-site zero-inflated count data.

| S-EPMC8490431 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data