Multi-index comprehensive evaluation model for assessing risk to trainees in an emergency rescue training base for building collapse.

Rescues from building collapse accidents present a significant challenge for China's emergency rescue system. However, there are also many risk factors in a training scenario, which have been summarized in this study. A hierarchical indicator system for personnel safety was established, including 12 first-level indicators and 23s-level indicators. Then, an improved Grey-DEMATEL-ISM-MICMAC evaluation model was constructed to evaluate the level of risk. Influencing factor scores were determined according to the responses from the questionnaire survey. The influencing degree, influenced degree, centrality, and causality were identified, and the importance, relevance, and clustering of the various factors were obtained after making quantitative calculations. The results showed that the order of priority for solving the essential issues was safety education (A2), operating standards and proficiency (A10), equipment inspection (A4), equipment warehousing maintenance and records (A21). The solving of safety education was identified to be the most essential priority. The priority control order of direct causes was Scientific design and construction (A5), Potential fixed hazards in the facility (A12), Physical fitness of personnel (A1), Weather influences (A18), and Initiation efficiency of emergency plans (A20), and direct control measures for these five factors could achieve a relatively significant effect.

Preparation and Characteristics of Building Dust Suppressants with Strong Resistance to Harsh Environments.

Most dust suppressants used for buildings currently lack sufficient resistance to harsh conditions, such as high temperatures and wind erosion. To solve this problem, it is necessary to develop a new type of dust suppressant. In this study, the guar gum molecule was chemically modified to remove the active hydroxyl group in order to significantly improve the stability and adhesion of guar gum. Eventually, a composite dust suppressant was synthesized by incorporating a surfactant and an absorbent agent into modified guar gum. The functional groups of the reaction products were analyzed via infrared experiments, thus confirming the success of the modification. Wind erosion resistance and scanning electron microscopy experiments confirmed the improved bonding capabilities of the composite dust suppressant with dust particles. In experiments on wind erosion resistance, the dust fixation rate exceeded 50% after the application of the composite dust suppressant. The results of the thermogravimetric tests showed that the maximum mass loss rate of the samples with modified guar gum dust suppressants was 6.0% and 28% lower than those of the samples with unmodified guar gum dust suppressants and water, respectively. Furthermore, the tests conducted on pH value and corrosion resistance indicated that the pH value of this dust suppressant was comparable to that of tap water and demonstrated a similar rate of metal corrosion. The practical significance of this study is to improve the dust suppressant used in buildings, to improve the performance of dust suppressant and resistance to harsh environment, and to help to continuously improve the health of personnel and environmental protection during construction. The practical significance of this study is to improve the dust suppressant used in buildings, to improve the performance of dust suppressant and resistance to harsh environments, and to help to continuously improve the health of personnel and environmental protection during construction, which has positive practical significance for the building industry and related fields.

MIX-TPI: a flexible prediction framework for TCR-pMHC interactions based on multimodal representations.

MOTIVATION: The interactions between T-cell receptors (TCR) and peptide-major histocompatibility complex (pMHC) are essential for the adaptive immune system. However, identifying these interactions can be challenging due to the limited availability of experimental data, sequence data heterogeneity, and high experimental validation costs. RESULTS: To address this issue, we develop a novel computational framework, named MIX-TPI, to predict TCR-pMHC interactions using amino acid sequences and physicochemical properties. Based on convolutional neural networks, MIX-TPI incorporates sequence-based and physicochemical-based extractors to refine the representations of TCR-pMHC interactions. Each modality is projected into modality-invariant and modality-specific representations to capture the uniformity and diversities between different features. A self-attention fusion layer is then adopted to form the classification module. Experimental results demonstrate the effectiveness of MIX-TPI in comparison with other state-of-the-art methods. MIX-TPI also shows good generalization capability on mutual exclusive evaluation datasets and a paired TCR dataset. AVAILABILITY AND IMPLEMENTATION: The source code of MIX-TPI and the test data are available at: https://github.com/Wolverinerine/MIX-TPI.

Source Free Semi-Supervised Transfer Learning for Diagnosis of Mental Disorders on fMRI Scans.

The high prevalence of mental disorders gradually poses a huge pressure on the public healthcare services. Deep learning-based computer-aided diagnosis (CAD) has emerged to relieve the tension in healthcare institutions by detecting abnormal neuroimaging-derived phenotypes. However, training deep learning models relies on sufficient annotated datasets, which can be costly and laborious. Semi-supervised learning (SSL) and transfer learning (TL) can mitigate this challenge by leveraging unlabeled data within the same institution and advantageous information from source domain, respectively. This work is the first attempt to propose an effective semi-supervised transfer learning (SSTL) framework dubbed S3TL for CAD of mental disorders on fMRI data. Within S3TL, a secure cross-domain feature alignment method is developed to generate target-related source model in SSL. Subsequently, we propose an enhanced dual-stage pseudo-labeling approach to assign pseudo-labels for unlabeled samples in target domain. Finally, an advantageous knowledge transfer method is conducted to improve the generalization capability of the target model. Comprehensive experimental results demonstrate that S3TL achieves competitive accuracies of 69.14%, 69.65%, and 72.62% on ABIDE-I, ABIDE-II, and ADHD-200 datasets, respectively. Furthermore, the simulation experiments also demonstrate the application potential of S3TL through model interpretation analysis and federated learning extension.

Spatial-Temporal Co-Attention Learning for Diagnosis of Mental Disorders From Resting-State fMRI Data.

Neuroimaging techniques have been widely adopted to detect the neurological brain structures and functions of the nervous system. As an effective noninvasive neuroimaging technique, functional magnetic resonance imaging (fMRI) has been extensively used in computer-aided diagnosis (CAD) of mental disorders, e.g., autism spectrum disorder (ASD) and attention deficit/hyperactivity disorder (ADHD). In this study, we propose a spatial-temporal co-attention learning (STCAL) model for diagnosing ASD and ADHD from fMRI data. In particular, a guided co-attention (GCA) module is developed to model the intermodal interactions of spatial and temporal signal patterns. A novel sliding cluster attention module is designed to address global feature dependency of self-attention mechanism in fMRI time series. Comprehensive experimental results demonstrate that our STCAL model can achieve competitive accuracies of 73.0 ± 4.5%, 72.0 ± 3.8%, and 72.5 ± 4.2% on the ABIDE I, ABIDE II, and ADHD-200 datasets, respectively. Moreover, the potential for feature pruning based on the co-attention scores is validated by the simulation experiment. The clinical interpretation analysis of STCAL can allow medical professionals to concentrate on the discriminative regions of interest and key time frames from fMRI data.

Study of the Change Laws of Free Radicals and Functional Groups during Coal Oxidation.

In order to study the change laws of free radicals and functional groups during low-temperature coal oxidation, three coal samples with different metamorphic degrees were selected for ESR and FTIR analysis. The results showed that the concentration of free radicals increased as the temperature increased; meanwhile, the types of free radicals changed constantly, and the free radical variation range decreased with the increase in coal metamorphism. The side chains of aliphatic hydrocarbons in coal with a low metamorphic degree decreased by varying amounts in the initial heating stage. The -OH content of bituminous coal and lignite increased first and then decreased, while that in anthracite decreased first and then increased. In the initial oxidation stage, -COOH first increased rapidly, then decreased rapidly, and then increased before finally decreasing. The content of -C=O in bituminous coal and lignite increased in the initial stage of oxidation. Through gray relational analysis, it was found that there was a significant relationship between free radicals and functional groups, and -OH had the strongest correlation with free radicals. This paper provides a theoretical basis for studying the mechanism of functional groups transforming into free radicals in the process of coal spontaneous combustion.

Federated Multi-Task Learning for Joint Diagnosis of Multiple Mental Disorders on MRI Scans.

OBJECTIVE: Deep learning (DL) techniques have been introduced to assist doctors in the interpretation of medical images by detecting image-derived phenotype abnormality. Yet the privacy-preserving policy of medical images disables the effective training of DL model using sufficiently large datasets. As a decentralized computing paradigm to address this issue, federated learning (FL) allows the training process to occur in individual institutions with local datasets, and then aggregates the resultant weights without risk of privacy leakage. METHODS: We propose an effective federated multi-task learning (MTL) framework to jointly identify multiple related mental disorders based on functional magnetic resonance imaging data. A federated contrastive learning-based feature extractor is developed to extract high-level features across client models. To ease the optimization conflicts of updating shared parameters in MTL, we present a federated multi-gate mixture of expert classifier for the joint classification. The proposed framework also provides practical modules, including personalized model learning, privacy protection, and federated biomarker interpretation. RESULTS: On real-world datasets, the proposed framework achieves robust diagnosis accuracies of 69.48 ± 1.6%, 71.44 ± 3.2%, and 83.29 ± 3.2% in autism spectrum disorder, attention deficit/hyperactivity disorder, and schizophrenia, respectively. CONCLUSION: The proposed framework can effectively ease the domain shift between clients via federated MTL. SIGNIFICANCE: The current work provides insights into exploiting the advantageous knowledge shared in related mental disorders for improving the generalization capability of computer-aided detection approaches.

Interpretable artificial intelligence model for accurate identification of medical conditions using immune repertoire.

Underlying medical conditions, such as cancer, kidney disease and heart failure, are associated with a higher risk for severe COVID-19. Accurate classification of COVID-19 patients with underlying medical conditions is critical for personalized treatment decision and prognosis estimation. In this study, we propose an interpretable artificial intelligence model termed VDJMiner to mine the underlying medical conditions and predict the prognosis of COVID-19 patients according to their immune repertoires. In a cohort of more than 1400 COVID-19 patients, VDJMiner accurately identifies multiple underlying medical conditions, including cancers, chronic kidney disease, autoimmune disease, diabetes, congestive heart failure, coronary artery disease, asthma and chronic obstructive pulmonary disease, with an average area under the receiver operating characteristic curve (AUC) of 0.961. Meanwhile, in this same cohort, VDJMiner achieves an AUC of 0.922 in predicting severe COVID-19. Moreover, VDJMiner achieves an accuracy of 0.857 in predicting the response of COVID-19 patients to tocilizumab treatment on the leave-one-out test. Additionally, VDJMiner interpretively mines and scores V(D)J gene segments of the T-cell receptors that are associated with the disease. The identified associations between single-cell V(D)J gene segments and COVID-19 are highly consistent with previous studies. The source code of VDJMiner is publicly accessible at https://github.com/TencentAILabHealthcare/VDJMiner. The web server of VDJMiner is available at https://gene.ai.tencent.com/VDJMiner/.

Multitask Learning for Joint Diagnosis of Multiple Mental Disorders in Resting-State fMRI.

Facing the increasing worldwide prevalence of mental disorders, the symptom-based diagnostic criteria struggle to address the urgent public health concern due to the global shortfall in well-qualified professionals. Thanks to the recent advances in neuroimaging techniques, functional magnetic resonance imaging (fMRI) has surfaced as a new solution to characterize neuropathological biomarkers for detecting functional connectivity (FC) anomalies in mental disorders. However, the existing computer-aided diagnosis models for fMRI analysis suffer from unstable performance on large datasets. To address this issue, we propose an efficient multitask learning (MTL) framework for joint diagnosis of multiple mental disorders using resting-state fMRI data. A novel multiobjective evolutionary clustering algorithm is presented to group regions of interests (ROIs) into different clusters for FC pattern analysis. On the optimal clustering solution, the multicluster multigate mixture-of-expert model is used for the final classification by capturing the highly consistent feature patterns among related diagnostic tasks. Extensive simulation experiments demonstrate that the performance of the proposed framework is superior to that of the other state-of-the-art methods. Moreover, the potential for practical application of the framework is also validated in terms of limited computational resources, real-time analysis, and insufficient training data. The proposed model can identify the remarkable interpretative biomarkers associated with specific mental disorders for clinical interpretation analysis.

Attention-Like Multimodality Fusion With Data Augmentation for Diagnosis of Mental Disorders Using MRI.

The globally rising prevalence of mental disorders leads to shortfalls in timely diagnosis and therapy to reduce patients' suffering. Facing such an urgent public health problem, professional efforts based on symptom criteria are seriously overstretched. Recently, the successful applications of computer-aided diagnosis approaches have provided timely opportunities to relieve the tension in healthcare services. Particularly, multimodal representation learning gains increasing attention thanks to the high temporal and spatial resolution information extracted from neuroimaging fusion. In this work, we propose an efficient multimodality fusion framework to identify multiple mental disorders based on the combination of functional and structural magnetic resonance imaging. A multioutput conditional generative adversarial network (GAN) is developed to address the scarcity of multimodal data for augmentation. Based on the augmented training data, the multiheaded gating fusion model is proposed for classification by extracting the complementary features across different modalities. The experiments demonstrate that the proposed model can achieve robust accuracies of 75.1 ± 1.5%, 72.9 ± 1.1%, and 87.2 ± 1.5% for autism spectrum disorder (ASD), attention deficit/hyperactivity disorder, and schizophrenia, respectively. In addition, the interpretability of our model is expected to enable the identification of remarkable neuropathology diagnostic biomarkers, leading to well-informed therapeutic decisions.

Prediction of biomarker-disease associations based on graph attention network and text representation.

MOTIVATION: The associations between biomarkers and human diseases play a key role in understanding complex pathology and developing targeted therapies. Wet lab experiments for biomarker discovery are costly, laborious and time-consuming. Computational prediction methods can be used to greatly expedite the identification of candidate biomarkers. RESULTS: Here, we present a novel computational model named GTGenie for predicting the biomarker-disease associations based on graph and text features. In GTGenie, a graph attention network is utilized to characterize diverse similarities of biomarkers and diseases from heterogeneous information resources. Meanwhile, a pretrained BERT-based model is applied to learn the text-based representation of biomarker-disease relation from biomedical literature. The captured graph and text features are then integrated in a bimodal fusion network to model the hybrid entity representation. Finally, inductive matrix completion is adopted to infer the missing entries for reconstructing relation matrix, with which the unknown biomarker-disease associations are predicted. Experimental results on HMDD, HMDAD and LncRNADisease data sets showed that GTGenie can obtain competitive prediction performance with other state-of-the-art methods. AVAILABILITY: The source code of GTGenie and the test data are available at: https://github.com/Wolverinerine/GTGenie.

Performance Optimization Approach of Polymer Modified Asphalt Mixtures with PET and PE Wastes: A Safety Study for Utilizing Eco-Friendly Circular Economy-Based SDGs Concepts.

Eco-friendly waste utilization helps in the development of sustainable infrastructures. Recently, researchers have focused on the production of road infrastructures using the circular economy concept of human safety. The objective of this study is to investigate and explore the utilization of optimum polymer waste content for the development of polymer-modified asphalt mixtures using response surface methodology (RSM). RSM based on Box-Behnken design (BBD) was employed to optimize experimental design and included three factors: X1, polymer type; X2, polymer contents; and X3, testing day. The optimized responses determined by the RSM were as follows: MS of 42.98 kN, MF of 5.08 mm, and MQ of 8.66 kN/mm, indicating a favorable and consistent precision in comparison with experimental values. Moreover, the Marshall characteristics of samples prepared with PE were quite improved compared to PET. In conclusion, the incorporation of such polymer wastes in road construction is a sustainable and cost-effective way of improving their engineering properties. This study will help in the development of sustainable road infrastructures supporting human safety and environmentally friendly practices.

Characterization and Performance Testing of an Intumescent Nanoinhibitor for Inhibiting Coal Spontaneous Combustion.

Considering disadvantages such as the low thermal stability and environmental pollution of existing gel inhibitors, a green and stable intumescent nanoinhibitor (INI) was prepared and tested. First, polyacrylamide (PAM), nano-silica, and intumescent flame retardant (IFR) were selected as raw materials. The INI was prepared by nanoparticle modification and cross-linking polymerization. Then, the structure and physical properties of INI were tested by Fourier transform infrared spectroscopy, scanning electron microscopy, and rheological experiments. Meanwhile, the inhibition performance of INI was studied through thermogravimetric analysis-Fourier transfer infrared spectroscopy (TGA-FTIR) analysis. The results suggest that the nanomodification improved the dispersibility of INI particles. The addition of modified nano-silica (MNS) and IFR enhances the strength of the reticular structure, thereby improving the transport convenience and covering ability of the INI gel. At high temperatures, IFR can generate a porous foamed carbon layer that further coats the coal. After INI inhibition treatment, the characteristic temperature and activation energy of coal were significantly improved, and the production of carbon monoxide and carbon dioxide decreased. Hence, irrespective of physical properties, physical inhibition performance, or chemical inhibition performance, INI performed well. Research results can provide valuable references for the preparation and performance study of a coal spontaneous combustion inhibitor.

GBDR: a Bayesian model for precise prediction of pathogenic microorganisms using 16S rRNA gene sequences.

BACKGROUND: Recent evidences have suggested that human microorganisms participate in important biological activities in the human body. The dysfunction of host-microbiota interactions could lead to complex human disorders. The knowledge on host-microbiota interactions can provide valuable insights into understanding the pathological mechanism of diseases. However, it is time-consuming and costly to identify the disorder-specific microbes from the biological "haystack" merely by routine wet-lab experiments. With the developments in next-generation sequencing and omics-based trials, it is imperative to develop computational prediction models for predicting microbe-disease associations on a large scale. RESULTS: Based on the known microbe-disease associations derived from the Human Microbe-Disease Association Database (HMDAD), the proposed model shows reliable performance with high values of the area under ROC curve (AUC) of 0.9456 and 0.8866 in leave-one-out cross validations and five-fold cross validations, respectively. In case studies of colorectal carcinoma, 80% out of the top-20 predicted microbes have been experimentally confirmed via published literatures. CONCLUSION: Based on the assumption that functionally similar microbes tend to share the similar interaction patterns with human diseases, we here propose a group based computational model of Bayesian disease-oriented ranking to prioritize the most potential microbes associating with various human diseases. Based on the sequence information of genes, two computational approaches (BLAST+ and MEGA 7) are leveraged to measure the microbe-microbe similarity from different perspectives. The disease-disease similarity is calculated by capturing the hierarchy information from the Medical Subject Headings (MeSH) data. The experimental results illustrate the accuracy and effectiveness of the proposed model. This work is expected to facilitate the characterization and identification of promising microbial biomarkers.

Influence of Temperature Change on the Change Law of Free Radicals in Coal.

This study investigates changes in the concentration and types of free radicals in the process of coal heating, first rising and then falling. Hailar lignite, Panjiang bituminous coal, and Yangquan anthracite were selected as coal test samples. The results show that the lignite's concentration of free radical changes during heating is greater than that of bituminous coal or anthracite. It clearly shows that lignite is more prone to spontaneous combustion. In the heating and cooling portion of the experiment, the concentration of free radicals during the cooling process was much more than that of free radicals at the same temperature during the heating process. These results obtained from this research study can provide a reference for the prevention and control of the spontaneous combustion of coal with changes in temperature. This study provides a theoretical basis for the prevention and control of spontaneous combustion of coal and the selection of retarding agents and methods in the process of flame retarding by testing the free radical changes of coal at different temperatures. Also, it provides a reference for preventing and controlling coal oxidation with the change in temperature, first rising and then falling.

Study on the physicochemical characteristics and dust suppression performance of new type chemical dust suppressant for copper mine pavement.

Copper mine road dust is the major source of dust in mine operations. The dust produced on the road surface is a great hazard to the workers. Aiming at the road dust of an open-pit mine, this paper conducts a physical and chemical analysis of a new type of chemical dust suppressant. It is prepared by using sodium polyacrylate as a binder, sodium carbonate as a moisture absorbent, polyethylene glycol as a water-retaining agent, and alkyl glycoside as a surfactant. Physical and chemical characteristics and dust suppression performance of dust suppressant were tested. The results show that the dust suppressant has a pH of 11.03, a viscosity of 18.5 mPa·s, and a surface tension of 28.1 mN/m. The content of heavy metal ions contained is less than the maximum concentration defined by "The norms for the integrated treatment of copper mine acidic waste water." Under the same temperature condition, the greater the humidity, the stronger the hygroscopicity. Especially when the humidity is 30%, the hygroscopic effect is contrary to water. The dust suppressant also has good anti-evaporation properties, and it could maintain a moisture content of 4% to 5% after being placed at room temperature for 10 days. Compared with water, the dust suppressant has better performance of wind erosion, water erosion, and compression resistance. Under the same conditions, the loss rate of water is 2 times that of the dust suppressant, and the pressure of the dust suppressant sample is about 3 times that of water. The dust suppressant has a much higher dust removal efficiency for all dust and respirable dust than water under the same conditions. Finally, the test results and mechanism of the dust suppression mechanism of the dust suppressant are described and analyzed, which shows that the dust suppressant studied in this paper has good performance and is suitable for road dust prevention.

Numerical Simulation of the Dust Production and Transportation Law of an Intermediate Mine Heap.

In view of the current serious dust generation and environmental pollution that occur during the unloading process of an intermediate mine heap, in this study, the flow field and dust migration law for an intermediate mine heap were simulated numerically. Based on the mathematical model of the flow field and dust field, a numerical simulation was used to obtain the impact airflow and dust distribution law under different unloading conditions. The effects of different factors on the impact airflow and dust were studied. It could be concluded that the maximum impact wind velocity and dust concentration increased with an increase in the unloading flow. When the heap height is 23 m, the relationship between the maximum impact wind velocity and unloading volume was v = 0.05124(M p)0.62584 and the relationship between the dust concentration and mine unloading flow was c = 7.05613(M p)0.35002. The smaller the ore particle size, the larger the impact airflow and the greater the dust concentration. The relationship between the maximum impact wind velocity and the particle size was v = 1.54000(d)-0.23786. The relationship between the dust concentration and ore particle size was c = 30.45323(d)-0.54273. The greater the maximum impact wind speed, the more the dust generated. The existence of natural wind flow will initially accelerate the speed of dust diffusion and increase the dust concentration, but with the increase in natural wind flow, the diffusion effect will gradually reduce the dust concentration. An increase in the mine heap height will cause the impact wind's speed and influence range to continuously decrease but will only have a small effect on the dust concentration.

Predicting microRNA-disease associations from lncRNA-microRNA interactions via Multiview Multitask Learning.

MOTIVATION: Identifying microRNAs that are associated with different diseases as biomarkers is a problem of great medical significance. Existing computational methods for uncovering such microRNA-diseases associations (MDAs) are mostly developed under the assumption that similar microRNAs tend to associate with similar diseases. Since such an assumption is not always valid, these methods may not always be applicable to all kinds of MDAs. Considering that the relationship between long noncoding RNA (lncRNA) and different diseases and the co-regulation relationships between the biological functions of lncRNA and microRNA have been established, we propose here a multiview multitask method to make use of the known lncRNA-microRNA interaction to predict MDAs on a large scale. The investigation is performed in the absence of complete information of microRNAs and any similarity measurement for it and to the best knowledge, the work represents the first ever attempt to discover MDAs based on lncRNA-microRNA interactions. RESULTS: In this paper, we propose to develop a deep learning model called MVMTMDA that can create a multiview representation of microRNAs. The model is trained based on an end-to-end multitasking approach to machine learning so that, based on it, missing data in the side information can be determined automatically. Experimental results show that the proposed model yields an average area under ROC curve of 0.8410+/-0.018, 0.8512+/-0.012 and 0.8521+/-0.008 when k is set to 2, 5 and 10, respectively. In addition, we also propose here a statistical approach to predicting lncRNA-disease associations based on these associations and the MDA discovered using MVMTMDA. AVAILABILITY: Python code and the datasets used in our studies are made available at https://github.com/yahuang1991polyu/MVMTMDA/.

Identifying Autism Spectrum Disorder From Resting-State fMRI Using Deep Belief Network.

With the increasing prevalence of autism spectrum disorder (ASD), it is important to identify ASD patients for effective treatment and intervention, especially in early childhood. Neuroimaging techniques have been used to characterize the complex biomarkers based on the functional connectivity anomalies in the ASD. However, the diagnosis of ASD still adopts the symptom-based criteria by clinical observation. The existing computational models tend to achieve unreliable diagnostic classification on the large-scale aggregated data sets. In this work, we propose a novel graph-based classification model using the deep belief network (DBN) and the Autism Brain Imaging Data Exchange (ABIDE) database, which is a worldwide multisite functional and structural brain imaging data aggregation. The remarkable connectivity features are selected through a graph extension of K -nearest neighbors and then refined by a restricted path-based depth-first search algorithm. Thanks to the feature reduction, lower computational complexity could contribute to the shortening of the training time. The automatic hyperparameter-tuning technique is introduced to optimize the hyperparameters of the DBN by exploring the potential parameter space. The simulation experiments demonstrate the superior performance of our model, which is 6.4% higher than the best result reported on the ABIDE database. We also propose to use the data augmentation and the oversampling technique to identify further the possible subtypes within the ASD. The interpretability of our model enables the identification of the most remarkable autistic neural correlation patterns from the data-driven outcomes.

Identification of Autistic Risk Candidate Genes and Toxic Chemicals via Multilabel Learning.

As a group of complex neurodevelopmental disorders, autism spectrum disorder (ASD) has been reported to have a high overall prevalence, showing an unprecedented spurt since 2000. Due to the unclear pathomechanism of ASD, it is challenging to diagnose individuals with ASD merely based on clinical observations. Without additional support of biochemical markers, the difficulty of diagnosis could impact therapeutic decisions and, therefore, lead to delayed treatments. Recently, accumulating evidence have shown that both genetic abnormalities and chemical toxicants play important roles in the onset of ASD. In this work, a new multilabel classification (MLC) model is proposed to identify the autistic risk genes and toxic chemicals on a large-scale data set. We first construct the feature matrices and partially labeled networks for autistic risk genes and toxic chemicals from multiple heterogeneous biological databases. Based on both global and local measure metrics, the simulation experiments demonstrate that the proposed model achieves superior classification performance in comparison with the other state-of-the-art MLC methods. Through manual validation with existing studies, 60% and 50% out of the top-20 predicted risk genes are confirmed to have associations with ASD and autistic disorder, respectively. To the best of our knowledge, this is the first computational tool to identify ASD-related risk genes and toxic chemicals, which could lead to better therapeutic decisions of ASD.