Human non-histone lysine crotonylation plays crucial roles in biological activities.However,traditional wet-lab experiments are time-consuming and labor-intensive,making computational prediction methods increasingly popular in recent years.Despite the biological importance of lysine crotonylation,there are relatively few studies on human non-histone proteins.In this study,we developed an ensemble deep learning predictor named iHNHC-RsFPN by constructing a Residual Pyramid Network(RsFPN).First,three feature extraction methods were employed to encode sequence samples.Next,weak classifi-ers based on RsFPN were individually trained for different feature types.Finally,these weak classifiers were integrated to build a robust final predictor.Independent test results demonstrated that iHNHC-RsF-PN achieved outstanding performance across four key metrics:sensitivity(Sn=0.8580),specificity(Sp=0.7463),accuracy(Acc=0.7798),and Matthews correlation coefficient(MCC=0.5586).Comparative experiments revealed that iHNHC-RsFPN significantly improved prediction accuracy for hu-man non-histone crotonylation sites over existing methods.Additionally,we established a user-friendly web server(http://www.lzzzlab.top/ihnc/)that provides straightforward prediction services without complex calculations,facilitating further research for experts in related fields.

Human non-histone lysine crotonylation plays crucial roles in biological activities.However,traditional wet-lab experiments are time-consuming and labor-intensive,making computational prediction methods increasingly popular in recent years.Despite the biological importance of lysine crotonylation,there are relatively few studies on human non-histone proteins.In this study,we developed an ensemble deep learning predictor named iHNHC-RsFPN by constructing a Residual Pyramid Network(RsFPN).First,three feature extraction methods were employed to encode sequence samples.Next,weak classifi-ers based on RsFPN were individually trained for different feature types.Finally,these weak classifiers were integrated to build a robust final predictor.Independent test results demonstrated that iHNHC-RsF-PN achieved outstanding performance across four key metrics:sensitivity(Sn=0.8580),specificity(Sp=0.7463),accuracy(Acc=0.7798),and Matthews correlation coefficient(MCC=0.5586).Comparative experiments revealed that iHNHC-RsFPN significantly improved prediction accuracy for hu-man non-histone crotonylation sites over existing methods.Additionally,we established a user-friendly web server(http://www.lzzzlab.top/ihnc/)that provides straightforward prediction services without complex calculations,facilitating further research for experts in related fields.

Sepsis causes high mortality and morbidity. Static lactate concentration and early lactate clearance are cited to be a predictor for sepsis survival. This study examined the clinical utility of static lactate concentration and early lactate clearance within the first six hours of admission in Emergency Department (ED) to predict 28-day mortality rate in sepsis patients. Patients who presented with sepsis, severe sepsis or septic shock and admitted to ED of Universiti Kebangsaan Malaysia Medical Centre were recruited. Blood lactate concentrations were measured upon admission (H0), at 1st hour (H1) and 6th hour (H6), respectively. Either standard treatment of sepsis or early goal directed therapy was initiated according to sepsis severity. A follow-up report was conducted at 28 days via telephone call, e-mail or case notes. Patients were later classified into survivor and non-survivor as final outcome. Static lactate concentration appeared to be significantly higher for non-survivor as compared to the survival group at H0, H1 and H6 (p<0.05). The lactate clearance trend reflects no relationship between early lactate clearance and 28-day mortality. Static lactate concentration showed a superior predictor for sepsis over early lactate clearance. Although early lactate clearance was unable to prove its ability to predict 28-day mortality, our findings suggest it can be a useful tool to gauge the resuscitation outcome.
Sepsis