The molecular mechanisms of peptidyl-prolyl cis/trans isomerase Pin1 and its relevance to kidney disease.

Pin1 is a member of the peptidyl-prolyl cis/trans isomerase subfamily and is widely expressed in various cell types and tissues. Alterations in Pin1 expression levels play pivotal roles in both physiological processes and multiple pathological conditions, especially in the onset and progression of kidney diseases. Herein, we present an overview of the role of Pin1 in the regulation of fibrosis, oxidative stress, and autophagy. It plays a significant role in various kidney diseases including Renal I/R injury, chronic kidney disease with secondary hyperparathyroidism, diabetic nephropathy, renal fibrosis, and renal cell carcinoma. The representative therapeutic agent Juglone has emerged as a potential treatment for inhibiting Pin1 activity and mitigating kidney disease. Understanding the role of Pin1 in kidney diseases is expected to provide new insights into innovative therapeutic interventions and strategies. Consequently, this review delves into the molecular mechanisms of Pin1 and its relevance in kidney disease, paving the way for novel therapeutic approaches.

A tunable ultra-broadband and ultra-high sensitivity far-infrared metamaterial absorber based on VO2 and graphene.

We proposed a far-infrared tunable metamaterial absorber using vanadium dioxide (VO2) and graphene as controlling materials. The properties of the absorber are investigated theoretically using the finite-difference time-domain (FDTD) technique. It was found that when the Fermi energy level of graphene is fixed at zero, VO2 is in the insulated state, and the metasurface exhibits far-infrared broadband absorption performance, with absorptance exceeding 90% in the wavelength range of 12.6 µm to 23.2 µm. In addition, by elevating the Fermi energy level of graphene, the absorption bandwidth of the device is expanded continuously. When the VO2 is in the metallic state, the device can flexibly transform into a far-infrared narrowband absorber. The device also has the advantage of being insensitive to changes in polarization and incident angle. The origin of the absorption and the tuning principle of the device were analyzed and verified successfully by using an equivalent circuit model (ECM). Besides, we also studied the refraction index sensing characteristics of the absorber. Surprisingly, the absorber exhibits excellent sensing characteristics, and its sensitivity (S) reaches 14.108 µm per RIU and the figure of merit (FOM) is 6.13 per RIU.

Cope with copper: From molecular mechanisms of cuproptosis to copper-related kidney diseases.

Cuproptosis has recently been identified as a novel regulatory mechanism of cell death. It is characterized by the accumulation of copper in mitochondria and its binding to acylated proteins. These characteristics lead to the downregulation of iron-sulfur cluster proteins and protein toxicity stress, ultimately resulting in cell death. Cuproptosis is distinct from other types of cell death, including necrosis, apoptosis, ferroptosis, and pyroptosis. Cu induces oxidative stress damage, protein acylation, and the oligomerization of acylated TCA cycle proteins. These processes lead to the downregulation of iron-sulfur cluster proteins and protein toxicity stress, disrupting cellular Cu homeostasis, and causing cell death. Cuproptosis plays a significant role in the development and progression of various kidney diseases such as acute kidney injury, chronic kidney disease, diabetic nephropathy, kidney transplantation, and kidney stones. On the one hand, inducers of cuproptosis, such as disulfiram (DSF), chloroquinolone, and elesclomol facilitate cuproptosis by promoting cell oxidative stress. In contrast, inhibitors of Cu chelators, such as tetraethylenepentamine and tetrathiomolybdate, relieve these diseases by inhibiting apoptosis. To summarize, cuproptosis plays a significant role in the pathogenesis of kidney disease. This review comprehensively discusses the molecular mechanisms underlying cuproptosis and its significance in kidney diseases.

The Burden of Cancer and Pre-cancerous Conditions Among Transgender Individuals in a Large Healthcare Network.

The current study aimed to examine the prevalence of and risk factors for cancer and pre-cancerous conditions, comparing transgender and cisgender individuals, using 2012-2023 electronic health record data from a large healthcare system. We identified 2,745 transgender individuals using a previously validated computable phenotype and 54,900 matched cisgender individuals. We calculated the prevalence of cancer and pre-cancer related to human papillomavirus (HPV), human immunodeficiency virus (HIV), tobacco, alcohol, lung, breast, colorectum, and built multivariable logistic models to examine the association between gender identity and the presence of cancer or pre-cancer. Results indicated similar odds of developing cancer across gender identities, but transgender individuals exhibited significantly higher risks for pre-cancerous conditions, including alcohol-related, breast, and colorectal pre-cancers compared to cisgender women, and HPV-related, tobacco-related, alcohol-related, and colorectal pre-cancers compared to cisgender men. These findings underscore the need for tailored interventions and policies addressing cancer health disparities affecting the transgender population.

GluN2B-containing NMDA receptor attenuated neuronal apoptosis in the mouse model of HIBD through inhibiting endoplasmic reticulum stress-activated PERK/eIF2α signaling pathway.

Introduction: Neonatal hypoxic-ischemic brain damage (HIBD) refers to brain damage in newborns caused by hypoxia and reduced or even stopped cerebral blood flow during the perinatal period. Currently, there are no targeted treatments for neonatal ischemic hypoxic brain damage, primarily due to the incomplete understanding of its pathophysiological mechanisms. Especially, the role of NMDA receptors is less studied in HIBD. Therefore, this study explored the molecular mechanism of endogenous protection mediated by GluN2B-NMDAR in HIBD. Method: Hypoxic ischemia was induced in mice aged 9-11 days. The brain damage was examined by Nissl staining and HE staining, while neuronal apoptosis was examined by Hoechst staining and TTC staining. And cognitive deficiency of mice was examined by various behavior tests including Barnes Maze, Three Chamber Social Interaction Test and Elevated Plus Maze. The activation of ER stress signaling pathways were evaluated by Western blot. Results: We found that after HIBD induction, the activation of GluN2B-NMDAR attenuated neuronal apoptosis and brain damage. Meanwhile, the ER stress PERK/eIF2α signaling pathway was activated in a time-dependent manner after HIBE. Furthermore, after selective inhibiting GluN2B-NMDAR in HIBD mice with ifenprodil, the PERK/eIF2α signaling pathway remains continuously activated, leading to neuronal apoptosis, morphological brain damage. and aggravating deficits in spatial memory, cognition, and social abilities in adult mice. Discussion: The results of this study indicate that, unlike its role in adult brain damage, GluN2B in early development plays a neuroprotective role in HIBD by inhibiting excessive activation of the PERK/eIF2α signaling pathway. This study provides theoretical support for the clinical development of targeted drugs or treatment methods for HIBD.

Proximity-Guaranteed DNA Machine for Accurate Identification of Breast Cancer Extracellular Vesicles.

Breast cancer is one of the most diagnosed cancers worldwide. Precise diagnosis and subtyping have important significance for targeted therapy and prognosis prediction of breast cancer. Herein, we design a proximity-guaranteed DNA machine for accurate identification of breast cancer extracellular vesicles (EVs), which is beneficial to explore the subtype features of breast cancer. In our design, two proximity probes are located close on the same EV through specific recognition of coexisting surface biomarkers, thus being ligated with the help of click chemistry. Then, the ligated product initiates the operation of a DNA machine involving catalytic hairpin assembly and clusters of regularly interspaced short palindromic repeats (CRISPR)-Cas12a-mediated trans-cleavage, which finally generates a significant response that enables the identification of EVs expressing both biomarkers. Principle-of-proof studies are performed using EVs derived from the breast cancer cell line BT474 as the models, confirming the high sensitivity and specificity of the DNA machine. When further applied to clinical samples, the DNA machine is shown to be capable of not only distinguishing breast cancer patients with special subtypes but also realizing the tumor staging regarding the disease progression. Therefore, our work may provide new insights into the subtype-based diagnosis of breast cancer as well as identification of more potential therapeutic targets in the future.

ESPDHot: An Effective Machine Learning-Based Approach for Predicting Protein-DNA Interaction Hotspots.

Protein-DNA interactions are pivotal to various cellular processes. Precise identification of the hotspot residues for protein-DNA interactions holds great significance for revealing the intricate mechanisms in protein-DNA recognition and for providing essential guidance for protein engineering. Aiming at protein-DNA interaction hotspots, this work introduces an effective prediction method, ESPDHot based on a stacked ensemble machine learning framework. Here, the interface residue whose mutation leads to a binding free energy change (ΔΔG) exceeding 2 kcal/mol is defined as a hotspot. To tackle the imbalanced data set issue, the adaptive synthetic sampling (ADASYN), an oversampling technique, is adopted to synthetically generate new minority samples, thereby rectifying data imbalance. As for molecular characteristics, besides traditional features, we introduce three new characteristic types including residue interface preference proposed by us, residue fluctuation dynamics characteristics, and coevolutionary features. Combining the Boruta method with our previously developed Random Grouping strategy, we obtained an optimal set of features. Finally, a stacking classifier is constructed to output prediction results, which integrates three classical predictors, Support Vector Machine (SVM), XGBoost, and Artificial Neural Network (ANN) as the first layer, and Logistic Regression (LR) algorithm as the second one. Notably, ESPDHot outperforms the current state-of-the-art predictors, achieving superior performance on the independent test data set, with F1, MCC, and AUC reaching 0.571, 0.516, and 0.870, respectively.

Semaglutide alters gut microbiota and improves NAFLD in db/db mice.

Non-alcoholic fatty liver disease (NAFLD) is the most common liver disease associated with type 2 diabetes mellitus (T2D). NAFLD can progress to nonalcoholic steatohepatitis (NASH), cirrhosis, and even cancer, all of which have a very poor prognosis. Semaglutide, a novel glucagon-like peptide-1 (GLP-1) receptor agonist, has been recognized as a specific drug for the treatment of diabetes. In this study, we used a gene mutation mouse model (db/db mice) to investigate the potential liver-improving effects of semaglutide. The results showed that semaglutide improved lipid levels and glucose metabolism in db/db mice. HE staining and oil red staining showed alleviation of liver damage and reduction of hepatic lipid deposition after injection of semaglutide. In addition, semaglutide also improved the integrity of gut barrier and altered gut microbiota, especially Alloprevotella, Alistpes, Ligilactobacillus and Lactobacillus. In summary, our findings validate that semaglutide induces modifications in the composition of the gut microbiota and ameliorates NAFLD, positioning it as a promising therapeutic candidate for addressing hepatic steatosis and associated inflammation.

Mitochondrial tRNA pseudouridylation governs erythropoiesis.

Pseudouridine is the most prevalent RNA modification, and its aberrant function is implicated in various human diseases. However, the specific impact of pseudouridylation on hematopoiesis remains poorly understood. In this study, we investigated the role of tRNA pseudouridylation in erythropoiesis and its association with mitochondrial myopathy, lactic acidosis, and sideroblastic anemia syndrome (MLASA) pathogenesis. By utilizing patient-specific induced pluripotent stem cells (iPSCs) carrying a genetic PUS1 mutation and a corresponding mutant mouse model, we demonstrated impaired erythropoiesis in MLASA iPSCs and anemia in the MLASA mouse model. Both MLASA iPSCs and mouse erythroblasts exhibited compromised mitochondrial function and impaired protein synthesis. Mechanistically, we revealed that PUS1 deficiency resulted in reduced mitochondrial tRNA levels due to pseudouridylation loss, leading to aberrant mitochondrial translation. Screening of mitochondrial supplements aimed at enhancing respiration or heme synthesis showed limited effect in promoting erythroid differentiation. Interestingly, the mTOR inhibitor rapamycin facilitated erythroid differentiation in MLASA-iPSCs by suppressing mTOR signaling and protein synthesis, and consistent results were observed in the MLASA mouse model. Importantly, rapamycin treatment effectively ameliorated anemia phenotypes in the MLASA patient. Our findings provide novel insights into the crucial role of mitochondrial tRNA pseudouridylation in governing erythropoiesis and present potential therapeutic strategies for anemia patients facing challenges related to protein translation.

Combining prognostic value of serum carbohydrate antigen 19-9 and tumor size reduction ratio in pancreatic ductal adenocarcinoma.

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a common cancer with increasing morbidity and mortality due to changes of social environment. AIM: To evaluate the significance of serum carbohydrate antigen 19-9 (CA19-9) and tumor size changes pre- and post-neoadjuvant therapy (NAT). METHODS: This retrospective study was conducted at the Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital. This study specifically assessed CA19-9 levels and tumor size before and after NAT. RESULTS: A total of 156 patients who completed NAT and subsequently underwent tumor resection were included in this study. The average age was 65.4 ± 10.6 years and 72 (46.2%) patients were female. Before survival analysis, we defined the post-NAT serum CA19-9 level/pre-NAT serum CA19-9 level as the CA19-9 ratio (CR). The patients were divided into three groups: CR < 0.5, CR > 0.5 and < 1 and CR > 1. With regard to tumor size measured by both computed tomography and magnetic resonance imaging, we defined the post-NAT tumor size/pre-NAT tumor size as the tumor size ratio (TR). The patients were then divided into three groups: TR < 0.5, TR > 0.5 and < 1 and TR > 1. Based on these groups divided according to CR and TR, we performed both overall survival (OS) and disease-free survival (DFS) analyses. Log-rank tests showed that both OS and DFS were significantly different among the groups according to CR and TR (P < 0.05). CR and TR after NAT were associated with increased odds of achieving a complete or near-complete pathologic response. Moreover, CR (hazard ratio: 1.721, 95%CI: 1.373-3.762; P = 0.006), and TR (hazard ratio: 1.435, 95%CI: 1.275-4.363; P = 0.014) were identified as independent factors associated with OS. CONCLUSION: This study demonstrated that post-NAT serum CA19-9 level/pre-NAT serum CA19-9 level and post-NAT tumor size/pre-NAT tumor size were independent factors associated with OS in patients with PDAC who received NAT and subsequent surgical resection.

XELOX (capecitabine plus oxaliplatin) plus bevacizumab (anti-VEGF-A antibody) with or without adoptive cell immunotherapy in the treatment of patients with previously untreated metastatic colorectal cancer: a multicenter, open-label, randomized, controlled, phase 3 trial.

Fluoropyrimidine-based combination chemotherapy plus targeted therapy is the standard initial treatment for unresectable metastatic colorectal cancer (mCRC), but the prognosis remains poor. This phase 3 trial (ClinicalTrials.gov: NCT03950154) assessed the efficacy and adverse events (AEs) of the combination of PD-1 blockade-activated DC-CIK (PD1-T) cells with XELOX plus bevacizumab as a first-line therapy in patients with mCRC. A total of 202 participants were enrolled and randomly assigned in a 1:1 ratio to receive either first-line XELOX plus bevacizumab (the control group, n = 102) or the same regimen plus autologous PD1-T cell immunotherapy (the immunotherapy group, n = 100) every 21 days for up to 6 cycles, followed by maintenance treatment with capecitabine and bevacizumab. The main endpoint of the trial was progression-free survival (PFS). The median follow-up was 19.5 months. Median PFS was 14.8 months (95% CI, 11.6-18.0) for the immunotherapy group compared with 9.9 months (8.0-11.8) for the control group (hazard ratio [HR], 0.60 [95% CI, 0.40-0.88]; p = 0.009). Median overall survival (OS) was not reached for the immunotherapy group and 25.6 months (95% CI, 18.3-32.8) for the control group (HR, 0.57 [95% CI, 0.33-0.98]; p = 0.043). Grade 3 or higher AEs occurred in 20.0% of patients in the immunotherapy group and 23.5% in the control groups, with no toxicity-associated deaths reported. The addition of PD1-T cells to first-line XELOX plus bevacizumab demonstrates significant clinical improvement of PFS and OS with well tolerability in patients with previously untreated mCRC.

Hydrothermal route upcycling surgical masks into dual-emitting carbon dots as ratiometric fluorescent probe for Cr (VI) and corrosion inhibitor in saline solution.

Exploration effective route to convert plastic waste into valuable carbon dots with bifunction of metal fluorescence monitoring and corrosion protection in seawater is promising. Herein, using "white-pollution" polypropylene surgical masks as a single precursor, dual-emitting carbon dots (CDs) with excellent ratiometric fluorescent sensitivity and corrosion inhibitor efficiency were fabricated with high yield (∼100 %) by a one-pot in situ acid oxidation hydrothermal strategy without post-treatment and organic solvents. Chemical, structural, morphological, optical properties and the Cr (VI) detection and Cu inhibition mechanism of the synthesized CDs had been systematically studied. Furthermore, a dual-response-OFF proportional fluorescent probe had been developed for the detection of the analyte Cr (VI) with a low detection limit of 24 nM. Additionally, the corrosion inhibition efficiency of the prepared CDs reached approximately 94.01 % for Cu substrate in 3.5 wt% NaCl electrolyte under a CDs concentration of 200 mg/L, which is higher than that of most previous reports.

Cold Pressing of Perovskite-ZIF Glass Interpenetrating Networks with Stable Photoelectric Response.

The protection of lead halide perovskite within a stable matrix normally leads to the loss of semiconducting properties. Here, we report the synthesis of perovskite-ZIF glass interpenetrating networks via a cold pressing method, which allows the advantages of bright photoluminescence, high photoconductivity and environmental stability. This hybrid architecture has provided a novel design strategy for the real-world application of perovskite-based devices.

Nicotinamide mononucleotide maintains cytoskeletal stability and fortifies mitochondrial function to mitigate oocyte damage induced by Triocresyl phosphate.

Triocresyl phosphate (TOCP) was commonly used as flame retardant, plasticizer, lubricant, and jet fuel additive. Studies have shown adverse effects of TOCP on the reproductive system. However, the potential harm brought by TOCP, especially to mammalian female reproductive cells, remains a mystery. In this study, we employed an in vitro model for the first time to investigate the effects of TOCP on the maturation process of mouse oocytes. TOCP exposure hampered the meiotic division process, as evidenced by a reduction in the extrusion of the first polar body from oocytes. Subsequent research revealed the disruption of the oocyte cell cytoskeleton induced by TOCP, resulting in abnormalities in spindle organization, chromosome alignment, and actin filament distribution. This disturbance further extended to the rearrangement of organelles within oocytes, particularly affecting the mitochondria. Importantly, after TOCP treatment, mitochondrial function in oocytes was impaired, leading to oxidative stress, DNA damage, cell apoptosis, and subsequent changes of epigenetic modifications. Supplementation with nicotinamide mononucleotide (NMN) alleviated the harmful effects of TOCP. NMN exerted its mitigating effects through two fundamental mechanisms. On one hand, NMN conferred stability to the cell cytoskeleton, thereby supporting nuclear maturation. On the other hand, NMN enhanced mitochondrial function within oocytes, reducing the excess reactive oxygen species (ROS), restoring meiotic division abnormalities caused by TOCP, preventing oocyte DNA damage, and suppressing epigenetic changes. These findings not only enhance our understanding of the molecular basis of TOCP induced oocyte damage but also offer a promising avenue for the potential application of NMN in optimizing reproductive treatment strategies.

Crown-Assisted CsCu2I3 Growth and Trap Passivation for Perovskite Light-Emitting Diodes.

Copper (Cu)-based perovskites are promising for lead-free perovskite light-emitting diodes (PeLEDs). However, it remains a significant challenge to achieve high performance devices due to the nonradiative loss caused by the disordered crystallization and lack of passivation. Crown ethers are known to form host-guest complexes by the interaction between C-O-C groups and certain cations, and 18-crown-6 (18C6) with an appropriate complementary size can interact with Cs+ and Cu+ cations. Herein, we studied the interaction between CsCu2I3 and two crowns with the same cyclic size, 18C6 and dibenzo-18-crown-6 (D18C6). Particularly, D18C6 can reduce the nonradiative recombination rate of CsCu2I3 film by passivating the defects and optimizing the film morphology effectively. The room mean square (RMS) decreased from 5.06 to 2.95 nm, and the PLQY was promoted from 4.71% to 19.9%. Besides, D18C6 can also decrease the barrier of hole injection. The PeLEDs based on D18C6-modified CsCu2I3 realized noticeable improvement with a maximum luminance and EQE of 583 cd/m2 and 0.662%, respectively.

Machine Learning Prediction of Autism Spectrum Disorder Through Linking Mothers' and Children's Electronic Health Record Data.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder typically diagnosed in children. Early detection of ASD, particularly in girls who are often diagnosed late, can aid long-term development for children. We aimed to develop machine learning models for predicting ASD diagnosis in children, both boys and girls, using child-mother linked electronic health records (EHRs) data from a large clinical research network. Model features were children and mothers' risk factors in EHRs, including maternal health factors. We tested XGBoost and logistic regression with Random Oversampling (ROS) and Random Undersampling (RUS) to address imbalanced data. Logistic regression with RUS considering a three-year observation window for children's risk factors achieved the best performance for predicting ASD among the overall study population (AUROC = 0.798), boys (AUROC = 0.786), and girls (AUROC = 0.791). We calculated SHAP values to quantify the impacts of important clinical and sociodemographic risk factors.

Long-term remission and survival in patients with relapsed or refractory multiple myeloma after treatment with LCAR-B38M CAR T cells: 5-year follow-up of the LEGEND-2 trial.

BACKGROUND: The autologous anti-B-cell maturation antigen (BCMA) chimeric antigen receptor (CAR) T-cell therapy LCAR-B38M has been approved for the treatment of relapsed and refractory multiple myeloma in many countries across the world under the name ciltacabtagene autoleucel. LEGEND-2 was the first-in-human trial of LCAR-B38M and yielded deep and durable therapeutic responses. Here, we reported the outcomes in LEGEND-2 after a minimal 5-year follow-up. METHODS: Participants received an average dose of 0.5 × 106 cells/kg LCAR-B38M in split or single unfractionated infusions after cyclophosphamide-based lymphodepletion therapy. Investigator-assessed response, survival, safety and pharmacokinetics were evaluated. RESULTS: Seventy-four participants enrolled and had a median follow-up of 65.4 months. The 5-year progression-free survival (PFS) and overall survival (OS) rates were 21.0% and 49.1%, with progressive flattening of the survival curves over time. Patients with complete response (CR) had longer PFS and OS, with 5-year rates of 28.4% and 65.7%, respectively. Twelve patients (16.2%) remained relapse-free irrespective of baseline high-risk cytogenetic abnormality and all had normal humoral immunity reconstituted. An ongoing CR closely correlated with several prognostic baseline indices including favorable performance status, immunoglobulin G subtype, and absence of extramedullary disease, as well as a combination cyclophosphamide and fludarabine preconditioning strategy. Sixty-two (83.8%) suffered progressive disease (PD) and/or death; however, 61.1% of PD patients could well respond to subsequent therapies, among which, the proteasome inhibitor-based regimens benefited the most. Concerning the safety, hematologic and hepatic function recovery were not significantly different between non-PD and PD/Death groups. A low rate of second primary malignancy (5.4%) and no severe virus infection were observed. The patients who tested positive for COVID-19 merely presented self-limiting symptoms. In addition, a sustainable CAR T population of one case with persistent remission was delineated, which was enriched with indolently proliferative and lowly cytotoxic CD4/CD8 double-negative functional T lymphocytes. CONCLUSIONS: These data, representing the longest follow-up of BCMA-redirected CAR T-cell therapy to date, demonstrate long-term remission and survival with LCAR-B38M for advanced myeloma. TRIAL REGISTRATION: LEGEND-2 was registered under the trial numbers NCT03090659, ChiCTRONH-17012285.

Loss of RNA-binding protein CELF2 promotes acute leukemia development via FAT10-mTORC1.

RNA-binding proteins (RBPs) are critical regulators for RNA transcription and translation. As a key member of RBPs, ELAV-like family protein 2 (CELF2) has been shown to regulate RNA splicing and embryonic hematopoietic development and was frequently seen dysregulated in acute myeloid leukemia (AML). However, the functional role(s) of CELF2 in hematopoiesis and leukemogenesis has not been fully elucidated. In the current study, we showed that Celf2 deficiency in hematopoietic system led to enhanced HSCs self-renewal and differentiation toward myeloid cells in mice. Loss of Celf2 accelerated myeloid cell transformation and AML development in MLL-AF9-induced AML murine models. Gene expression profiling integrated with RNA immunoprecipitation sequencing (RIP-Seq), together with biochemical experiments revealed that CELF2 deficiency stabilizes FAT10 mRNA, promotes FAT10 translation, thereby increases AKT phosphorylation and mTORC1 signaling pathway activation. Notably, combination therapy with a mTORC1 inhibitor (Rapamycin) and a MA9/DOTL1 inhibitor (EPZ-5676) reduced the leukemia burden in MLL-AF9 mice lacking Celf2 in vivo. Our study elucidated a novel mechanism by which the CELF2/FAT10-AKT/mTORC1 axis regulates the proliferation of normal blood cells and the development of AML, thus providing potential therapeutic targets for myeloid leukemia suppression.

PMSPcnn: Predicting protein stability changes upon single point mutations with convolutional neural network.

Protein missense mutations and resulting protein stability changes are important causes for many human genetic diseases. However, the accurate prediction of stability changes due to mutations remains a challenging problem. To address this problem, we have developed an unbiased effective model: PMSPcnn that is based on a convolutional neural network. We have included an anti-symmetry property to build a balanced training dataset, which improves the prediction, in particular for stabilizing mutations. Persistent homology, which is an effective approach for characterizing protein structures, is used to obtain topological features. Additionally, a regression stratification cross-validation scheme has been proposed to improve the prediction for mutations with extreme ΔΔG. For three test datasets: Ssym, p53, and myoglobin, PMSPcnn achieves a better performance than currently existing predictors. PMSPcnn also outperforms currently available methods for membrane proteins. Overall, PMSPcnn is a promising method for the prediction of protein stability changes caused by single point mutations.