Cox-nnet v2.0: improved neural-network based survival prediction extended to large-scale EMR data.
Ontology highlight
ABSTRACT: Summary
Cox-nnet is a neural-network based prognosis prediction method, originally applied to genomics data. Here we propose the version 2 of Cox-nnet, with significant improvement on efficiency and interpretability, making it suitable to predict prognosis based on large-scale population data, including those electronic medical records (EMR) datasets. We also add permutation-based feature importance scores and the direction of feature coefficients. When applied on a kidney transplantation dataset, Cox-nnet v2.0 reduces the training time of Cox-nnet up to 32 folds (n = 10,000) and achieves better prediction accuracy than Cox-PH (p < 0.05). It also achieves similarly superior performance on a publicly available SUPPORT data (n = 8,000). The high efficiency and accuracy make Cox-nnet v2.0 a desirable method for survival prediction in large-scale EMR data.Availability and implementation
Cox-nnet v2.0 is freely available to the public at https://github.com/lanagarmire/Cox-nnet-v2.0.Supplementary information
Supplementary data are available at Bioinformatics online.
SUBMITTER: Wang D
PROVIDER: S-EPMC8428611 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:End-user training is an essential element of electronic medical record (EMR) implementation and frequently suffers from minimal institutional investment. In addition, discussion of successful EMR training programs for physicians is limited in the literature. The authors describe a successful physician-training program at Stanford Children's Health as part of a large scale EMR implementation. Evaluations of classroom training, obtained at the conclusion of each class, revealed high physician satisfaction with the program. Free-text comments from learners focused on duration and timing of training, the learning environment, quality of the instructors, and specificity of training to their role or department. Based upon participant feedback and institutional experience, best practice recommendations, including physician engagement, curricular design, and assessment of proficiency and recognition, are suggested for future provider EMR training programs. The authors strongly recommend the creation of coursework to group providers by common workflow.
| S-EPMC4377562 | biostudies-literature
Project description:USEEIO v2.0 is an environmental-economic model of US goods and services that can be used for life cycle assessment, footprinting, national prioritization, and related applications. This paper describes the development of the model and accompanies the release of a full model dataset as well as various supporting datasets of national environmental totals by US industry. Novel methodological elements since USEEIO v1 models include waste sector disaggregation, final demand vectors for US consumption and production, a domestic form of the model that can be used to separate domestic and foreign impacts, and price adjustment matrices for converting outputs to purchaser price and in various US dollar years. Improvements in modeling national totals of industry and environmental flows are described. The model is validated through reproduction of national totals from input data sources and through analysis of changes from the most recent complete USEEIO model that can be explained based on data updates or method changes. The model datasets can all be reproduced with open source software packages.
| S-EPMC9065037 | biostudies-literature
Project description:MotivationAutomated function prediction (AFP) of proteins is a large-scale multi-label classification problem. Two limitations of most network-based methods for AFP are (i) a single model must be trained for each species and (ii) protein sequence information is totally ignored. These limitations cause weaker performance than sequence-based methods. Thus, the challenge is how to develop a powerful network-based method for AFP to overcome these limitations.ResultsWe propose DeepGraphGO, an end-to-end, multispecies graph neural network-based method for AFP, which makes the most of both protein sequence and high-order protein network information. Our multispecies strategy allows one single model to be trained for all species, indicating a larger number of training samples than existing methods. Extensive experiments with a large-scale dataset show that DeepGraphGO outperforms a number of competing state-of-the-art methods significantly, including DeepGOPlus and three representative network-based methods: GeneMANIA, deepNF and clusDCA. We further confirm the effectiveness of our multispecies strategy and the advantage of DeepGraphGO over so-called difficult proteins. Finally, we integrate DeepGraphGO into the state-of-the-art ensemble method, NetGO, as a component and achieve a further performance improvement.Availability and implementationhttps://github.com/yourh/DeepGraphGO.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8294856 | biostudies-literature
Project description:Motivation:Accurate contact predictions can be used for predicting the structure of proteins. Until recently these methods were limited to very big protein families, decreasing their utility. However, recent progress by combining direct coupling analysis with machine learning methods has made it possible to predict accurate contact maps for smaller families. To what extent these predictions can be used to produce accurate models of the families is not known. Results:We present the PconsFold2 pipeline that uses contact predictions from PconsC3, the CONFOLD folding algorithm and model quality estimations to predict the structure of a protein. We show that the model quality estimation significantly increases the number of models that reliably can be identified. Finally, we apply PconsFold2 to 6379 Pfam families of unknown structure and find that PconsFold2 can, with an estimated 90% specificity, predict the structure of up to 558 Pfam families of unknown structure. Out of these, 415 have not been reported before. Availability and Implementation:Datasets as well as models of all the 558 Pfam families are available at http://c3.pcons.net/ . All programs used here are freely available. Contact:arne@bioinfo.se.
| S-EPMC5870574 | biostudies-literature
Project description:MotivationLigand binding is a key aspect of the function of many proteins. Thus, binding ligand prediction provides important insight in understanding the biological function of proteins. Binding ligand prediction is also useful for drug design and examining potential drug side effects.ResultsWe present a computational method named Patch-Surfer2.0, which predicts binding ligands for a protein pocket. By representing and comparing pockets at the level of small local surface patches that characterize physicochemical properties of the local regions, the method can identify binding pockets of the same ligand even if they do not share globally similar shapes. Properties of local patches are represented by an efficient mathematical representation, 3D Zernike Descriptor. Patch-Surfer2.0 has significant technical improvements over our previous prototype, which includes a new feature that captures approximate patch position with a geodesic distance histogram. Moreover, we constructed a large comprehensive database of ligand binding pockets that will be searched against by a query. The benchmark shows better performance of Patch-Surfer2.0 over existing methods.Availability and implementationhttp://kiharalab.org/patchsurfer2.0/ CONTACT: dkihara@purdue.eduSupplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC4341070 | biostudies-literature
Project description:Multi-omics data, that is, datasets containing different types of high-dimensional molecular variables, are increasingly often generated for the investigation of various diseases. Nevertheless, questions remain regarding the usefulness of multi-omics data for the prediction of disease outcomes such as survival time. It is also unclear which methods are most appropriate to derive such prediction models. We aim to give some answers to these questions through a large-scale benchmark study using real data. Different prediction methods from machine learning and statistics were applied on 18 multi-omics cancer datasets (35 to 1000 observations, up to 100 000 variables) from the database 'The Cancer Genome Atlas' (TCGA). The considered outcome was the (censored) survival time. Eleven methods based on boosting, penalized regression and random forest were compared, comprising both methods that do and that do not take the group structure of the omics variables into account. The Kaplan-Meier estimate and a Cox model using only clinical variables were used as reference methods. The methods were compared using several repetitions of 5-fold cross-validation. Uno's C-index and the integrated Brier score served as performance metrics. The results indicate that methods taking into account the multi-omics structure have a slightly better prediction performance. Taking this structure into account can protect the predictive information in low-dimensional groups-especially clinical variables-from not being exploited during prediction. Moreover, only the block forest method outperformed the Cox model on average, and only slightly. This indicates, as a by-product of our study, that in the considered TCGA studies the utility of multi-omics data for prediction purposes was limited. Contact:moritz.herrmann@stat.uni-muenchen.de, +49 89 2180 3198 Supplementary information: Supplementary data are available at Briefings in Bioinformatics online. All analyses are reproducible using R code freely available on Github.
| S-EPMC8138887 | biostudies-literature
Project description:Glioblastoma multiforme (GBM) is the most aggressive and common primary central nervous system tumour. Despite extensive therapy, GBM patients usually have poor prognosis with a median survival of 12-15 months. Novel molecular biomarkers that can improve survival prediction and help with treatment strategies are still urgently required. Here we aimed to robustly identify a gene signature panel for improved survival prediction in primary GBM patients. We identified 2166 differentially expressed genes (DEGs) using meta-analysis of microarray datasets comprising of 955 samples (biggest primary GBM cohort for such studies as per our knowledge) and 3368 DEGs from RNA-seq dataset with 165 samples. Based on the 1443 common DEGs, using univariate Cox and least absolute shrinkage and selection operator (LASSO) with multivariate Cox regression, we identified a survival associated 4-gene signature panel including IGFBP2, PTPRN, STEAP2 and SLC39A10 and thereafter established a risk score model that performed well in survival prediction. High-risk group patients had significantly poorer survival as compared with those in the low-risk group (AUC = 0.766 for 1-year prediction). Multivariate analysis demonstrated that predictive value of the 4-gene signature panel was independent of other clinical and pathological features and hence is a potential prognostic biomarker. More importantly, we validated this signature in three independent GBM cohorts to test its generality. In conclusion, our integrated analysis using meta-analysis approach maximizes the use of the available gene expression data and robustly identified a 4-gene panel for predicting survival in primary GBM.
| S-EPMC7541357 | biostudies-literature
Project description:The collision cross section (CCS) values derived from ion mobility spectrometry can be used to improve the accuracy of compound identification. Here, we have developed the Structure included graph merging with adduct method for CCS prediction (SigmaCCS) based on graph neural networks using 3D conformers as inputs. A model was trained, evaluated, and tested with >5,000 experimental CCS values. It achieved a coefficient of determination of 0.9945 and a median relative error of 1.1751% on the test set. The model-agnostic interpretation method and the visualization of the learned representations were used to investigate the chemical rationality of SigmaCCS. An in-silico database with 282 million CCS values was generated for three different adduct types of 94 million compounds. Its source code is publicly available at https://github.com/zmzhang/SigmaCCS . Altogether, SigmaCCS is an accurate, rational, and off-the-shelf method to directly predict CCS values from molecular structures.
| S-EPMC10319785 | biostudies-literature
Project description:In many biomedical applications, outcome is measured as a "time-to-event" (e.g., disease progression or death). To assess the connection between features of a patient and this outcome, it is common to assume a proportional hazards model and fit a proportional hazards regression (or Cox regression). To fit this model, a log-concave objective function known as the "partial likelihood" is maximized. For moderate-sized data sets, an efficient Newton-Raphson algorithm that leverages the structure of the objective function can be employed. However, in large data sets this approach has two issues: (i) The computational tricks that leverage structure can also lead to computational instability; (ii) The objective function does not naturally decouple: Thus, if the data set does not fit in memory, the model can be computationally expensive to fit. This additionally means that the objective is not directly amenable to stochastic gradient-based optimization methods. To overcome these issues, we propose a simple, new framing of proportional hazards regression: This results in an objective function that is amenable to stochastic gradient descent. We show that this simple modification allows us to efficiently fit survival models with very large data sets. This also facilitates training complex, for example, neural-network-based, models with survival data.
| S-EPMC10724274 | biostudies-literature
Project description:When a moderate number of potential predictors are available and a survival model is fit with regularization to achieve variable selection, providing accurate inference on the predicted survival can be challenging. We investigate inference on the predicted survival estimated after fitting a Cox model under regularization guaranteeing the oracle property. We demonstrate that existing asymptotic formulas for the standard errors of the coefficients tend to underestimate the variability for some coefficients, while typical resampling such as the bootstrap tends to overestimate it; these approaches can both lead to inaccurate variance estimation for predicted survival functions. We propose a two-stage adaptation of a resampling approach that brings the estimated error in line with the truth. In stage 1, we estimate the coefficients in the observed data set and in [Formula: see text] resampled data sets, and allow the resampled coefficient estimates to vote on whether each coefficient should be 0. For those coefficients voted as zero, we set both the point and interval estimates to [Formula: see text] In stage 2, to make inference about coefficients not voted as zero in stage 1, we refit the penalized model in the observed data and in the [Formula: see text] resampled data sets with only variables corresponding to those coefficients. We demonstrate that ensemble voting-based point and interval estimators of the coefficients perform well in finite samples, and prove that the point estimator maintains the oracle property. We extend this approach to derive inference procedures for survival functions and demonstrate that our proposed interval estimation procedures substantially outperform estimators based on asymptotic inference or standard bootstrap. We further illustrate our proposed procedures to predict breast cancer survival in a gene expression study.
| S-EPMC5031946 | biostudies-literature