Machine learning algorithm integrates bulk and single-cell transcriptome sequencing to reveal immune-related personalized therapy prediction features for pancreatic cancer.

Pancreatic cancer (PC) is a digestive malignancy with worse overall survival. Tumor immune environment (TIME) alters the progression and proliferation of various solid tumors. Hence, we aimed to detect the TIME-related classifier to facilitate the personalized treatment of PC. Based on the 1612 immune-related genes (IRGs), we classified patients into Immune_rich and Immune_desert subgroups via consensus clustering. Patients in distinct subtypes exhibited a difference in sensitivity to immune checkpoint blockers (ICB). Next, the immune-related signature (IRS) model was established based on 8 IRGs (SYT12, TNNT1, TRIM46, SMPD3, ANLN, AFF3, CXCL9 and RP1L1) and validated its predictive efficiency in multiple cohorts. RT-qPCR experiments demonstrated the differential expression of 8 IRGs between tumor and normal cell lines. Patients who gained lower IRS score tended to be more sensitive to chemotherapy and immunotherapy, and obtained better overall survival compared to those with higher IRS scores. Moreover, scRNA-seq analysis revealed that fibroblast and ductal cells might affect malignant tumor cells via MIF-(CD74+CD44) and SPP1-CD44 axis. Eventually, we identified eight therapeutic targets and one agent for IRS high patients. Our study screened out the specific regulation pattern of TIME in PC, and shed light on the precise treatment of PC.

Performance characterization of PCR-free whole genome sequencing for clinical diagnosis.

ABSTRACT: To evaluate the performance of polymerase chain reaction (PCR)-free whole genome sequencing (WGS) for clinical diagnosis, and thereby revealing how experimental parameters affect variant detection.Five NA12878 samples were sequenced using MGISEQ-2000. NA12878 samples underwent WGS with differing deoxyribonucleic acid (DNA) input and library preparation protocol (PCR-based vs PCR-free protocols for library preparation). The depth of coverage and genotype quality of each sample were compared. The performance of each sample was measured for sensitivity, coverage of depth and breadth of coverage of disease-related genes, and copy number variants. We also developed a systematic WGS pipeline (PCR-free) for the analysis of 11 clinical cases.In general, NA12878-2 (PCR-free WGS) showed better depth of coverage and genotype quality distribution than NA12878-1 (PCR-based WGS). With a mean depth of ∼40×, the sensitivity of homozygous and heterozygous single nucleotide polymorphisms (SNPs) of NA12878-2 showed higher sensitivity (>99.77% and >99.82%) than NA12878-1, and positive predictive value exceeded 99.98% and 99.07%. The sensitivity and positive predictive value of homozygous and heterozygous indels for NA12878-2 (PCR-free WGS) showed great improvement than NA128878-1. The breadths of coverage for disease-related genes and copy number variants are slightly better for samples with PCR-free library preparation protocol than the sample with PCR-based library preparation protocol. DNA input also influences the performance of variant detection in samples with PCR-free WGS. All the 19 previously confirmed variants in 11 clinical cases were successfully detected by our WGS pipeline (PCR free).Different experimental parameters may affect variant detection for clinical WGS. Clinical scientists should know the range of sensitivity of variants for different methods of WGS, which would be useful when interpreting and delivering clinical reports.

FF-QuantSC: accurate quantification of fetal fraction by a neural network model.

BACKGROUND: Noninvasive prenatal testing (NIPT) is one of the most commonly employed clinical measures for screening of fetal aneuploidy. Fetal Fraction (ff) has been demonstrated to be one of the key factors affecting the performance of NIPT. Accurate quantification of ff plays vital role in NIPT. METHODS: In this study, we present a new approach, the accurate Quantification of Fetal Fraction with Shallow-Coverage sequencing of maternal plasma DNA (FF-QuantSC), for the estimation of ff in NIPT. The method employs neural network model and utilizes differential genomic patterns between fetal and maternal genomes to quantify ff. RESULTS: Our results show that the predicted ff by FF-QuantSC exhibit high correlation with the Y chromosome-based method on male pregnancies, and achieves the highest accuracy compared with other ff estimation approaches. We also demonstrate that the model generates statistically similar results on both male and female pregnancies. CONCLUSION: FF-QuantSC achieves high accuracy in ff quantification. The method is suitable for application in both male and female pregnancies. Since the method does not require additional information upon NIPT routines, it can be easily incorporated into current NIPT settings without causing extra costs. We believe that FF-QuantSC shall provide valuable additions to NIPT.

Noninvasive Fetal Trisomy (NIFTY) test: an advanced noninvasive prenatal diagnosis methodology for fetal autosomal and sex chromosomal aneuploidies.

BACKGROUND: Conventional prenatal screening tests, such as maternal serum tests and ultrasound scan, have limited resolution and accuracy. METHODS: We developed an advanced noninvasive prenatal diagnosis method based on massively parallel sequencing. The Noninvasive Fetal Trisomy (NIFTY) test, combines an optimized Student's t-test with a locally weighted polynomial regression and binary hypotheses. We applied the NIFTY test to 903 pregnancies and compared the diagnostic results with those of full karyotyping. RESULTS: 16 of 16 trisomy 21, 12 of 12 trisomy 18, two of two trisomy 13, three of four 45, X, one of one XYY and two of two XXY abnormalities were correctly identified. But one false positive case of trisomy 18 and one false negative case of 45, X were observed. The test performed with 100% sensitivity and 99.9% specificity for autosomal aneuploidies and 85.7% sensitivity and 99.9% specificity for sex chromosomal aneuploidies. Compared with three previously reported z-score approaches with/without GC-bias removal and with internal control, the NIFTY test was more accurate and robust for the detection of both autosomal and sex chromosomal aneuploidies in fetuses. CONCLUSION: Our study demonstrates a powerful and reliable methodology for noninvasive prenatal diagnosis.