Indentation Reverse Algorithm of Mechanical Response for Elastoplastic Coatings Based on LSTM Deep Learning.

The load-penetration depth (P-h) curves of different metallic coating materials can be determined by nanoindentation experiments, and it is a challenge to obtain stress-strain response and elastoplastic properties directly using P-h curves. These problems can be solved by means of finite element (FE) simulation along with reverse analyses and methods, which, however, typically occupy a lengthy time, in addition to the low generality of FE methodologies for different metallic materials. To eliminate the challenges that exist in conventional FE simulations, a long short-term memory (LSTM) neural network is proposed in this study and implemented to deep learn the time series of P-h curves, which is capable of mapping P-h curves to the corresponding stress-strain responses for elastoplastic materials. Prior to the operation of the neural network, 1000 sets of indentation data of metallic coating materials were generated using the FE method as the training and validating sets. Each dataset contains a set of P-h curves as well as the corresponding stress-strain curves, which are used as input data for the network and as training targets. The proposed LSTM neural networks, with various numbers of hidden layers and hidden units, are evaluated to determine the optimal hyperparameters by comparing their loss curves. Based on the analysis of the prediction results of the network, it is concluded that the relationship between the P-h curves of metallic coating materials and their stress-strain responses is well predicted, and this relationship basically coincides with the power-law equation. Furthermore, the deep learning method based on LSTM is advantageous to interpret the elastoplastic behaviors of coating materials from indentation measurement, making the predictions of stress-strain responses much more efficient than FE analysis. The established LSTM neural network exhibits the prediction accuracy up to 97%, which is proved to reliably satisfy the engineering requirements in practice.

[Clinical Features of 46 Multiple Myeloma Patients with Different Renal Pathology].

OBJECTIVE: To explore the clinical features of multiple myeloma with different renal pathology, and to evaluate its prognosis. METHODS: Clinical features and prognosis of 46 multiple myeloma patients with different renal pathology were analyzed retrospectively. According to renal pathology, the 46 patients were divided into 3 groups: cast nephropathy (24 cases), amyloidosis (15 cases) and other type (7 cases). RESULTS: By durie-Salmon staging system, 70.8% cases (17/24) in the cast nephropathy group were in Phase III, 90.9% (20/24) were in subtype B, while in amyloidosis group 53.3% (8/15) were in Phase I, 40% (6/15) were in subtype B, and in other types group, 71.4% (5/7) were in phase III, 57.1% (4/7) were in subtype B, the differences among them were statisticaily significant (P < 0.05). In cast nephropathy group, the monoclonal immunoglobulin could not be detected in 75% (18/24) cases, which was light chain type, while immunoglobulin in amyloidosis and other type groups were mainly IgG type in 73.3% (11/15) and 71.4% (5/7) respectively, the difference among them also was statistically significant (P < 0.05). The median survival time of patients in cast nephropathy group was 11 months, while that in amyloidosis and other type groups was 19 and 18 months, the differences among 3 groups were not significant (P > 0.05). CONCLUSION: In renal pathologic types, the cast nephropathy is the most common, followed by amylordosis. The multiple mycloma patients with defferent renal pathology show different clinical features. The multiple myeloma patients with renal amyloidosis have slighter clinical manifestations possibly with a better prognosis. Meanwhile, the non-amyloidosis types, especially cast nephropathy may predict a more serious manifications with poor prognosis.

PP2A and Aurora differentially modify Cdc13 to promote telomerase release from telomeres at G2/M phase.

In yeast, the initiation of telomere replication at the late S phase involves in combined actions of kinases on Cdc13, the telomere binding protein. Cdc13 recruits telomerase to telomeres through its interaction with Est1, a component of telomerase. However, how cells terminate the function of telomerase at G2/M is still elusive. Here we show that the protein phosphatase 2A (PP2A) subunit Pph22 and the yeast Aurora kinase homologue Ipl1 coordinately inhibit telomerase at G2/M by dephosphorylating and phosphorylating the telomerase recruitment domain of Cdc13, respectively. While Pph22 removes Tel1/Mec1-mediated Cdc13 phosphorylation to reduce Cdc13-Est1 interaction, Ipl1-dependent Cdc13 phosphorylation elicits dissociation of Est1-TLC1, the template RNA component of telomerase. Failure of these regulations prevents telomerase from departing telomeres, causing perturbed telomere lengthening and prolonged M phase. Together our results demonstrate that differential and additive actions of PP2A and Aurora on Cdc13 limit telomerase action by removing active telomerase from telomeres at G2/M phase.