Anticancer peptides constitute one of the most promising therapeutic agents for combating common human cancers. Using wet experiments to verify whether a peptide displays anticancer characteristics is time-consuming and costly. Hence, in this study, we proposed a computational method named identify anticancer peptides via deep representation learning features (iACP-DRLF) using light gradient boosting machine algorithm and deep representation learning features. Two kinds of sequence embedding technologies were used, namely soft symmetric alignment embedding and unified representation (UniRep) embedding, both of which involved deep neural network models based on long short-term memory networks and their derived networks. The results showed that the use of deep representation learning features greatly improved the capability of the models to discriminate anticancer peptides from other peptides. Also, UMAP (uniform manifold approximation and projection for dimension reduction) and SHAP (shapley additive explanations) analysis proved that UniRep have an advantage over other features for anticancer peptide identification. The python script and pretrained models could be downloaded from https://github.com/zhibinlv/iACP-DRLF or from http://public.aibiochem.net/iACP-DRLF/.
Respiration rate is an essential vital sign that requires monitoring under various conditions, including in strong electromagnetic environments such as in magnetic resonance imaging systems. To provide an electromagnetically-immune breath-sensing system, we propose an all-fiber-optic wearable breath sensor based on a fiber-tip microcantilever. The microcantilever was fabricated on a fiber-tip by two-photon polymerization microfabrication based on femtosecond laser, so that a micro Fabry–Pérot (FP) interferometer was formed between the microcantilever and the end-face of the fiber. The cavity length of the micro FP interferometer was reduced as a result of the bending of the microcantilever induced by breath airflow. The signal of breath rate was rebuilt by detecting power variations of the FP interferometer reflected light and applying dynamic thresholds. The breath sensor achieved a high sensitivity of 0.8 nm/(m/s) by detecting the reflection spectrum upon applied flow velocities from 0.53 to 5.31 m/s. This sensor was also shown to have excellent thermal stability as its cross-sensitivity of airflow with respect to the temperature response was only 0.095 (m/s)/°C. When mounted inside a wearable surgical mask, the sensor demonstrated the capability to detect various breath patterns, including normal, fast, random, and deep breaths. We anticipate the proposed wearable breath sensor could be a useful and reliable tool for respiration rate monitoring.
18 October 2020 in Computational and Mathematical Methods in Medicine
Enhancers are noncoding fragments in DNA sequences, which play an important role in gene transcription and translation. However, due to their high free scattering and positional variability, the identification and classification of enhancers have a higher level of complexity than those of coding genes. In order to solve this problem, many computer studies have been carried out in this field, but there are still some deficiencies in these prediction models. In this paper, we use various feature extraction strategies, dimension reduction technology, and a comprehensive application of machine model and recurrent neural network model to achieve an accurate prediction of enhancer identification and classification with the accuracy of was 76.7% and 84.9%, respectively. The model proposed in this paper is superior to the previous methods in performance index or feature dimension, which provides inspiration for the prediction of enhancers by computer technology in the future.
With the accumulation of data on 6mA modification sites, an increasing number of scholars have begun to focus on the identification of 6mA sites. Despite the recognized importance of 6mA sites, methods for their identification remain lacking, with most existing methods being aimed at their identification in individual species. In the present study, we aimed to develop an identification method suitable for multiple species. Based on previous research, we propose a method for 6mA site recognition. Our experiments prove that the proposed 6mA-Pred method is effective for identifying 6mA sites in genes from taxa such as rice, Mus musculus, and human. A series of experimental results show that 6mA-Pred is an excellent method. We provide the source code used in the study, which can be obtained from http://39.100.246.211:5004/6mA_Pred/.
A high sensitivity fiber-optic sensor based on self-imaging effect in a hollow-core capillary waveguide (HCCW) is presented for sensing applications. The sensor is composed of a section of HCCW fusion spliced between single mode fibers (SMFs). The self-imaging effect in the HCCW is investigated with different fiber lengths and arc-fusion parameters. By infiltrating the hollow core with index matching liquids, the peak wavelength of the proposed device shifts towards longer wavelengths. The temperature and refractive index (RI) responses of the sensor are studied systematically. When temperature is increased from 25 °C to 75 °C, the temperature sensitivity of the device can be improved significantly with the infiltrated structure, and reaches −0.49 nm/°C, compared with that of the un-filled device, which is 9.8 pm/°C. For the RI response, the liquid-filled structure achieves sensitivity of 12,005 nm/RIU in the range between 1.448 and 1.450, slightly higher than the 11,920 nm/RIU achieved by the un-filled one. The proposed sensor exhibits the advantages of simple structure, high sensitivity and low cost, which may find potential applications in physical and chemical sensing.