Network-based prediction approach for cancer-specific driver missense mutations using a graph neural network.

BACKGROUND: In cancer genomic medicine, finding driver mutations involved in cancer development and tumor growth is crucial. Machine-learning methods to predict driver missense mutations have been developed because variants are frequently detected by genomic sequencing. However, even though the abnormalities in molecular networks are associated with cancer, many of these methods focus on individual variants and do not consider molecular networks. Here we propose a new network-based method, Net-DMPred, to predict driver missense mutations considering molecular networks. Net-DMPred consists of the graph part and the prediction part. In the graph part, molecular networks are learned by a graph neural network (GNN). The prediction part learns whether variants are driver variants using features of individual variants combined with the graph features learned in the graph part. RESULTS: Net-DMPred, which considers molecular networks, performed better than conventional methods. Furthermore, the prediction performance differed by the molecular network structure used in learning, suggesting that it is important to consider not only the local network related to cancer but also the large-scale network in living organisms. CONCLUSIONS: We propose a network-based machine learning method, Net-DMPred, for predicting cancer driver missense mutations. Our method enables us to consider the entire graph architecture representing the molecular network because it uses GNN. Net-DMPred is expected to detect driver mutations from a lot of missense mutations that are not known to be associated with cancer.

Inhibition of the bone morphogenetic protein pathway suppresses tumor growth through downregulation of epidermal growth factor receptor in MEK/ERK-dependent colorectal cancer.

The bone morphogenetic protein (BMP) pathway promotes differentiation and induces apoptosis in normal colorectal epithelial cells. However, its role in colorectal cancer (CRC) is controversial, where it can act as context-dependent tumor promoter or tumor suppressor. Here we have found that CRC cells reside in a BMP-rich environment based on curation of two publicly available RNA-sequencing databases. Suppression of BMP using a specific BMP inhibitor, LDN193189, suppresses the growth of select CRC organoids. Colorectal cancer organoids treated with LDN193189 showed a decrease in epidermal growth factor receptor, which was mediated by protein degradation induced by leucine-rich repeats and immunoglobulin-like domains protein 1 (LRIG1) expression. Among 18 molecularly characterized CRC organoids, suppression of growth by BMP inhibition correlated with induction of LRIG1 gene expression. Notably, knockdown of LRIG1 in organoids diminished the growth-suppressive effect of LDN193189. Furthermore, in CRC organoids, which are susceptible to growth suppression by LDN193189, simultaneous treatment with LDN193189 and trametinib, an FDA-approved MEK inhibitor, resulted in cooperative growth inhibition both in vitro and in vivo. Taken together, the simultaneous inhibition of BMP and MEK could be a novel treatment option in CRC cases, and evaluating in vitro growth suppression and LRIG1 induction by BMP inhibition using patient-derived organoids could offer functional biomarkers for predicting potential responders to this regimen.

Molecular dynamics simulation-guided drug sensitivity prediction for lung cancer with rare EGFR mutations.

Next generation sequencing (NGS)-based tumor profiling identified an overwhelming number of uncharacterized somatic mutations, also known as variants of unknown significance (VUS). The therapeutic significance of EGFR mutations outside mutational hotspots, consisting of >50 types, in nonsmall cell lung carcinoma (NSCLC) is largely unknown. In fact, our pan-nation screening of NSCLC without hotspot EGFR mutations (n = 3,779) revealed that the majority (>90%) of cases with rare EGFR mutations, accounting for 5.5% of the cohort subjects, did not receive EGFR-tyrosine kinase inhibitors (TKIs) as a first-line treatment. To tackle this problem, we applied a molecular dynamics simulation-based model to predict the sensitivity of rare EGFR mutants to EGFR-TKIs. The model successfully predicted the diverse in vitro and in vivo sensitivities of exon 20 insertion mutants, including a singleton, to osimertinib, a third-generation EGFR-TKI (R2 = 0.72, P = 0.0037). Additionally, our model showed a higher consistency with experimentally obtained sensitivity data than other prediction approaches, indicating its robustness in analyzing complex cancer mutations. Thus, the in silico prediction model will be a powerful tool in precision medicine for NSCLC patients carrying rare EGFR mutations in the clinical setting. Here, we propose an insight to overcome mutation diversity in lung cancer.

Toward more accurate prediction of caspase cleavage sites: a comprehensive review of current methods, tools and features.

As one of the few irreversible protein posttranslational modifications, proteolytic cleavage is involved in nearly all aspects of cellular activities, ranging from gene regulation to cell life-cycle regulation. Among the various protease-specific types of proteolytic cleavage, cleavages by casapses/granzyme B are considered as essential in the initiation and execution of programmed cell death and inflammation processes. Although a number of substrates for both types of proteolytic cleavage have been experimentally identified, the complete repertoire of caspases and granzyme B substrates remains to be fully characterized. To tackle this issue and complement experimental efforts for substrate identification, systematic bioinformatics studies of known cleavage sites provide important insights into caspase/granzyme B substrate specificity, and facilitate the discovery of novel substrates. In this article, we review and benchmark 12 state-of-the-art sequence-based bioinformatics approaches and tools for caspases/granzyme B cleavage prediction. We evaluate and compare these methods in terms of their input/output, algorithms used, prediction performance, validation methods and software availability and utility. In addition, we construct independent data sets consisting of caspases/granzyme B substrates from different species and accordingly assess the predictive power of these different predictors for the identification of cleavage sites. We find that the prediction results are highly variable among different predictors. Furthermore, we experimentally validate the predictions of a case study by performing caspase cleavage assay. We anticipate that this comprehensive review and survey analysis will provide an insightful resource for biologists and bioinformaticians who are interested in using and/or developing tools for caspase/granzyme B cleavage prediction.

Trp53 Mutation in Keratin 5 (Krt5)-Expressing Basal Cells Facilitates the Development of Basal Squamous-Like Invasive Bladder Cancer in the Chemical Carcinogenesis of Mouse Bladder.

The biological processes of urothelial carcinogenesis are not fully understood, particularly regarding the relationship between specific genetic events, cell of origin, and molecular subtypes of subsequent tumors. N-butyl-N-(4-hydroxybutyl)-nitrosamine (BBN)-induced mouse bladder cancer is widely accepted as a useful model that recapitulates the pathway of human bladder tumorigenesis from dysplasia to invasive cancer via carcinoma in situ. However, the long and variable time of tumorigenesis often hinders efficient preclinical or translational research. We hypothesized that Trp53 mutation in specific types of urothelial cells facilitates efficient development of clinically relevant bladder cancer. Using lineage tracing, we showed that Trp53 mutation in Krt5-expressing cells resulted in more efficient tumorigenesis of mouse muscle-invasive bladder cancer (MIBC) with squamous differentiation compared with Trp53 mutation in Upk2-expressing cells, or wild-type or hemizygous Trp53 in the entire urothelium. Mouse MIBC that developed at 24 weeks of BBN treatment showed morphologic and genetic similarities to the basal squamous subtypes of human MIBC, irrespective of pre-induction of Trp53 mutation or whether the cell of origin was Krt5- or Upk2-expressing cells. Our findings suggest that intermediate cells as well as basal cells also can give rise to basal-like MIBC, with pre-induction of Trp53 mutation accelerating MIBC. Thus, in BBN chemical carcinogenesis, pre-induction of Trp53 mutation in basal cells facilitates efficient modeling of the basal squamous subtype of human MIBC.

[Mitral and Aortic Valve Replacement and Tricuspid Valve Repair in a Patient with Metal Allergy].

We report a 63-year-old woman came to our hospital with exertional dyspnea, palpitations, and abdominal distention. Echocardiography showed mitral, aortic, and tricuspid valve insufficiency, for which surgery was indicated. Twenty-six years ago, during dental therapy, she was diagnosed with metal allergy. A patch test demonstrated allergic reactions to manganese, chromium, and zinc. The patient underwent mitral and aortic valve replacement with the On-X prosthetic heart valve, which is primarily made of titanium and devoid of the allergens. She also underwent tricuspid valve repair with a Contour 3D annuloplasty ring, which is made of titanium alloy. She manifested no allergic symptoms three years after surgery. This case elucidates the importance of history taking regarding metal allergy and identification of allergens by patch testing in patients undergoing cardiac surgery involving metal device implantation.

[Minimally Invasive Cardiac Surgery Following Anesthesia Induction under Percutaneous Cardiopulmonary Support for Prosthetic Valve Dysfunction and Severe Pulmonary Hypertension in a Patient with Previous Mitral Valve Replacement].

A 47-year-old woman with a history of mitral valve replacement (MVR) through a median sternotomy was admitted to our hospital due to dyspnea on exertion. Echocardiography showed bioprosthetic valve dysfunction with mitral stenosis. Right heart catheter examination revealed severe pulmonary hypertension and right ventricular dysfunction. We considered that she could not tolerate the hemodynamic changes during induction of general anesthesia without any cardiopulmonary support. Therefore, the percutaneous cardiopulmonary support was started before induction of anesthesia. To avoid the risk of injury to cardiac structures, we performed redo mitral valve replacement via right mini-horacotomy in the 4th intercostal space. Severe calcification was found in the leaflets of the prosthetic valve. She was discharged home on postoperative day 42.

Association Between Preanalytical Factors and Tumor Mutational Burden Estimated by Next-Generation Sequencing-Based Multiplex Gene Panel Assay.

BACKGROUND: Tumor mutational burden (TMB) measured via next-generation sequencing (NGS)-based gene panel is a promising biomarker for response to immune checkpoint inhibitors (ICIs) in solid tumors. However, little is known about the preanalytical factors that can affect the TMB score. MATERIALS AND METHODS: Data of 199 patients with solid tumors who underwent multiplex NGS gene panel (OncoPrime), which was commercially provided by a Clinical Laboratory Improvement Amendments-licensed laboratory and covered 0.78 megabase (Mb) of capture size relevant to the TMB calculation, were reviewed. Associations between the TMB score and preanalytical factors, including sample DNA quality, sample type, sampling site, and storage period, were analyzed. Clinical outcomes of patients with a high TMB score (≥10 mutations per megabase) who received anti-programmed cell death protein 1 antibodies (n = 22) were also analyzed. RESULTS: Low DNA library concentration (<5 nM), formalin-fixed paraffin-embedded tissue (FFPE), and the prolonged sample storage period (range, 0.9-58.1 months) correlated with a higher TMB score. After excluding low DNA library samples from the analysis, FFPE samples, but not the sample storage period, exhibited a marked correlation with a high TMB score. Of 22 patients with a high TMB score, we observed the partial response in 2 patients (9.1%). CONCLUSION: Our results indicate that the TMB score estimated via NGS-based gene panel could be affected by the DNA library concentration and sample type. These factors could potentially increase the false-positive and/or artifactual variant calls. As each gene panel has its own pipeline for variant calling, it is unknown whether these factors have a significant effect in other platforms. IMPLICATIONS FOR PRACTICE: A high tumor mutational burden score, as estimated via next-generation sequencing-based gene panel testing, should be carefully interpreted as it could be affected by the DNA library concentration and sample type.

Exome Sequencing Landscape Analysis in Ovarian Clear Cell Carcinoma Shed Light on Key Chromosomal Regions and Mutation Gene Networks.

Previous studies have reported genome-wide mutation profile analyses in ovarian clear cell carcinomas (OCCCs). This study aims to identify specific novel molecular alterations by combined analyses of somatic mutation and copy number variation. We performed whole exome sequencing of 39 OCCC samples with 16 matching blood tissue samples. Four hundred twenty-six genes had recurrent somatic mutations. Among the 39 samples, ARID1A (62%) and PIK3CA (51%) were frequently mutated, as were genes such as KRAS (10%), PPP2R1A (10%), and PTEN (5%), that have been reported in previous OCCC studies. We also detected mutations in MLL3 (15%), ARID1B (10%), and PIK3R1 (8%), which are associations not previously reported. Gene interaction analysis and functional assessment revealed that mutated genes were clustered into groups pertaining to chromatin remodeling, cell proliferation, DNA repair and cell cycle checkpointing, and cytoskeletal organization. Copy number variation analysis identified frequent amplification in chr8q (64%), chr20q (54%), and chr17q (46%) loci as well as deletion in chr19p (41%), chr13q (28%), chr9q (21%), and chr18q (21%) loci. Integration of the analyses uncovered that frequently mutated or amplified/deleted genes were involved in the KRAS/phosphatidylinositol 3-kinase (82%) and MYC/retinoblastoma (75%) pathways as well as the critical chromatin remodeling complex switch/sucrose nonfermentable (85%). The individual and integrated analyses contribute details about the OCCC genomic landscape, which could lead to enhanced diagnostics and therapeutic options.

[Artificial Intelligence in Drug Discovery].

According to the increase of data generated from analytical instruments, application of artificial intelligence(AI)technology in medical field is indispensable. In particular, practical application of AI technology is strongly required in "genomic medicine" and "genomic drug discovery" that conduct medical practice and novel drug development based on individual genomic information. In our laboratory, we have been developing a database to integrate genome data and clinical information obtained by clinical genome analysis and a computational support system for clinical interpretation of variants using AI. In addition, with the aim of creating new therapeutic targets in genomic drug discovery, we have been also working on the development of a binding affinity prediction system for mutated proteins and drugs by molecular dynamics simulation using supercomputer "Kei". We also have tackled for problems in a drug virtual screening. Our developed AI technology has successfully generated virtual compound library, and deep learning method has enabled us to predict interaction between compound and target protein.

Clinical sequencing using a next-generation sequencing-based multiplex gene assay in patients with advanced solid tumors.

Advances in next-generation sequencing (NGS) technologies have enabled physicians to test for genomic alterations in multiple cancer-related genes at once in daily clinical practice. In April 2015, we introduced clinical sequencing using an NGS-based multiplex gene assay (OncoPrime) certified by the Clinical Laboratory Improvement Amendment. This assay covers the entire coding regions of 215 genes and the rearrangement of 17 frequently rearranged genes with clinical relevance in human cancers. The principal indications for the assay were cancers of unknown primary site, rare tumors, and any solid tumors that were refractory to standard chemotherapy. A total of 85 patients underwent testing with multiplex gene assay between April 2015 and July 2016. The most common solid tumor types tested were pancreatic (n = 19; 22.4%), followed by biliary tract (n = 14; 16.5%), and tumors of unknown primary site (n = 13; 15.3%). Samples from 80 patients (94.1%) were successfully sequenced. The median turnaround time was 40 days (range, 18-70 days). Potentially actionable mutations were identified in 69 of 80 patients (86.3%) and were most commonly found in TP53 (46.3%), KRAS (23.8%), APC (18.8%), STK11 (7.5%), and ATR (7.5%). Nine patients (13.0%) received a subsequent therapy based on the NGS assay results. Implementation of clinical sequencing using an NGS-based multiplex gene assay was feasible in the clinical setting and identified potentially actionable mutations in more than 80% of patients. Current challenges are to incorporate this genomic information into better therapeutic decision making.

Prediction of protein-protein interaction strength using domain features with supervised regression.

Proteins in living organisms express various important functions by interacting with other proteins and molecules. Therefore, many efforts have been made to investigate and predict protein-protein interactions (PPIs). Analysis of strengths of PPIs is also important because such strengths are involved in functionality of proteins. In this paper, we propose several feature space mappings from protein pairs using protein domain information to predict strengths of PPIs. Moreover, we perform computational experiments employing two machine learning methods, support vector regression (SVR) and relevance vector machine (RVM), for dataset obtained from biological experiments. The prediction results showed that both SVR and RVM with our proposed features outperformed the best existing method.

Distinct but interchangeable subpopulations of colorectal cancer cells with different growth fates and drug sensitivity.

Dynamic changes in cell properties lead to intratumor heterogeneity; however, the mechanisms of nongenetic cellular plasticity remain elusive. When the fate of each cell from colorectal cancer organoids was tracked through a clonogenic growth assay, the cells showed a wide range of growth ability even within the clonal organoids, consisting of distinct subpopulations; the cells generating large spheroids and the cells generating small spheroids. The cells from the small spheroids generated only small spheroids (S-pattern), while the cells from the large spheroids generated both small and large spheroids (D-pattern), both of which were tumorigenic. Transition from the S-pattern to the D-pattern occurred by various extrinsic triggers, in which Notch signaling and Musashi-1 played a key role. The S-pattern spheroids were resistant to chemotherapy and transited to the D-pattern upon drug treatment through Notch signaling. As the transition is linked to the drug resistance, it can be a therapeutic target.

Machine learning-based prediction of relapse in rheumatoid arthritis patients using data on ultrasound examination and blood test.

Recent effective therapies enable most rheumatoid arthritis (RA) patients to achieve remission; however, some patients experience relapse. We aimed to predict relapse in RA patients through machine learning (ML) using data on ultrasound (US) examination and blood test. Overall, 210 patients with RA in remission at baseline were dichotomized into remission (n = 150) and relapse (n = 60) based on the disease activity at 2-year follow-up. Three ML classifiers [Logistic Regression, Random Forest, and extreme gradient boosting (XGBoost)] and data on 73 features (14 US examination data, 54 blood test data, and five data on patient information) at baseline were used for predicting relapse. The best performance was obtained using the XGBoost classifier (area under the receiver operator characteristic curve (AUC) = 0.747), compared with Random Forest and Logistic Regression (AUC = 0.719 and 0.701, respectively). In the XGBoost classifier prediction, ten important features, including wrist/metatarsophalangeal superb microvascular imaging scores, were selected using the recursive feature elimination method. The performance was superior to that predicted by researcher-selected features, which are conventional prognostic markers. These results suggest that ML can provide an accurate prediction of relapse in RA patients, and the use of predictive algorithms may facilitate personalized treatment options.

Clinicopathological and molecular characterization of deficient mismatch repair colorectal cancer.

Tumors demonstrating deficient mismatch repair (dMMR) account for 12%-15% of colorectal cancers (CRCs), but their characteristics have not been fully elucidated. The aim of this study was to characterize dMMR CRCs in terms of clinicopathological findings and molecular alterations. Immunostaining for mismatch repair (MMR) proteins was performed to determine MMR status, and then MLH1 promoter methylation and genetic variants of 25 genes involved in colorectal carcinogenesis were analyzed by next-generation sequencing in dMMR tumors. Coexistence of precancerous lesions was histologically evaluated to characterize the type of precursors. Immunohistochemistry revealed 34 dMMR tumors in 492 CRCs. Among dMMR CRCs, there were 25 MLH1 methylation-positive, 16 BRAF V600E variant-positive, and 7 KRAS variant-positive tumors. Positive MLH1 methylation was associated with BRAF V600E, older age, and right-side tumor location. MLH1 methylated BRAF/KRAS wild-type tumors were distinct in that all 5 tumors possessed variants in ligand-independent WNT signaling genes including APC, AXIN2, and CTNNB1. Among 10 dMMR CRCs that presented with precancerous lesions, 4 BRAF variant-positive, 1 KRAS variant-positive, and 2 BRAF/KRAS wild-type MLH1 methylated tumors coexisted with serrated lesions, whereas 1 MLH1 methylated BRAF/KRAS wild-type tumor and 2 MLH1 unmethylated tumors accompanied conventional adenomas. The present study characterized distinct subgroups of dMMR CRCs based on molecular alterations including MLH1 methylation and variants in BRAF, KRAS, and ligand-independent WNT signaling genes. The existence of distinct precursor lesions including serrated lesion and conventional adenoma further illustrates the involvement of heterogeneous carcinogenetic pathways in the development of dMMR CRCs.

Prediction using step-wise L1, L2 regularization and feature selection for small data sets with large number of features.

BACKGROUND: Machine learning methods are nowadays used for many biological prediction problems involving drugs, ligands or polypeptide segments of a protein. In order to build a prediction model a so called training data set of molecules with measured target properties is needed. For many such problems the size of the training data set is limited as measurements have to be performed in a wet lab. Furthermore, the considered problems are often complex, such that it is not clear which molecular descriptors (features) may be suitable to establish a strong correlation with the target property. In many applications all available descriptors are used. This can lead to difficult machine learning problems, when thousands of descriptors are considered and only few (e.g. below hundred) molecules are available for training. RESULTS: The CoEPrA contest provides four data sets, which are typical for biological regression problems (few molecules in the training data set and thousands of descriptors). We applied the same two-step training procedure for all four regression tasks. In the first stage, we used optimized L1 regularization to select the most relevant features. Thus, the initial set of more than 6,000 features was reduced to about 50. In the second stage, we used only the selected features from the preceding stage applying a milder L2 regularization, which generally yielded further improvement of prediction performance. Our linear model employed a soft loss function which minimizes the influence of outliers. CONCLUSIONS: The proposed two-step method showed good results on all four CoEPrA regression tasks. Thus, it may be useful for many other biological prediction problems where for training only a small number of molecules are available, which are described by thousands of descriptors.

Suppression of IgE-Independent Degranulation of Murine Connective Tissue-Type Mast Cells by Dexamethasone.

Steroidal anti-inflammatory drugs are widely used for the treatment of chronic cutaneous inflammation, such as atopic dermatitis, although it remains unknown how they modulate cutaneous mast cell functions. We investigated the effects of prolonged treatment with a synthetic glucocorticoid, dexamethasone, on murine connective tissue-type mast cells using in vitro and in vivo models. Our connective tissue-type bone marrow-derived cultured mast cell model was found to be sensitive to mast cell secretagogues, such as compound 48/80 and substance P, and higher expression levels of α subunit of a trimeric G protein, Gi1, and several Mas-related G protein-coupled receptor (Mrgpr) subtypes were observed in comparison with immature cultured mast cells. Secretagogue-induced degranulation and up-regulation of these genes was suppressed when cultured in the presence of dexamethasone. The profiles of granule constituents were drastically altered by dexamethasone. Topical application of dexamethasone down-modulated secretagogue-induced degranulation and the expression levels of several Mrgpr subtypes in cutaneous tissue. These results suggest that mast cell-mediated IgE-independent cutaneous inflammation could be suppressed by steroidal anti-inflammatory drugs through the down-regulation of G αi1 and several Mrgpr subtypes in mast cells.

MGeND: an integrated database for Japanese clinical and genomic information.

To promote the implementation of genomic medicine, we developed an integrated database, the Medical Genomics Japan Variant Database (MGeND). In its first release, MGeND provides data regarding genomic variations in Japanese individuals, collected by research groups in five disease fields. These variations consist of curated SNV/INDEL variants and susceptibility variants for diseases established by genome-wide association study analysis. Furthermore, we recorded the frequencies of HLA alleles in infectious disease populations.

Combination treatment with highly bioavailable curcumin and NQO1 inhibitor exhibits potent antitumor effects on esophageal squamous cell carcinoma.

BACKGROUND: Esophageal squamous cell carcinoma (ESCC) is one of the most intractable cancers, so the development of novel therapeutics has been required to improve patient outcomes. Curcumin, a polyphenol from Curcuma longa, exhibits various health benefits including antitumor effects, but its clinical utility is limited because of low bioavailability. Theracurmin® (THC) is a highly bioavailable curcumin dispersed with colloidal submicron particles. METHODS: We examined antitumor effects of THC on ESCC cells by cell viability assay, colony and spheroid formation assay, and xenograft models. To reveal its mechanisms, we investigated the levels of reactive oxygen species (ROS) and performed microarray gene expression analysis. According to those analyses, we focused on NQO1, which involved in the removal of ROS, and examined the effects of NQO1-knockdown or overexpression on THC treatment. Moreover, the therapeutic effect of THC and NQO1 inhibitor on ESCC patient-derived xenografts (PDX) was investigated. RESULTS: THC caused cytotoxicity in ESCC cells, and suppressed the growth of xenografted tumors more efficiently than curcumin. THC increased ROS levels and activated the NRF2-NMRAL2P-NQO1 expressions. Inhibition of NQO1 in ESCC cells by shRNA or NQO1 inhibitor resulted in an increased sensitivity of cells to THC, whereas overexpression of NQO1 antagonized it. Notably, NQO1 inhibitor significantly enhanced the antitumor effects of THC in ESCC PDX tumors. CONCLUSIONS: These findings suggest the potential usefulness of THC and its combination with NQO1 inhibitor as a therapeutic option for ESCC.

A Platform for Comprehensive Genomic Profiling in Human Cancers and Pharmacogenomics Therapy Selection.

Recent innovations in next-generation sequencing (NGS) technologies have enabled comprehensive genomic profiling of human cancers in the clinical setting. The ability to profile has launched a worldwide trend known as precision medicine, and the fusion of genomic profiling and pharmacogenomics is paving the way for precision medicine for cancer. The profiling is coupled with information about chemical therapies available to patients with specific genotypes. As a result, the chemogenomic space in play is not only the standard chemical and genome space but also the mutational genome and chemical space. In this chapter, we introduce clinical genomic profiling using an NGS-based multiplex gene assay (OncoPrime™) at Kyoto University Hospital.