In recent years, a deep learning model called convolutional neural network with an ability of extracting features of high-level abstraction from minimum preprocessing data has been widely used. In this research, we pr...In recent years, a deep learning model called convolutional neural network with an ability of extracting features of high-level abstraction from minimum preprocessing data has been widely used. In this research, we proposed a new approach in classifying DNA sequences using the convolutional neural network while considering these sequences as text data. We used one-hot vectors to represent sequences as input to the model;therefore, it conserves the essential position information of each nucleotide in sequences. Using 12 DNA sequence datasets, we evaluated our proposed model and achieved significant improvements in all of these datasets. This result has shown a potential of using convolutional neural network for DNA sequence to solve other sequence problems in bioinformatics.展开更多
Emergence of drug resistant bacteria is one of the serious problems in today’s public health. However, the relationship between genomic mutation of bacteria and the phenotypic difference of them is still unclear. In ...Emergence of drug resistant bacteria is one of the serious problems in today’s public health. However, the relationship between genomic mutation of bacteria and the phenotypic difference of them is still unclear. In this paper, based on the mutation information in whole genome sequences of 96 MRSA strains, two kinds of phenotypes (pathogenicity and drug resistance) were learnt and predicted by machine learning algorithms. As a result of effective feature selection by cross entropy based sparse logistic regression, these phenotypes could be predicted in sufficiently high accuracy (100% and 97.87%, respectively) with less than 10 features. It means that we could develop a novel rapid test method in the future for checking MRSA phenotypes.展开更多
As a key technology of rapid and low-cost drug development, drug repositioning is getting popular. In this study, a text mining approach to the discovery of unknown drug-disease relation was tested. Using a word embed...As a key technology of rapid and low-cost drug development, drug repositioning is getting popular. In this study, a text mining approach to the discovery of unknown drug-disease relation was tested. Using a word embedding algorithm, senses of over 1.7 million words were well represented in sufficiently short feature vectors. Through various analysis including clustering and classification, feasibility of our approach was tested. Finally, our trained classification model achieved 87.6% accuracy in the prediction of drug-disease relation in cancer treatment and succeeded in discovering novel drug-disease relations that were actually reported in recent studies.展开更多
In many animal-related studies, a high-performance animal behavior recognition system can help researchers reduce or get rid of the limitation of human assessments and make the experiments easier to reproduce. Recentl...In many animal-related studies, a high-performance animal behavior recognition system can help researchers reduce or get rid of the limitation of human assessments and make the experiments easier to reproduce. Recently, although deep learning models are holding state-of-the-art performances in human action recognition tasks, these models are not well-studied in applying to animal behavior recognition tasks. One reason is the lack of extensive datasets which are required to train these deep models for good performances. In this research, we investigated two current state-of-the-art deep learning models in human action recognition tasks, the I3D model and the R(2 + 1)D model, in solving a mouse behavior recognition task. We compared their performances with other models from previous researches and the results showed that the deep learning models that pre-trained using human action datasets then fine-tuned using the mouse behavior dataset can outperform other models from previous researches. It also shows promises of applying these deep learning models to other animal behavior recognition tasks without any significant modification in the models’ architecture, all we need to do is collecting proper datasets for the tasks and fine-tuning the pre-trained models using the collected data.展开更多
Phosphorylation of protein is an important post-translational modification that enables activation of various enzymes and receptors included in signaling pathways. To reduce the cost of identifying phosphorylation sit...Phosphorylation of protein is an important post-translational modification that enables activation of various enzymes and receptors included in signaling pathways. To reduce the cost of identifying phosphorylation site by laborious experiments, computational prediction of it has been actively studied. In this study, by adopting a new set of features and applying feature selection by Random Forest with grid search before training by Support Vector Machine, our method achieved better or comparable performance of phosphorylation site prediction for two different data sets.展开更多
To classify DNA sequences, k-mer frequency is widely used since it can convert variable-length sequences into fixed-length and numerical feature vectors. However, in case of fixed-length DNA sequence classification, s...To classify DNA sequences, k-mer frequency is widely used since it can convert variable-length sequences into fixed-length and numerical feature vectors. However, in case of fixed-length DNA sequence classification, subsequences starting at a specific position of the given sequence can also be used as categorical features. Through the performance evaluation on six datasets of fixed-length DNA sequences, our algorithm based on the above idea achieved comparable or better performance than other state-of-the art algorithms.展开更多
We developed a ground observation system for solid precipitation using two-dimensional video disdrometer (2DVD). Among 16,010 particles observed by the system, around 10% of them were randomly sampled and manually cla...We developed a ground observation system for solid precipitation using two-dimensional video disdrometer (2DVD). Among 16,010 particles observed by the system, around 10% of them were randomly sampled and manually classified into five classes which are snowflake, snowflake-like, intermediate, graupel-like, and graupel. At first, each particle was represented as a vector of 72 features containing fractal dimension and box-count to represent the complexity of particle shape. Feature analysis on the dataset clarified the importance of fractal dimension and box-count features for characterizing particles varying from snowflakes to graupels. On the other hand, performance evaluation of two-class classification by Support Vector Machine (SVM) was conducted. The experimental results revealed that, by selecting only 10 features out of 72, the average accuracy of classifying particles into snowflakes and graupels could reach around 95.4%, which had not been achieved by previous studies.展开更多
In protein sequence classification research, it is popular to convert a variable length sequence of protein into a fixed length numerical vector by using various descriptors, for instance, composition of k-mer composi...In protein sequence classification research, it is popular to convert a variable length sequence of protein into a fixed length numerical vector by using various descriptors, for instance, composition of k-mer composition. Such position-independent descriptors are useful since they are applicable to any length of sequence;however, positional information of subsequence is discarded even though it might have high contribution to classification performance. To solve this problem, we divided the original sequence into some segments, and then calculated the numerical features for them. It enables us to partially introduce positional information (for instance, compositions of serine in anterior and posterior segments of a sequence). Through comprehensive experiments on the number of segments and length of overlapping region, we found our classification approach with sequence segmentation and feature selection is effective to improve the performance. We evaluated our approach on three protein classification problems and achieved significant improvement in all cases which have a dataset with sufficient amino acid in each sequence. This result has shown the great potential of using additional segments in protein sequence classification to solve other sequence problems in bioinformatics.展开更多
文摘In recent years, a deep learning model called convolutional neural network with an ability of extracting features of high-level abstraction from minimum preprocessing data has been widely used. In this research, we proposed a new approach in classifying DNA sequences using the convolutional neural network while considering these sequences as text data. We used one-hot vectors to represent sequences as input to the model;therefore, it conserves the essential position information of each nucleotide in sequences. Using 12 DNA sequence datasets, we evaluated our proposed model and achieved significant improvements in all of these datasets. This result has shown a potential of using convolutional neural network for DNA sequence to solve other sequence problems in bioinformatics.
文摘Emergence of drug resistant bacteria is one of the serious problems in today’s public health. However, the relationship between genomic mutation of bacteria and the phenotypic difference of them is still unclear. In this paper, based on the mutation information in whole genome sequences of 96 MRSA strains, two kinds of phenotypes (pathogenicity and drug resistance) were learnt and predicted by machine learning algorithms. As a result of effective feature selection by cross entropy based sparse logistic regression, these phenotypes could be predicted in sufficiently high accuracy (100% and 97.87%, respectively) with less than 10 features. It means that we could develop a novel rapid test method in the future for checking MRSA phenotypes.
文摘As a key technology of rapid and low-cost drug development, drug repositioning is getting popular. In this study, a text mining approach to the discovery of unknown drug-disease relation was tested. Using a word embedding algorithm, senses of over 1.7 million words were well represented in sufficiently short feature vectors. Through various analysis including clustering and classification, feasibility of our approach was tested. Finally, our trained classification model achieved 87.6% accuracy in the prediction of drug-disease relation in cancer treatment and succeeded in discovering novel drug-disease relations that were actually reported in recent studies.
文摘In many animal-related studies, a high-performance animal behavior recognition system can help researchers reduce or get rid of the limitation of human assessments and make the experiments easier to reproduce. Recently, although deep learning models are holding state-of-the-art performances in human action recognition tasks, these models are not well-studied in applying to animal behavior recognition tasks. One reason is the lack of extensive datasets which are required to train these deep models for good performances. In this research, we investigated two current state-of-the-art deep learning models in human action recognition tasks, the I3D model and the R(2 + 1)D model, in solving a mouse behavior recognition task. We compared their performances with other models from previous researches and the results showed that the deep learning models that pre-trained using human action datasets then fine-tuned using the mouse behavior dataset can outperform other models from previous researches. It also shows promises of applying these deep learning models to other animal behavior recognition tasks without any significant modification in the models’ architecture, all we need to do is collecting proper datasets for the tasks and fine-tuning the pre-trained models using the collected data.
文摘Phosphorylation of protein is an important post-translational modification that enables activation of various enzymes and receptors included in signaling pathways. To reduce the cost of identifying phosphorylation site by laborious experiments, computational prediction of it has been actively studied. In this study, by adopting a new set of features and applying feature selection by Random Forest with grid search before training by Support Vector Machine, our method achieved better or comparable performance of phosphorylation site prediction for two different data sets.
文摘To classify DNA sequences, k-mer frequency is widely used since it can convert variable-length sequences into fixed-length and numerical feature vectors. However, in case of fixed-length DNA sequence classification, subsequences starting at a specific position of the given sequence can also be used as categorical features. Through the performance evaluation on six datasets of fixed-length DNA sequences, our algorithm based on the above idea achieved comparable or better performance than other state-of-the art algorithms.
文摘We developed a ground observation system for solid precipitation using two-dimensional video disdrometer (2DVD). Among 16,010 particles observed by the system, around 10% of them were randomly sampled and manually classified into five classes which are snowflake, snowflake-like, intermediate, graupel-like, and graupel. At first, each particle was represented as a vector of 72 features containing fractal dimension and box-count to represent the complexity of particle shape. Feature analysis on the dataset clarified the importance of fractal dimension and box-count features for characterizing particles varying from snowflakes to graupels. On the other hand, performance evaluation of two-class classification by Support Vector Machine (SVM) was conducted. The experimental results revealed that, by selecting only 10 features out of 72, the average accuracy of classifying particles into snowflakes and graupels could reach around 95.4%, which had not been achieved by previous studies.
文摘In protein sequence classification research, it is popular to convert a variable length sequence of protein into a fixed length numerical vector by using various descriptors, for instance, composition of k-mer composition. Such position-independent descriptors are useful since they are applicable to any length of sequence;however, positional information of subsequence is discarded even though it might have high contribution to classification performance. To solve this problem, we divided the original sequence into some segments, and then calculated the numerical features for them. It enables us to partially introduce positional information (for instance, compositions of serine in anterior and posterior segments of a sequence). Through comprehensive experiments on the number of segments and length of overlapping region, we found our classification approach with sequence segmentation and feature selection is effective to improve the performance. We evaluated our approach on three protein classification problems and achieved significant improvement in all cases which have a dataset with sufficient amino acid in each sequence. This result has shown the great potential of using additional segments in protein sequence classification to solve other sequence problems in bioinformatics.