蛋白质结构预测综述

蛋白质结构预测对于从分子层面理解蛋白质的生物功能具有重要意义。本研究从同源建模、自由建模等经典方法 以及深度学习这几个方面来阐述蛋白质结构预测方面的进展。已知结构蛋白质模板数量的增加、序列比对等算法对信息 提取能力的提升以及片段拼接技术的应用使得同源建模在预测蛋白结构的能力大大提升。域分割和片段分割技术及并 行计算策略的应用使得自由建模方法在预测远程氨基酸接触能力不断提升。深度学习技术与以上经典方法的结合提升 了蛋白结构预测的准确性和速度，但是对于没有同源性蛋白结构的预测，仍然存在巨大的挑战。     

基于运动量的神经网络心率预测器的设计及对比研究

目的 利用神经网络建立有效的基于运动量的心率预测模型,分析运动量与心率变化之间的关系.方法 通过对运动量信号进行不同分析（预处理）,并采用不同的神经网络的结构及学习算法,单步或多步预测方式建立了6个预测模型,然后利用采集到的真实数据进行测试,并对各模型结构框架及预测结果进行了对比.结果 建立的模型平均预测误差均保持在一个很小的范围内.结论 利用神经网络建立心率预测模型可有效地反映运动量如何影响心率变化.对比结果表明,在单步预测中,利用神经网络拓扑增强技术（neuro-evolution of augmenting topologies,NEAT）建立的心率预测模型可达到最佳的预测效果,而多步预测利用Adams-Bashforth技术得到的预测结果是最好的.     

基于超声影像组学的原发性肝细胞癌分级预测

目的:针对原发性肝细胞癌（HCC）肿瘤分级预测难题，提出一种基于灰阶超声成像的影像组学预测模型。方法:首先，由超声医生对肿瘤区域进行手动分割，其次，采用影像组学方法对肿瘤区域提取形状、一阶统计、纹理特征，计算特征间Pearson相关系数剔除冗余特征，最后通过单变量分析筛选得到特征子集，采用LASSO构建HCC分级预测模型；利用留一法计算模型的受试者操作特性曲线下的面积（AUC）评估模型对HCC分级的预测能力。结果:利用43例经手术病理证实的HCC患者的灰阶超声图像构建HCC分级预测模型，所建模型由6个与分级高度相关的影像特征组成，模型具有较强的预测能力（AUC=0.76）。结论:基于灰阶超声成像的影像特征与HCC分级高度相关，所建影像组学模型能够较好地预测HCC分级。     

基于3D-ResNet深度影像特征的胆囊癌生存预测模型

建立一个精准的个体化胆囊癌患者生存预测模型,分析、寻找新的胆囊癌预后因素,对于患者预后评估、治疗模式选择、手术患者筛选、术后辅助治疗方案确定及医疗资源合理使用均具有重要意义。本文提出一种基于3D-ResNet提取深度影像特征建立胆囊癌患者生存预后模型的方法,通过迁移学习以及训练3D-ResNet自动提取患者CT的深度特征,并利用提取的深度影像特征,通过Cox比例风险回归模型建立胆囊癌患者的生存预测模型。实验结果表明,基于深度影像特征建立的胆囊癌患者预后因子在预测患者生存时的C指数达到0.734,利用深度影像特征预后因子预测患者的1、3、5年存活率AUC分别达到0.833、0.791、0.813。本方法对胆囊癌预后预测有着良好的指示作用。     

基于K空间数据的深度核磁共振图像重建

传统的核磁共振(magnetic resonance imaging,MRI)成像技术中,图像重建算法与脉冲序列和K空间采样轨迹等因素密切相关。深度MRI成像采用了全新的重建方法。本研究采用深度卷积神经网络W-net对数据样本进行学习,从欠采集的K空间数据快速重建出高质量的图像。采用迁移学习方法,优化原模型参数,提升模型对各方向扫描、含病灶(如肿瘤)的大脑,以及结构较简单的膝盖等MRI数据的泛化能力。对比不同欠采样率的K空间输入数据,分析模型性能;并添加数据更新层,改进模型结构。测试结果表明,改进后的模型重建质量更优,对病灶和小脑纹理细节的恢复更好。     

基于卷积神经网络的房颤患者导管消融术后复发预测

通过采集患者术前的基础病史信息、影像检查信息、生化检查信息等资料,利用统计学和卷积神经网络相结合的方法对导管消融术预后情况进行预测。本研究中纳入了121例经射频消融手术治疗后的房颤患者,利用深度学习,先将生化检查的60个指标通过调整结构与参数建立3个房颤复发预测模型,复发预测精度最高为0.7（95%CI:0.536~0.864）。然后,将基础病史资料特征信息、影像检查信息进行统计学筛选和数据标准化处理,根据P值将差异性最大的10个特征与生化检查的60个特征融合,进行多因素跨模态的深度学习,建立3个深度模型,得到的房颤复发预测模型最高准确率为0.8（95%CI:0.657~0.943）。通过多组实验发现,深度模型并非越复杂越好,在样本量有限的情况下,选取合理的模型复杂度,并纳入多种模态特征可以获得更高的预测精度。     

基于多粒度级联森林的骨质疏松性骨折预测研究

目的骨质疏松性骨折(osteoporotic fracture,OF)的预测对于骨折防范具有重要的临床指导意义。针对传统logistic回归预测模型存在的精度不高和未考虑遗传因子问题,本文引入多粒度级联森林(multi-grained cascade forest,gcForest)并结合遗传因子来预测OF。方法首先基于 t 分布邻域嵌入( t -distributed stochastic neighbor embedding, t -SNE)算法对OF关联基因位点进行非线性降维,降维后的基因位点与临床因素构成特征组。然后构建gcForest模型对OF进行预测。最后通过10次十折分层交叉验证与logistic、梯度提升决策树、随机森林进行对比。结果基于gcForest的模型分类精度为0.892 7,AUC值为0.92±0.05,泛化性能最优。结论在考虑遗传因素的条件下,gcForest分类效果优于其他模型,验证了本文方法的高效性和实用性。     

基于样本增强的帕金森病识别算法研究

帕金森病患者早期存在声带损伤,其声纹特征与健康人存在明显差异,可以利用该差异识别帕金森病,但帕金森病患者声纹数据样本不足,因此本文提出双自注意力深度卷积生成对抗网络模型进行样本增强,生成高分辨率的语谱图,进而采用深度学习方法进行帕金森病识别。该模型通过增加网络深度并结合梯度惩罚、频谱归一化技术改进样本的纹理清晰度,并且构建一个基于迁移学习的纯粹的卷积神经网络家族（ConvNeXt）作为分类网络,以此提取声纹特征并进行分类,提升了帕金森病识别准确率。在帕金森病语音数据集上进行本文算法有效性验证实验,对比样本增强前,本文所提模型生成的样本清晰度以及弗雷谢起始距离（FID）均得到提高,并且本文网络模型能够获得98.8%的准确率。本文研究结果表明,基于双自注意力深度卷积生成对抗网络样本增强的帕金森病识别算法能够准确区分健康人和帕金森病患者,有助于解决帕金森病早期识别声纹数据样本不足的问题。综上,本文方法有效提高小样本帕金森病语音数据集分类准确率,为早期帕金森病语音诊断提供了一种有效的解决思路。     

协同训练算法在无创血糖检测中的应用

目的:在无创血糖检测方法的研究中,因无创生理参数相比血糖真值更易于获取,病理数据库中未用血糖真值标记样本的数量远大于有标记的样本,若能将未标记样本应用于传统有监督血糖预测模型的训练中,将有效扩充训练样本集并提高模型的泛化能力。 方法:在基于能量代谢守恒法的理论基础上,利用无创生理参数天然的多视图特性,将半监督学习算法应用于无创血糖的预测中,提出一种基于多视图协同训练与支持向量机技术的血糖预测算法。结果:经实验分析,在一定标记率下,基于协同训练的学习算法相比传统的有监督学习算法预测误差更小。说明未标记样本能够有效提升原始模型的泛化能力。 结论:协同训练的引入,充分利用了规模较大的未标记样本,提高了模型泛化能力,并减少了血糖样本采集中标记样本的工作量,为今后无创血糖算法的研究提供了新思路。     

基于TCGA数据库探究ESCRT相关基因对膀胱癌的潜在预后价值

目的 通过癌症基因图谱(TCGA)分析内吞体分选转运复合体(ESCRT)相关基因对膀胱癌预后的潜在预测价值,构建和评估膀胱癌预后模型。方法 通过访问TCGA数据库获取膀胱癌的临床病例资料和转录组数据。筛选与ESCRT相关基因在膀胱肿瘤组织与正常组织中的差异表达基因进行相关功能学富集分析,构建蛋白相互作用网络,采用Lasso和Cox回归方法,筛选与患者总生存期密切相关的基因,基于这些基因进一步构建出患者预后风险评分模型,并评估其预测能力。结果 从TCGA数据库下载包含405个膀胱癌组织和19个正常组织的RNA-seq信息,通过差异分析筛选出6个重合基因即膀胱癌差异表达的ESCRT家族基因,经过单因素Cox回归分析,发现存在3个基因对膀胱癌患者的预后有显著的影响。通过Lasso和Cox回归筛选分析最终得到2个(MVB12B、CHMP4C)与膀胱癌预后相关的关键基因并以此构建预后模型,预测训练集和验证集的1年、3年和5年ROC曲线下面积分别为0.768、0.694、0.732和0.651、0.720、0.776。结论 成功构建了基于2个关键DEGs表达的膀胱癌预后风险预测模型,该模型可为预测...     

基于DNABERT编码的启动子预测模型

启动子是位于基因上游区域的特定DNA序列,通过识别和预测DNA序列中的启动子,可以更好地理解基因调控的机制,促进生物学和医学研究的进展。通过实验的方法来预测启动子既昂贵又费时,而通过计算方法进行启动子预测同样存在不足之处,如精度有待提升、序列编码方式所包含的信息量不足等。该文提出了一种新的编码方式,将预训练模型DNABERT应用于启动子预测的编码,并测试了使用不同深度学习模型进行预测的效果。实验结果表明,使用经过预训练和微调的DNABERT进行编码的Transformer模型在启动子预测任务中取得了较好的效果。     

Classification of parotid gland tumors by using multimodal MRI and deep learning

Various MRI sequences have shown their potential to discriminate parotid gland tumors, including but not limited to T₂‐weighted, postcontrast T₁‐weighted, and diffusion‐weighted images. In this study, we present a fully automatic system for the diagnosis of parotid gland tumors by using deep learning methods trained on multimodal MRI images. We used a two‐dimensional convolution neural network, U‐Net, to segment and classify parotid gland tumors. The U‐Net model was trained with transfer learning, and a specific design of the batch distribution optimized the model accuracy. We also selected five combinations of MRI contrasts as the input data of the neural network and compared the classification accuracy of parotid gland tumors. The results indicated that the deep learning model with diffusion‐related parameters performed better than those with structural MR images. The performance results (n = 85) of the diffusion‐based model were as follows: accuracy of 0.81, 0.76, and 0.71, sensitivity of 0.83, 0.63, and 0.33, and specificity of 0.80, 0.84, and 0.87 for Warthin tumors, pleomorphic adenomas, and malignant tumors, respectively. Combining diffusion‐weighted and contrast‐enhanced T₁‐weighted images did not improve the prediction accuracy. In summary, the proposed deep learning model could classify Warthin tumor and pleomorphic adenoma tumor but not malignant tumor.     

Combined prediction of transmembrane topology and signal peptide of β-barrel proteins: Using a hidden Markov model and genetic algorithms

Background

Hidden Markov models (HMMs) have been extensively used in computational molecular biology, for modelling protein and nucleic acid sequences. The design of the model architecture and the algorithms for parameter estimation and decoding are extremely important for improve the performance of HMM. In topology prediction of transmembrane β-barrels proteins (TMBs), the Baum-Welch algorithm is widely adapted for HMM training but usually leads to a sub-optimal model in practice. In addition, all the existing HMM-based predictors are only designed to model the transmembrane segment without a submodel to model the signal peptide (SP) for full-length sequences. It is not convenient for users to investigate the structures of full-length TMB sequences.

Results

We present here, an HMM that combine a transmembrane barrel submodel and an SP submodel for both topology and SP predictions. A new genetic algorithm (GA) is presented here to training the model, at the same time the Posterior-Viterbi algorithm is adopted for decoding. A dataset including 33 TMBs that is the most so far in literature are collected for model training and testing. Results of self-consistency and jackknife tests shows the GA has better global performance than the Baum-Welch algorithm. Results of jackknife tests show that this method performs better than all well known existing methods for topology predictions. Furthermore, it provides a function to predict SP in full-length TMBs sequences with fairish accuracy.

Conclusion

We show that our combined HMM-based method is a better choice for TMB topology prediction, which implements topology predictions with higher accuracy and additional SP predictions for full-length TMB sequences.     

A prediction model of substrates and non-substrates of breast cancer resistance protein (BCRP) developed by GA-CG-SVM method

Breast cancer resistance protein (BCRP) is one of the key multi-drug resistance proteins, which significantly influences the therapeutic effects of many drugs, particularly anti-cancer drugs. Thus, distinguishing between substrates and non-substrates of BCRP is important not only for clinical use but also for drug discovery and development. In this study, a prediction model of the substrates and non-substrates of BCRP was developed using a modified support vector machine (SVM) method, namely GA–CG–SVM. The overall prediction accuracy of the established GA–CG–SVM model is 91.3% for the training set and 85.0% for an independent validation set. For comparison, two other machine learning methods, namely, C4.5 DT and k-NN, were also adopted to build prediction models. The results show that the GA–CG–SVM model is significantly superior to C4.5 DT and k-NN models in terms of the prediction accuracy. To sum up, the prediction model of BCRP substrates and non-substrates generated by the GA–CG–SVM method is sufficiently good and could be used as a screening tool for identifying the substrates and non-substrates of BCRP.     

Prediction of Neurological Outcomes in Out-of-hospital Cardiac Arrest Survivors Immediately after Return of Spontaneous Circulation: Ensemble Technique with Four Machine Learning Models

BackgroundWe performed this study to establish a prediction model for 1-year neurological outcomes in out-of-hospital cardiac arrest (OHCA) patients who achieved return of spontaneous circulation (ROSC) immediately after ROSC using machine learning methods.MethodsWe performed a retrospective analysis of an OHCA survivor registry. Patients aged ≥ 18 years were included. Study participants who had registered between March 31, 2013 and December 31, 2018 were divided into a develop dataset (80% of total) and an internal validation dataset (20% of total), and those who had registered between January 1, 2019 and December 31, 2019 were assigned to an external validation dataset. Four machine learning methods, including random forest, support vector machine, ElasticNet and extreme gradient boost, were implemented to establish prediction models with the develop dataset, and the ensemble technique was used to build the final prediction model. The prediction performance of the model in the internal validation and the external validation dataset was described with accuracy, area under the receiver-operating characteristic curve, area under the precision-recall curve, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Futhermore, we established multivariable logistic regression models with the develop set and compared prediction performance with the ensemble models. The primary outcome was an unfavorable 1-year neurological outcome.ResultsA total of 1,207 patients were included in the study. Among them, 631, 139, and 153 were assigned to the develop, the internal validation and the external validation datasets, respectively. Prediction performance metrics for the ensemble prediction model in the internal validation dataset were as follows: accuracy, 0.9620 (95% confidence interval [CI], 0.9352–0.9889); area under receiver-operator characteristics curve, 0.9800 (95% CI, 0.9612–0.9988); area under precision-recall curve, 0.9950 (95% CI, 0.9860–1.0000); sensitivity, 0.9594 (95% CI, 0.9245–0.9943); specificity, 0.9714 (95% CI, 0.9162–1.0000); PPV, 0.9916 (95% CI, 0.9752–1.0000); NPV, 0.8718 (95% CI, 0.7669–0.9767). Prediction performance metrics for the model in the external validation dataset were as follows: accuracy, 0.8509 (95% CI, 0.7825–0.9192); area under receiver-operator characteristics curve, 0.9301 (95% CI, 0.8845–0.9756); area under precision-recall curve, 0.9476 (95% CI, 0.9087–0.9867); sensitivity, 0.9595 (95% CI, 0.9145–1.0000); specificity, 0.6500 (95% CI, 0.5022–0.7978); PPV, 0.8353 (95% CI, 0.7564–0.9142); NPV, 0.8966 (95% CI, 0.7857–1.0000). All the prediction metrics were higher in the ensemble models, except NPVs in both the internal and the external validation datasets.ConclusionWe established an ensemble prediction model for prediction of unfavorable 1-year neurological outcomes in OHCA survivors using four machine learning methods. The prediction performance of the ensemble model was higher than the multivariable logistic regression model, while its performance was slightly decreased in the external validation dataset.     

基于深度学习的行人属性多标签识别

行人属性通常指的是行人的一些可被观察到的外部特征,如性别、年龄、服饰、携带品等。作为行人外部的软生物特征,行人属性对于行人检测和再识别是非常重要的,并且在智能视频监控场景和基于视频的商业智能应用中显示出巨大的潜力。在目前的行人属性多标签分类识别中,主要有基于手工设计特征的方法和基于深度学习的方法。然而,手工设计特征的方法难以应对复杂的真实视频监控场景,在实际应用中取得的效果并不是很理想。采用深度卷积网络模型,包含3个卷积层和2个全连接层,使用Sigmoid交叉熵损失函数,训练平台为Caffe深度学习框架,通过在包含19 000张行人图片的PETA数据集上对10种行人属性进行训练和测试,得到85.2%的平均识别精度。加入正样本比例指数因子改进损失函数后,平均识别精度达到89.2%,使网络性能有明显的提高。     

Molecular characterization of FrpB, the 70-kilodalton iron-regulated outer membrane protein of Neisseria meningitidis.

The structural gene encoding the 70-kDa outer membrane protein FrpB of Neisseria meningitidis was cloned and sequenced. A mutant lacking FrpB was constructed. No difference in iron utilization between the mutant and the parental strain was observed. A minor effect of the mutation on serum resistance was observed. A topology model for FrpB in the outer membrane is proposed.     

Medical decision support system for diagnosis of neuromuscular disorders using DWT and fuzzy support vector machines

The motor unit action potentials (MUAPs) in an electromyographic (EMG) signal provide a significant source of information for the assessment of neuromuscular disorders. In this work, different types of machine learning methods were used to classify EMG signals and compared in relation to their accuracy in classification of EMG signals. The models automatically classify the EMG signals into normal, neurogenic or myopathic. The best averaged performance over 10 runs of randomized cross-validation is also obtained by different classification models. Some conclusions concerning the impacts of features on the EMG signal classification were obtained through analysis of the classification techniques. The comparative analysis suggests that the fuzzy support vector machines (FSVM) modelling is superior to the other machine learning methods in at least three points: slightly higher recognition rate; insensitivity to overtraining; and consistent outputs demonstrating higher reliability. The combined model with discrete wavelet transform (DWT) and FSVM achieves the better performance for internal cross validation (External cross validation) with the area under the receiver operating characteristic (ROC) curve (AUC) and accuracy equal to 0.996 (0.970) and 97.67% (93.5%), respectively. These results show that the proposed model have the potential to obtain a reliable classification of EMG signals, and to assist the clinicians for making a correct diagnosis of neuromuscular disorders.