Inferring Protein Sequence-Function Relationships with Large-Scale Positive-Unlabeled Learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Song H
PROVIDER: S-EPMC7856229 | biostudies-literature |
REPOSITORIES: biostudies-literature
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.
| S-EPMC6929327 | biostudies-literature
Project description: Not available
| EMPIAR-10592 | biostudies-other
Project description:Automated segmentation of cellular electron microscopy (EM) datasets remains a challenge. Supervised deep learning (DL) methods that rely on region-of-interest (ROI) annotations yield models that fail to generalize to unrelated datasets. Newer unsupervised DL algorithms require relevant pre-training images, however, pre-training on currently available EM datasets is computationally expensive and shows little value for unseen biological contexts, as these datasets are large and homogeneous. To address this issue, we present CEM500K, a nimble 25 GB dataset of 0.5 × 106 unique 2D cellular EM images curated from nearly 600 three-dimensional (3D) and 10,000 two-dimensional (2D) images from >100 unrelated imaging projects. We show that models pre-trained on CEM500K learn features that are biologically relevant and resilient to meaningful image augmentations. Critically, we evaluate transfer learning from these pre-trained models on six publicly available and one newly derived benchmark segmentation task and report state-of-the-art results on each. We release the CEM500K dataset, pre-trained models and curation pipeline for model building and further expansion by the EM community. Data and code are available at https://www.ebi.ac.uk/pdbe/emdb/empiar/entry/10592/ and https://git.io/JLLTz.
| S-EPMC8032397 | biostudies-literature
Project description:Pupylation plays a key role in regulating various protein functions as a crucial posttranslational modification of prokaryotes. In order to understand the molecular mechanism of pupylation, it is important to identify pupylation substrates and sites accurately. Several computational methods have been developed to identify pupylation sites because the traditional experimental methods are time-consuming and labor-sensitive. With the existing computational methods, the experimentally annotated pupylation sites are used as the positive training set and the remaining nonannotated lysine residues as the negative training set to build classifiers to predict new pupylation sites from the unknown proteins. However, the remaining nonannotated lysine residues may contain pupylation sites which have not been experimentally validated yet. Unlike previous methods, in this study, the experimentally annotated pupylation sites were used as the positive training set whereas the remaining nonannotated lysine residues were used as the unlabeled training set. A novel method named PUL-PUP was proposed to predict pupylation sites by using positive-unlabeled learning technique. Our experimental results indicated that PUL-PUP outperforms the other methods significantly for the prediction of pupylation sites. As an application, PUL-PUP was also used to predict the most likely pupylation sites in nonannotated lysine sites.
| S-EPMC4992543 | biostudies-literature
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.
| S-EPMC3467748 | biostudies-literature
Project description:Identifying drug-target interaction (DTI) candidates is crucial for drug repositioning. However, usually only positive DTIs are deposited in known databases, which challenges computational methods to predict novel DTIs due to the lack of negative samples. To overcome this dilemma, researchers usually randomly select negative samples from unlabeled drug-target pairs, which introduces a lot of false-positives. In this study, a negative sample extraction method named NDTISE is first developed to screen strong negative DTI examples based on positive-unlabeled learning. A novel DTI screening framework, PUDTI, is then designed to infer new drug repositioning candidates by integrating NDTISE, probabilities that remaining ambiguous samples belong to the positive and negative classes, and an SVM-based optimization model. We investigated the effectiveness of NDTISE on a DTI data provided by NCPIS. NDTISE is much better than random selection and slightly outperforms NCPIS. We then compared PUDTI with 6 state-of-the-art methods on 4 classes of DTI datasets from human enzymes, ion channels, GPCRs and nuclear receptors. PUDTI achieved the highest AUC among the 7 methods on all 4 datasets. Finally, we validated a few top predicted DTIs through mining independent drug databases and literatures. In conclusion, PUDTI provides an effective pre-filtering method for new drug design.
| S-EPMC5556112 | biostudies-literature
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.
| S-EPMC4016241 | biostudies-literature
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).
| S-EPMC3995644 | biostudies-literature
Project description:Recent large-scale data sets of protein complex purifications have provided unprecedented insights into the organization of cellular protein complexes. Several computational methods have been developed to detect co-complexed proteins in these data sets. Their common aim is the identification of biologically relevant protein complexes. However, much less is known about the network of direct physical protein contacts within the detected protein complexes. Therefore, our work investigates whether direct physical contacts can be computationally derived by combining raw data of large-scale protein complex purifications. We assess four established scoring schemes and introduce a new scoring approach that is specifically devised to infer direct physical protein contacts from protein complex purifications. The physical contacts identified by the five methods are comprehensively benchmarked against different reference sets that provide evidence for true physical contacts. Our results show that raw purification data can indeed be exploited to determine high-confidence physical protein contacts within protein complexes. In particular, our new method outperforms competing approaches at discovering physical contacts involving proteins that have been screened multiple times in purification experiments. It also excels in the analysis of recent protein purification screens of molecular chaperones and protein kinases. In contrast to previous findings, we observe that physical contacts inferred from purification experiments of protein complexes can be qualitatively comparable to binary protein interactions measured by experimental high-throughput assays such as yeast two-hybrid. This suggests that computationally derived physical contacts might complement binary protein interaction assays and guide large-scale interactome mapping projects by prioritizing putative physical contacts for further experimental screens.
| S-EPMC3108834 | biostudies-literature
Project description:Similarity-based search of sequence collections is a core task in bioinformatics, one dominated for most of the genomic era by exact and heuristic alignment-based algorithms. However, even efficient heuristics such as BLAST may not scale to the data sets now emerging, motivating a range of alignment-free alternatives exploiting the underlying lexical structure of each sequence. In this paper, we introduce two supervised approaches-SuperVec and SuperVecX-to learn sequence embeddings. These methods extend earlier Representation Learning (RepL) based methods to include class-related information for each sequence during training. Including class information ensures that related sequence fragments have proximal representations in the target space, better reflecting the structure of the domain. We show the quality of the embeddings learned through these methods on (i) sequence retrieval and (ii) classification tasks. We also propose an hierarchical tree-based approach specifically designed for the sequence retrieval problem. The resulting methods, which we term H-SuperVec or H-SuperVecX, according to their respective use of SuperVec or SuperVecX, learn embeddings across a range of feature spaces based on exclusive and exhaustive subsets of the class labels. Experiments show that the proposed methods perform better for retrieval and classification tasks over existing (unsupervised) RepL-based approaches. Further, the new methods are an order of magnitude faster than BLAST for the database retrieval task, supporting hybrid approaches that rapidly filter the collection so that only potentially relevant records remain. Such filtering of the original database allows slower but more accurate methods to be executed quickly over a far smaller dataset. Thus, we may achieve faster query processing and higher precision than before.
| S-EPMC7069636 | biostudies-literature