Circular-SWAT for deep learning based diagnostic classification of Alzheimer's disease: application to metabolome data.

BACKGROUND: Deep learning has shown potential in various scientific domains but faces challenges when applied to complex, high-dimensional multi-omics data. Alzheimer's Disease (AD) is a neurodegenerative disorder that lacks targeted therapeutic options. This study introduces the Circular-Sliding Window Association Test (c-SWAT) to improve the classification accuracy in predicting AD using serum-based metabolomics data, specifically lipidomics. METHODS: The c-SWAT methodology builds upon the existing Sliding Window Association Test (SWAT) and utilizes a three-step approach: feature correlation analysis, feature selection, and classification. Data from 997 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) served as the basis for model training and validation. Feature correlations were analyzed using Weighted Gene Co-expression Network Analysis (WGCNA), and Convolutional Neural Networks (CNN) were employed for feature selection. Random Forest was used for the final classification. FINDINGS: The application of c-SWAT resulted in a classification accuracy of up to 80.8% and an AUC of 0.808 for distinguishing AD from cognitively normal older adults. This marks a 9.4% improvement in accuracy and a 0.169 increase in AUC compared to methods without c-SWAT. These results were statistically significant, with a p-value of 1.04 × 10ˆ-4. The approach also identified key lipids associated with AD, such as Cer(d16:1/22:0) and PI(37:6). INTERPRETATION: Our results indicate that c-SWAT is effective in improving classification accuracy and in identifying potential lipid biomarkers for AD. These identified lipids offer new avenues for understanding AD and warrant further investigation. FUNDING: The specific funding of this article is provided in the acknowledgements section.

Deep learning-based identification of genetic variants: application to Alzheimer's disease classification.

Deep learning is a promising tool that uses nonlinear transformations to extract features from high-dimensional data. Deep learning is challenging in genome-wide association studies (GWAS) with high-dimensional genomic data. Here we propose a novel three-step approach (SWAT-CNN) for identification of genetic variants using deep learning to identify phenotype-related single nucleotide polymorphisms (SNPs) that can be applied to develop accurate disease classification models. In the first step, we divided the whole genome into nonoverlapping fragments of an optimal size and then ran convolutional neural network (CNN) on each fragment to select phenotype-associated fragments. In the second step, using a Sliding Window Association Test (SWAT), we ran CNN on the selected fragments to calculate phenotype influence scores (PIS) and identify phenotype-associated SNPs based on PIS. In the third step, we ran CNN on all identified SNPs to develop a classification model. We tested our approach using GWAS data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) including (N = 981; cognitively normal older adults (CN) = 650 and AD = 331). Our approach identified the well-known APOE region as the most significant genetic locus for AD. Our classification model achieved an area under the curve (AUC) of 0.82, which was compatible with traditional machine learning approaches, random forest and XGBoost. SWAT-CNN, a novel deep learning-based genome-wide approach, identified AD-associated SNPs and a classification model for AD and may hold promise for a range of biomedical applications.

Deep learning detection of informative features in tau PET for Alzheimer's disease classification.

BACKGROUND: Alzheimer's disease (AD) is the most common type of dementia, typically characterized by memory loss followed by progressive cognitive decline and functional impairment. Many clinical trials of potential therapies for AD have failed, and there is currently no approved disease-modifying treatment. Biomarkers for early detection and mechanistic understanding of disease course are critical for drug development and clinical trials. Amyloid has been the focus of most biomarker research. Here, we developed a deep learning-based framework to identify informative features for AD classification using tau positron emission tomography (PET) scans. RESULTS: The 3D convolutional neural network (CNN)-based classification model of AD from cognitively normal (CN) yielded an average accuracy of 90.8% based on five-fold cross-validation. The LRP model identified the brain regions in tau PET images that contributed most to the AD classification from CN. The top identified regions included the hippocampus, parahippocampus, thalamus, and fusiform. The layer-wise relevance propagation (LRP) results were consistent with those from the voxel-wise analysis in SPM12, showing significant focal AD associated regional tau deposition in the bilateral temporal lobes including the entorhinal cortex. The AD probability scores calculated by the classifier were correlated with brain tau deposition in the medial temporal lobe in MCI participants (r = 0.43 for early MCI and r = 0.49 for late MCI). CONCLUSION: A deep learning framework combining 3D CNN and LRP algorithms can be used with tau PET images to identify informative features for AD classification and may have application for early detection during prodromal stages of AD.

Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data.

Deep learning, a state-of-the-art machine learning approach, has shown outstanding performance over traditional machine learning in identifying intricate structures in complex high-dimensional data, especially in the domain of computer vision. The application of deep learning to early detection and automated classification of Alzheimer's disease (AD) has recently gained considerable attention, as rapid progress in neuroimaging techniques has generated large-scale multimodal neuroimaging data. A systematic review of publications using deep learning approaches and neuroimaging data for diagnostic classification of AD was performed. A PubMed and Google Scholar search was used to identify deep learning papers on AD published between January 2013 and July 2018. These papers were reviewed, evaluated, and classified by algorithm and neuroimaging type, and the findings were summarized. Of 16 studies meeting full inclusion criteria, 4 used a combination of deep learning and traditional machine learning approaches, and 12 used only deep learning approaches. The combination of traditional machine learning for classification and stacked auto-encoder (SAE) for feature selection produced accuracies of up to 98.8% for AD classification and 83.7% for prediction of conversion from mild cognitive impairment (MCI), a prodromal stage of AD, to AD. Deep learning approaches, such as convolutional neural network (CNN) or recurrent neural network (RNN), that use neuroimaging data without pre-processing for feature selection have yielded accuracies of up to 96.0% for AD classification and 84.2% for MCI conversion prediction. The best classification performance was obtained when multimodal neuroimaging and fluid biomarkers were combined. Deep learning approaches continue to improve in performance and appear to hold promise for diagnostic classification of AD using multimodal neuroimaging data. AD research that uses deep learning is still evolving, improving performance by incorporating additional hybrid data types, such as-omics data, increasing transparency with explainable approaches that add knowledge of specific disease-related features and mechanisms.

A possible mechanism for low affinity of silkworm Na+/K+-ATPase for K.

The affinity for K+ of silkworm nerve Na+/K+-ATPase is markedly lower than that of mammalian Na+/K+-ATPase (Homareda 2010). In order to obtain clues on the molecular basis of the difference in K+ affinities, we cloned cDNAs of silkworm (Bombyx mori) nerve Na+/K+-ATPase α and ß subunits, and analyzed the deduced amino acid sequences. The molecular masses of the α and ß subunits were presumed to be 111.5 kDa with ten transmembrane segments and 37.7 kDa with a single transmembrane segment, respectively. The α subunit showed 75% identity and 93% homology with the pig Na+/K+-ATPase α1 subunit. On the other hand, the amino acid identity of the ß subunit with mammalian counterparts was as low as 30%. Cloned α and ß cDNAs were co-expressed in cultured silkworm ovary-derived cells, BM-N cells, which lack endogenous Na+/K+-ATPase. Na+/K+-ATPase expressed in the cultured cells showed a low affinity for K+ and a high affinity for Na+, characteristic of the silkworm nerve Na+/K+-ATPase. These results suggest that the ß subunit is responsible for the affinity for K+ of Na+/K+-ATPase.

Improving Protein Fold Recognition by Deep Learning Networks.

For accurate recognition of protein folds, a deep learning network method (DN-Fold) was developed to predict if a given query-template protein pair belongs to the same structural fold. The input used stemmed from the protein sequence and structural features extracted from the protein pair. We evaluated the performance of DN-Fold along with 18 different methods on Lindahl's benchmark dataset and on a large benchmark set extracted from SCOP 1.75 consisting of about one million protein pairs, at three different levels of fold recognition (i.e., protein family, superfamily, and fold) depending on the evolutionary distance between protein sequences. The correct recognition rate of ensembled DN-Fold for Top 1 predictions is 84.5%, 61.5%, and 33.6% and for Top 5 is 91.2%, 76.5%, and 60.7% at family, superfamily, and fold levels, respectively. We also evaluated the performance of single DN-Fold (DN-FoldS), which showed the comparable results at the level of family and superfamily, compared to ensemble DN-Fold. Finally, we extended the binary classification problem of fold recognition to real-value regression task, which also show a promising performance. DN-Fold is freely available through a web server at http://iris.rnet.missouri.edu/dnfold.

Improving protein fold recognition by random forest.

BACKGROUND: Recognizing the correct structural fold among known template protein structures for a target protein (i.e. fold recognition) is essential for template-based protein structure modeling. Since the fold recognition problem can be defined as a binary classification problem of predicting whether or not the unknown fold of a target protein is similar to an already known template protein structure in a library, machine learning methods have been effectively applied to tackle this problem. In our work, we developed RF-Fold that uses random forest - one of the most powerful and scalable machine learning classification methods - to recognize protein folds. RESULTS: RF-Fold consists of hundreds of decision trees that can be trained efficiently on very large datasets to make accurate predictions on a highly imbalanced dataset. We evaluated RF-Fold on the standard Lindahl's benchmark dataset comprised of 976 × 975 target-template protein pairs through cross-validation. Compared with 17 different fold recognition methods, the performance of RF-Fold is generally comparable to the best performance in fold recognition of different difficulty ranging from the easiest family level, the medium-hard superfamily level, and to the hardest fold level. Based on the top-one template protein ranked by RF-Fold, the correct recognition rate is 84.5%, 63.4%, and 40.8% at family, superfamily, and fold levels, respectively. Based on the top-five template protein folds ranked by RF-Fold, the correct recognition rate increases to 91.5%, 79.3% and 58.3% at family, superfamily, and fold levels. CONCLUSIONS: The good performance achieved by the RF-Fold demonstrates the random forest's effectiveness for protein fold recognition.

Molecular identification of necrophagous muscidae and sarcophagidae fly species collected in Korea by mitochondrial cytochrome C oxidase subunit I nucleotide sequences.

Identification of insect species is an important task in forensic entomology. For more convenient species identification, the nucleotide sequences of cytochrome c oxidase subunit I (COI) gene have been widely utilized. We analyzed full-length COI nucleotide sequences of 10 Muscidae and 6 Sarcophagidae fly species collected in Korea. After DNA extraction from collected flies, PCR amplification and automatic sequencing of the whole COI sequence were performed. Obtained sequences were analyzed for a phylogenetic tree and a distance matrix. Our data showed very low intraspecific sequence distances and species-level monophylies. However, sequence comparison with previously reported sequences revealed a few inconsistencies or paraphylies requiring further investigation. To the best of our knowledge, this study is the first report of COI nucleotide sequences from Hydrotaea occulta, Muscina angustifrons, Muscina pascuorum, Ophyra leucostoma, Sarcophaga haemorrhoidalis, Sarcophaga harpax, and Phaonia aureola.

Using the developmental gene bicoid to identify species of forensically important blowflies (Diptera: calliphoridae).

Identifying species of insects used to estimate postmortem interval (PMI) is a major subject in forensic entomology. Because forensic insect specimens are morphologically uniform and are obtained at various developmental stages, DNA markers are greatly needed. To develop new autosomal DNA markers to identify species, partial genomic sequences of the bicoid (bcd) genes, containing the homeobox and its flanking sequences, from 12 blowfly species (Aldrichina grahami, Calliphora vicina, Calliphora lata, Triceratopyga calliphoroides, Chrysomya megacephala, Chrysomya pinguis, Phormia regina, Lucilia ampullacea, Lucilia caesar, Lucilia illustris, Hemipyrellia ligurriens and Lucilia sericata; Calliphoridae: Diptera) were determined and analyzed. This study first sequenced the ten blowfly species other than C. vicina and L. sericata. Based on the bcd sequences of these 12 blowfly species, a phylogenetic tree was constructed that discriminates the subfamilies of Calliphoridae (Luciliinae, Chrysomyinae, and Calliphorinae) and most blowfly species. Even partial genomic sequences of about 500 bp can distinguish most blowfly species. The short intron 2 and coding sequences downstream of the bcd homeobox in exon 3 could be utilized to develop DNA markers for forensic applications. These gene sequences are important in the evolution of insect developmental biology and are potentially useful for identifying insect species in forensic science.

Use of cytochrome c oxidase subunit i (COI) nucleotide sequences for identification of the Korean Luciliinae fly species (Diptera: Calliphoridae) in forensic investigations.

Blowflies, especially species belonging to the subfamily Luciliinae, are the first insects to lay eggs on corpses in Korea. Fast and accurate species identification has been a key task for forensic entomologists. Because conventional morphologic identification methods have many limitations with respect to forensic practice, molecular methods have been proposed to identify fly species of forensic importance. To this end, the authors amplified and sequenced the full length of the cytochrome c oxidase subunit I (COI) gene of the Luciliinae fly species collected in Korea. The results showed the COI sequences are instrumental in identifying Luciliinae fly species. However, when compared with previously reported data, considerable inconsistencies were noted. Hemipyrellia ligurriens data in this study differed significantly from two of the five pre-existing data. Two closely related species, Lucilia illustris and Lucilia caesar, showed an overlap of COI haplotypes due to four European sequences. The results suggest that more individuals from various geographic regions and additive nuclear DNA markers should be analyzed, and morphologic identification keys must be reconfirmed to overcome these inconsistencies.

Sequences of the cytochrome C oxidase subunit I (COI) gene are suitable for species identification of Korean Calliphorinae flies of forensic importance (Diptera: Calliphoridae).

Calliphorinae fly species are important indicators of the postmortem interval especially during early spring and late fall in Korea. Although nucleotide sequences of various Calliphorinae fly species are available, there has been no research on the cytochrome c oxidase subunit I (COI) nucleotide sequences of Korean Calliphorinae flies. Here, we report the full-length sequences of the COI gene of four Calliphorinae fly species collected in Korea (five individuals of Calliphora vicina, five Calliphora lata, four Triceratopyga calliphoroides and three Aldrichina grahami). Each COI gene was amplified by polymerase chain reaction and directly sequenced and the resulting nucleotide sequences were aligned and analyzed by MEGA4 software. The results indicate that COI nucleotide sequences can be used to distinguish between these four species. Our phylogenetic result coincides with recent taxonomic views on the subfamily Calliphorinae in that the genera Aldrichina and Triceratopyga are nested within the genus Calliphora.