A method to improve protein function prediction for sparsely annotated PPI networks is introduced. The method extends the DSD
majority vote algorithm introduced by Cao et al. to give confidence
scores on predicted labels and to use predictions of high confidence
to predict the labels of other nodes in subsequent rounds. We call
this a majority vote cascade. Several cascade variants are tested in
a stringent cross-validation experiment on PPI networks from S.
cerevisiae and D. melanogaster, and we show that for many different
settings with several alternative confidence functions, cascading improves the accuracy of the predictions. A list of the most confident
new label predictions in the two networks is also reported.
Code, networks for the cross-validation experiments, and supplementary figures and tables appear at http://bcb.cs.tufts.edu/cascade.
more »
« less
Majority Vote Cascading: A Semi-Supervised Framework for Improving Protein Function Prediction
A method to improve protein function prediction for sparsely annotated PPI networks is introduced. The method extends the DSD majority vote algorithm introduced by Cao et al. to give confidence scores on predicted labels and to use predictions of high confidence to predict the labels of other nodes in subsequent rounds. We call this a majority vote cascade. Several cascade variants are tested in a stringent cross-validation experiment on PPI networks from S. cerevisiae and D. melanogaster, and we show that for many different settings with several alternative confidence functions, cascading improves the accuracy of the predictions. A list of the most confident new label predictions in the two networks is also reported. Code and networks for the cross-validation experiments appear at http://bcb.cs.tufts.edu/cascade.
more »
« less
- NSF-PAR ID:
- 10346852
- Date Published:
- Journal Name:
- IEEE/ACM Transactions on Computational Biology and Bioinformatics
- ISSN:
- 1545-5963
- Page Range / eLocation ID:
- 1 to 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Motivation One of the core problems in the analysis of biological networks is the link prediction problem. In particular, existing interactions networks are noisy and incomplete snapshots of the true network, with many true links missing because those interactions have not yet been experimentally observed. Methods to predict missing links have been more extensively studied for social than for biological networks; it was recently argued that there is some special structure in protein–protein interaction (PPI) network data that might mean that alternate methods may outperform the best methods for social networks. Based on a generalization of the diffusion state distance, we design a new embedding-based link prediction method called global and local integrated diffusion embedding (GLIDE). GLIDE is designed to effectively capture global network structure, combined with alternative network type-specific customized measures that capture local network structure. We test GLIDE on a collection of three recently curated human biological networks derived from the 2016 DREAM disease module identification challenge as well as a classical version of the yeast PPI network in rigorous cross validation experiments. Results We indeed find that different local network structure is dominant in different types of biological networks. We find that the simple local network measures are dominant in the highly connected network core between hub genes, but that GLIDE’s global embedding measure adds value in the rest of the network. For example, we make GLIDE-based link predictions from genes known to be involved in Crohn’s disease, to genes that are not known to have an association, and make some new predictions, finding support in other network data and the literature. Availability and implementation GLIDE can be downloaded at https://bitbucket.org/kap_devkota/glide. Supplementary information Supplementary data are available at Bioinformatics online.more » « less
-
null (Ed.)In this paper, we quantify the joint acoustic emissions (JAEs) from the knees of children with juvenile idiopathic arthritis (JIA) and support their use as a novel biomarker of the disease. JIA is the most common rheumatic disease of childhood; it has a highly variable presentation, and few reliable biomarkers which makes diagnosis and personalization of care difficult. The knee is the most commonly affected joint with hallmark synovitis and inflammation that can extend to damage the underlying cartilage and bone. During movement of the knee, internal friction creates JAEs that can be non-invasively measured. We hypothesize that these JAEs contain clinically relevant information that could be used for the diagnosis and personalization of treatment of JIA. In this study, we record and compare the JAEs from 25 patients with JIA−10 of whom were recorded a second time 3–6 months later—and 18 healthy age- and sex-matched controls. We compute signal features from each of those record cycles of flexion/extension and train a logistic regression classification model. The model classified each cycle as having JIA or being healthy with 84.4% accuracy using leave-one-subject-out cross validation (LOSO-CV). When assessing the full JAE recording of a subject (which contained at least 8 cycles of flexion/extension), a majority vote of the cycle labels accurately classified the subjects as having JIA or being healthy 100% of the time. Using the output probabilities of a JIA class as a basis for a joint health score and test it on the follow-up patient recordings. In all 10 of our 6-week follow-up recordings, the score accurately tracked with successful treatment of the condition. Our proposed JAE-based classification model of JIA presents a compelling case for incorporating this novel joint health assessment technique into the clinical work-up and monitoring of JIA.more » « less
-
Martelli, Pier Luigi (Ed.)Abstract Motivation Transferring knowledge between species is challenging: different species contain distinct proteomes and cellular architectures, which cause their proteins to carry out different functions via different interaction networks. Many approaches to protein functional annotation use sequence similarity to transfer knowledge between species. These approaches cannot produce accurate predictions for proteins without homologues of known function, as many functions require cellular context for meaningful prediction. To supply this context, network-based methods use protein-protein interaction (PPI) networks as a source of information for inferring protein function and have demonstrated promising results in function prediction. However, most of these methods are tied to a network for a single species, and many species lack biological networks. Results In this work, we integrate sequence and network information across multiple species by computing IsoRank similarity scores to create a meta-network profile of the proteins of multiple species. We use this integrated multispecies meta-network as input to train a maxout neural network with Gene Ontology terms as target labels. Our multispecies approach takes advantage of more training examples, and consequently leads to significant improvements in function prediction performance compared to two network-based methods, a deep learning sequence-based method and the BLAST annotation method used in the Critial Assessment of Functional Annotation. We are able to demonstrate that our approach performs well even in cases where a species has no network information available: when an organism’s PPI network is left out we can use our multi-species method to make predictions for the left-out organism with good performance. Availability and implementation The code is freely available at https://github.com/nowittynamesleft/NetQuilt. The data, including sequences, PPI networks and GO annotations are available at https://string-db.org/. Supplementary information Supplementary data are available at Bioinformatics online.more » « less
-
Wang, L. ; Dou, Q. ; Fletcher, P.T. ; Speidel, S. ; Li, S. (Ed.)Model calibration measures the agreement between the predicted probability estimates and the true correctness likelihood. Proper model calibration is vital for high-risk applications. Unfortunately, modern deep neural networks are poorly calibrated, compromising trustworthiness and reliability. Medical image segmentation particularly suffers from this due to the natural uncertainty of tissue boundaries. This is exasperated by their loss functions, which favor overconfidence in the majority classes. We address these challenges with DOMINO, a domain-aware model calibration method that leverages the semantic confusability and hierarchical similarity between class labels. Our experiments demonstrate that our DOMINO-calibrated deep neural networks outperform non-calibrated models and state-of-the-art morphometric methods in head image segmentation. Our results show that our method can consistently achieve better calibration, higher accuracy, and faster inference times than these methods, especially on rarer classes. This performance is attributed to our domain-aware regularization to inform semantic model calibration. These findings show the importance of semantic ties between class labels in building confidence in deep learning models. The framework has the potential to improve the trustworthiness and reliability of generic medical image segmentation models. The code for this article is available at: https://github.com/lab-smile/DOMINO.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TCBB.2021.3059812
