Uncovering prostate cancer aggressiveness signal in T2-weighted MRI through a three-reference tissues normalization technique.

Quantitative T2-weighted MRI (T2W) interpretation is impeded by the variability of acquisition-related features, such as field strength, coil type, signal amplification, and pulse sequence parameters. The main purpose of this work is to develop an automated method for prostate T2W intensity normalization. The procedure includes the following: (i) a deep learning-based network utilizing MASK R-CNN for automatic segmentation of three reference tissues: gluteus maximus muscle, femur, and bladder; (ii) fitting a spline function between average intensities in these structures and reference values; and (iii) using the function to transform all T2W intensities. The T2W distributions in the prostate cancer regions of interest (ROIs) and normal appearing prostate tissue (NAT) were compared before and after normalization using Student's t-test. The ROIs' T2W associations with the Gleason Score (GS), Decipher genomic score, and a three-tier prostate cancer risk were evaluated with Spearman's correlation coefficient (rS ). T2W differences in indolent and aggressive prostate cancer lesions were also assessed. The MASK R-CNN was trained with manual contours from 32 patients. The normalization procedure was applied to an independent MRI dataset from 83 patients. T2W differences between ROIs and NAT significantly increased after normalization. T2W intensities in 231 biopsy ROIs were significantly negatively correlated with GS (rS = -0.21, p = 0.001), Decipher (rS = -0.193, p = 0.003), and three-tier risk (rS = -0.235, p < 0.001). The average T2W intensities in the aggressive ROIs were significantly lower than in the indolent ROIs after normalization. In conclusion, the automated triple-reference tissue normalization method significantly improved the discrimination between prostate cancer and normal prostate tissue. In addition, the normalized T2W intensities of cancer exhibited a significant association with tumor aggressiveness. By improving the quantitative utilization of the T2W in the assessment of prostate cancer on MRI, the new normalization method represents an important advance over clinical protocols that do not include sequences for the measurement of T2 relaxation times.

Multi-Action Knee Contact Force Prediction by Domain Adaptation.

Most recent musculoskeletal dynamics estimation methods are designed for predefined actions, such as gait, and don't generalize to various tasks. In this work, we address the problem of estimating internal biomechanical forces during more than one actions by introducing unsupervised domain adaptation into a deep learning model. More specifically, we developed a Bidirectional Long Short-Term Memory network for knee contact force prediction, enhanced with correlation alignment layers, in order to minimize the domain shift between kinematic data from different actions. Furthermore, we used the novel Neural State Machine (NSM) as a simulation platform to test and visualize our model predictions in a wide range of trajectories adapted to different 3D scene geometries in real-time. We conducted multiple experiments, including comparison with previous models, model alignment across action classes and real-to-synthetic data alignment. The results showed that the proposed deep learning architecture with domain adaptation performs better than the benchmark in terms of NRMSE and t-test. Overall, our method is capable of predicting knee contact forces for more than one action classes using a single architecture and thereby opens the path for estimating internal forces for intermediate actions, while the knowledge of the hidden state of motion may be used to support personalized rehabilitation. Moreover, our model can be easily integrated into any human motion simulation environment, which shows its potential in enabling biomechanical analysis in an automated and computationally efficient way.

A Deep Learning Approach for Automatic Segmentation during Daily MRI-Linac Radiotherapy of Glioblastoma.

Glioblastoma changes during chemoradiotherapy are inferred from high-field MRI before and after treatment but are rarely investigated during radiotherapy. The purpose of this study was to develop a deep learning network to automatically segment glioblastoma tumors on daily treatment set-up scans from the first glioblastoma patients treated on MRI-linac. Glioblastoma patients were prospectively imaged daily during chemoradiotherapy on 0.35T MRI-linac. Tumor and edema (tumor lesion) and resection cavity kinetics throughout the treatment were manually segmented on these daily MRI. Utilizing a convolutional neural network, an automatic segmentation deep learning network was built. A nine-fold cross-validation schema was used to train the network using 80:10:10 for training, validation, and testing. Thirty-six glioblastoma patients were imaged pre-treatment and 30 times during radiotherapy (n = 31 volumes, total of 930 MRIs). The average tumor lesion and resection cavity volumes were 94.56 ± 64.68 cc and 72.44 ± 35.08 cc, respectively. The average Dice similarity coefficient between manual and auto-segmentation for tumor lesion and resection cavity across all patients was 0.67 and 0.84, respectively. This is the first brain lesion segmentation network developed for MRI-linac. The network performed comparably to the only other published network for auto-segmentation of post-operative glioblastoma lesions. Segmented volumes can be utilized for adaptive radiotherapy and propagated across multiple MRI contrasts to create a prognostic model for glioblastoma based on multiparametric MRI.

Machine learning approaches for 3D motion synthesis and musculoskeletal dynamics estimation: A Survey.

The inference of 3D motion and dynamics of the human musculoskeletal system has traditionally been solved using physics-based methods that exploit physical parameters to provide realistic simulations. Yet, such methods suffer from computational complexity and reduced stability, hindering their use in computer graphics applications that require real-time performance. With the recent explosion of data capture (mocap, video) machine learning (ML) has started to become popular as it is able to create surrogate models harnessing the huge amount of data stemming from various sources, minimizing computational time (instead of resource usage), and most importantly, approximate real-time solutions. The main purpose of this paper is to provide a review and classification of the most recent works regarding motion prediction, motion synthesis as well as musculoskeletal dynamics estimation problems using ML techniques, in order to offer sufficient insight into the state-of-the-art and draw new research directions. While the study of motion may appear distinct to musculoskeletal dynamics, these application domains provide jointly the link for more natural computer graphics character animation, since ML-based musculoskeletal dynamics estimation enables modeling of more long-term, temporally evolving, ergonomic effects, while offering automated and fast solutions. Overall, our review offers an in-depth presentation and classification of ML applications in human motion analysis, unlike previous survey articles focusing on specific aspects of motion prediction.

Joint Deformable Image Registration and ADC Map Regularization: Application to DWI-Based Lymphoma Classification.

The Apparent Diffusion Coefficient (ADC) is considered an importantimaging biomarker contributing to the assessment of tissue microstructure and pathophy- siology. It is calculated from Diffusion-Weighted Magnetic Resonance Imaging (DWI) by means of a diffusion model, usually without considering any motion during image acquisition. We propose a method to improve the computation of the ADC by coping jointly with both motion artifacts in whole-body DWI (through group-wise registration) and possible instrumental noise in the diffusion model. The proposed deformable registration method yielded on average the lowest ADC reconstruction error on data with simulated motion and diffusion. Moreover, our approach was applied on whole-body diffusion weighted images obtained with five different b-values from a cohort of 38 patients with histologically confirmed lymphomas of three different types (Hodgkin, diffuse large B-cell lymphoma and follicular lymphoma). Evaluation on the real data showed that ADC-based features, extracted using our joint optimization approach classified lymphomas with an accuracy of approximately 78.6% (yielding a 11% increase in respect to the standard features extracted from unregistered diffusion-weighted images). Furthermore, the correlation between diffusion characteristics and histopathological findings was higher than any other previous approach of ADC computation.

Laser fabrication and evaluation of holographic intrinsic physical unclonable functions.

Optical Physical Unclonable Functions (PUFs) are well established as the most powerful anticounterfeiting tool. Despite the merits of optical PUFs, widespread use is hindered by existing implementations that are complicated and expensive. On top, the overwhelming majority of optical PUFs refer to extrinsic implementations. Here we overcome these limitations to demonstrate for the first time strong intrinsic optical PUFs with exceptional security characteristics. In doing so, we use Computer-Generated Holograms (CGHs) as optical, intrinsic, and image-based PUFs. The required randomness is offered by the non-deterministic fabrication process achieved with industrial friendly, nanosecond pulsed fiber lasers. Adding to simplicity and low cost, the digital fingerprint is derived by a setup which is designed to be adjustable in a production line. In addition, we propose a novel signature encoding and authentication mechanism that exploits manifold learning techniques to efficiently differentiate data reconstruction-related variation from counterfeit attacks. The proposed method is applied experimentally on silver plates. The robustness of the fabricated intrinsic optical PUFs is evaluated over time. The results have shown exceptional values for robustness and a probability of cloning up to [Formula: see text], which exceeds the standard acceptance rate in security applications.

Machine learning based analysis of stroke lesions on mouse tissue sections.

An unbiased, automated and reliable method for analysis of brain lesions in tissue after ischemic stroke is missing. Manual infarct volumetry or by threshold-based semi-automated approaches is laborious, and biased to human error or biased by many false -positive and -negative data, respectively. Thereby, we developed a novel machine learning, atlas-based method for fully automated stroke analysis in mouse brain slices stained with 2% Triphenyltetrazolium-chloride (2% TTC), named "StrokeAnalyst", which runs on a user-friendly graphical interface. StrokeAnalyst registers subject images on a common spatial domain (a novel mouse TTC- brain atlas of 80 average mathematical images), calculates pixel-based, tissue-intensity statistics (z-scores), applies outlier-detection and machine learning (Random-Forest) models to increase accuracy of lesion detection, and produces volumetry data and detailed neuroanatomical information per lesion. We validated StrokeAnalyst in two separate experimental sets using the filament stroke model. StrokeAnalyst detects stroke lesions in a rater-independent and reproducible way, correctly detects hemispheric volumes even in presence of post-stroke edema and significantly minimizes false-positive errors compared to threshold-based approaches (false-positive rate 1.2-2.3%, p < 0.05). It can process scanner-acquired, and even smartphone-captured or pdf-retrieved images. Overall, StrokeAnalyst surpasses all previous TTC-volumetry approaches and increases quality, reproducibility and reliability of stroke detection in relevant preclinical models.

Regularized multi-structural shape modeling of the knee complex based on deep functional maps.

The incorporation of a-priori knowledge on the shape of anatomical structures and their variation through Statistical Shape Models (SSMs) has shown to be very effective in guiding highly uncertain image segmentation problems. In this paper, we construct multiple-structure SSMs of purely geometric nature, that describe the relationship between adjacent anatomical components through Canonical Correlation Analysis. Shape inference is then conducted based on a regularization term on the shape likelihood providing more reliable structure representations. A fundamental prerequisite for performing statistical shape analysis on a set of objects is the identification of corresponding points on their associated surfaces. We address the correspondence problem using the recently proposed Functional Maps framework, which is a generalization of point-to-point correspondence to manifolds. Additionally, we show that, by incorporating techniques from the deep learning theory into this framework, we can further enhance the ability of SSMs to better capture the shape variation in a given dataset. The efficiency of our approach is illustrated through the creation of 3D models of the human knee complex in two application scenarios: incomplete or noisy shape reconstruction and missing structure estimation.

Deep Multi-Instance Learning Using Multi-Modal Data for Diagnosis of Lymphocytosis.

We investigate the use of recent advances in deep learning and propose an end-to-end trainable multi-instance convolutional neural network within a mixture-of-experts formulation that combines information from two types of data-images and clinical attributes-for the diagnosis of lymphocytosis. The convolutional network learns to extract meaningful features from images of blood cells using an embedding level approach and aggregates them. Moreover, the mixture-of-experts model combines information from these images as well as clinical attributes to form an end-to-end trainable pipeline for diagnosis of lymphocytosis. Our results demonstrate that even the convolutional network by itself is able to discover meaningful associations between the images and the diagnosis, indicating the presence of important unexploited information in the images. The mixture-of-experts formulation is shown to be more robust while maintaining performance via. a repeatability study to assess the effect of variability in data acquisition on the predictions. The proposed methods are compared with different methods from literature based both on conventional handcrafted features and machine learning, and on recent deep learning models based on attention mechanisms. Our method reports a balanced accuracy of [Formula: see text] and outperfroms the handcrafted feature-based and attention-based approaches as well that of biologists which scored [Formula: see text], [Formula: see text] and [Formula: see text] respectively. These results give insights on the potentials of the applicability of the proposed method in clinical practice. Our code and datasets can be found at https://github.com/msahasrabudhe/lymphoMIL.

Real-Time Prediction of Joint Forces by Motion Capture and Machine Learning.

Conventional biomechanical modelling approaches involve the solution of large systems of equations that encode the complex mathematical representation of human motion and skeletal structure. To improve stability and computational speed, being a common bottleneck in current approaches, we apply machine learning to train surrogate models and to predict in near real-time, previously calculated medial and lateral knee contact forces (KCFs) of 54 young and elderly participants during treadmill walking in a speed range of 3 to 7 km/h. Predictions are obtained by fusing optical motion capture and musculoskeletal modeling-derived kinematic and force variables, into regression models using artificial neural networks (ANNs) and support vector regression (SVR). Training schemes included either data from all subjects (LeaveTrialsOut) or only from a portion of them (LeaveSubjectsOut), in combination with inclusion of ground reaction forces (GRFs) in the dataset or not. Results identify ANNs as the best-performing predictor of KCFs, both in terms of Pearson R (0.89-0.98 for LeaveTrialsOut and 0.45-0.85 for LeaveSubjectsOut) and percentage normalized root mean square error (0.67-2.35 for LeaveTrialsOut and 1.6-5.39 for LeaveSubjectsOut). When GRFs were omitted from the dataset, no substantial decrease in prediction power of both models was observed. Our findings showcase the strength of ANNs to predict simultaneously multi-component KCF during walking at different speeds-even in the absence of GRFs-particularly applicable in real-time applications that make use of knee loading conditions to guide and treat patients.

Deep CNN Sparse Coding for Real Time Inhaler Sounds Classification.

Effective management of chronic constrictive pulmonary conditions lies in proper and timely administration of medication. As a series of studies indicates, medication adherence can effectively be monitored by successfully identifying actions performed by patients during inhaler usage. This study focuses on the recognition of inhaler audio events during usage of pressurized metered dose inhalers (pMDI). Aiming at real-time performance, we investigate deep sparse coding techniques including convolutional filter pruning, scalar pruning and vector quantization, for different convolutional neural network (CNN) architectures. The recognition performance has been assessed on three healthy subjects following both within and across subjects modeling strategies. The selected CNN architecture classified drug actuation, inhalation and exhalation events, with 100%, 92.6% and 97.9% accuracy, respectively, when assessed in a leave-one-subject-out cross-validation setting. Moreover, sparse coding of the same architecture with an increasing compression rate from 1 to 7 resulted in only a small decrease in classification accuracy (from 95.7% to 94.5%), obtained by random (subject-agnostic) cross-validation. A more thorough assessment on a larger dataset, including recordings of subjects with multiple respiratory disease manifestations, is still required in order to better evaluate the method's generalization ability and robustness.

FrailSafe: An ICT Platform for Unobtrusive Sensing of Multi-Domain Frailty for Personalized Interventions.

The implications of frailty in older adults' health status and autonomy necessitates the understanding and effective management of this widespread condition as a priority for modern societies. Despite its importance, we still stand far from early detection, effective management and prevention of frailty. One of the most important reasons for this is the lack of sensitive instruments able to early identify frailty and pre-frailty conditions. The FrailSafe system provides a novel approach to this complex, medical, social and public health problem. It aspires to identify the most important components of frailty, construct cumulative metrics serving as biomarkers, and apply this knowledge and expertise for self-management and prevention. This paper presents a high-level overview of the FrailSafe system architecture providing details on the monitoring sensors and devices, the software front-ends for the interaction of the users with the system, as well as the back-end part including the data analysis and decision support modules. Data storage, remote processing and security issues are also discussed. The evaluation of the system by older individuals from 3 different countries highlighted the potential of frailty prediction strategies based on information and communication technology (ICT).

AVATREE: An open-source computational modelling framework modelling Anatomically Valid Airway TREE conformations.

This paper presents AVATREE, a computational modelling framework that generates Anatomically Valid Airway tree conformations and provides capabilities for simulation of broncho-constriction apparent in obstructive pulmonary conditions. Such conformations are obtained from the personalized 3D geometry generated from computed tomography (CT) data through image segmentation. The patient-specific representation of the bronchial tree structure is extended beyond the visible airway generation depth using a knowledge-based technique built from morphometric studies. Additional functionalities of AVATREE include visualization of spatial probability maps for the airway generations projected on the CT imaging data, and visualization of the airway tree based on local structure properties. Furthermore, the proposed toolbox supports the simulation of broncho-constriction apparent in pulmonary diseases, such as chronic obstructive pulmonary disease (COPD) and asthma. AVATREE is provided as an open-source toolbox in C++ and is supported by a graphical user interface integrating the modelling functionalities. It can be exploited in studies of gas flow, gas mixing, ventilation patterns and particle deposition in the pulmonary system, with the aim to improve clinical decision making.

Quantification of Cystic Fibrosis Lung Disease with Radiomics-based CT Scores.

PURPOSE: To develop radiomics-based CT scores for assessing lung disease severity and exacerbation risk in adult patients with cystic fibrosis (CF). MATERIALS AND METHODS: This two-center retrospective observational study was approved by an institutional ethics committee, and the need for patient consent was waived. A total of 215 outpatients with CF referred for unenhanced follow-up chest CT were evaluated in two different centers between January 2013 and December 2016. After lung segmentation, chest CT scans from center 1 (training cohort, 162 patients [median age, 29 years; interquartile range {IQR}, 24-36 years; 84 men]) were used to build CT scores from 38 extracted CT features, using five different machine learning techniques trained to predict a clinical prognostic score, the Nkam score. The correlations between the developed CT scores, two different clinical prognostic scores (Liou and CF-ABLE), forced expiratory volume in 1 second (FEV1), and risk of respiratory exacerbations were evaluated in the test cohort (center 2, 53 patients [median age, 27 years; IQR, 22-35 years; 34 men]) using the Spearman rank coefficient. RESULTS: In the test cohort, all radiomics-based CT scores showed moderate to strong correlation with the Nkam score (R = 0.57 to 0.63, P < .001) and Liou scores (R = -0.55 to -0.65, P < .001), whereas the correlation with CF-ABLE score was weaker (R = 0.28 to 0.38, P = .005 to .048). The developed CT scores showed strong correlation with predicted FEV1 (R = -0.62 to -0.66, P < .001) and weak to moderate correlation with the number of pulmonary exacerbations to occur in the 12 months after the CT examination (R = 0.38 to 0.55, P < .001 to P = .006). CONCLUSION: Radiomics can be used to build automated CT scores that correlate to clinical severity and exacerbation risk in adult patients with CF.Supplemental material is available for this article.See also the commentary by Elicker and Sohn in this issue.© RSNA, 2020.

Deep Learning-based Approach for Automated Assessment of Interstitial Lung Disease in Systemic Sclerosis on CT Images.

PURPOSE: To develop a deep learning algorithm for the automatic assessment of the extent of systemic sclerosis (SSc)-related interstitial lung disease (ILD) on chest CT images. MATERIALS AND METHODS: This retrospective study included 208 patients with SSc (median age, 57 years; 167 women) evaluated between January 2009 and October 2017. A multicomponent deep neural network (AtlasNet) was trained on 6888 fully annotated CT images (80% for training and 20% for validation) from 17 patients with no, mild, or severe lung disease. The model was tested on a dataset of 400 images from another 20 patients, independently partially annotated by three radiologist readers. The ILD contours from the three readers and the deep learning neural network were compared by using the Dice similarity coefficient (DSC). The correlation between disease extent obtained from the deep learning algorithm and that obtained by using pulmonary function tests (PFTs) was then evaluated in the remaining 171 patients and in an external validation dataset of 31 patients based on the analysis of all slices of the chest CT scan. The Spearman rank correlation coefficient (ρ) was calculated to evaluate the correlation between disease extent and PFT results. RESULTS: The median DSCs between the readers and the deep learning ILD contours ranged from 0.74 to 0.75, whereas the median DSCs between contours from radiologists ranged from 0.68 to 0.71. The disease extent obtained from the algorithm, by analyzing the whole CT scan, correlated with the diffusion lung capacity for carbon monoxide, total lung capacity, and forced vital capacity (ρ = -0.76, -0.70, and -0.62, respectively; P < .001 for all) in the dataset for the correlation with PFT results. The disease extents correlated with diffusion lung capacity for carbon monoxide, total lung capacity, and forced vital capacity were ρ = -0.65, -0.70, and -0.57, respectively, in the external validation dataset (P < .001 for all). CONCLUSION: The developed algorithm performed similarly to radiologists for disease-extent contouring, which correlated with pulmonary function to assess CT images from patients with SSc-related ILD.Supplemental material is available for this article.© RSNA, 2020.

Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data.

The physiological monitoring of older people using wearable sensors has shown great potential in improving their quality of life and preventing undesired events related to their health status. Nevertheless, creating robust predictive models from data collected unobtrusively in home environments can be challenging, especially for vulnerable ageing population. Under that premise, we propose an activity recognition scheme for older people exploiting feature extraction and machine learning, along with heuristic computational solutions to address the challenges due to inconsistent measurements in non-standardized environments. In addition, we compare the customized pipeline with deep learning architectures, such as convolutional neural networks, applied to raw sensor data without any pre- or post-processing adjustments. The results demonstrate that the generalizable deep architectures can compensate for inconsistencies during data acquisition providing a valuable alternative.

Integrating an openEHR-based personalized virtual model for the ageing population within HBase.

BACKGROUND: Frailty is a common clinical syndrome in ageing population that carries an increased risk for adverse health outcomes including falls, hospitalization, disability, and mortality. As these outcomes affect the health and social care planning, during the last years there is a tendency of investing in monitoring and preventing strategies. Although a number of electronic health record (EHR) systems have been developed, including personalized virtual patient models, there are limited ageing population oriented systems. METHODS: We exploit the openEHR framework for the representation of frailty in ageing population in order to attain semantic interoperability, and we present the methodology for adoption or development of archetypes. We also propose a framework for a one-to-one mapping between openEHR archetypes and a column-family NoSQL database (HBase) aiming at the integration of existing and newly developed archetypes into it. RESULTS: The requirement analysis of our study resulted in the definition of 22 coherent and clinically meaningful parameters for the description of frailty in older adults. The implemented openEHR methodology led to the direct use of 22 archetypes, the modification and reuse of two archetypes, and the development of 28 new archetypes. Additionally, the mapping procedure led to two different HBase tables for the storage of the data. CONCLUSIONS: In this work, an openEHR-based virtual patient model has been designed and integrated into an HBase storage system, exploiting the advantages of the underlying technologies. This framework can serve as a base for the development of a decision support system using the openEHR's Guideline Definition Language in the future.

An automated computed tomography score for the cystic fibrosis lung.

OBJECTIVES: To develop an automated density-based computed tomography (CT) score evaluating high-attenuating lung structural abnormalities in patients with cystic fibrosis (CF). METHODS: Seventy adult CF patients were evaluated. The development cohort comprised 17 patients treated with ivacaftor, with 45 pre-therapeutic and follow-up chest CT scans. Another cohort of 53 patients not treated with ivacaftor was used for validation. CT-density scores were calculated using fixed and adapted thresholds based on histogram characteristics, such as the mode and standard deviation. Visual CF-CT score was also calculated. Correlations between the CT scores and forced expiratory volume in 1 s (FEV1% pred), and between their changes over time were assessed. RESULTS: On cross-sectional evaluation, the correlation coefficients between FEV1%pred and the automated scores were slightly lower to that of the visual score in the development and validation cohorts (R = up to -0.68 and -0.61, versus R = -0.72 and R = -0.64, respectively). Conversely, the correlation to FEV1%pred tended to be higher for automated scores (R = up to -0.61) than for visual score (R = -0.49) on longitudinal follow-up. Automated scores based on Mode + 3 SD and Mode +300 HU showed the highest cross-sectional (R = -0.59 to -0.68) and longitudinal (R = -0.51 to -0.61) correlation coefficients to FEV1%pred. CONCLUSIONS: The developed CT-density score reliably quantifies high-attenuating lung structural abnormalities in CF. KEY POINTS: • Automated CT score shows moderate to good cross-sectional correlations with FEV 1 %pred . • CT score has potential to be integrated into the standard reporting workflow.

EnzyNet: enzyme classification using 3D convolutional neural networks on spatial representation.

During the past decade, with the significant progress of computational power as well as ever-rising data availability, deep learning techniques became increasingly popular due to their excellent performance on computer vision problems. The size of the Protein Data Bank (PDB) has increased more than 15-fold since 1999, which enabled the expansion of models that aim at predicting enzymatic function via their amino acid composition. Amino acid sequence, however, is less conserved in nature than protein structure and therefore considered a less reliable predictor of protein function. This paper presents EnzyNet, a novel 3D convolutional neural networks classifier that predicts the Enzyme Commission number of enzymes based only on their voxel-based spatial structure. The spatial distribution of biochemical properties was also examined as complementary information. The two-layer architecture was investigated on a large dataset of 63,558 enzymes from the PDB and achieved an accuracy of 78.4% by exploiting only the binary representation of the protein shape. Code and datasets are available at https://github.com/shervinea/enzynet.

Automatic single- and multi-label enzymatic function prediction by machine learning.

The number of protein structures in the PDB database has been increasing more than 15-fold since 1999. The creation of computational models predicting enzymatic function is of major importance since such models provide the means to better understand the behavior of newly discovered enzymes when catalyzing chemical reactions. Until now, single-label classification has been widely performed for predicting enzymatic function limiting the application to enzymes performing unique reactions and introducing errors when multi-functional enzymes are examined. Indeed, some enzymes may be performing different reactions and can hence be directly associated with multiple enzymatic functions. In the present work, we propose a multi-label enzymatic function classification scheme that combines structural and amino acid sequence information. We investigate two fusion approaches (in the feature level and decision level) and assess the methodology for general enzymatic function prediction indicated by the first digit of the enzyme commission (EC) code (six main classes) on 40,034 enzymes from the PDB database. The proposed single-label and multi-label models predict correctly the actual functional activities in 97.8% and 95.5% (based on Hamming-loss) of the cases, respectively. Also the multi-label model predicts all possible enzymatic reactions in 85.4% of the multi-labeled enzymes when the number of reactions is unknown. Code and datasets are available at https://figshare.com/s/a63e0bafa9b71fc7cbd7.