Increasing riverine export of dissolved organic carbon from China.

River transport of dissolved organic carbon (DOC) to the ocean is a crucial but poorly quantified regional carbon cycle component. Large uncertainties remaining on the riverine DOC export from China, as well as its trend and drivers of change, have challenged the reconciliation between atmosphere-based and land-based estimates of China's land carbon sink. Here, we harmonized a large database of riverine in-situ measurements and applied a random forest model, to quantify riverine DOC fluxes (FDOC ) and DOC concentrations (CDOC ) in rivers across China. This study proposes the first DOC modeling effort capable of reproducing well the magnitude of riverine CDOC and FDOC , as well as its trends, on a monthly scale and with a much wider spatial distribution over China compared to previous studies that mainly focused on annual-scale estimates and large rivers. Results show that over the period 2001-2015, the average CDOC was 2.25 ± 0.45 mg/L and average FDOC was 4.04 ± 1.02 Tg/year. Simultaneously, we found a significant increase in FDOC (+0.044 Tg/year2 , p = .01), but little change in CDOC (-0.001 mg/L/year, p > .10). Although the trend in CDOC is not significant at the country scale, it is significantly increasing in the Yangtze River Basin and Huaihe River Basin (0.005 and 0.013 mg/L/year, p < .05) while significantly decreasing in the Yellow River Basin and Southwest Rivers Basin (-0.043 and -0.014 mg/L/year, p = .01). Changes in hydrology, play a stronger role than direct impacts of anthropogenic activities in determining the spatio-temporal variability of FDOC and CDOC across China. However, and in contrast with other basins, the significant increase in CDOC in the Yangtze River Basin and Huaihe River Basin is attributable to direct anthropogenic activities. Given the dominance of hydrology in driving FDOC , the increase in FDOC is likely to continue under the projected increase in river discharge over China resulting from a future wetter climate.

Classification models and SAR analysis on HDAC1 inhibitors using machine learning methods.

Histone deacetylase (HDAC) 1, a member of the histone deacetylases family, plays a pivotal role in various tumors. In this study, we collected 7313 human HDAC1 inhibitors with bioactivities to form a dataset. Then, the dataset was divided into a training set and a test set using two splitting methods: (1) Kohonen's self-organizing map and (2) random splitting. The molecular structures were represented by MACCS fingerprints, RDKit fingerprints, topological torsions fingerprints and ECFP4 fingerprints. A total of 80 classification models were built by using five machine learning methods, including decision tree (DT), random forest, support vector machine, eXtreme Gradient Boosting and deep neural network. Model 15A_2 built by the XGBoost algorithm based on ECFP4 fingerprints showed the best performance, with an accuracy of 88.08% and an MCC value of 0.76 on the test set. Finally, we clustered the 7313 HDAC1 inhibitors into 31 subsets, and the substructural features in each subset were investigated. Moreover, using DT algorithm we analyzed the structure-activity relationship of HDAC1 inhibitors. It may conclude that some substructures have a significant effect on high activity, such as N-(2-amino-phenyl)-benzamide, benzimidazole, AR-42 analogues, hydroxamic acid with a middle chain alkyl and 4-aryl imidazole with a midchain of alkyl whose α carbon is chiral.

Machine learning-based classification models for non-covalent Bruton's tyrosine kinase inhibitors: predictive ability and interpretability.

In this study, we built classification models using machine learning techniques to predict the bioactivity of non-covalent inhibitors of Bruton's tyrosine kinase (BTK) and to provide interpretable and transparent explanations for these predictions. To achieve this, we gathered data on BTK inhibitors from the Reaxys and ChEMBL databases, removing compounds with covalent bonds and duplicates to obtain a dataset of 3895 inhibitors of non-covalent. These inhibitors were characterized using MACCS fingerprints and Morgan fingerprints, and four traditional machine learning algorithms (decision trees (DT), random forests (RF), support vector machines (SVM), and extreme gradient boosting (XGBoost)) were used to build 16 classification models. In addition, four deep learning models were developed using deep neural networks (DNN). The best model, Model D_4, which was built using XGBoost and MACCS fingerprints, achieved an accuracy of 94.1% and a Matthews correlation coefficient (MCC) of 0.75 on the test set. To provide interpretable explanations, we employed the SHAP method to decompose the predicted values into the contributions of each feature. We also used K-means dimensionality reduction and hierarchical clustering to visualize the clustering effects of molecular structures of the inhibitors. The results of this study were validated using crystal structures, and we found that the interaction between the BTK amino acid residue and the important features of clustered scaffold was consistent with the known properties of the complex crystal structures. Overall, our models demonstrated high predictive ability and a qualitative model can be converted to a quantitative model to some extent by SHAP, making them valuable for guiding the design of new BTK inhibitors with desired activity.

Automated Seizure Detection in Patients with Cardiac Arrest: A Retrospective Review of Ceribell™ Rapid-EEG Recordings.

BACKGROUND: In patients with cardiac arrest who remain comatose after return of spontaneous circulation, seizures and other abnormalities on electroencephalogram (EEG) are common. Thus, guidelines recommend urgent initiation of EEG for the evaluation of seizures in this population. Point-of-care EEG systems, such as Ceribell™ Rapid Response EEG (Rapid-EEG), allow for prompt initiation of EEG monitoring, albeit through a reduced-channel montage. Rapid-EEG incorporates an automated seizure detection software (Clarity™) to measure seizure burden in real time and alert clinicians at the bedside when a high seizure burden, consistent with possible status epilepticus, is identified. External validation of Clarity is still needed. Our goal was to evaluate the real-world performance of Clarity for the detection of seizures and status epilepticus in a sample of patients with cardiac arrest. METHODS: This study was a retrospective review of Rapid-EEG recordings from all the patients who were admitted to the medical intensive care unit at Kent Hospital (Warwick, RI) between 6/1/2021 and 3/18/2022 for management after cardiac arrest and who underwent Rapid-EEG monitoring as part of their routine clinical care (n = 21). Board-certified epileptologists identified events that met criteria for seizures or status epilepticus, as per the 2021 American Clinical Neurophysiology Society's Standardized Critical Care EEG Terminology, and evaluated any seizure burden detections generated by Clarity. RESULTS: In this study, 4 of 21 patients with cardiac arrest (19.0%) who underwent Rapid-EEG monitoring had multiple electrographic seizures, and 2 of those patients (9.5%) had electrographic status epilepticus within the first 24 h of the study. None of these ictal abnormalities were detected by the Clarity seizure detection system. Clarity showed 0% seizure burden throughout the entirety of all four Rapid-EEG recordings, including the EEG pages that showed definite seizures or status epilepticus. CONCLUSIONS: The presence of frequent electrographic seizures and/or status epilepticus can go undetected by Clarity. Timely and careful review of all raw Rapid-EEG recordings by a qualified human EEG reader is necessary to guide clinical care, regardless of Clarity seizure burden measurements.

Motor-cognitive functions required for driving in post-stroke individuals identified via machine-learning analysis.

BACKGROUND: People who were previously hospitalised with stroke may have difficulty operating a motor vehicle, and their driving aptitude needs to be evaluated to prevent traffic accidents in today's car-based society. Although the association between motor-cognitive functions and driving aptitude has been extensively studied, motor-cognitive functions required for driving have not been elucidated. METHODS: In this paper, we propose a machine-learning algorithm that introduces sparse regularization to automatically select driving aptitude-related indices from 65 input indices obtained from 10 tests of motor-cognitive function conducted on 55 participants with stroke. Indices related to driving aptitude and their required tests can be identified based on the output probability of the presence or absence of driving aptitude to provide evidence for identifying subjects who must undergo the on-road driving test. We also analyzed the importance of the indices of motor-cognitive function tests in evaluating driving aptitude to further clarify the relationship between motor-cognitive function and driving aptitude. RESULTS: The experimental results showed that the proposed method achieved predictive evaluation of the presence or absence of driving aptitude with high accuracy (area under curve 0.946) and identified a group of indices of motor-cognitive function tests that are strongly related to driving aptitude. CONCLUSIONS: The proposed method is able to effectively and accurately unravel driving-related motor-cognitive functions from a panoply of test results, allowing for autonomous evaluation of driving aptitude in post-stroke individuals. This has the potential to reduce the number of screening tests required and the corresponding clinical workload, further improving personal and public safety and the quality of life of individuals with stroke.

Design of OMC-Sagnac Loop Using PDMS and Different Package Structures to Improve Sensing Performance and Optimize the Ill-Conditioned Matrix.

In the process of ocean exploration, highly accurate and sensitive measurements of seawater temperature and pressure significantly impact the study of seawater's physical, chemical, and biological processes. In this paper, three different package structures, V-shape, square-shape, and semicircle-shape, are designed and fabricated, and an optical microfiber coupler combined Sagnac loop (OMCSL) is encapsulated in these structures with polydimethylsiloxane (PDMS). Then, the temperature and pressure response characteristics of the OMCSL, under different package structures, are analyzed by simulation and experiment. The experimental results show that structural change hardly affects temperature sensitivity, and square-shape has the highest pressure sensitivity. In addition, with an input error of 1% F.S., temperature and pressure errors were calculated, which shows that a semicircle-shape structure can increase the angle between lines in the sensitivity matrix method (SMM), and reduce the effect of the input error, thus optimizing the ill-conditioned matrix. Finally, this paper shows that using the machine learning method (MLM) effectively improves demodulation accuracy. In conclusion, this paper proposes to optimize the ill-conditioned matrix problem in SMM demodulation by improving sensitivity with structural optimization, which essentially explains the cause of the large errors for multiparameter cross-sensitivity. In addition, this paper proposes to use the MLM to solve the problem of large errors in the SMM, which provides a new method to solve the problem of the ill-conditioned matrix in SMM demodulation. These have practical implications for engineering an all-optical sensor that can be used for detection in the ocean environment.

Biodegradability analysis of Dioxins through in silico methods: Model construction and mechanism analysis.

The biodegradation treatment of dioxins has long been of interest due to its good ecological and economic effects. In this study, the biodegradability of polychlorinated dibenzo-p-dioxins (PCDDs) were investigated by constructing machine learning and multiple linear regression models. The maximum chlorine atomic charge (qHirshfeldCl+), which characterizes the biodegradation ability of PCDDs, was used as the response value. The random forest model was used to rank the importance on the 1471 descriptors of PCDDs, and the BCUTp-1 h, QXZ, JGI4, ATSC8c, VE3_Dt, topoShape, and maxwHBa were screened as the important descriptors by Pearson's correlation coefficient method. A quantitative structure-activity relationship (QSAR) model was constructed to predict the biodegradability of PCDDs. In addition, the extreme gradient boosting (XGBoost) and random forest model were also constructed and proved the good predictability of QSAR model. The biodegradability of polychlorinated dibenzofurans (PCDFs) can also be predicted by the constructed three models from a certain level after adjusting some model parameters, which further proved the versatility of the models. Besides, the sensitivity analysis of the QSAR model and a 3D-QSAR model was developed to investigate the biodegradability mechanisms of PCDDs. Results showed that the descriptors BCUTp-1 h, JGI4, and maxwHBa were the key descriptors in the biodegradability effect by the sensitivity analysis of the QSAR model. Coupled with the results of PCDDs biodegradability 3D-QSAR model, BCUTp-1 h, JGI4, and maxwHBa were confirmed as the main descriptors that affect the biodegradability of dioxins. This study provides a novel theoretical perspective for the research of the biodegradation of both PCDDs and PCDFs dioxins.

Machine Learning-Based Model for Estimating Vancomycin Maintenance Dose to Target the Area under the Concentration Curve of 400-600 mg·h/L in Japanese Patients.

In therapeutic drug monitoring of vancomycin (VCM), the area under the concentration-time curve (AUC) is related to clinical efficacy and toxicity. Determining the maintenance for patient is necessary since VCM concentrations are affected by factors such as renal function. We constructed a machine learning-based model to estimate the maintenance dose to target an AUC of 400-600 mg⋅h/L in each combination of patient's factors. This retrospective observational study was conducted at two hospitals. Patients who received VCM intravenously with measured trough and another point (e.g., peak) concentrations within the November 2011 to March 2019 period were enrolled. We extracted the factors that affect VCM concentration and constructed a decision tree model using a classification and regression tree algorithm. Of the 1380 patients, 822 were included. Training data were split up to four times and included 24 subgroups. The average corrected VCM daily doses ranged 17.6-59.4 mg/kg. Estimated glomerular filtration rate, age, and body mass index were selected as predictive variables that affected the recommended daily dose. In the validation data, our model had slightly higher proportions of AUC of 400-600 mg⋅h/L than other nomograms. However, our model was based only on limited patients. Thus, further clinical studies are needed to develop a general-purpose model in the future. We successfully constructed a model that recommends VCM maintenance daily doses with AUC of 400-600 mg⋅h/L for each combination of independent variables. Our model has the potential for application as a simple decision-making tool for medical staff.

Simulation of the pollution abatement behavior of regional metal-related enterprises based on the interactive perspective of industrial agglomerations and emission reduction effects.

A machine learning method was used to process a multiagent information database to study the spatial distribution characteristics of agglomerations of metal-related enterprises and to analyze the spatial and temporal differentiation characteristics of pollution reduction in metal-related enterprises. Based on the spatial distribution of enterprises and a simulation of their pollution reduction behaviors, the layout of 380 enterprises sample is optimized, and the direction of industrial transfer is planned to give full play to the pollution reduction effect of enterprise agglomeration. The results showed that (1) the metal-related enterprises in the Chang-Zhu-Tan urban agglomeration have obvious spatial heterogeneity and are mainly distributed in the district of Changsha, the Qingshuitang Industrial Zone, Liling city and the Qibaoshan Industrial Zone of Liuyang city, while the metal-related enterprises in Shaoshan city, Zhuzhou County and Liling city are scattered. (2) The pollution emission behaviors of enterprises differ in time and space, and the pollution concentrations are highest in industrial parks such as Qingshuitang and Zhubu Port. (3) There is an interactive relationship between the degree of enterprise agglomeration and the pollution reduction effect. The spatial positive coupling degree between the concentration of metal-related enterprises and the degree of metal-related pollution is significant, accounting for 94.96% of the study area. Low pollution-high agglomeration areas, high pollution-low agglomeration areas, high pollution-high agglomeration areas, and low pollution-low agglomeration area account for 1.01%, 4.03%, 2.87%, and 92.09% of the study area, respectively. Finally, based on the new development concept of dual circulation and the theory of a two-oriented society in the new era, the paper puts forward suggestions and policies for the sustainable development of industrial transfer.

Analyzing brain structural differences among undergraduates with different grades of self-esteem using multiple anatomical brain network.

BACKGROUND: Self-esteem is the individual evaluation of oneself. People with high self-esteem grade have mental health and can bravely cope with the threats from the environment. With the development of neuroimaging techniques, researches on cognitive neural mechanisms of self-esteem are increased. Existing methods based on brain morphometry and single-layer brain network cannot characterize the subtle structural differences related to self-esteem. METHOD: To solve this issue, we proposed a multiple anatomical brain network based on multi-resolution region of interest (ROI) template to study the brain structural connections of self-esteem. The multiple anatomical brain network consists of ROI features and hierarchal brain network features that are extracted from structural MRI. For each layer, we calculated the correlation relationship between pairs of ROIs. In order to solve the high-dimensional problem caused by the large amount of network features, feature selection methods (t-test, mRMR, and SVM-RFE) are adopted to reduce the number of features while retaining discriminative information to the maximum extent. Multi-kernel SVM is employed to integrate the various types of features by appropriate weight coefficient. RESULT: The experimental results show that the proposed method can improve classification accuracy to 97.26% compared with single-layer brain network. CONCLUSIONS: The proposed method provides a new perspective for the analysis of brain structural differences of self-esteem, which also has potential guiding significance in other researches involved brain cognitive activity and brain disease diagnosis.

Predicting HIV drug resistance using weighted machine learning method at target protein sequence-level.

Acquired immune deficiency syndrome (AIDS) is a fatal disease caused by human immunodeficiency virus (HIV). Although 23 different drugs have been available, the treatment of AIDS remains challenging because the virus mutates very quickly which can lead to drug resistance. Therefore, predicting drug resistance before treatment is crucial for individual treatments. Here, based on HIV target protein sequence information, we analyzed 21-drug resistance caused by mutated residues using machine learning (ML) methods. To transform target sequences into numeric vectors, seven physicochemical properties were used, which can well represent the interacting characteristics of target proteins. Then, principal component analysis (PCA) method was adopted to reduce the feature dimensionality. Random forest (RF) and support vector machine (SVM) based on three different kernel functions, including linear, polynomial and radial basis function (RBF), were all employed. By comparisons, we found that RBF-based SVM method gives a comparative performance with RF model. Further, we added the weight information to RBF-based SVM method by four different weight evaluation methods of RF, eXtreme Gradient Boosting (XGB), CfsSubsetEval and ReliefFAttributeEval, respectively. Results show that the RF-weighted RBF-based SVM yield the superior performance and 13 out of 21 drug models provide the correlation coefficients (R2) over 0.8 and 3 of them are higher than 0.9. Finally, position-specific importance analysis indicates that most of the mutation residues with high RF weight scores are proved to be closely related with drug resistance, which has been revealed in previous reports. Overall, we can expect that this method can be a supplementary tool for predicting HIV drug resistance for newly discovered mutations. Here, based on HIV target protein sequence information, we analyzed 21-drug resistance caused by mutated residues using machine learning (ML) methods by fusing the weight information of different mutation positions.

Discovery of novel DGAT1 inhibitors by combination of machine learning methods, pharmacophore model and 3D-QSAR model.

DGAT1 plays a crucial controlling role in triglyceride biosynthetic pathways, which makes it an attractive therapeutic target for obesity. Thus, development of DGAT1 inhibitors with novel chemical scaffolds is desired and important in the drug discovery. In this investigation, the multistep virtual screening methods, including machine learning methods and common feature pharmacophore model, were developed and used to identify novel DGAT1 inhibitors from BioDiversity database with 30,000 compounds. 531 compounds were predicted as DGAT1 inhibitors by combination of machine learning methods comprising of SVM, NB and RP models. Then, 12 agents were filtered from 531 compounds by using the common feature pharmacophore model. The 3D chemical structures of the 12 hits coordinated with surface charges and isosurface have been carefully analyzed by the established 3D-QSAR model. Finally, 8 compounds with desired properties were retained from the final hits and have been assigned to another research group to complete the follow-up compound synthesis and biologic evaluation.

Monitoring the Burden of Seizures and Highly Epileptiform Patterns in Critical Care with a Novel Machine Learning Method.

INTRODUCTION: Current electroencephalography (EEG) practice relies on interpretation by expert neurologists, which introduces diagnostic and therapeutic delays that can impact patients' clinical outcomes. As EEG practice expands, these experts are becoming increasingly limited resources. A highly sensitive and specific automated seizure detection system would streamline practice and expedite appropriate management for patients with possible nonconvulsive seizures. We aimed to test the performance of a recently FDA-cleared machine learning method (Claritγ, Ceribell Inc.) that measures the burden of seizure activity in real time and generates bedside alerts for possible status epilepticus (SE). METHODS: We retrospectively identified adult patients (n = 353) who underwent evaluation of possible seizures with Rapid Response EEG system (Rapid-EEG, Ceribell Inc.). Automated detection of seizure activity and seizure burden throughout a recording (calculated as the percentage of ten-second epochs with seizure activity in any 5-min EEG segment) was performed with Claritγ, and various thresholds of seizure burden were tested (≥ 10% indicating ≥ 30 s of seizure activity in the last 5 min, ≥ 50% indicating ≥ 2.5 min of seizure activity, and ≥ 90% indicating ≥ 4.5 min of seizure activity and triggering a SE alert). The sensitivity and specificity of Claritγ's real-time seizure burden measurements and SE alerts were compared to the majority consensus of at least two expert neurologists. RESULTS: Majority consensus of neurologists labeled the 353 EEGs as normal or slow activity (n = 249), highly epileptiform patterns (HEP, n = 87), or seizures [n = 17, nine longer than 5 min (e.g., SE), and eight shorter than 5 min]. The algorithm generated a SE alert (≥ 90% seizure burden) with 100% sensitivity and 93% specificity. The sensitivity and specificity of various thresholds for seizure burden during EEG recordings for detecting patients with seizures were 100% and 82% for ≥ 50% seizure burden and 88% and 60% for ≥ 10% seizure burden. Of the 179 EEG recordings in which the algorithm detected no seizures, seizures were identified by the expert reviewers in only two cases, indicating a negative predictive value of 99%. DISCUSSION: Claritγ detected SE events with high sensitivity and specificity, and it demonstrated a high negative predictive value for distinguishing nonepileptiform activity from seizure and highly epileptiform activity. CONCLUSIONS: Ruling out seizures accurately in a large proportion of cases can help prevent unnecessary or aggressive over-treatment in critical care settings, where empiric treatment with antiseizure medications is currently prevalent. Claritγ's high sensitivity for SE and high negative predictive value for cases without epileptiform activity make it a useful tool for triaging treatment and the need for urgent neurological consultation.

Study on dynamic thermal characteristics of thermoelectric radiant cooling panel system through a hybrid method.

Thermoelectric radiant panel system (TERP), requires no hydronic pipes, pumps and chillers and the size is compact in solid form. In this study, the main results include a new system model of TERP and some new findings on the system dynamic characteristics. The new model integrates finite difference method and state-space matrix, which is an integration of great simulation accuracy, high speed, and easy implementation. The thermal response time (TRT) and its asynchronism are confirmed and a new concept of AM (Asynchronism Magnitude) is defined to measure the degree of TRT asynchronism. Some new observations are obtained: (1) Under a certain environment, AM becomes a constant even when different step changes of current are imposed; (2) The TRT asynchronism disappeared at the second stage when environmental condition is step changed. Three new definitions of TRT are proposed and compared. Finally, in order to realize the fast and accurate prediction of TRT for the use of system on-line control or fast evaluation under dynamic state, an artificial neural network-based model is proved to be effective. The dynamic analysis can offer a new paradigm to the evaluation, control and optimization of radiant cooling and other dynamic systems.

Real-time detection of potable-reclaimed water pipe cross-connection events by conventional water quality sensors using machine learning methods.

Risk of cross-connection is becoming higher due to greater construction of potable-reclaimed water dual distribution systems. Cross-connection events can result in serious health concerns and reduce public confidence in reclaimed water. Thus, reliable, cost-effective and real-time online detection methods for early warning are required. The current study carried out pilot-scale experiments to simulate potable-reclaimed water pipe cross-connection events for different mixing ratios (from 30% to 1%) using machine learning methods based on multiple conventional water quality parameters. The parameters included residual chlorine, pH, turbidity, temperature, conductivity, oxidation-reduction potential and chemical oxygen demand. The results showed that correlated variation occurred among water quality parameters at the time of the cross-connection event. A single parameter-based method can be effective at high mixing ratios, but not at low mixing ratios. The direct supporting vector machine (SVM)-based method managed to overcome this drawback, but coped poorly with abnormal readings of water parameter sensors. In that respect, a Pearson correlation coefficient (PCC)-SVM-based method was developed. It provided not only high detection performance under normal conditions, but also remained reliable when abnormal readings occurred. The detection accuracy and true positive rate of this method was still over 88%, and the false positive rate was below 12%, given a sudden variation of an individual water quality parameter. The receiver operating characteristic curves further confirmed the promising practical applicability of this PCC-SVM-based method for early detection of cross-connection events.

Impact of Sliding Window Length in Indoor Human Motion Modes and Pose Pattern Recognition Based on Smartphone Sensors.

Human activity recognition (HAR) is essential for understanding people’s habits and behaviors, providing an important data source for precise marketing and research in psychology and sociology. Different approaches have been proposed and applied to HAR. Data segmentation using a sliding window is a basic step during the HAR procedure, wherein the window length directly affects recognition performance. However, the window length is generally randomly selected without systematic study. In this study, we examined the impact of window length on smartphone sensor-based human motion and pose pattern recognition. With data collected from smartphone sensors, we tested a range of window lengths on five popular machine-learning methods: decision tree, support vector machine, K-nearest neighbor, Gaussian naïve Bayesian, and adaptive boosting. From the results, we provide recommendations for choosing the appropriate window length. Results corroborate that the influence of window length on the recognition of motion modes is significant but largely limited to pose pattern recognition. For motion mode recognition, a window length between 2.5⁻3.5 s can provide an optimal tradeoff between recognition performance and speed. Adaptive boosting outperformed the other methods. For pose pattern recognition, 0.5 s was enough to obtain a satisfactory result. In addition, all of the tested methods performed well.

PON-tstab: Protein Variant Stability Predictor. Importance of Training Data Quality.

Several methods have been developed to predict effects of amino acid substitutions on protein stability. Benchmark datasets are essential for method training and testing and have numerous requirements including that the data is representative for the investigated phenomenon. Available machine learning algorithms for variant stability have all been trained with ProTherm data. We noticed a number of issues with the contents, quality and relevance of the database. There were errors, but also features that had not been clearly communicated. Consequently, all machine learning variant stability predictors have been trained on biased and incorrect data. We obtained a corrected dataset and trained a random forests-based tool, PON-tstab, applicable to variants in any organism. Our results highlight the importance of the benchmark quality, suitability and appropriateness. Predictions are provided for three categories: stability decreasing, increasing and those not affecting stability.

Feasibility Study of a Generalized Framework for Developing Computer-Aided Detection Systems-a New Paradigm.

We propose a generalized framework for developing computer-aided detection (CADe) systems whose characteristics depend only on those of the training dataset. The purpose of this study is to show the feasibility of the framework. Two different CADe systems were experimentally developed by a prototype of the framework, but with different training datasets. The CADe systems include four components; preprocessing, candidate area extraction, candidate detection, and candidate classification. Four pretrained algorithms with dedicated optimization/setting methods corresponding to the respective components were prepared in advance. The pretrained algorithms were sequentially trained in the order of processing of the components. In this study, two different datasets, brain MRA with cerebral aneurysms and chest CT with lung nodules, were collected to develop two different types of CADe systems in the framework. The performances of the developed CADe systems were evaluated by threefold cross-validation. The CADe systems for detecting cerebral aneurysms in brain MRAs and for detecting lung nodules in chest CTs were successfully developed using the respective datasets. The framework was shown to be feasible by the successful development of the two different types of CADe systems. The feasibility of this framework shows promise for a new paradigm in the development of CADe systems: development of CADe systems without any lesion specific algorithm designing.

IonchanPred 2.0: A Tool to Predict Ion Channels and Their Types.

Ion channels (IC) are ion-permeable protein pores located in the lipid membranes of all cells. Different ion channels have unique functions in different biological processes. Due to the rapid development of high-throughput mass spectrometry, proteomic data are rapidly accumulating and provide us an opportunity to systematically investigate and predict ion channels and their types. In this paper, we constructed a support vector machine (SVM)-based model to quickly predict ion channels and their types. By considering the residue sequence information and their physicochemical properties, a novel feature-extracted method which combined dipeptide composition with the physicochemical correlation between two residues was employed. A feature selection strategy was used to improve the performance of the model. Comparison results of in jackknife cross-validation demonstrated that our method was superior to other methods for predicting ion channels and their types. Based on the model, we built a web server called IonchanPred which can be freely accessed from http://lin.uestc.edu.cn/server/IonchanPredv2.0.

Recent Advances in Conotoxin Classification by Using Machine Learning Methods.

Conotoxins are disulfide-rich small peptides, which are invaluable peptides that target ion channel and neuronal receptors. Conotoxins have been demonstrated as potent pharmaceuticals in the treatment of a series of diseases, such as Alzheimer's disease, Parkinson's disease, and epilepsy. In addition, conotoxins are also ideal molecular templates for the development of new drug lead compounds and play important roles in neurobiological research as well. Thus, the accurate identification of conotoxin types will provide key clues for the biological research and clinical medicine. Generally, conotoxin types are confirmed when their sequence, structure, and function are experimentally validated. However, it is time-consuming and costly to acquire the structure and function information by using biochemical experiments. Therefore, it is important to develop computational tools for efficiently and effectively recognizing conotoxin types based on sequence information. In this work, we reviewed the current progress in computational identification of conotoxins in the following aspects: (i) construction of benchmark dataset; (ii) strategies for extracting sequence features; (iii) feature selection techniques; (iv) machine learning methods for classifying conotoxins; (v) the results obtained by these methods and the published tools; and (vi) future perspectives on conotoxin classification. The paper provides the basis for in-depth study of conotoxins and drug therapy research.