AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples.

The detection of somatic DNA variants in tumor samples with low tumor purity or sequencing depth remains a daunting challenge despite numerous attempts to address this problem. In this study, we constructed a substantially extended set of actual positive variants originating from a wide range of tumor purities and sequencing depths, as well as actual negative variants derived from sequencer-specific sequencing errors. A deep learning model named AIVariant, trained on this extended dataset, outperforms previously reported methods when tested under various tumor purities and sequencing depths, especially low tumor purity and sequencing depth.

Prediction of clinically significant prostate cancer using polygenic risk models in Asians.

PURPOSE: To develop and evaluate the performance of a polygenic risk score (PRS) constructed in a Korean male population to predict clinically significant prostate cancer (csPCa). MATERIALS AND METHODS: Total 2,702 PCa samples and 7,485 controls were used to discover csPCa susceptible single nucleotide polymorphisms (SNPs). Males with biopsy-proven or post-radical prostatectomy Gleason score 7 or higher were included for analysis. After genotype imputation for quality control, logistic regression models were applied to test association and calculate effect size. Extracted candidate SNPs were further tested to compare predictive performance according to number of SNPs included in the PRS. The best-fit model was validated in an independent cohort of 311 cases and 822 controls. RESULTS: Of the 83 candidate SNPs with significant PCa association reported in previous literature, rs72725879 located in PRNCR1 showed the highest significance for PCa risk (odds ratio, 0.597; 95% confidence interval [CI], 0.555-0.641; p=4.3×10-45). Thirty-two SNPs within 26 distinct loci were further selected for PRS construction. Best performance was found with the top 29 SNPs, with AUC found to be 0.700 (95% CI, 0.667-0.734). Males with very-high PRS (above the 95th percentile) had a 4.92-fold increased risk for csPCa. CONCLUSIONS: Ethnic-specific PRS was developed and validated in Korean males to predict csPCa susceptibility using the largest csPCa sample size in Asia. PRS can be a potential biomarker to predict individual risk. Future multi-ethnic trials are required to further validate our results.

Predicting the efficiency of prime editing guide RNAs in human cells.

Prime editing enables the introduction of virtually any small-sized genetic change without requiring donor DNA or double-strand breaks. However, evaluation of prime editing efficiency requires time-consuming experiments, and the factors that affect efficiency have not been extensively investigated. In this study, we performed high-throughput evaluation of prime editor 2 (PE2) activities in human cells using 54,836 pairs of prime editing guide RNAs (pegRNAs) and their target sequences. The resulting data sets allowed us to identify factors affecting PE2 efficiency and to develop three computational models to predict pegRNA efficiency. For a given target sequence, the computational models predict efficiencies of pegRNAs with different lengths of primer binding sites and reverse transcriptase templates for edits of various types and positions. Testing the accuracy of the predictions using test data sets that were not used for training, we found Spearman's correlations between 0.47 and 0.81. Our computational models and information about factors affecting PE2 efficiency will facilitate practical application of prime editing.

Development and Validation of a Next-Generation Sequencing-Based Multigene Assay to Predict the Prognosis of Estrogen Receptor-Positive, HER2-Negative Breast Cancer.

PURPOSE: Multigene assays provide useful prognostic information regarding hormone receptor (HR)-positive breast cancer. Next-generation sequencing (NGS)-based platforms have numerous advantages including reproducibility and adaptability in local laboratories. This study aimed to develop and validate an NGS-based multigene assay to predict the distant recurrence risk. EXPERIMENTAL DESIGN: In total, 179 genes including 30 reference genes highly correlated with the 21-gene recurrence score (RS) algorithm were selected from public databases. Targeted RNA-sequencing was performed using 250 and 93 archived breast cancer samples with a known RS in the training and verification sets, respectively, to develop the algorithm and NGS-Prognostic Score (NGS-PS). The assay was validated in 413 independent samples with long-term follow-up data on distant metastasis. RESULTS: In the verification set, the NGS-PS and 21-gene RS displayed 91.4% concurrence (85/93 samples). In the validation cohort of 413 samples, area under the receiver operating characteristic curve plotted using NGS-PS values classified for distant recurrence was 0.76. The best NGS-PS cut-off value predicting distant metastasis was 20. Furthermore, 269 and 144 patients were classified as low- and high-risk patients in accordance with the cut-off. Five- and 10-year estimates of distant metastasis-free survival (DMFS) for low- versus high-risk groups were 97.0% versus 77.8% and 93.2% versus 64.4%, respectively. The age-related HR for distant recurrence without chemotherapy was 9.73 (95% CI, 3.59-26.40) and 3.19 (95% CI, 1.40-7.29) for patients aged ≤50 and >50 years, respectively. CONCLUSIONS: The newly developed and validated NGS-based multigene assay can predict the distant recurrence risk in ER-positive, HER2-negative breast cancer.

Correction: A genetic variant in SLC28A3, rs56350726, is associated with progression to castration-resistant prostate cancer in a Korean population with metastatic prostate cancer.

[This corrects the article DOI: 10.18632/oncotarget.18298.].

HiComet: a high-throughput comet analysis tool for large-scale DNA damage assessment.

BACKGROUND: DNA damage causes aging, cancer, and other serious diseases. The comet assay can detect multiple types of DNA lesions with high sensitivity, and it has been widely applied. Although comet assay platforms have improved the limited throughput and reproducibility of traditional assays in recent times, analyzing large quantities of comet data often requires a tremendous human effort. To overcome this challenge, we proposed HiComet, a computational tool that can rapidly recognize and characterize a large number of comets, using little user intervention. RESULTS: We tested HiComet with real data from 35 high-throughput comet assay experiments, with over 700 comets in total. The proposed method provided unprecedented levels of performance as an automated comet recognition tool in terms of robustness (measured by precision and recall) and throughput. CONCLUSIONS: HiComet is an automated tool for high-throughput comet-assay analysis and could significantly facilitate characterization of individual comets by accelerating its most rate-limiting step. An online implementation of HiComet is freely available at https://github.com/taehoonlee/HiComet/ .

A genetic variant in SLC28A3, rs56350726, is associated with progression to castration-resistant prostate cancer in a Korean population with metastatic prostate cancer.

Background: Genetic variation which related with progression to castration-resistant prostate cancer (CRPC) during androgen-deprivation therapy (ADT) has not been elucidated in patients with metastatic prostate cancer (mPCa). Therefore, we assessed the association between genetic variats in mPCa and progession to CRPC. Results: Analysis of exome genotypes revealed that 42 SNPs were significantly associated with mPCa. The top five polymorphisms were statistically significantly associated with metastatic disease. In addition, one of these SNPs, rs56350726, was significantly associated with time to CRPC in Kaplan-Meier analysis (Log-rank test, p = 0.011). In multivariable Cox regression, rs56350726 was strongly associated with progression to CRPC (HR = 4.172 95% CI = 1.223-14.239, p = 0.023). Materials and Methods: We assessed genetic variation among 1000 patients with PCa with or without metastasis, using 242,221 single nucleotide polymorphisms (SNPs) on the custom HumanExome BeadChip v1.0 (Illuminam Inc.). We analyzed the time to CRPC in 110 of the 1000 patients who were treated with ADT. Genetic data were analyzed using unconditional logistic regression and odds ratios calculated as estimates of relative risk of metastasis. We identified SNPs associated with metastasis and analyzed the relationship between these SNPs and time to CRPC in mPCa. Conclusions: Based on a genetic variation, the five top SNPs were observed to associate with mPCa. And one (SLC28A3, rs56350726) of five SNP was found the association with the progression to CRPC in patients with mPCa.

Genetic risk score to predict biochemical recurrence after radical prostatectomy in prostate cancer: prospective cohort study.

PURPOSE: To investigate the genetic risk score (GRS) from a large-scale exome-wide association study as a tool of prediction for biochemical recurrence (BCR) after radical prostatectomy (RP) in prostate cancer (PCa). RESULTS: The 16 SNPs were selected as significant predictors of BCR. The GRS in men experiencing BCR was -1.21, significantly higher than in non-BCR patients (-2.43) (p < 0.001). The 10-year BCR-free survival rate was 46.3% vs. 81.8% in the high-versus low GRS group, respectively (p < 0.001). The GRS was a significant factor after adjusting for other variables in Cox proportional hazard models (HR:1.630, p < 0.001). The predictive ability of the multivariate model without GRS was 84.4%, increased significantly to 88.0% when GRS was included (p = 0.0026). MATERIALS AND METHODS: Total 912 PCa patients were enrolled who had received RP and genotype analysis using Exome chip (HumanExome BeadChip). Genetic results were obtained by the methods of logistic regression analysis which measured the odds ratio (OR) to BCR. The GRS was calculated by the sum of each weighted-risk allele count multiplied by the natural logarithm of the respective ORs. Survival analyses were performed using the GRS. We compared the accuracy of separate multivariate models incorporating clinicopathological factors that either included or excluded the GRS. CONCLUSIONS: GRS had additional predictive gain of BCR after RP in PCa. The addition of personally calculated GRS significantly increased the BCR prediction rate. After validation of these results, GRS of BCR could be potential biomarker to predict clinical outcomes.

Prediction of pathologic femoral fractures in patients with lung cancer using machine learning algorithms: Comparison of computed tomography-based radiological features with clinical features versus without clinical features.

PURPOSE: The purpose of this article is to compare the predictive power of two models trained with computed tomography (CT)-based radiological features and both CT-based radiological and clinical features for pathologic femoral fractures in patients with lung cancer using machine learning algorithms. METHODS: Between January 2010 and December 2014, 315 lung cancer patients with metastasis to the femur were included. Among them, 84 patients who underwent CT scan and were followed up for more than 3 months were enrolled. We examined clinical and radiological risk factors affecting pathologic fracture through logistic regression. Predictive analysis was performed using five different supervised learning algorithms. The power of predictive model trained with CT-based radiological features was compared to those trained with both CT-based radiological and clinical features. RESULTS: In multivariate logistic regression, female sex (odds ratio = 0.25, p = 0.0126), osteolysis (odds ratio = 7.62, p = 0.0239), and absence of radiation therapy (odds ratio = 10.25, p = 0.0258) significantly increased the risk of pathologic fracture in proximal femur. The predictive model trained with both CT-based radiological and clinical features showed the highest area under the receiver operating characteristic curve (0.80 ± 0.14, p < 0.0001) through gradient boosting algorithm. CONCLUSION: We believe that machine learning algorithms may be useful in the prediction of pathologic femoral fracture, which are multifactorial problem.

Exome-based genome-wide association study and risk assessment using genetic risk score to prostate cancer in the Korean population.

PURPOSE: To investigate exome-wide genetic variants associated with prostate cancer (PCa) in Koreans and evaluate the discriminative ability by the genetic risk score (GRS). PATIENTS AND METHODS: We prospectively recruited 1,001 PCa cases from a tertiary hospital and conducted a case-control study including 2,641 healthy men (Stage I). Participants were analyzed using HumanExome BeadChip. For the external validation, additionally enrolled 514 PCa cases and 548 controls (independent cohort) were analyzed for the identified single nucleotide polymorphisms (SNPs) of Stage I (Stage II). The GRS was calculated as a non-weighted sum of the risk allele counts and investigated for accuracy of prediction of PCa. RESULTS: the mean age was 66.3 years, and the median level of prostate specific antigen (PSA) was 9.19 ng/ml in PCa cases. In Stage I, 4 loci containing 5 variants (rs1512268 on 8p21.2; rs1016343 and rs7837688 on 8q24.21; rs7501939 on 17q12, and rs2735839 on 19q13.33) were confirmed to reach exome-wide significance (p<8.3x10-7). In Stage II, the mean GRS was 4.23 ± 1.44 for the controls and 4.78 ± 1.43 for the cases. As a reference to GRS 4, GRS 6, 7 and 8 showed a statistically significant risk of PCa (OR=1.85, 2.11 and 3.34, respectively). CONCLUSIONS: The five variants were validated to associate with PCa in firstly performed exome-wide study in Koreans. The addition of individualized calculated GRS effectively enhanced the accuracy of prediction. These results need to be validated in future studies.

Development and External Validation of the Korean Prostate Cancer Risk Calculator for High-Grade Prostate Cancer: Comparison with Two Western Risk Calculators in an Asian Cohort.

PURPOSE: We developed the Korean Prostate Cancer Risk Calculator for High-Grade Prostate Cancer (KPCRC-HG) that predicts the probability of prostate cancer (PC) of Gleason score 7 or higher at the initial prostate biopsy in a Korean cohort (http://acl.snu.ac.kr/PCRC/RISC/). In addition, KPCRC-HG was validated and compared with internet-based Western risk calculators in a validation cohort. MATERIALS AND METHODS: Using a logistic regression model, KPCRC-HG was developed based on the data from 602 previously unscreened Korean men who underwent initial prostate biopsies. Using 2,313 cases in a validation cohort, KPCRC-HG was compared with the European Randomized Study of Screening for PC Risk Calculator for high-grade cancer (ERSPCRC-HG) and the Prostate Cancer Prevention Trial Risk Calculator 2.0 for high-grade cancer (PCPTRC-HG). The predictive accuracy was assessed using the area under the receiver operating characteristic curve (AUC) and calibration plots. RESULTS: PC was detected in 172 (28.6%) men, 120 (19.9%) of whom had PC of Gleason score 7 or higher. Independent predictors included prostate-specific antigen levels, digital rectal examination findings, transrectal ultrasound findings, and prostate volume. The AUC of the KPCRC-HG (0.84) was higher than that of the PCPTRC-HG (0.79, p<0.001) but not different from that of the ERSPCRC-HG (0.83) on external validation. Calibration plots also revealed better performance of KPCRC-HG and ERSPCRC-HG than that of PCPTRC-HG on external validation. At a cut-off of 5% for KPCRC-HG, 253 of the 2,313 men (11%) would not have been biopsied, and 14 of the 614 PC cases with Gleason score 7 or higher (2%) would not have been diagnosed. CONCLUSIONS: KPCRC-HG is the first web-based high-grade prostate cancer prediction model in Korea. It had higher predictive accuracy than PCPTRC-HG in a Korean population and showed similar performance with ERSPCRC-HG in a Korean population. This prediction model could help avoid unnecessary biopsy and reduce overdiagnosis and overtreatment in clinical settings.

Genome-wide detection of allelic genetic variation to predict advanced-stage prostate cancer after radical prostatectomy using an exome SNP chip.

OBJECTIVES: Genetic variations among patients with prostate cancer (PCa) who underwent radical prostatectomies were evaluated to predict advanced stage above T3 using an exome single nucleotide polymorphism (SNP) chip array. MATERIALS AND METHODS: We collected data of genetic SNP variants from 820 patients with PCa who underwent radical prostatectomy (RP) using a custom HumanExome BeadChip v1.0 (Illumina Inc.). We selected the SNPs that were most significantly associated with advanced-stage PCa (≥ T3) among the 242,186 SNPs that were genotyped, and we compared the accuracies of the associations using a multivariate logistic model that incorporated clinical factors and clinicogenetic factors. RESULTS: Among the total cohort, 360 patients (43.9%) had advanced pathologic stage (≥ T3) after RP, of whom 262 (32.0%) had extracapsular extensions, 79 (9.6%) had seminal vesicle invasions, and 10 (1.3%) had bladder neck invasions. The exome array analysis indicated that 5 SNPs (rs6804162, rs8055236, rs56335308, rs6104, and rs12618769) were significant for predicting T3 stage after RP in patients with PCa. These genetic markers were significant factors after adjusting for other clinical parameters, and they increased the accuracy of a multivariate model for predicting advanced stage of PCa (83.9%-87.2%, P = 0.0001). CONCLUSIONS: Based on a genetic array, the selected SNPs were found to be independent predictors for advanced stage after RP, and the addition of individualized genetic information effectively enhanced the accuracy of predicting advanced-stage disease. These results should be validated in another independent cohort.

Genome-wide detection of allelic genetic variation to predict biochemical recurrence after radical prostatectomy among prostate cancer patients using an exome SNP chip.

PURPOSES: Genetic variations among prostate cancer patients who underwent radical prostatectomies were evaluated to predict biochemical recurrence, and used to develop a clinical-genetic model that combines data on clinicopathological factors of prostate cancer and individual genetic variations. MATERIALS AND METHODS: We genotyped 242,186 SNPs on a custom HumanExome BeadChip v1.0 (Illuminam Inc.) from the blood DNA of 776 PCa patients who underwent radical prostatectomy. Genetic data were analyzed to calculate an odds ratio as an estimate of the relative risk of biochemical recurrence. And we compared accuracies from the multivariate model incorporating clinicopathological factors between included and excluded selected lead single nucleotide polymorphisms. Biochemical recurrence-free survival outcomes also analyzed using these genetic variations. RESULTS: Genetic array analysis indicated that eight single nucleotide polymorphisms (rs77080351, rs200944490, rs2071292, rs117237810, rs191118242, rs4965121, rs61742396, and rs6573513) were significant to predict biochemical recurrence after radical prostatectomy. When a multivariate model incorporating clinicopathological factors was devised to predict biochemical recurrence, the predictive accuracy of model was 85.1 %. By adding in two individual variations of single nucleotide polymorphisms in the multivariate model, the predictive accuracy increased to 87.7 % (P = 0.045). With three variations of single nucleotide polymorphisms, the predictive accuracy further improved to 89.0 % (P = 0.025). These genetic variations had a significantly decreased biochemical recurrence-free survival rate. CONCLUSIONS: Based on exome array, the selected single nucleotide polymorphisms were predictors for biochemical recurrence. The addition of individualized genetic information effectively enhanced the predictive accuracy of biochemical recurrence among prostate cancer patients who underwent radical prostatectomy.

A clinicogenetic model to predict lymph node invasion by use of genome-based biomarkers from exome arrays in prostate cancer patients.

PURPOSE: Genetic variations among prostate cancer (PCa) patients who underwent radical prostatectomy (RP) and pelvic lymph node dissection were evaluated to predict lymph node invasion (LNI). Exome arrays were used to develop a clinicogenetic model that combined clinical data related to PCa and individual genetic variations. MATERIALS AND METHODS: We genotyped 242,186 single-nucleotide polymorphisms (SNPs) by using a custom HumanExome BeadChip v1.0 (Illumina Inc.) from the blood DNA of 341 patients with PCa. The genetic data were analyzed to calculate an odds ratio as an estimate of the relative risk of LNI. We compared the accuracies of the multivariate logistic model incorporating clinical factors between the included and excluded selected SNPs. The Cox proportional hazard models with or without genetic factors for predicting biochemical recurrence (BCR) were analyzed. RESULTS: The genetic analysis indicated that five SNPs (rs75444444, rs8055236, rs2301277, rs9300039, and rs6908581) were significant for predicting LNI in patients with PCa. When a multivariate model incorporating clinical factors was devised to predict LNI, the predictive accuracy of the multivariate model was 80.7%. By adding genetic factors in the aforementioned multivariate model, the predictive accuracy increased to 93.2% (p=0.006). These genetic variations were significant factors for predicting BCR after adjustment for other variables and after adding the predictive gain to BCR. CONCLUSIONS: Based on the results of the exome array, the selected SNPs were predictors for LNI. The addition of individualized genetic information effectively enhanced the predictive accuracy of LNI and BCR among patients with PCa who underwent RP.

The use of exome genotyping to predict pathological Gleason score upgrade after radical prostatectomy in low-risk prostate cancer patients.

BACKGROUND: Active surveillance (AS) is a promising option for patients with low-risk prostate cancer (PCa), however current criteria could not select the patients correctly, many patients who fulfilled recent AS criteria experienced pathological Gleason score upgrade (PGU) after radical prostatectomy (RP). In this study, we aimed to develop an accurate model for predicting PGU among low-risk PCa patients by using exome genotyping. METHODS: We genotyped 242,221 single nucleotide polymorphisms (SNP)s on a custom HumanExome BeadChip v1.0 (Illuminam Inc.) in blood DNA from 257 low risk PCa patients (PSA <10 ng/ml, biopsy Gleason score (GS) ≤6 and clinical stage ≤T2a) who underwent radical prostatectomy. Genetic data were analyzed using an unconditional logistic regression to calculate an odds ratio as an estimate of relative risk of PGU, which defined pathologic GS above 7. Among them, we selected persistent SNPs after multiple testing using FDR method, and we compared accuracies from the multivariate logistic model incorporating clinical factors between included and excluded selected SNP information. RESULTS: After analysis of exome genotyping, 15 SNPs were significant to predict PGU in low risk PCa patients. Among them, one SNP--rs33999879 remained significant after multiple testing. When a multivariate model incorporating factors in Epstein definition--PSA density, biopsy GS, positive core number, tumor per core ratio and age was devised for the prediction of PGU, the predictive accuracy of the multivariate model was 78.4% (95%CI: 0.726-0.834). By addition the factor of rs33999879 in aforementioned multivariate model, the predictive accuracy was 82.9%, which was significantly increased (p = 0.0196). CONCLUSION: The rs33999879 SNP is a predictor for PGU. The addition of genetic information from the exome sequencing effectively enhanced the predictive accuracy of the multivariate model to establish suitable active surveillance criteria.

Can the prostate risk calculator based on Western population be applied to Asian population?

BACKGROUND: We developed a korean prostate cancer risk calculator (KPCRC) for predicting the probability of a positive initial prostate biopsy using clinical and laboratory data from a Korean male population (http://pcrc.korea.ac.kr). We compared its performance to prostate-specific antigen (PSA) testing and the Prostate Risk Calculator 3 (PRC 3) based on data from the Dutch part of European Randomized Study of Screening for Prostate Cancer (ERSPC), which predicts biopsy results for previously unscreened men. METHODS: Data were collected from 602 Korean men who were previously unscreened and underwent initial ten-core prostate biopsies. Multiple logistic regression analysis was performed to determine the significant predictors. Area under the receiver operating characteristic curve (AUC) and calibration plots of both calculators were evaluated. RESULTS: Prostate cancer (PCa) was detected in 172 (28.6%) men. Independent predictors of a positive biopsy included advanced age, elevated PSA levels, reduced volume of the transition zone, and abnormal digital rectal examination findings. The AUC of the KPCRC was higher than the PRC 3 and PSA alone on internal and external validation. Calibration plots of the KPCRC showed better performance than the other models on internal and external validation. Applying a cut-off of 10% of KPCRC implied that 251 of the 602 men (42%) would not have been biopsied and that 12 of the 172 PCa cases (7%) would not have been diagnosed. CONCLUSIONS: The KPCRC improves the performance of the PRC 3 and PSA testing in predicting Korean population's risk of PCa. It implies that Asian populations need their own risk calculators for PCa.

Initial biopsy outcome prediction in Korean patients-comparison of a noble web-based Korean prostate cancer risk calculator versus prostate-specific antigen testing.

We developed and validated a novel Korean prostate cancer risk calculator (KPCRC) for predicting the probability of a positive initial prostate biopsy in a Korean population. Data were collected from 602 Koreans who underwent initial prostate biopsies due to an increased level of prostate-specific antigen (PSA), a palpable nodule upon digital rectal examination (DRE), or a hypoechoic lesion upon transrectal ultrasound (TRUS). The clinical and laboratory variables were analyzed by simple and multiple logistic regression analysis. The area under the receiver operating characteristic curve (AUC) was computed to compare its performance to PSA testing alone. Prostate cancer was detected in 172 (28.6%) men. Independent predictors included age, DRE findings, PSA level, and prostate transitional zone volume. We developed the KPCRC using these variables. The AUC for the selected model was 0.91, and that of PSA testing alone was 0.83 (P < 0.001). The AUC for the selected model with an additional dataset was 0.79, and that of PSA testing alone was 0.73 (P = 0.004). The calculator is available on the website: http://pcrc.korea.ac.kr. The KPCRC improved the performance of PSA testing alone in predicting the risk of prostate cancer in a Korean population. This calculator would be a practical tool for physicians and patients.

Nonlinear preprocessing method for detecting peaks from gas chromatograms.

BACKGROUND: The problem of locating valid peaks from data corrupted by noise frequently arises while analyzing experimental data. In various biological and chemical data analysis tasks, peak detection thus constitutes a critical preprocessing step that greatly affects downstream analysis and eventual quality of experiments. Many existing techniques require the users to adjust parameters by trial and error, which is error-prone, time-consuming and often leads to incorrect analysis results. Worse, conventional approaches tend to report an excessive number of false alarms by finding fictitious peaks generated by mere noise. RESULTS: We have designed a novel peak detection method that can significantly reduce parameter sensitivity, yet providing excellent peak detection performance and negligible false alarm rates from gas chromatographic data. The key feature of our new algorithm is the successive use of peak enhancement algorithms that are deliberately designed for a gradual improvement of peak detection quality. We tested our approach with real gas chromatograms as well as intentionally contaminated spectra that contain Gaussian or speckle-type noise. CONCLUSION: Our results demonstrate that the proposed method can achieve near perfect peak detection performance while maintaining very small false alarm probabilities in case of gas chromatograms. Given the fact that biological signals appear in the form of peaks in various experimental data and that the propose method can easily be extended to such data, our approach will be a useful and robust tool that can help researchers highlight valid signals in their noisy measurements.

Exploiting binary abstractions in deciphering gene interactions.

We consider computationally reconstructing gene regulatory networks on top of the binary abstraction of gene expression state information. Unlike previous Boolean network approaches, the proposed method does not handle noisy gene expression values directly. Instead, two-valued "hidden state" information is derived from gene expression profiles using a robust statistical technique, and a gene interaction network is inferred from this hidden state information. In particular, we exploit Espresso, a well-known 2-level Boolean logic optimizer in order to determine the core network structure. The resulting gene interaction networks can be viewed as dynamic Bayesian networks, which have key advantages over more conventional Bayesian networks in terms of biological phenomena that can be represented. The authors tested the proposed method with a time-course gene expression data set from microarray experiments on anti-cancer drugs doxorubicin and paclitaxel. A gene interaction network was produced by our method, and the identified genes were validated with a public annotation database. The experimental studies we conducted suggest that the proposed method inspired by engineering systems can be a very effective tool to decipher complex gene interactions in living systems.

Prediction of regulatory modules comprising microRNAs and target genes.

MOTIVATION: MicroRNAs (miRNAs) are small endogenous RNAs that can play important regulatory roles via the RNA-interference pathway by targeting mRNAs for cleavage or translational repression. We propose a computational method to predict miRNA regulatory modules (MRMs) or groups of miRNAs and target genes that are believed to participate cooperatively in post-transcriptional gene regulation. RESULTS: We tested our method with the human genes and miRNAs, predicting 431 MRMs. We analyze a module with genes: BTG2, WT1, PPM1D, PAK7 and RAB9B, and miRNAs: miR-15a and miR-16. Review of the literature and annotation with Gene Ontology terms reveal that the roles of these genes can indeed be closely related in specific biological processes, such as gene regulation involved in breast, renal and prostate cancers. Furthermore, it has been reported that miR-15a and miR-16 are deleted together in certain types of cancer, suggesting a possible connection between these miRNAs and cancers. Given that most known functionalities of miRNAs are related to negative gene regulation, extending our approach and exploiting the insight thus obtained may provide clues to achieving practical accuracy in the reverse-engineering of gene regulatory networks. AVAILABILITY: A list of predicted modules is available from the authors upon request.