Dataset Information

Inferring Protein Sequence-Function Relationships with Large-Scale Positive-Unlabeled Learning.

ABSTRACT: Machine learning can infer how protein sequence maps to function without requiring a detailed understanding of the underlying physical or biological mechanisms. It is challenging to apply existing supervised learning frameworks to large-scale experimental data generated by deep mutational scanning (DMS) and related methods. DMS data often contain high-dimensional and correlated sequence variables, experimental sampling error and bias, and the presence of missing data. Notably, most DMS data do not contain examples of negative sequences, making it challenging to directly estimate how sequence affects function. Here, we develop a positive-unlabeled (PU) learning framework to infer sequence-function relationships from large-scale DMS data. Our PU learning method displays excellent predictive performance across ten large-scale sequence-function datasets, representing proteins of different folds, functions, and library types. The estimated parameters pinpoint key residues that dictate protein structure and function. Finally, we apply our statistical sequence-function model to design highly stabilized enzymes.

SUBMITTER: Song H

PROVIDER: S-EPMC7856229 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Inferring Protein Sequence-Function Relationships with Large-Scale Positive-Unlabeled Learning.

Song Hyebin H Bremer Bennett J BJ Hinds Emily C EC Raskutti Garvesh G Romero Philip A PA

Cell systems 20201118 1

Machine learning can infer how protein sequence maps to function without requiring a detailed understanding of the underlying physical or biological mechanisms. It is challenging to apply existing supervised learning frameworks to large-scale experimental data generated by deep mutational scanning (DMS) and related methods. DMS data often contain high-dimensional and correlated sequence variables, experimental sampling error and bias, and the presence of missing data. Notably, most DMS data do n ...[more]

PMID: 33212013

Similar Datasets

Project description:BackgroundDrug-drug interactions (DDIs) are a major concern in patients' medication. It's unfeasible to identify all potential DDIs using experimental methods which are time-consuming and expensive. Computational methods provide an effective strategy, however, facing challenges due to the lack of experimentally verified negative samples.ResultsTo address this problem, we propose a novel positive-unlabeled learning method named DDI-PULearn for large-scale drug-drug-interaction predictions. DDI-PULearn first generates seeds of reliable negatives via OCSVM (one-class support vector machine) under a high-recall constraint and via the cosine-similarity based KNN (k-nearest neighbors) as well. Then trained with all the labeled positives (i.e., the validated DDIs) and the generated seed negatives, DDI-PULearn employs an iterative SVM to identify a set of entire reliable negatives from the unlabeled samples (i.e., the unobserved DDIs). Following that, DDI-PULearn represents all the labeled positives and the identified negatives as vectors of abundant drug properties by a similarity-based method. Finally, DDI-PULearn transforms these vectors into a lower-dimensional space via PCA (principal component analysis) and utilizes the compressed vectors as input for binary classifications. The performance of DDI-PULearn is evaluated on simulative prediction for 149,878 possible interactions between 548 drugs, comparing with two baseline methods and five state-of-the-art methods. Related experiment results show that the proposed method for the representation of DDIs characterizes them accurately. DDI-PULearn achieves superior performance owing to the identified reliable negatives, outperforming all other methods significantly. In addition, the predicted novel DDIs suggest that DDI-PULearn is capable to identify novel DDIs.ConclusionsThe results demonstrate that positive-unlabeled learning paves a new way to tackle the problem caused by the lack of experimentally verified negatives in the computational prediction of DDIs.

Project description:BackgroundIdentifying disease genes from human genome is an important but challenging task in biomedical research. Machine learning methods can be applied to discover new disease genes based on the known ones. Existing machine learning methods typically use the known disease genes as the positive training set P and the unknown genes as the negative training set N (non-disease gene set does not exist) to build classifiers to identify new disease genes from the unknown genes. However, such kind of classifiers is actually built from a noisy negative set N as there can be unknown disease genes in N itself. As a result, the classifiers do not perform as well as they could be.ResultInstead of treating the unknown genes as negative examples in N, we treat them as an unlabeled set U. We design a novel positive-unlabeled (PU) learning algorithm PUDI (PU learning for disease gene identification) to build a classifier using P and U. We first partition U into four sets, namely, reliable negative set RN, likely positive set LP, likely negative set LN and weak negative set WN. The weighted support vector machines are then used to build a multi-level classifier based on the four training sets and positive training set P to identify disease genes. Our experimental results demonstrate that our proposed PUDI algorithm outperformed the existing methods significantly.ConclusionThe proposed PUDI algorithm is able to identify disease genes more accurately by treating the unknown data more appropriately as unlabeled set U instead of negative set N. Given that many machine learning problems in biomedical research do involve positive and unlabeled data instead of negative data, it is possible that the machine learning methods for these problems can be further improved by adopting PU learning methods, as we have done here for disease gene identification.Availability and implementationThe executable program and data are available at http://www1.i2r.a-star.edu.sg/~xlli/PUDI/PUDI.html.

Project description:BackgroundPretraining labeled datasets, like ImageNet, have become a technical standard in advanced medical image analysis. However, the emergence of self-supervised learning (SSL), which leverages unlabeled data to learn robust features, presents an opportunity to bypass the intensive labeling process. In this study, we explored if SSL for pretraining on non-medical images can be applied to chest radiographs and how it compares to supervised pretraining on non-medical images and on medical images.MethodsWe utilized a vision transformer and initialized its weights based on the following: (i) SSL pretraining on non-medical images (DINOv2), (ii) supervised learning (SL) pretraining on non-medical images (ImageNet dataset), and (iii) SL pretraining on chest radiographs from the MIMIC-CXR database, the largest labeled public dataset of chest radiographs to date. We tested our approach on over 800,000 chest radiographs from 6 large global datasets, diagnosing more than 20 different imaging findings. Performance was quantified using the area under the receiver operating characteristic curve and evaluated for statistical significance using bootstrapping.ResultsSSL pretraining on non-medical images not only outperformed ImageNet-based pretraining (p < 0.001 for all datasets) but, in certain cases, also exceeded SL on the MIMIC-CXR dataset. Our findings suggest that selecting the right pretraining strategy, especially with SSL, can be pivotal for improving diagnostic accuracy of artificial intelligence in medical imaging.ConclusionsBy demonstrating the promise of SSL in chest radiograph analysis, we underline a transformative shift towards more efficient and accurate AI models in medical imaging.Relevance statementSelf-supervised learning highlights a paradigm shift towards the enhancement of AI-driven accuracy and efficiency in medical imaging. Given its promise, the broader application of self-supervised learning in medical imaging calls for deeper exploration, particularly in contexts where comprehensive annotated datasets are limited.

Project description:An increasing number of genes have been experimentally confirmed in recent years as causative genes to various human diseases. The newly available knowledge can be exploited by machine learning methods to discover additional unknown genes that are likely to be associated with diseases. In particular, positive unlabeled learning (PU learning) methods, which require only a positive training set P (confirmed disease genes) and an unlabeled set U (the unknown candidate genes) instead of a negative training set N, have been shown to be effective in uncovering new disease genes in the current scenario. Using only a single source of data for prediction can be susceptible to bias due to incompleteness and noise in the genomic data and a single machine learning predictor prone to bias caused by inherent limitations of individual methods. In this paper, we propose an effective PU learning framework that integrates multiple biological data sources and an ensemble of powerful machine learning classifiers for disease gene identification. Our proposed method integrates data from multiple biological sources for training PU learning classifiers. A novel ensemble-based PU learning method EPU is then used to integrate multiple PU learning classifiers to achieve accurate and robust disease gene predictions. Our evaluation experiments across six disease groups showed that EPU achieved significantly better results compared with various state-of-the-art prediction methods as well as ensemble learning classifiers. Through integrating multiple biological data sources for training and the outputs of an ensemble of PU learning classifiers for prediction, we are able to minimize the potential bias and errors in individual data sources and machine learning algorithms to achieve more accurate and robust disease gene predictions. In the future, our EPU method provides an effective framework to integrate the additional biological and computational resources for better disease gene predictions.

Project description:The cytosolic glutathione transferase (cytGST) superfamily comprises more than 13,000 nonredundant sequences found throughout the biosphere. Their key roles in metabolism and defense against oxidative damage have led to thousands of studies over several decades. Despite this attention, little is known about the physiological reactions they catalyze and most of the substrates used to assay cytGSTs are synthetic compounds. A deeper understanding of relationships across the superfamily could provide new clues about their functions. To establish a foundation for expanded classification of cytGSTs, we generated similarity-based subgroupings for the entire superfamily. Using the resulting sequence similarity networks, we chose targets that broadly covered unknown functions and report here experimental results confirming GST-like activity for 82 of them, along with 37 new 3D structures determined for 27 targets. These new data, along with experimentally known GST reactions and structures reported in the literature, were painted onto the networks to generate a global view of their sequence-structure-function relationships. The results show how proteins of both known and unknown function relate to each other across the entire superfamily and reveal that the great majority of cytGSTs have not been experimentally characterized or annotated by canonical class. A mapping of taxonomic classes across the superfamily indicates that many taxa are represented in each subgroup and highlights challenges for classification of superfamily sequences into functionally relevant classes. Experimental determination of disulfide bond reductase activity in many diverse subgroups illustrate a theme common for many reaction types. Finally, sequence comparison between an enzyme that catalyzes a reductive dechlorination reaction relevant to bioremediation efforts with some of its closest homologs reveals differences among them likely to be associated with evolution of this unusual reaction. Interactive versions of the networks, associated with functional and other types of information, can be downloaded from the Structure-Function Linkage Database (SFLD; http://sfld.rbvi.ucsf.edu).

Dataset Information

Inferring Protein Sequence-Function Relationships with Large-Scale Positive-Unlabeled Learning.

Publications

Inferring Protein Sequence-Function Relationships with Large-Scale Positive-Unlabeled Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets