ALBERT

Description: Accurately detecting anomalies and timely interventions are critical for cloud application maintenance. Traditional methods for performance anomaly detection based on thresholds and rules work well for simple key performance indicator (KPI) monitoring. Unfortunately, it is difficult to find the appropriate threshold levels when there are significant differences between KPI values at different times during the day or when there are significant fluctuations stemming from different usage patterns. Therefore, anomaly detection presents a challenge for all types of temporal data, particularly when non-stationary time series have special adaptability requirements or when the nature of potential anomalies is vaguely defined or unknown. To address this limitation, we propose a novel anomaly detector (called KPI-TSAD) for time-series KPIs based on supervised deep-learning models with convolution and long short-term memory (LSTM) neural networks, and a variational auto-encoder (VAE) oversampling model was used to address the imbalanced classification problem. Compared with other related research on Yahoo’s anomaly detection benchmark datasets, KPI-TSAD exhibited better performance, with both its accuracy and F-score exceeding 0.90 on the A1benchmark and A2Benchmark datasets. Finally, KPI-TSAD continued to perform well on several KPI monitoring datasets from real production environments, with the average F-score exceeding 0.72.

Description: Abstract 4725 Chemotherapy is widely used in treatment of myeloid leukemia, the efficancy of which, however, is often hampered by the development of intrinsic and acquired multidrug resistance(MDR), the exact mechanism of which is still unclear. Overexpression and deregulated activation of protein tyrosine kinase(PTK) are frequently observed in several types of hematologic malignancies, the abnormally signal cascade transducted by which has been demonstrated to play an important role in antiapoptosis, differentiation block, enhancing autonomous proliferation, and also in inducing drug resistance. EphB4 is also a protein tyrosine kinase, a member of the largest family of receptor tyrosine kinase, which has been found with abnormally upregulated expression or activity in many types of cancer especially solid tumor types, such as mammary adenocarcinoma, colon carcinoma, ovarian cancer and prostatic carcinoma. Here the aim of our study was to examine the expression and biological role of EphB4 in drug resistance of myeloid leukemia. Using RT-PCR assay and western blot, we tested the mRNA level in 35 myeloid leukemia patients including 4 cases of acute myeloid leukemia(AML) with primary multiple drug-resistance(MDR), 3 cases of AML which have relapsed, 5 cases of newly diagnosed AML, 5 cases of AML which got (complete remission) CR at the first chemotherapy treatment, 9 cases of chronic myeloid leukemia in chronic phase(CML-CP), and 9 cases of CML in blast crisis(CML-BC). The results showed the EphB4 mRNA level was significantly upregulated in AML bearing relapse(EphB4/β-actin ratio:0.962±0.114) or MDR(EphB4/β-actin ratio: 0.993±0.047) and also in CML-BC(EphB4/β-actin ratio: 1.001±0.060) compared with newly diagnosed AML(EphB4/β-actin ratio: 0.332±0.014), AML with CR(EphB4/β-actin ratio:0.401±0.015) and CML-CP(EphB4/β-actin ratio: 0.432±0.020). Subsequently, we examined both the transcriptional and translational level of EphB4 in several myeloid leukemia cell lines including K562, HL60,U937,KG1α and an adriamycin-resistant cell line—HL60/ADM, and drug-resistant capacity of the five cell lines was also tested by CCK-8 assay. Finally EphB4 protein expression is found to be upregulated at both transcriptional and translational level in K562, KG1αand HL60/ADM, which showed stronger capacity of resistance to gradient concentrations of adriamycin(IC50 of K562:0.451±0.037ug/ml,KG1α:0.217±0.017ug/ml, HL60/ADM: 2.663±0.102ug/ml) compared with that of HL60 and U937(IC50 of HL60:0.040±0.001ug/ml, U937:0.040±0.005ug/ml) in which little or no expression of EphB4 mRNA or protein was observed. And the most noteworthy is that HL60/ADM, which shows the strongest drug resistant capability. also bears the most amount of EphB4 at both transcriptional level (EphB4 /β-actin ratio: 1.002±0.017), and translational level (EphB4 /β-actin ratio: 0.975±0.051). These data supports a role for EphB4 in inducing drug resistance and raise the possibility that therapeutic intervention to EphB4 expression or signaling might inhibit or even reverse drug resistande in meyloid leukemia. Disclosures: No relevant conflicts of interest to declare.

Description: Abstract 4735 Purpose: Monosomal karyotype (MK) refers to the presence of two or more distinct autosomal monosomies or a single monosomy associated with a structural abnormality. To analyze the prognosis of cytogenetic components of a complex karyotype or Monosomal Karyotype in acute myeloid leukemia (AML) except acute promyelocytic leukemia(APL). Patients and Methods:Cytogenetics and overall survival (OS), Disease free survival(DFS) were analyzed in 551 AML patients age 14 to 60 years in our center.Results: There ware 235 patiets with cytogenetic abnormalities, 25 cases with inv(16)(p13.1q22) or t(16;16)(p13.1;q22),and 63 cases with t(8;21); 31 cases (13.2%)met the criteria for MK and 39 cases (16.6%) had a complex karyotype without monosomies. OS was significantly inferior in patients with MK compared with those with a complex karyotype without monosomies (P0.05□GHR 3.42,95% confidence interval(95%CI),2.96-6.70). There was significant difference in regardless of whether OS or DFS between MK+ patients with MK− patients (P