Deep Learning Improves Pancreatic Cancer Diagnosis Using RNA-Based Variants.

For optimal pancreatic cancer treatment, early and accurate diagnosis is vital. Blood-derived biomarkers and genetic predispositions can contribute to early diagnosis, but they often have limited accuracy or applicability. Here, we seek to exploit the synergy between them by combining the biomarker CA19-9 with RNA-based variants. We use deep sequencing and deep learning to improve differentiating pancreatic cancer and chronic pancreatitis. We obtained samples of nucleated cells found in peripheral blood from 268 patients suffering from resectable, non-resectable pancreatic cancer, and chronic pancreatitis. We sequenced RNA with high coverage and obtained millions of variants. The high-quality variants served as input together with CA19-9 values to deep learning models. Our model achieved an area under the curve (AUC) of 96% in differentiating resectable cancer from pancreatitis using a test cohort. Moreover, we identified variants to estimate survival in resectable cancer. We show that the blood transcriptome harbours variants, which can substantially improve noninvasive clinical diagnosis.

Development of a rapid detection method to detect tdh gene in Vibrio parahaemolyticus using 2-step ultrarapid real-time polymerase chain reaction.

Thermostable direct hemolysin encoded by tdh gene has been considered an important virulence factor in pathogenic Vibrio parahaemolyticus. Two-step ultrarapid real-time polymerase chain reaction (URRT PCR) with a microchip was devised to detect V. parahaemolyticus carrying tdh gene. This novel method has a 6-µL reaction volume and extremely reduces running time since one cycle can be completed in 10 s or less. Consequently, 35 cycles of URRT PCR was successfully able to detect up to 100 fg (18 copies) of genomic DNA from pathogenic V. parahaemolyticus carrying tdh gene in 6 min. These results indicate that this method is at present the most rapid detection method for tdh gene and pathogenic V. parahaemolyticus.

Rapid detection of virulence stx2 gene of Enterohemorrhagic Escherichia coli using two-step ultra-rapid real-time PCR.

A rapid detection method for Enterohemorrhagic Escherichia coli (EHEC), which has the virulent stx2 gene, was developed using a two-step, ultra-rapid real-time (URRT) PCR. URRT PCR was designed to detect the stx2 gene using a microchip-based, real-time PCR system, GenSpector TMC-1000, which only has a 6 microl total reaction volume with an extremely short denaturation step and combined annealing/extension step (1 and 3 s, respectively) for each cycle. Specific primers for the stx2 gene were designed to amplify a 100 bp region known for genetic stability among the various EHEC strains. Using the URRT PCR method, stx2 gene could be detected in 7 min 8 s including melting point (Tm) analysis. The detection limit for the stx2 gene for URRT-PCR was estimated to be 3 c.f.u./PCR with the amplification product having a consistent Tm of 85.2 +/- 0.4 degrees C. This method was tested for the various applications relevant to the different EHEC strains and was useful for the rapid detection of stx2-carrying EHEC strains.