The log data generated during the operation of a software system contains information about the system, and using logs for anomaly detection can detect system failures in a timely manner. Most of the existing log anomaly detection methods are specific to a particular system, have cold start problems, and are sensitive to updates in log format. In this paper, we propose a log anomaly detection method LogBD based on pre-training model and domain adaptation, which uses the pre-training model BERT to learn the semantic information of logs, and can solve the problems caused by multiple meaning words and log statement updates. An anomaly detection method LogBD based on distance to determine anomalies is constructed based on domain adaptation, using TCN networks to extract common features of different system logs and map them to the same hypersphere space. Finally, experiments are conducted on two publicly available datasets to evaluate the method, and the experimental results show that the method can better solve the log instability problem and has some improvement in the cross-system log anomaly detection effect.

Acute myeloid leukemia (AML) is a hematological malignancy that is the culmination of genetic and epigenetic alterations in the hematopoietic progenitor cells, leading to uncontrolled proliferation at the expense of normal hematopoiesis and bone marrow exhaustion. Although the outcomes for pediatric AML have improved in recent decades, at least one third of children still have relapses. Recent studies have notably highlighted the important role of dysregulated epi-genetic mechanisms in myeloid leukemogenesis. Epigenetic modifications are frequently reversible compared to genetic alterations, thus providing opportunities for targeted epigenetic therapy. In this review, we summarize the landscape of epigenetic alterations and the progress to date in epigenetic targeted therapy, and focus on the future role of epigenetic abnormalities in predicting relapse and the precision therapy in pediatric AML.

Sequential hypothesis test and change-point detection when the distribution parameters are unknown is a fundamental problem in statistics and machine learning. We show that for such problems, detection procedures based on sequential likelihood ratios with simple one-sample update estimates such as online mirror descent are nearly second-order optimal. This means that the upper bound for the algorithm performance meets the lower bound asymptotically up to a log-log factor in the false-alarm rate when it tends to zero. This is a blessing, since although the generalized likelihood ratio (GLR) statistics are optimal theoretically, but they cannot be computed recursively, and their exact computation usually requires infinite memory of historical data. We prove the nearly second-order optimality by making a connection between sequential analysis and online convex optimization and leveraging the logarithmic regret bound property of online mirror descent algorithm. Numerical and real data examples validate our theory.

Acute lymphoblastic leukemia is the most common malignancy in children and is characterized by numerous genetic and epigenetic abnormalities. Epigenetic mechanisms, which involve DNA methylations and histone modifications, result in the heritable silencing of genes without a change in their coding sequence. Emerging studies are increasing our understanding of the epigenetic role of leukemogenesis and have demonstrated the potential of DNA methylations and histone modifications as a biomarker for lineage and subtypes classification, predicting relapse, and disease progression in ALL. Epigenetic abnormalities are relatively reversible when treated with some small molecule-based agents compared to genetic alterations. In this review, we conclude the genetic and epigenetic characteristics in ALL and discuss the future role of DNA methylation and histone modifications in predicting relapse, finally focus on the individual and precision therapy targeting epigenetic alterations.

The current pneumonia epidemic could evolve into a pandemic on a global scale if not effectively contained. The COVID-19 virus possesses a 61-amino acid open reading frame resembling SARS-CoV virulence factor - ORF6 peptide. The isoleucine content is 15.9% in ORF6 of SARS-CoV versus 16.4% of that in SARS-CoV-2. Given the proton affinity in the carbonyl oxygen in isoleucine, augmented proton traffic can enhance proton-ion antiport and prompt cell swelling. Calorie restriction has been confirmed in animal studies to extend lifespan, and its underlying mechanism is not fully known. As the content of essential amino acids in the open reading frame of SARS-CoV-2 reaches 57.4%, a starch/vitamin diet served for short period of time does not give rise to essential amino acids and halts virion production, which could be adopted as prophylactic approach of many viral infections. Plant-based diet or fasting/boiled rice water can also minimize the intake of essential amino acids or all amino acids respectively. Furthermore, several proteins of SARS-CoV-2 possess high valine plus glycine content which is implicated in heart disease, justifying the aforementioned approaches.