Advances in AI and machine learning for predictive medicine

The field of omics, driven by advances in high-throughput sequencing, faces a data explosion. This abundance of data offers unprecedented opportunities for predictive modeling in precision medicine, but also presents formidable challenges in data analysis and interpretation. Traditional machine learning (ML) techniques have been partly successful in generating predictive models for omics analysis but exhibit limitations in handling potential relationships within the data for more accurate prediction. This review explores a revolutionary shift in predictive modeling through the application of deep learning (DL), specifically convolutional neural networks (CNNs). Using transformation methods such as DeepInsight, omics data with independent variables in tabular (table-like, including vector) form can be turned into image-like representations, enabling CNNs to capture latent features effectively. This approach not only enhances predictive power but also leverages transfer learning, reducing computational time, and improving performance. However, integrating CNNs in predictive omics data analysis is not without challenges, including issues related to model interpretability, data heterogeneity, and data size. Addressing these challenges requires a multidisciplinary approach, involving collaborations between ML experts, bioinformatics researchers, biologists, and medical doctors. This review illuminates these complexities and charts a course for future research to unlock the full predictive potential of CNNs in omics data analysis and related fields.

PepCNN deep learning tool for predicting peptide binding residues in proteins using sequence, structural, and language model features

Protein-peptide interactions play a crucial role in various cellular processes and are implicated in abnormal cellular behaviors leading to diseases such as cancer. Therefore, understanding these interactions is vital for both functional genomics and drug discovery efforts. Despite a significant increase in the availability of protein-peptide complexes, experimental methods for studying these interactions remain laborious, time-consuming, and expensive. Computational methods offer a complementary approach but often fall short in terms of prediction accuracy. To address these challenges, we introduce PepCNN, a deep learning-based prediction model that incorporates structural and sequence-based information from primary protein sequences. By utilizing a combination of half-sphere exposure, position specific scoring matrices from multiple-sequence alignment tool, and embedding from a pre-trained protein language model, PepCNN outperforms state-of-the-art methods in terms of specificity, precision, and AUC. The PepCNN software and datasets are publicly available at https://github.com/abelavit/PepCNN.git .

scDeepInsight: a supervised cell-type identification method for scRNA-seq data with deep learning

Annotation of cell-types is a critical step in the analysis of single-cell RNA sequencing (scRNA-seq) data that allows the study of heterogeneity across multiple cell populations. Currently, this is most commonly done using unsupervised clustering algorithms, which project single-cell expression data into a lower dimensional space and then cluster cells based on their distances from each other. However, as these methods do not use reference datasets, they can only achieve a rough classification of cell-types, and it is difficult to improve the recognition accuracy further. To effectively solve this issue, we propose a novel supervised annotation method, scDeepInsight. The scDeepInsight method is capable of performing manifold assignments. It is competent in executing data integration through batch normalization, performing supervised training on the reference dataset, doing outlier detection and annotating cell-types on query datasets. Moreover, it can help identify active genes or marker genes related to cell-types. The training of the scDeepInsight model is performed in a unique way. Tabular scRNA-seq data are first converted to corresponding images through the DeepInsight methodology. DeepInsight can create a trainable image transformer to convert non-image RNA data to images by comprehensively comparing interrelationships among multiple genes. Subsequently, the converted images are fed into convolutional neural networks such as EfficientNet-b3. This enables automatic feature extraction to identify the cell-types of scRNA-seq samples. We benchmarked scDeepInsight with six other mainstream cell annotation methods. The average accuracy rate of scDeepInsight reached 87.5%, which is more than 7% higher compared with the state-of-the-art methods.

Time-dependent cell-state selection identifies transiently expressed genes regulating ILC2 activation

The decision of whether cells are activated or not is controlled through dynamic intracellular molecular networks. However, the low population of cells during the transition state of activation renders the analysis of the transcriptome of this state technically challenging. To address this issue, we have developed the Time-Dependent Cell-State Selection (TDCSS) technique, which employs live-cell imaging of secretion activity to detect an index of the transition state, followed by the simultaneous recovery of indexed cells for subsequent transcriptome analysis. In this study, we used the TDCSS technique to investigate the transition state of group 2 innate lymphoid cells (ILC2s) activation, which is indexed by the onset of interleukin (IL)-13 secretion. The TDCSS approach allowed us to identify time-dependent genes, including transiently induced genes (TIGs). Our findings of IL4 and MIR155HG as TIGs have shown a regulatory function in ILC2s activation.

Topologically associating domain underlies tissue specific expression of long intergenic non-coding RNAs

Accumulating evidence indicates that long intergenic non-coding RNAs (lincRNAs) show more tissue-specific expression patterns than protein-coding genes (PCGs). However, although lincRNAs are subject to canonical transcriptional regulation like PCGs, the molecular basis for the specificity of their expression patterns remains unclear. Here, using expression data and coordinates of topologically associating domains (TADs) in human tissues, we show that lincRNA loci are significantly enriched in the more internal region of TADs compared to PCGs and that lincRNAs within TADs have higher tissue specificity than those outside TADs. Based on these, we propose an analytical framework to interpret transcriptional status using lincRNA as an indicator. We applied it to hypertrophic cardiomyopathy data and found disease-specific transcriptional regulation: ectopic expression of keratin at the TAD level and derepression of myocyte differentiation-related genes by E2F1 with down-regulation of LINC00881. Our results provide understanding of the function and regulation of lincRNAs according to genomic structure.

CNN-Pred: Prediction of single-stranded and double-stranded DNA-binding protein using convolutional neural networks

DNA-binding proteins play a vital role in biological activity including DNA replication, DNA packing, and DNA reparation. DNA-binding proteins can be classified into single-stranded DNA-binding proteins (SSBs) or double-stranded DNA-binding proteins (DSBs). Determining whether a protein is DSB or SSB helps determine the protein's function. Therefore, many studies have been conducted to accurately identify DSB and SSB in recent years. Despite all the efforts have been made so far, the DSB and SSB prediction performance remains limited. In this study, we propose a new method called CNN-Pred to accurately predict DSB and SSB. To build CNN-Pred, we first extract evolutionary-based features in the form of mono-gram and bi-gram profiles using position specific scoring matrix (PSSM). We then, use 1D-convolutional neural network (CNN) as the classifier to our extracted features. Our results demonstrate that CNN-Pred can enhance the DSB and SSB prediction accuracies by more than 4%, on the independent test compared to previous studies found in the literature. CNN-pred as a standalone tool and all its source codes are publicly available at: https://github.com/MLBC-lab/CNN-Pred.

DeepInsight-3D architecture for anti-cancer drug response prediction with deep-learning on multi-omics

Modern oncology offers a wide range of treatments and therefore choosing the best option for particular patient is very important for optimal outcome. Multi-omics profiling in combination with AI-based predictive models have great potential for streamlining these treatment decisions. However, these encouraging developments continue to be hampered by very high dimensionality of the datasets in combination with insufficiently large numbers of annotated samples. Here we proposed a novel deep learning-based method to predict patient-specific anticancer drug response from three types of multi-omics data. The proposed DeepInsight-3D approach relies on structured data-to-image conversion that then allows use of convolutional neural networks, which are particularly robust to high dimensionality of the inputs while retaining capabilities to model highly complex relationships between variables. Of particular note, we demonstrate that in this formalism additional channels of an image can be effectively used to accommodate data from different omics layers while implicitly encoding the connection between them. DeepInsight-3D was able to outperform other state-of-the-art methods applied to this task. The proposed improvements can facilitate the development of better personalized treatment strategies for different cancers in the future.

Targeted deep sequencing analyses of long QT syndrome in a Japanese population

Long QT syndrome (LQTS) is one of the most common inherited arrhythmias and multiple genes have been reported as causative. Presently, genetic diagnosis for LQTS patients is becoming widespread and contributing to implementation of therapies. However, causative genetic mutations cannot be detected in about 20% of patients. To elucidate additional genetic mutations in LQTS, we performed deep-sequencing of previously reported 15 causative and 85 candidate genes for this disorder in 556 Japanese LQTS patients. We performed in-silico filtering of the sequencing data and found 48 novel variants in 33 genes of 53 cases. These variants were predicted to be damaging to coding proteins or to alter the binding affinity of several transcription factors. Notably, we found that most of the LQTS-related variants in the RYR2 gene were in the large cytoplasmic domain of the N-terminus side. They might be useful for screening of LQTS patients who had no known genetic factors. In addition, when the mechanisms of these variants in the development of LQTS are revealed, it will be useful for early diagnosis, risk stratification, and selection of treatment.

Principal component analysis of early immune cell dynamics during pembrolizumab treatment of advanced urothelial carcinoma

Immune checkpoint inhibitors have been approved as second-line therapy for patients with advanced urothelial carcinoma (UC). However, which patients will obtain clinical benefit remains to be determined. To identify predictive biomarkers for the pembrolizumab (PEM) response early during treatment, the present study investigated 31 patients with chemotherapy-resistant recurrent or metastatic UC who received 200 mg PEM intravenously every 3 weeks. Blood was taken just before the first dose and again before the second dose, and the peripheral blood mononuclear cells of all 31 pairs of blood samples were immune phenotyped by flow cytometry. Data were assessed by principal component analysis (PCA), correlation analysis and Cox proportional hazards modeling in order to comprehensively determine the effects of PEM on peripheral mononuclear immune cells. Absolute counts of CD45RA+CD27-CCR7- terminally differentiated CD8+ T cells and KLRG1+CD57+ senescent CD8+ T cells were significantly increased after PEM administration (P=0.042 and P=0.043, respectively). Senescent and exhausted CD4⁺ and CD8⁺ T cell dynamics were strongly associated with each other. By contrast, counts of monocytic myeloid-derived suppressor cells (mMDSCs) were not associated with other immune cell phenotypes. The results of PCA and non-hierarchical clustering of patients suggested that excessive T cell senescence and differentiation early during treatment were not necessarily associated with a survival benefit. However, decreased mMDSC counts after PEM were associated with improved overall survival. In conclusion, early on-treatment peripheral T cell status was associated with response to PEM; however, it was not associated with clinical benefit. By contrast, decreased peripheral mMDSC counts did predict improved overall survival.

Abstract 5210: Tumor immune characterization identifies age-stratified biomarkers for nivolumab in patients with head and neck squamous cell carcinoma: A nationwide collaborative study in Japan

Background: Biomarkers predicting therapeutic response to immunotherapy have been widely explored via monitoring the liquid and tissue-derived components. Increasing treatment options for recurrent/metastatic head and neck squamous cell carcinoma (R/M HNSCC) mandates prediction of the therapeutic response of anti-PD-1 antibody alone as well as optimization of the treatment sequence. In view of improving biomarkers predicting the efficacy of immunotherapy for R/M HNSCC, we hypothesized that biomarkers can be personalized depending on clinicopathological backgrounds and treatment sequence.

Methods: In this study, we retrospectively included formalin-fixed paraffin-embedded (FFPE) samples, peripheral blood cell counts at treatment, clinicopathological information, and outcome data for patients with R/M HNSCC receiving nivolumab across 22 institutions in Japan (N = 100). FFPE samples were subjected to 14-marker multiplex immunohistochemistry (IHC) and image cytometry analysis (Tsujikawa T et al. Cell Reports, 2017) to quantitatively evaluate CD8+ T cells, helper T cells, regulatory T cells, B cells, natural killer (NK) cells, macrophages, dendritic cells, CD66b+ granulocytes, mast cells, programmed death ligand 1 (PD-L1) and PD-1 expression in a single slide. Intratumoral and circulating immune cell frequencies were comparatively analyzed between responders (CR, n = 14; PR, n = 39) and non-responders (SD, n = 2; PD, n = 45).

Results: Of 100 patients included, responders had significantly lower smoking and alcohol index, higher incidence of immune related adverse events, and higher PD-L1 expression in immune cells as well as PD-L1 combined positive score (CPS) than non-responders. Next, focusing on the history of prior therapy, stratified analysis revealed that the frequency of NK cells was associated with nivolumab response in patients with prior cetuximab use, but not in cetuximab-naïve status. Furthermore, stratified analysis by patient age revealed that nivolumab response was significantly associated with high CPS and lymphoid-inflamed profiles based on cell densities of nine immune cell lineages in the group aged 65 years or older, but not in the group under 65 years of age. On the contrary, the neutrophil/lymphocyte ratios (NLR) in peripheral blood counts at nivolumab treatment were significantly lower in responders (mean 4.96) than those in non-responders (mean 10.46) in the group under 65 years of age, but not in those over 65 years of age (7.41 versus 8.47).

Conclusions: Using peripheral blood data and tumor tissue profiling stratified by patient age and prior treatment might provide better predictive biomarkers in nivolumab response to HNSCC. Further preclinical and clinical studies elucidating immune mechanisms in different patient backgrounds will be warranted.

Citation Format: Takahiro Tsujikawa, Kazuchika Ohno, Sumiyo Saburi, Junichi Mitsuda, Kanako Yoshimura, Alisa Kimura, Hiroki Morimoto, Gaku Ohmura, Akihito Arai, Hiroshi Ogi, Saya Shibata, Yosuke Ariizumi, Akihisa Tasaki, Ryosuke Takahashi, Yumiko Tateishi, Hiroaki Kawabe, Sadakatsu Ikeda, Kei-ichi Morita, Tatsuhiko Tsunoda, Takumi Akashi, Morito Kurata, Issei Imoto, Yasushi Shimizu, Akihito Watanabe, Yukinori Asada, Ryuichi Hayashi, Yuki Saito, Hiroyuki Ozawa, Kiyoaki Tsukahara, Nobuhiko Oridate, Arata Horii, Takashi Maruo, Nobuhiro Hanai, Hidenori Inohara, Hiroshi Iwai, Takashi Fujii, Ken-ichi Nibu, Shigemichi Iwae, Tsutomu Ueda, Ryuji Yasumatsu, Hirohito Umeno, Muneyuki Masuda, Kyoko Itoh, Shigeru Hirano, Takahiro Asakage. Tumor immune characterization identifies age-stratified biomarkers for nivolumab in patients with head and neck squamous cell carcinoma: A nationwide collaborative study in Japan [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 5210.

Association between high immune activity and worse prognosis in uveal melanoma and low-grade glioma in TCGA transcriptomic data

BACKGROUND

Immune status in the tumor microenvironment is an important determinant of cancer progression and patient prognosis. Although a higher immune activity is often associated with a better prognosis, this trend is not absolute and differs across cancer types. We aimed to give insights into why some cancers do not show better survival despite higher immunity by assessing the relationship between different biological factors, including cytotoxicity, and patient prognosis in various cancer types using RNA-seq data collected by The Cancer Genome Atlas.

RESULTS

Results showed that a higher immune activity was associated with worse overall survival in patients with uveal melanoma and low-grade glioma, which are cancers of immune-privileged sites. In these cancers, epithelial or endothelial mesenchymal transition and inflammatory state as well as immune activation had a notable negative correlation with patient survival. Further analysis using additional single-cell data of uveal melanoma and glioma revealed that epithelial or endothelial mesenchymal transition was mainly induced in retinal pigment cells or endothelial cells that comprise the blood-retinal and blood-brain barriers, which are unique structures of the eye and central nervous system, respectively. Inflammation was mainly promoted by macrophages, and their infiltration increased significantly in response to immune activation. Furthermore, we found the expression of inflammatory chemokines, particularly CCL5, was strongly correlated with immune activity and associated with poor survival, particularly in these cancers, suggesting that these inflammatory mediators are potential molecular targets for therapeutics.

CONCLUSIONS

In uveal melanoma and low-grade glioma, inflammation from macrophages and epithelial or endothelial mesenchymal transition are particularly associated with a poor prognosis. This implies that they loosen the structures of the blood barrier and impair homeostasis and further recruit immune cells, which could result in a feedback loop of additional inflammatory effects leading to runaway conditions.

Unique characteristics of tertiary lymphoid structures in kidney clear cell carcinoma: prognostic outcome and comparison with bladder cancer

BACKGROUND

The aims of this study were (1) to clarify the impact of tertiary lymphoid structure (TLS) status on the outcome and immunogenomic profile of human clear cell renal cell carcinoma (ccRCC) and (2) to determine phenotypic differences in TLSs between different types of genitourinary cancer, that is, urinary ccRCC and bladder cancer.

METHODS

We performed a quantitative immunohistological analysis of ccRCC tissue microarrays and conducted integrated genome mutation analysis by next-generation sequencing and methylation array analysis. Since the tumor immune microenvironment of ccRCC often differs from that of other cancer types, we analyzed the phenotypic differences in TLSs between ccRCC and in-house bladder cancer specimens.

RESULTS

Varying distribution patterns of TLSs were observed throughout ccRCC tumors, revealing that the presence of TLSs was related to poor prognosis. An analysis of genomic alterations based on TLS status in ccRCC revealed that alterations in the PI3K-mTOR pathway were highly prevalent in TLS-positive tumors. DNA methylation profiling also revealed distinct differences in methylation signatures among ccRCC samples with different TLS statuses. However, the TLS characteristics of ccRCC and bladder cancer markedly differed: TLSs had the exact opposite prognostic impact on bladder cancer as on ccRCC. The maturity and spatial distribution of TLSs were significantly different between the two cancer types; TLSs were more mature with follicle-like germinal center organization and likely to be observed inside the tumor in bladder cancer. Labeling for CD8, FOXP3, PD-1, and PD-L1 showed marked differences in the diversity of the immune microenvironment surrounding TLSs. The proportions of CD8-, FOXP3-, and PD-L1-positive cells were significantly higher in TLSs in bladder cancer than in TLSs in ccRCC; rather the proportion of PD-1-positive cells was significantly higher in TLSs in ccRCC than in TLSs in bladder cancer.

CONCLUSION

The immunobiology of ccRCC is unique, and various cancerous phenomena conflict with that seen in other cancer types; therefore, comparing the TLS characteristics between ccRCC and bladder cancer may help reveal differences in the prognostic impact, maturity and spatial distribution of TLSs and in the immune environment surrounding TLSs between the two cancers.

Verification of the Usefulness of an Assessment and Risk Control Sheet that Promotes Management of Cancer Drug Therapy

Background: Proper management of adverse events is crucial for the safe and effective implementation of anticancer drug treatment. Showa University Hospital uses our interview sheet (assessment and risk control [ARC] sheet) for the accurate evaluation of adverse events. On the day of anticancer drug treatment, a nurse conducts a face-to-face interview. As a feature of the ARC sheet, by separately describing the symptoms the day before treatment and the day of treatment and sharing the information on the medical record, it is possible to clearly determine the status of adverse events. In this study, we hypothesized that the usefulness and points for improvement of the ARC sheet would be clarified by using and evaluating a patient questionnaire.

Methods: This study included 174 patients (144 at Showa University Hospital (Hatanodai Hospital) and 30 at Showa University Koto Toyosu Hospital (Toyosu Hospital) who underwent pre-examination interviews by nurses and received cancer chemotherapy at the outpatient center of Hatanodai and Toyosu Hospital. In the questionnaire survey, the ARC sheet’s content and quality, respondents’ satisfaction, structural strengths, and points for improvement were evaluated on a five-point scale.

Results: The patient questionnaire received responses from 160 participants, including the ARC sheet use group (132 people) and the non-use group (28 people). Unlike the ARC sheet non-use group, the ARC sheet use group recognized that the sheet was useful to understand the adverse events of aphthous ulcers (p = 0.017) and dysgeusia (p = 0.006). In the satisfaction survey questionnaire, there was a high sense of security in the pre-examination interviews by nurses using the ARC sheet.

Conclusions: The ARC sheet is considered an effective tool for comprehensively evaluating adverse events. Pre-examination interviews by nurses using ARC sheets accurately determined the adverse events experienced by patients with anxiety and tension due to confrontation with physicians.

Immune subtypes and neoantigen-related immune evasion in advanced colorectal cancer

Elimination of cancerous cells by the immune system is an important mechanism of protection from cancer, however, its effectiveness can be reduced owing to development of resistance and evasion. To understand the systemic immune response in advanced untreated primary colorectal cancer, we analyze immune subtypes and immune evasion via neoantigen-related mechanisms. We identify a distinctive cancer subtype characterized by immune evasion and very poor overall survival. This subtype has less clonal highly expressed neoantigens and high chromosomal instability, resulting in adaptive immune resistance mediated by the immune checkpoint molecules and neoantigen presentation disorders. We also observe that neoantigen depletion caused by immunoediting and high clonal neoantigen load are correlated with a good overall survival. Our results indicate that the status of the tumor microenvironment and neoantigen composition are promising new prognostic biomarkers with potential relevance for treatment plan decisions in advanced CRC.

Four pedigrees with aminoacyl-tRNA synthetase abnormalities

Aminoacyl tRNA synthetases (ARSs) are highly conserved enzymes that link amino acids to their cognate tRNAs. Thirty-seven ARSs are known and their deficiencies cause various genetic disorders. Variants in some ARSs are associated with the autosomal dominant inherited form of axonal neuropathy, including Charcot-Marie-Tooth (CMT) disease. Variants of genes encoding ARSs often cause disorders in an autosomal recessive fashion. The clinical features of cytosolic ARS deficiencies are more variable, including systemic features. Deficiencies of ARSs localized in the mitochondria are often associated with neurological disorders including Leigh and early-onset epileptic syndromes. Whole exome sequencing (WES) is an efficient way to identify the genes causing various symptoms in patients. We identified 4 pedigrees with novel compound heterozygous variants in ARS genes (WARS1, MARS1, AARS2, and PARS2) by WES. Some unique manifestations were noted. The number of patients with ARSs has been increasing since the application of WES. Our findings broaden the known genetic and clinical spectrum associated with ARS variants.

DeepFeature: feature selection in nonimage data using convolutional neural network

Artificial intelligence methods offer exciting new capabilities for the discovery of biological mechanisms from raw data because they are able to detect vastly more complex patterns of association that cannot be captured by classical statistical tests. Among these methods, deep neural networks are currently among the most advanced approaches and, in particular, convolutional neural networks (CNNs) have been shown to perform excellently for a variety of difficult tasks. Despite that applications of this type of networks to high-dimensional omics data and, most importantly, meaningful interpretation of the results returned from such models in a biomedical context remains an open problem. Here we present, an approach applying a CNN to nonimage data for feature selection. Our pipeline, DeepFeature, can both successfully transform omics data into a form that is optimal for fitting a CNN model and can also return sets of the most important genes used internally for computing predictions. Within the framework, the Snowfall compression algorithm is introduced to enable more elements in the fixed pixel framework, and region accumulation and element decoder is developed to find elements or genes from the class activation maps. In comparative tests for cancer type prediction task, DeepFeature simultaneously achieved superior predictive performance and better ability to discover key pathways and biological processes meaningful for this context. Capabilities offered by the proposed framework can enable the effective use of powerful deep learning methods to facilitate the discovery of causal mechanisms in high-dimensional biomedical data.

Genotype-Structure-Phenotype Correlations of Disease-Associated IGF1R Variants and Similarities to Those of INSR Variants

We previously reported genotype-phenotype correlations in 12 missense variants causing severe insulin resistance, located in the second and third fibronectin type III (FnIII) domains of the insulin receptor (INSR), containing the α-β cleavage and part of insulin-binding sites. This study aimed to identify genotype-phenotype correlations in FnIII domain variants of IGF1R, a structurally related homolog of INSR, which may be associated with growth retardation, using the recently reported crystal structures of IGF1R. A structural bioinformatics analysis of five previously reported disease-associated heterozygous missense variants and a likely benign variant in the FnIII domains of IGF1R predicted that the disease-associated variants would severely impair the hydrophobic core formation and stability of the FnIII domains or affect the α-β cleavage site, while the likely benign variant would not affect the folding of the domains. A functional analysis of these variants in CHO cells showed impaired receptor processing and autophosphorylation in cells expressing the disease-associated variants but not in those expressing the wild-type form or the likely benign variant. These results demonstrated genotype-phenotype correlations in the FnIII domain variants of IGF1R, which are presumably consistent with those of INSR and would help in the early diagnosis of patients with disease-associated IGF1R variants.

Structural basis of ethnic-specific variants of PAX4 associated with type 2 diabetes

Recently, we conducted genome-wide association studies of type 2 diabetes (T2D) in a Japanese population, which identified 20 novel T2D loci that were not associated with T2D in Europeans. Moreover, nine novel missense risk variants, such as those of PAX4, were not rare in the Japanese population, but rare in Europeans. We report in silico structural analysis of ethnic-specific variants of PAX4, which suggests the pathogenic effect of these variants.

ELF3 Overexpression as Prognostic Biomarker for Recurrence of Stage II Colorectal Cancer

BACKGROUND/AIM

Adjuvant chemotherapy for high-risk Stage II colorectal cancer (CRC) is weakly recommended; however, no consensus exists on "high-risk" definition. Prognostic biomarker identification is important for selecting patients with poor prognosis who may benefit from adjuvant chemotherapy.

MATERIALS AND METHODS

Using Microarray data analyses, ELF3 was identified as a candidate gene highly expressed in Stage II CRC with distant recurrences. ELF3 mRNA expression in 168 Stage II CRC patients was subjected to quantitative RT-PCR analysis and ELF3 protein expression in 185 patients was quantified by immunohistochemical analysis. The relationship between mRNA and protein expression levels and patient characteristics were also investigated.

RESULTS

The overall recurrence rate and relapse-free survival were significantly poorer in the ELF3 high-expression than the low-expression group at the mRNA and protein levels. High ELF3 mRNA and protein expression levels were independent poor prognostic factors.

CONCLUSION

High ELF3 expression was associated with recurrence of Stage II.

Forecasting the spread of COVID-19 using LSTM network

BACKGROUND

The novel coronavirus (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2, and within a few months, it has become a global pandemic. This forced many affected countries to take stringent measures such as complete lockdown, shutting down businesses and trade, as well as travel restrictions, which has had a tremendous economic impact. Therefore, having knowledge and foresight about how a country might be able to contain the spread of COVID-19 will be of paramount importance to the government, policy makers, business partners and entrepreneurs. To help social and administrative decision making, a model that will be able to forecast when a country might be able to contain the spread of COVID-19 is needed.

RESULTS

The results obtained using our long short-term memory (LSTM) network-based model are promising as we validate our prediction model using New Zealand's data since they have been able to contain the spread of COVID-19 and bring the daily new cases tally to zero. Our proposed forecasting model was able to correctly predict the dates within which New Zealand was able to contain the spread of COVID-19. Similarly, the proposed model has been used to forecast the dates when other countries would be able to contain the spread of COVID-19.

CONCLUSION

The forecasted dates are only a prediction based on the existing situation. However, these forecasted dates can be used to guide actions and make informed decisions that will be practically beneficial in influencing the real future. The current forecasting trend shows that more stringent actions/restrictions need to be implemented for most of the countries as the forecasting model shows they will take over three months before they can possibly contain the spread of COVID-19.

SPECTRA: a tool for enhanced brain wave signal recognition

Background

Brain wave signal recognition has gained increased attention in neuro-rehabilitation applications. This has driven the development of brain–computer interface (BCI) systems. Brain wave signals are acquired using electroencephalography (EEG) sensors, processed and decoded to identify the category to which the signal belongs. Once the signal category is determined, it can be used to control external devices. However, the success of such a system essentially relies on significant feature extraction and classification algorithms. One of the commonly used feature extraction technique for BCI systems is common spatial pattern (CSP).

Results

The performance of the proposed spatial-frequency-temporal feature extraction (SPECTRA) predictor is analysed using three public benchmark datasets. Our proposed predictor outperformed other competing methods achieving lowest average error rates of 8.55%, 17.90% and 20.26%, and highest average kappa coefficient values of 0.829, 0.643 and 0.595 for BCI Competition III dataset IVa, BCI Competition IV dataset I and BCI Competition IV dataset IIb, respectively.

Conclusions

Our proposed SPECTRA predictor effectively finds features that are more separable and shows improvement in brain wave signal recognition that can be instrumental in developing improved real-time BCI systems that are computationally efficient.

Homozygous ADCY5 mutation causes early-onset movement disorder with severe intellectual disability

BACKGROUND

Mutations of theADCY5 have been identified in patients with familial dyskinesia, early-onsetautosomal dominant chorea and dystonia, and benign hereditary chorea. Most ofthe ADCY5 mutations are de novo or transmitted in an autosomal dominantfashion. Only two pedigrees are known to show autosomal recessive inheritance.

OBJECTIVES

We report twosiblings with severe ID, dystonic movement, and growth failure with unknownetiology.

METHODS

We planned a proband-parentapproach using whole exome sequencing.

RESULTS

Homozygous mutationin exon 21 of the ADCY5 (p.R1238W) was identified in the siblings. Althoughtheir parents were heterozygous for the mutation, they were free from clinicalmanifestations.

CONCLUSIONS

Our results furtherexpand the phenotype/genotype correlations of the ADCY5-related disorders.Mutations of ADCY5 should be considered in pediatric patients with ID andinvoluntary movement.

De novo ATP1A3 variants cause polymicrogyria

Polymicrogyria is a common malformation of cortical development whose etiology remains elusive. We conducted whole-exome sequencing for 124 patients with polymicrogyria and identified de novo ATP1A3 variants in eight patients. Mutated ATP1A3 causes functional brain diseases, including alternating hemiplegia of childhood (AHC), rapid-onset dystonia parkinsonism (RDP), and cerebellar ataxia, areflexia, pes cavus, optic nerve atrophy, and sensorineural deafness (CAPOS). However, our patients showed no clinical features of AHC, RDP, or CAPOS and had a completely different phenotype: a severe form of polymicrogyria with epilepsy and developmental delay. Detected variants had different locations in ATP1A3 and different functional properties compared with AHC-, RDP-, or CAPOS-associated variants. In the developing cerebral cortex of mice, radial neuronal migration was impaired in neurons overexpressing the ATP1A3 variant of the most severe patients, suggesting that this variant is involved in cortical malformation pathogenesis. We propose a previously unidentified category of polymicrogyria associated with ATP1A3 abnormalities.

Deep Learning Approach for Automated Detection of Myopic Maculopathy and Pathologic Myopia in Fundus Images

PURPOSE

To determine whether eyes with pathologic myopia can be identified and whether each type of myopic maculopathy lesion on fundus photographs can be diagnosed by deep learning (DL) algorithms.

DESIGN

A DL algorithm was developed to recognize myopic maculopathy features and to categorize the myopic maculopathy automatically.

PARTICIPANTS

We examined 7020 fundus images from 4432 highly myopic eyes obtained from the Advanced Clinical Center for Myopia.

METHODS

Deep learning (DL) algorithms were developed to recognize the key features of myopic maculopathy with 5176 fundus images. These algorithms were also used to develop a Meta-analysis for Pathologic Myopia (META-PM) study categorizing system (CS) by adding a specific processing layer. Models and the system were evaluated by 1844 fundus image. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to determine the performance of each DL algorithm. The rate of correct predictions was used to determine the performance of the META-PM study CS.

MAIN OUTCOME MEASURES

Four trained DL models were able to recognize the lesions of myopic maculopathy accurately with high sensitivity and specificity. The META-PM study CS also showed a high accuracy and was qualified to be used in a semiautomated way during screening for myopic maculopathy in highly myopic eyes.

RESULTS

The sensitivity of the DL models was 84.44% for diffuse atrophy, 87.22% for patchy atrophy, 85.10% for macular atrophy, and 37.07% for choroidal neovascularization, and the AUC values were 0.970, 0.978, 0.982, and 0.881, respectively. The rate of total correct predictions from the META-PM study CS was 87.53%, with rates of 90.18%, 95.28%, 97.50%, and 91.14%, respectively, for each type of lesion. The META-PM study CS showed an overall rate of 92.08% in detecting pathologic myopia correctly, which was defined as having myopic maculopathy equal to or more serious than diffuse atrophy.

CONCLUSIONS

The novel DL models and system can achieve high sensitivity and specificity in identifying the different types of lesions of myopic maculopathy. These results will assist in the screening for pathologic myopia and subsequent protection of patients against low vision and blindness caused by myopic maculopathy.

Prognosis prediction model for conversion from mild cognitive impairment to Alzheimer's disease created by integrative analysis of multi-omics data

BACKGROUND

Mild cognitive impairment (MCI) is a precursor to Alzheimer's disease (AD), but not all MCI patients develop AD. Biomarkers for early detection of individuals at high risk for MCI-to-AD conversion are urgently required.

METHODS

We used blood-based microRNA expression profiles and genomic data of 197 Japanese MCI patients to construct a prognosis prediction model based on a Cox proportional hazard model. We examined the biological significance of our findings with single nucleotide polymorphism-microRNA pairs (miR-eQTLs) by focusing on the target genes of the miRNAs. We investigated functional modules from the target genes with the occurrence of hub genes though a large-scale protein-protein interaction network analysis. We further examined the expression of the genes in 610 blood samples (271 ADs, 248 MCIs, and 91 cognitively normal elderly subjects [CNs]).

RESULTS

The final prediction model, composed of 24 miR-eQTLs and three clinical factors (age, sex, and APOE4 alleles), successfully classified MCI patients into low and high risk of MCI-to-AD conversion (log-rank test P = 3.44 × 10^-4 and achieved a concordance index of 0.702 on an independent test set. Four important hub genes associated with AD pathogenesis (SHC1, FOXO1, GSK3B, and PTEN) were identified in a network-based meta-analysis of miR-eQTL target genes. RNA-seq data from 610 blood samples showed statistically significant differences in PTEN expression between MCI and AD and in SHC1 expression between CN and AD (PTEN, P = 0.023; SHC1, P = 0.049).

CONCLUSIONS

Our proposed model was demonstrated to be effective in MCI-to-AD conversion prediction. A network-based meta-analysis of miR-eQTL target genes identified important hub genes associated with AD pathogenesis. Accurate prediction of MCI-to-AD conversion would enable earlier intervention for MCI patients at high risk, potentially reducing conversion to AD.

Clinical usefulness of multigene screening with phenotype-driven bioinformatics analysis for the diagnosis of patients with monogenic diabetes or severe insulin resistance

AIMS

Monogenic diabetes is clinically heterogeneous and differs from common forms of diabetes (type 1 and 2). We aimed to investigate the clinical usefulness of a comprehensive genetic testing system, comprised of targeted next-generation sequencing (NGS) with phenotype-driven bioinformatics analysis in patients with monogenic diabetes, which uses patient genotypic and phenotypic data to prioritize potentially causal variants.

METHODS

We performed targeted NGS of 383 genes associated with monogenic diabetes or common forms of diabetes in 13 Japanese patients with suspected (n = 10) or previously diagnosed (n = 3) monogenic diabetes or severe insulin resistance. We performed in silico structural analysis and phenotype-driven bioinformatics analysis of candidate variants from NGS data.

RESULTS

Among the patients suspected having monogenic diabetes or insulin resistance, we diagnosed 3 patients as subtypes of monogenic diabetes due to disease-associated variants of INSR, LMNA, and HNF1B. Additionally, in 3 other patients, we detected rare variants with potential phenotypic effects. Notably, we identified a novel missense variant in TBC1D4 and an MC4R variant, which together may cause a mixed phenotype of severe insulin resistance.

CONCLUSIONS

This comprehensive approach could assist in the early diagnosis of patients with monogenic diabetes and facilitate the provision of tailored therapy.

Integrative immunogenomic analysis of gastric cancer dictates novel immunological classification and the functional status of tumor-infiltrating cells

Objectives

A better understanding of antitumor immunity will help predict the prognosis of gastric cancer patients and tailor the appropriate therapies in each patient. Therefore, we propose a novel immunological classification of gastric cancer.

Methods

We performed whole‐exome sequencing (WES), RNA‐Seq and flow cytometry in 29 gastric cancer patients who received surgery. The TCGA data set of 323 gastric cancer patients and RNA‐Seq data of 45 patients who received pembrolizumab (Kim et al. Nat Med 2018; 24: 1449–1458) were also analysed.

Results

Immunogram analysis of cancer–immunity interaction of gastric cancer revealed immune signatures of four main types, designated Hot1, Hot2, Intermediate and Cold. Immunologically hot tumors displayed a dysfunctional T‐cell signature, while cold tumors had an exclusion signature. Ex vivo tumor‐infiltrating lymphocyte analysis documented T‐cell dysfunction with the expression of checkpoint molecules and impaired cytokine production. The T‐cell function was more profoundly damaged in Hot1 than Hot2 tumors. Patients in Hot2 subtypes had better survival in our cohort and TCGA cohort. Although these immunological subtypes overlapped to some degree with the molecular subtypes in the TCGA, intratumoral immune responses cannot be predicted solely based on histological or molecular subtyping of gastric cancer. Molecular and immunological classifications complement each other to predict the responses to anti‐PD‐1 therapy and have the potential to be a biomarker for the treatment of gastric cancer.

Conclusion

The immunological classification of gastric cancer resulted in four subtypes. Hot tumors were further divided into two subtypes, between which the functional status of T cells was different.

Single-stranded and double-stranded DNA-binding protein prediction using HMM profiles

BACKGROUND

DNA-binding proteins perform important roles in cellular processes and are involved in many biological activities. These proteins include crucial protein-DNA binding domains and can interact with single-stranded or double-stranded DNA, and accordingly classified as single-stranded DNA-binding proteins (SSBs) or double-stranded DNA-binding proteins (DSBs). Computational prediction of SSBs and DSBs helps in annotating protein functions and understanding of protein-binding domains.

RESULTS

Performance is reported using the DNA-binding protein dataset that was recently introduced by Wang et al., [1]. The proposed method achieved a sensitivity of 0.600, specificity of 0.792, AUC of 0.758, MCC of 0.369, accuracy of 0.744, and F-measure of 0.536, on the independent test set.

CONCLUSION

The proposed method with the hidden Markov model (HMM) profiles for feature extraction, outperformed the benchmark method in the literature and achieved an overall improvement of approximately 3%. The source code and supplementary information of the proposed method is available at https://github.com/roneshsharma/Predict-DNA-binding-proteins/wiki.

Variants encoding a restricted carboxy-terminal domain of SLC12A2 cause hereditary hearing loss in humans

Hereditary hearing loss is challenging to diagnose because of the heterogeneity of the causative genes. Further, some genes involved in hereditary hearing loss have yet to be identified. Using whole-exome analysis of three families with congenital, severe-to-profound hearing loss, we identified a missense variant of SLC12A2 in five affected members of one family showing a dominant inheritance mode, along with de novo splice-site and missense variants of SLC12A2 in two sporadic cases, as promising candidates associated with hearing loss. Furthermore, we detected another de novo missense variant of SLC12A2 in a sporadic case. SLC12A2 encodes Na⁺, K⁺, 2Cl⁻ cotransporter (NKCC) 1 and plays critical roles in the homeostasis of K⁺-enriched endolymph. Slc12a2-deficient mice have congenital, profound deafness; however, no human variant of SLC12A2 has been reported as associated with hearing loss. All identified SLC12A2 variants mapped to exon 21 or its 3’-splice site. In vitro analysis indicated that the splice-site variant generates an exon 21-skipped SLC12A2 mRNA transcript expressed at much lower levels than the exon 21-included transcript in the cochlea, suggesting a tissue-specific role for the exon 21-encoded region in the carboy-terminal domain. In vitro functional analysis demonstrated that Cl⁻ influx was significantly decreased in all SLC12A2 variants studied. Immunohistochemistry revealed that SLC12A2 is located on the plasma membrane of several types of cells in the cochlea, including the strial marginal cells, which are critical for endolymph homeostasis. Overall, this study suggests that variants affecting exon 21 of the SLC12A2 transcript are responsible for hereditary hearing loss in humans.

Sounds are perceived by auditory sensory cells, owing to tissues surrounding them, including the cochlear lateral wall. Part of the cochlear lateral wall, the stria vascularis, is critical for production and maintenance of inner-ear fluid with a high potassium concentration, and for generating the positive voltage in the inner ear, important for sound perception, by stimulating secretion of potassium from marginal cells. The gene SLC12A2 encodes a protein involved in sodium, potassium, and chloride transport essential for proper function of specific cells in the stria vascularis; however, human variants of SLC12A2 have not previously been associated with hearing loss. By comprehensive genetic analysis of protein-coding sequences, we identified four candidate changes in SLC12A2 in four families with congenital, severe-to-profound hearing loss. Intriguingly, all four genetic variants were either within or at the 3’-splice site of the exon 21 which encodes a part of the carboxy terminal intracellular domain of SLC12A2. Experiments in cultured cells showed that skipping or mutation of exon 21 significantly decreased chloride influx mediated by the SLC12A2 protein. Overall, our results strongly indicate that mutations influencing exon 21 of SLC12A2 represent a novel mechanism underlying deafness in humans.

Unveiling synapse pathology in spinal bulbar muscular atrophy by genome-wide transcriptome analysis of purified motor neurons derived from disease specific iPSCs

Spinal bulbar muscular atrophy (SBMA) is an adult-onset, slowly progressive motor neuron disease caused by abnormal CAG repeat expansion in the androgen receptor (AR) gene. Although ligand (testosterone)-dependent mutant AR aggregation has been shown to play important roles in motor neuronal degeneration by the analyses of transgenic mice models and in vitro cell culture models, the underlying disease mechanisms remain to be fully elucidated because of the discrepancy between model mice and SBMA patients. Thus, novel human disease models that recapitulate SBMA patients’ pathology more accurately are required for more precise pathophysiological analysis and the development of novel therapeutics. Here, we established disease specific iPSCs from four SBMA patients, and differentiated them into spinal motor neurons. To investigate motor neuron specific pathology, we purified iPSC-derived motor neurons using flow cytometry and cell sorting based on the motor neuron specific reporter, HB9^e438::Venus, and proceeded to the genome-wide transcriptome analysis by RNA sequences. The results revealed the involvement of the pathology associated with synapses, epigenetics, and endoplasmic reticulum (ER) in SBMA. Notably, we demonstrated the involvement of the neuromuscular synapse via significant upregulation of Synaptotagmin, R-Spondin2 (RSPO2), and WNT ligands in motor neurons derived from SBMA patients, which are known to be associated with neuromuscular junction (NMJ) formation and acetylcholine receptor (AChR) clustering. These aberrant gene expression in neuromuscular synapses might represent a novel therapeutic target for SBMA.

Quantification of multicellular colonization in tumor metastasis using exome-sequencing data

Metastasis is a major cause of cancer-related mortality, and it is essential to understand how metastasis occurs in order to overcome it. One relevant question is the origin of a metastatic tumor cell population. Although the hypothesis of a single-cell origin for metastasis from a primary tumor has long been prevalent, several recent studies using mouse models have supported a multicellular origin of metastasis. Human bulk whole-exome sequencing (WES) studies also have demonstrated a multiple "clonal" origin of metastasis, with different mutational compositions. Specifically, there has not yet been strong research to determine how many founder cells colonize a metastatic tumor. To address this question, under the metastatic model of "single bottleneck followed by rapid growth," we developed a method to quantify the "founder cell population size" in a metastasis using paired WES data from primary and metachronous metastatic tumors. Simulation studies demonstrated the proposed method gives unbiased results with sufficient accuracy in the range of realistic settings. Applying the proposed method to real WES data from four colorectal cancer patients, all samples supported a multicellular origin of metastasis and the founder size was quantified, ranging from 3 to 17 cells. Such a wide-range of founder sizes estimated by the proposed method suggests that there are large variations in genetic similarity between primary and metastatic tumors in the same subjects, which may explain the observed (dis)similarity of drug responses between tumors.

Pan-cancer analysis of whole genomes

Cancer is driven by genetic change, and the advent of massively parallel sequencing has enabled systematic documentation of this variation at the whole-genome scale1-3. Here we report the integrative analysis of 2,658 whole-cancer genomes and their matching normal tissues across 38 tumour types from the Pan-Cancer Analysis of Whole Genomes (PCAWG) Consortium of the International Cancer Genome Consortium (ICGC) and The Cancer Genome Atlas (TCGA). We describe the generation of the PCAWG resource, facilitated by international data sharing using compute clouds. On average, cancer genomes contained 4-5 driver mutations when combining coding and non-coding genomic elements; however, in around 5% of cases no drivers were identified, suggesting that cancer driver discovery is not yet complete. Chromothripsis, in which many clustered structural variants arise in a single catastrophic event, is frequently an early event in tumour evolution; in acral melanoma, for example, these events precede most somatic point mutations and affect several cancer-associated genes simultaneously. Cancers with abnormal telomere maintenance often originate from tissues with low replicative activity and show several mechanisms of preventing telomere attrition to critical levels. Common and rare germline variants affect patterns of somatic mutation, including point mutations, structural variants and somatic retrotransposition. A collection of papers from the PCAWG Consortium describes non-coding mutations that drive cancer beyond those in the TERT promoter4; identifies new signatures of mutational processes that cause base substitutions, small insertions and deletions and structural variation5,6; analyses timings and patterns of tumour evolution7; describes the diverse transcriptional consequences of somatic mutation on splicing, expression levels, fusion genes and promoter activity8,9; and evaluates a range of more-specialized features of cancer genomes8,10-18.

Analyses of non-coding somatic drivers in 2,658 cancer whole genomes

The discovery of drivers of cancer has traditionally focused on protein-coding genes1-4. Here we present analyses of driver point mutations and structural variants in non-coding regions across 2,658 genomes from the Pan-Cancer Analysis of Whole Genomes (PCAWG) Consortium5 of the International Cancer Genome Consortium (ICGC) and The Cancer Genome Atlas (TCGA). For point mutations, we developed a statistically rigorous strategy for combining significance levels from multiple methods of driver discovery that overcomes the limitations of individual methods. For structural variants, we present two methods of driver discovery, and identify regions that are significantly affected by recurrent breakpoints and recurrent somatic juxtapositions. Our analyses confirm previously reported drivers6,7, raise doubts about others and identify novel candidates, including point mutations in the 5' region of TP53, in the 3' untranslated regions of NFKBIZ and TOB1, focal deletions in BRD4 and rearrangements in the loci of AKR1C genes. We show that although point mutations and structural variants that drive cancer are less frequent in non-coding genes and regulatory sequences than in protein-coding genes, additional examples of these drivers will be found as more cancer genomes become available.

Bigram-PGK: phosphoglycerylation prediction using the technique of bigram probabilities of position specific scoring matrix

BACKGROUND

The biological process known as post-translational modification (PTM) is a condition whereby proteomes are modified that affects normal cell biology, and hence the pathogenesis. A number of PTMs have been discovered in the recent years and lysine phosphoglycerylation is one of the fairly recent developments. Even with a large number of proteins being sequenced in the post-genomic era, the identification of phosphoglycerylation remains a big challenge due to factors such as cost, time consumption and inefficiency involved in the experimental efforts. To overcome this issue, computational techniques have emerged to accurately identify phosphoglycerylated lysine residues. However, the computational techniques proposed so far hold limitations to correctly predict this covalent modification.

RESULTS

We propose a new predictor in this paper called Bigram-PGK which uses evolutionary information of amino acids to try and predict phosphoglycerylated sites. The benchmark dataset which contains experimentally labelled sites is employed for this purpose and profile bigram occurrences is calculated from position specific scoring matrices of amino acids in the protein sequences. The statistical measures of this work, such as sensitivity, specificity, precision, accuracy, Mathews correlation coefficient and area under ROC curve have been reported to be 0.9642, 0.8973, 0.8253, 0.9193, 0.8330, 0.9306, respectively.

CONCLUSIONS

The proposed predictor, based on the feature of evolutionary information and support vector machine classifier, has shown great potential to effectively predict phosphoglycerylated and non-phosphoglycerylated lysine residues when compared against the existing predictors. The data and software of this work can be acquired from https://github.com/abelavit/Bigram-PGK.

A comparison of machine learning classifiers for dementia with Lewy bodies using miRNA expression data

Background

Dementia with Lewy bodies (DLB) is the second most common subtype of neurodegenerative dementia in humans following Alzheimer’s disease (AD). Present clinical diagnosis of DLB has high specificity and low sensitivity and finding potential biomarkers of prodromal DLB is still challenging. MicroRNAs (miRNAs) have recently received a lot of attention as a source of novel biomarkers.

Methods

In this study, using serum miRNA expression of 478 Japanese individuals, we investigated potential miRNA biomarkers and constructed an optimal risk prediction model based on several machine learning methods: penalized regression, random forest, support vector machine, and gradient boosting decision tree.

Results

The final risk prediction model, constructed via a gradient boosting decision tree using 180 miRNAs and two clinical features, achieved an accuracy of 0.829 on an independent test set. We further predicted candidate target genes from the miRNAs. Gene set enrichment analysis of the miRNA target genes revealed 6 functional genes included in the DHA signaling pathway associated with DLB pathology. Two of them were further supported by gene-based association studies using a large number of single nucleotide polymorphism markers (BCL2L1: P = 0.012, PIK3R2: P = 0.021).

Conclusions

Our proposed prediction model provides an effective tool for DLB classification. Also, a gene-based association test of rare variants revealed that BCL2L1 and PIK3R2 were statistically significantly associated with DLB.

OPAL: prediction of MoRF regions in intrinsically disordered protein sequences

Motivation

Intrinsically disordered proteins lack stable 3-dimensional structure and play a crucial role in performing various biological functions. Key to their biological function are the molecular recognition features (MoRFs) located within long disordered regions. Computationally identifying these MoRFs from disordered protein sequences is a challenging task. In this study, we present a new MoRF predictor, OPAL, to identify MoRFs in disordered protein sequences. OPAL utilizes two independent sources of information computed using different component predictors. The scores are processed and combined using common averaging method. The first score is computed using a component MoRF predictor which utilizes composition and sequence similarity of MoRF and non-MoRF regions to detect MoRFs. The second score is calculated using half-sphere exposure (HSE), solvent accessible surface area (ASA) and backbone angle information of the disordered protein sequence, using information from the amino acid properties of flanks surrounding the MoRFs to distinguish MoRF and non-MoRF residues.

Results

OPAL is evaluated using test sets that were previously used to evaluate MoRF predictors, MoRFpred, MoRFchibi and MoRFchibi-web. The results demonstrate that OPAL outperforms all the available MoRF predictors and is the most accurate predictor available for MoRF prediction. It is available at http://www.alok-ai-lab.com/tools/opal/.

Contact

ashwini@hgc.jp or alok.sharma@griffith.edu.au.

Supplementary information

Supplementary data are available at Bioinformatics online.

Brain wave classification using long short-term memory network based OPTICAL predictor

Brain-computer interface (BCI) systems having the ability to classify brain waves with greater accuracy are highly desirable. To this end, a number of techniques have been proposed aiming to be able to classify brain waves with high accuracy. However, the ability to classify brain waves and its implementation in real-time is still limited. In this study, we introduce a novel scheme for classifying motor imagery (MI) tasks using electroencephalography (EEG) signal that can be implemented in real-time having high classification accuracy between different MI tasks. We propose a new predictor, OPTICAL, that uses a combination of common spatial pattern (CSP) and long short-term memory (LSTM) network for obtaining improved MI EEG signal classification. A sliding window approach is proposed to obtain the time-series input from the spatially filtered data, which becomes input to the LSTM network. Moreover, instead of using LSTM directly for classification, we use regression based output of the LSTM network as one of the features for classification. On the other hand, linear discriminant analysis (LDA) is used to reduce the dimensionality of the CSP variance based features. The features in the reduced dimensional plane after performing LDA are used as input to the support vector machine (SVM) classifier together with the regression based feature obtained from the LSTM network. The regression based feature further boosts the performance of the proposed OPTICAL predictor. OPTICAL showed significant improvement in the ability to accurately classify left and right-hand MI tasks on two publically available datasets. The improvements in the average misclassification rates are 3.09% and 2.07% for BCI Competition IV Dataset I and GigaDB dataset, respectively. The Matlab code is available at https://github.com/ShiuKumar/OPTICAL .

HseSUMO: Sumoylation site prediction using half-sphere exposures of amino acids residues

Background

Post-translational modifications are viewed as an important mechanism for controlling protein function and are believed to be involved in multiple important diseases. However, their profiling using laboratory-based techniques remain challenging. Therefore, making the development of accurate computational methods to predict post-translational modifications is particularly important for making progress in this area of research.

Results

This work explores the use of four half-sphere exposure-based features for computational prediction of sumoylation sites. Unlike most of the previously proposed approaches, which focused on patterns of amino acid co-occurrence, we were able to demonstrate that protein structural based features could be sufficiently informative to achieve good predictive performance. The evaluation of our method has demonstrated high sensitivity (0.9), accuracy (0.89) and Matthew’s correlation coefficient (0.78–0.79). We have compared these results to the recently released pSumo-CD method and were able to demonstrate better performance of our method on the same evaluation dataset.

Conclusions

The proposed predictor HseSUMO uses half-sphere exposures of amino acids to predict sumoylation sites. It has shown promising results on a benchmark dataset when compared with the state-of-the-art method.

The extracted data of this study can be accessed at https://github.com/YosvanyLopez/HseSUMO.

Electronic supplementary material

The online version of this article (10.1186/s12864-018-5206-8) contains supplementary material, which is available to authorized users.

Navigating the disease landscape: knowledge representations for contextualizing molecular signatures

Large amounts of data emerging from experiments in molecular medicine are leading to the identification of molecular signatures associated with disease subtypes. The contextualization of these patterns is important for obtaining mechanistic insight into the aberrant processes associated with a disease, and this typically involves the integration of multiple heterogeneous types of data. In this review, we discuss knowledge representations that can be useful to explore the biological context of molecular signatures, in particular three main approaches, namely, pathway mapping approaches, molecular network centric approaches and approaches that represent biological statements as knowledge graphs. We discuss the utility of each of these paradigms, illustrate how they can be leveraged with selected practical examples and identify ongoing challenges for this field of research.

Risk prediction models for dementia constructed by supervised principal component analysis using miRNA expression data

Alzheimer's disease (AD) is the most common subtype of dementia, followed by Vascular Dementia (VaD), and Dementia with Lewy Bodies (DLB). Recently, microRNAs (miRNAs) have received a lot of attention as the novel biomarkers for dementia. Here, using serum miRNA expression of 1,601 Japanese individuals, we investigated potential miRNA biomarkers and constructed risk prediction models, based on a supervised principal component analysis (PCA) logistic regression method, according to the subtype of dementia. The final risk prediction model achieved a high accuracy of 0.873 on a validation cohort in AD, when using 78 miRNAs: Accuracy = 0.836 with 86 miRNAs in VaD; Accuracy = 0.825 with 110 miRNAs in DLB. To our knowledge, this is the first report applying miRNA-based risk prediction models to a dementia prospective cohort. Our study demonstrates our models to be effective in prospective disease risk prediction, and with further improvement may contribute to practical clinical use in dementia.

Discovering MoRFs by trisecting intrinsically disordered protein sequence into terminals and middle regions

Background

Molecular Recognition Features (MoRFs) are short protein regions present in intrinsically disordered protein (IDPs) sequences. MoRFs interact with structured partner protein and upon interaction, they undergo a disorder-to-order transition to perform various biological functions. Analyses of MoRFs are important towards understanding their function.

Results

Performance is reported using the MoRF dataset that has been previously used to compare the other existing MoRF predictors. The performance obtained in this study is equivalent to the benchmarked OPAL predictor, i.e., OPAL achieved AUC of 0.815, whereas the model in this study achieved AUC of 0.819 using TEST set.

Conclusion

Achieving comparable performance, the proposed method can be used as an alternative approach for MoRF prediction.

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2396-7) contains supplementary material, which is available to authorized users.

MYCN de novo gain-of-function mutation in a patient with a novel megalencephaly syndrome

BACKGROUND

In this study, we aimed to identify the gene abnormality responsible for pathogenicity in an individual with an undiagnosed neurodevelopmental disorder with megalencephaly, ventriculomegaly, hypoplastic corpus callosum, intellectual disability, polydactyly and neuroblastoma. We then explored the underlying molecular mechanism.

METHODS

Trio-based, whole-exome sequencing was performed to identify disease-causing gene mutation. Biochemical and cell biological analyses were carried out to elucidate the pathophysiological significance of the identified gene mutation.

RESULTS

We identified a heterozygous missense mutation (c.173C>T; p.Thr58Met) in the MYCN gene, at the Thr58 phosphorylation site essential for ubiquitination and subsequent MYCN degradation. The mutant MYCN (MYCN-T58M) was non-phosphorylatable at Thr58 and subsequently accumulated in cells and appeared to induce CCND1 and CCND2 expression in neuronal progenitor and stem cells in vitro. Overexpression of Mycn mimicking the p.Thr58Met mutation also promoted neuronal cell proliferation, and affected neuronal cell migration during corticogenesis in mouse embryos.

CONCLUSIONS

We identified a de novo c.173C>T mutation in MYCN which leads to stabilisation and accumulation of the MYCN protein, leading to prolonged CCND1 and CCND2 expression. This may promote neurogenesis in the developing cerebral cortex, leading to megalencephaly. While loss-of-function mutations in MYCN are known to cause Feingold syndrome, this is the first report of a germline gain-of-function mutation in MYCN identified in a patient with a novel megalencephaly syndrome similar to, but distinct from, CCND2-related megalencephaly-polymicrogyria-polydactyly-hydrocephalus syndrome. The data obtained here provide new insight into the critical role of MYCN in brain development, as well as the consequences of MYCN defects.

PhoglyStruct: Prediction of phosphoglycerylated lysine residues using structural properties of amino acids

The biological process known as post-translational modification (PTM) contributes to diversifying the proteome hence affecting many aspects of normal cell biology and pathogenesis. There have been many recently reported PTMs, but lysine phosphoglycerylation has emerged as the most recent subject of interest. Despite a large number of proteins being sequenced, the experimental method for detection of phosphoglycerylated residues remains an expensive, time-consuming and inefficient endeavor in the post-genomic era. Instead, the computational methods are being proposed for accurately predicting phosphoglycerylated lysines. Though a number of predictors are available, performance in detecting phosphoglycerylated lysine residues is still limited. In this paper, we propose a new predictor called PhoglyStruct that utilizes structural information of amino acids alongside a multilayer perceptron classifier for predicting phosphoglycerylated and non-phosphoglycerylated lysine residues. For the experiment, we located phosphoglycerylated and non-phosphoglycerylated lysines in our employed benchmark. We then derived and integrated properties such as accessible surface area, backbone torsion angles, and local structure conformations. PhoglyStruct showed significant improvement in the ability to detect phosphoglycerylated residues from non-phosphoglycerylated ones when compared to previous predictors. The sensitivity, specificity, accuracy, Mathews correlation coefficient and AUC were 0.8542, 0.7597, 0.7834, 0.5468 and 0.8077, respectively. The data and Matlab/Octave software packages are available at https://github.com/abelavit/PhoglyStruct .