Deep learning-guided adjuvant chemotherapy selection for elderly patients with breast cancer.

PURPOSE: The efficacy of adjuvant chemotherapy in elderly breast cancer patients is currently controversial. This study aims to provide personalized adjuvant chemotherapy recommendations using deep learning (DL). METHODS: Six models with various causal inference approaches were trained to make individualized chemotherapy recommendations. Patients who received actual treatment recommended by DL models were compared with those who did not. Inverse probability treatment weighting (IPTW) was used to reduce bias. Linear regression, IPTW-adjusted risk difference (RD), and SurvSHAP(t) were used to interpret the best model. RESULTS: A total of 5352 elderly breast cancer patients were included. The median (interquartile range) follow-up time was 52 (30-80) months. Among all models, the balanced individual treatment effect for survival data (BITES) performed best. Treatment according to following BITES recommendations was associated with survival benefit, with a multivariate hazard ratio (HR) of 0.78 (95% confidence interval (CI): 0.64-0.94), IPTW-adjusted HR of 0.74 (95% CI: 0.59-0.93), RD of 12.40% (95% CI: 8.01-16.90%), IPTW-adjusted RD of 11.50% (95% CI: 7.16-15.80%), difference in restricted mean survival time (dRMST) of 12.44 (95% CI: 8.28-16.60) months, IPTW-adjusted dRMST of 7.81 (95% CI: 2.93-11.93) months, and p value of the IPTW-adjusted Log-rank test of 0.033. By interpreting BITES, the debiased impact of patient characteristics on adjuvant chemotherapy was quantified, which mainly included breast cancer subtype, tumor size, number of positive lymph nodes, TNM stages, histological grades, and surgical type. CONCLUSION: Our results emphasize the potential of DL models in guiding adjuvant chemotherapy decisions for elderly breast cancer patients.

Time-gated imaging through dense fog via physics-driven Swin transformer.

Imaging through the fog is valuable for many areas, such as autonomous driving and cosmic exploration. However, due to the influence of strong backscattering and diffuse reflection generated by the dense fog on the temporal-spatial correlations of photons returning from the target object, the reconstruction quality of most existing methods is significantly reduced under dense fog conditions. In this study, we describe the optical scatter imaging process and propose a physics-driven Swin Transformer method utilizing Time-of-Flight (ToF) and Deep Learning principles to mitigate scattering effects and reconstruct targets in conditions of heterogeneous dense fog. The results suggest that, despite the exponential decrease in the number of ballistic photons as the optical thickness of fog increases, the Physics-Driven Swin Transformer method demonstrates satisfactory performance in imaging targets obscured by dense fog. Importantly, this article highlights that even in dense fog imaging experiments with optical thickness reaching up to 3.0, which exceeds previous studies, commonly utilized quantitative evaluation metrics like PSNR and SSIM indicate that our method is cutting-edge in imaging through dense fog.

Application of a circular-shaped pulsed field ablation catheter with magnetic sensors for pulmonary vein isolation: a multi-centre clinical study report.

AIMS: A few studies have reported the effect and safety of pulsed field ablation (PFA) catheters for ablating atrial fibrillation (AF), which were mainly based on basket-shaped or flower-shaped designs. However, the clinical application of a circular-shaped multi-electrode catheter with magnetic sensors is very limited. To study the efficacy and safety of a PFA system in patients with paroxysmal AF using a circular-shaped multi-electrode catheter equipped with magnetic sensors for pulmonary vein isolation (PVI). METHODS AND RESULTS: A novel proprietary bipolar PFA system was used for PVI, which utilized a circular-shaped multi-electrode catheter with magnetic sensors and allowed for three-dimensional model reconstruction, mapping, and ablation in one map. To evaluate the efficacy, efficiency, and safety of this PFA system, a prospective, multi-centre, single-armed, pre-market clinical study was performed. From July 2021 to December 2022, 151 patients with paroxysmal AF were included and underwent PVI. The study examined procedure time, immediate success rate, procedural success rate at 12 months, and relevant complications. In all 151 patients, all the pulmonary veins were acutely isolated using the studied system. Pulsed field ablation delivery was 78.4 ± 41.8 times and 31.3 ± 16.7 ms per patient. Skin-to-skin procedure time was 74.2 ± 29.8 min, and fluoroscopy time was 13.1 ± 7.6 min. The initial 11 (7.2%) cases underwent procedures with deep sedation anaesthesia, and the following cases underwent local anaesthesia. In the initial 11 cases, 4 cases (36.4%) presented transient vagal responses, and the rest were all successfully preventatively treated with atropine injection and rapid fluid infusion. No severe complications were found during or after the procedure. During follow-up, 3 cases experienced atrial flutter, and 11 cases had AF recurrence. The estimated 12-month Kaplan-Meier of freedom from arrhythmia was 88.4%. CONCLUSION: The PFA system, comprised of a circular PFA catheter with magnetic sensors, could rapidly achieve PVI under three-dimensional guidance and demonstrated excellent safety with comparable effects.

PI-NLOS: polarized infrared non-line-of-sight imaging.

Passive non-line-of-sight (NLOS) imaging is a promising technique to enhance visual perception for the occluded object hidden behind the wall. Here we present a data-driven NLOS imaging framework by using polarization cue and long-wavelength infrared (LWIR) images. We design a dual-channel input deep neural network to fuse the intensity features from polarized LWIR images and contour features from polarization degree images for NLOS scene reconstruction. To train the model, we create a polarized LWIR NLOS dataset which contains over ten thousand images. The paper demonstrates the passive NLOS imaging experiment in which the hidden people is approximate 6 meters away from the relay wall. It is an exciting finding that even the range is further than that in the prior works. The quantitative evaluation metric of PSNR and SSIM show that our method as an advance over state-of-the-art in passive NLOS imaging.

IiSVP of Isatis indigotica can reduce the size and repress the development of floral organs.

KEY MESSAGE: IiSVP of Isatis indigotica was cloned and its expression pattern was analyzed. Ectopic expression of IiSVP in Arabidopsis could delay the flowering time and reduce the size of the floral organs. SVP (SHORT VEGETATIVE PHASE) can negatively regulate the flowering time of Arabidopsis. In the present work, the cDNA of IiSVP, an orthologous gene of AtSVP in I. indigotica, was cloned. IiSVP was highly expressed in rosette leaves, inflorescences and petals, but weakly expressed in sepals, pistils and young silicles. The results of subcellular localization showed that IiSVP was localized in nucleus. Bioinformatics analysis indicated that this protein was a MADS-box transcription factor. Constitutive expression of IiSVP in Arabidopsis thaliana resulted in decrease of the number of petals and stamens, and curly sepals were formed. In IiSVP transgenic Arabidopsis plants, obvious phenotypic variations in flowers could be observed, especially the size of the floral organs. In comparison with the wild-type plants, the size of petals, stamens and pistil in IiSVP transgenic Arabidopsis plants was decreased significantly. In some transgenic plants, the petals were wrapped by the sepals. Yeast two-hybrid experiments showed that IiSVP could form higher-order complexes with other MADS proteins, including IiSEP1, IiSEP3, IiAP1 and IiSEP4, but could not interact with IiSEP2. In this work, it was proved that the flowering process and the floral development in Arabidopsis could be affected by IiSVP from I. indigotica Fortune.

Functional identification of the different regions in B-class floral homeotic MADS-box proteins IiAP3 and IiPI from Isatis indigotica.

APETALA3 (AP3) and PISTILLATA (PI) are B-class MADS-box floral homeotic genes of Arabidopsis and are involved in specifying the identity of petals and stamens. In the present work, IiAP3 and IiPI, the respective orthologous genes of AP3 and PI, were cloned from Isatis indigotica. By expressing in ap3-6 and pi-1 homozygous mutant and in wild-type Arabidopsis under the control of AP3 promoter or CaMV 35S promoter, we demonstrated that IiAP3 and IiPI were functionally equivalent to AP3 and PI of Arabidopsis. Referring to previous reports and the research results in the present work, expression patterns of AP3 and PI homologs are not the same in different angiosperms possessing diverse floral structures. It suggests that the alterations in expression may contribute to the changing morphology of flowers. To further determine the relationship between IiAP3 and IiPI, the coding sequences of the different structural regions in these two proteins were swapped with each other, and the data collected from transgenic Arabidopsis plants of the chimeric constructs suggested that MADS domain was irreplaceable for the function of IiAP3, K domain of IiAP3 was involved in specifying the identity of stamens, K domain of IiPI was mainly related to the formation of petals, and C-terminal region of IiPI was involved in characterization of stamens. In addition, a complete KC region of these two proteins was more effective in phenotypic complementation of the mutants.

Derivation and validation of a nomogram for predicting nonventilator hospital-acquired pneumonia among older hospitalized patients.

BACKGROUND: Currently, there is no effective tool for predicting the risk of nonventilator hospital-acquired pneumonia (NV-HAP) in older hospitalized patients. The current study aimed to develop and validate a simple nomogram and a dynamic web-based calculator for predicting the risk of NV-HAP among older hospitalized patients. METHODS: A retrospective evaluation was conducted on 15,420 consecutive older hospitalized patients admitted to a tertiary hospital in China between September 2017 and June 2020. The patients were randomly divided into training (n = 10,796) and validation (n = 4624) cohorts at a ratio of 7:3. Predictors of NV-HAP were screened using the least absolute shrinkage and selection operator method and multivariate logistic regression. The identified predictors were integrated to construct a nomogram using R software. Furthermore, the optimum cut-off value for the clinical application of the model was calculated using the Youden index. The concordance index (C-index), GiViTI calibration belts, and decision curve were analysed to validate the discrimination, calibration, and clinical utility of the model, respectively. Finally, a dynamic web-based calculator was developed to facilitate utilization of the nomogram. RESULTS: Predictors included in the nomogram were the Charlson comorbidity index, NRS-2002, enteral tube feeding, Barthel Index, use of sedatives, use of NSAIDs, use of inhaled steroids, and "time at risk". The C-index of the nomogram for the training and validation cohorts was 0.813 and 0.821, respectively. The 95% CI region of the GiViTI calibration belt in the training (P = 0.694) and validation (P = 0.614) cohorts did not cross the diagonal bisector line, suggesting that the prediction model had good discrimination and calibration. Furthermore, the optimal cut-off values for the training and validation cohorts were 1.58 and 1.74%, respectively. Analysis of the decision curve showed that the nomogram had good clinical value when the threshold likelihood was between 0 and 49%. CONCLUSION: The developed nomogram can be used to predict the risk of NV-HAP among older hospitalized patients. It can, therefore, help healthcare providers initiate targeted medical interventions in a timely manner for high-risk groups.

Role of melatonin in UV-B signaling pathway and UV-B stress resistance in Arabidopsis thaliana.

Melatonin (N-acetyl-5-methoxytryptamine) plays important roles in plant defences against a variety of biotic and abiotic stresses, including UV-B stress. Molecular mechanisms underlying functions of melatonin in plant UV-B responses are poorly understood. Here, we show that melatonin effect on molecular signalling pathways, physiological changes and UV-B stress resistance in Arabidopsis. Both exogenous and endogenous melatonin affected expression of UV-B signal transduction pathway genes. Experiments using UV-B signalling component mutants cop1-4 and hy5-215 revealed that melatonin not only acts as an antioxidant to promote UV-B stress resistance, but also regulates expression of several key components of UV-B signalling pathway, including ubiquitin-degrading enzyme (COP1), transcription factors (HY5, HYH) and RUP1/2. Our findings indicate that melatonin delays and subsequently enhances expression of COP1, HY5, HYH and RUP1/2, which act as central effectors in UV-B signalling pathway, thus regulating their effects on antioxidant systems to protect the plant from UV-B stress.

Signals in systemic acquired resistance of plants against microbial pathogens.

After a local infection by the microbial pathogens, plants will produce strong resistance in distal tissues to cope with the subsequent biotic attacks. This type of the resistance in the whole plant is termed as systemic acquired resistance (SAR). The priming of SAR can confer the robust defense responses and the broad-spectrum disease resistances in plants. In general, SAR is activated by the signal substances generated at the local sites of infection, and these small signaling molecules can be rapidly transported to the systemic tissues through the phloem. In the last two decades, numerous endogenous metabolites were proved to be the potential elicitors of SAR, including methyl salicylate (MeSA), azelaic acid (AzA), glycerol-3-phosphate (G3P), free radicals (NO and ROS), pipecolic acid (Pip), N-hydroxy-pipecolic acid (NHP), dehydroabietinal (DA), monoterpenes (α-pinene and ß-pinene) and NAD(P). In the meantime, the proteins associated with the transport of these signaling molecules were also identified, such as DIR1 (DEFECTIVE IN INDUCED RESISTANCE 1) and AZI1 (AZELAIC ACID INDUCED 1). This review summarizes the recent findings related to synthesis, transport and interaction of the different signal substances in SAR.

Ectopic expression of IiSHP2 from Isatis indigotica Fortune, a PLE-lineage MADS-box gene, influences leaf, floral organ and silique morphology in Arabidopsis thaliana.

In order to ascertain the regulatory mechanism of fruit development in Isatis indigotica Fortune, the complementary DNA (cDNA) sequence of the SHATTERPROOF 2 (SHP2) orthologous gene was identified by Rapid Amplification of cDNA Ends technology and the corresponding gene was named IiSHP2. The expression pattern of IiSHP2 was determined by quantitative reverse transcription-polymerase chain reaction and wild-type Col-0 Arabidopsis plants were transformed with the IiSHP2 gene using Agrobacterium tumefaciens and the floral-dip method. Expression analyses indicated that IiSHP2 was highly expressed in flowers, silicles and seeds. Compared to wild-type plants, IiSHP2 transgenic lines bolted earlier. Detailed phenotypic observations showed that the size of the rosette and cauline leaves in transgenic lines was reduced and the cauline leaves of the transgenic lines were incurved and displayed a funnel-like shape. During the reproductive growth stage, IiSHP2 transgenic plants produced shortened sepals and the flower buds were not encapsulated completely. Moreover, the petals of the transgenic lines were converted into stamineous tissues, accompanied by exposed stamens, short malformed siliques and wrinkled valves, indicating a severe decline in fertility. These experimental conclusions are valuable as a reference for the breeding of medicinal plants.

NPR1 and Redox Rhythmx: Connections, between Circadian Clock and Plant Immunity.

The circadian clock in plants synchronizes biological processes that display cyclic 24-h oscillation based on metabolic and physiological reactions. This clock is a precise timekeeping system, that helps anticipate diurnal changes; e.g., expression levels of clock-related genes move in synchrony with changes in pathogen infection and help prepare appropriate defense responses in advance. Salicylic acid (SA) is a plant hormone and immune signal involved in systemic acquired resistance (SAR)-mediated defense responses. SA signaling induces cellular redox changes, and degradation and rhythmic nuclear translocation of the non-expresser of PR genes 1 (NPR1) protein. Recent studies demonstrate the ability of the circadian clock to predict various potential attackers, and of redox signaling to determine appropriate defense against pathogen infection. Interaction of the circadian clock with redox rhythm promotes the balance between immunity and growth. We review here a variety of recent evidence for the intricate relationship between circadian clock and plant immune response, with a focus on the roles of redox rhythm and NPR1 in the circadian clock and plant immunity.

Characterization and phylogenetic analysis of fifteen NtabSPL genes in Nicotiana tabacum L. cv. Qinyan95.

Fifteen SPL (SQUAMOSA PROMOTER BINDING PROTEIN-LIKE) genes were identified and characterized in Nicotiana tabacum L. cv. Qinyan95. The exon-intron structures of these genes were determined according to the coding sequences confirmed by RT-PCR and the genomic DNA sequences downloaded from the databases in Sol Genomics Network, and thirteen of them were found to carry the response element of miR156. To elucidate the origin of the validated NtabSPL genes, multiple alignments of the nucleotide sequences encompassing the open reading frames were conducted by using the orthologs in N. tabacum, Nicotiana sylvestris, Nicotiana tomentosiformis, and Nicotiana otophora. The results showed that six NtabSPL genes were derived from a progenitor of N. sylvestris, and nine NtabSPL genes were derived from a progenitor of N. tomentosiformis, further corroborating that N. tabacum came from the interspecific hybridization between the ancestors of N. sylvestris and N. tomentosiformis. In contrast to previous statements about highly repetitive sequences, the genome of N. tabacum mainly retained the paternal-derived SPL genes in diploidization process. Phylogenetic analyses based on the highly conserved SBP (SQUAMOSA PROMOTER BINDING PROTEIN) domains and the full-length amino acid sequences reveal that the SPL proteins of tobacco, tomato, and Arabidopsis can be categorized into eight groups. It is worth noting that N. tabacum contains seven NtabSPL6 genes originated from two parental genomes and NtabSPL6-2 possesses a GC-AG intron. In addition, transgenic tobacco plants harboring Arabidopsis Pri-miR156A were generated by Agrobacterium-mediated transformation method, and the constitutive expression of miR156 could obviously inhibit the activity of the NtabSPL genes containing its target site, suggesting the function of miR156 is conservative in tobacco and Arabidopsis.

Ectopic expression of miR156 represses nodulation and causes morphological and developmental changes in Lotus japonicus.

The effects of microRNA156 overexpression on general plant architecture, branching, flowering time and nodulation were investigated in the model legume, Lotus japonicus. We cloned an miR156 homolog, LjmiR156a, from L. japonicus, and investigated its SQUAMOSA PROMOTER BINDING PROTEIN LIKE (SPL) genes and its biological function at enhancing vegetative biomass yield, extending flowering time, and its impact on nodulation. Thirteen potential targets for LjmiR156 were identified in vitro and their expression profiles were determined in aerial and underground parts of mature plants, including genes coding for eight SPLs, one WD-40, one RNA-directed DNA polymerase, two transport proteins, and one histidine-phosphotransfer protein. Two SPL and one WD-40 cleavage targets for LjmiR156-TC70253, AU089191, and TC57859-were identified. Transgenic plants with ectopic expression of LjmiR156a showed enhanced branching, dramatically delayed flowering, underdeveloped roots, and reduced nodulation. We also examined the transcript levels of key genes involved in nodule organogenesis and infection thread formation to determine the role of miR156 in regulating symbiosis. Overexpression of LjmiR156a led to repression of several nodulation genes during the early stages of root development such as three ENOD genes, SymPK, POLLUX, CYCLOPS, Cerberus, and Nsp1, and the stimulation of NFR1. Our results show that miR156 regulates vegetative biomass yield, flowering time and nodulation by silencing downstream target SPLs and other genes, suggesting that the miR156 regulatory network could be modified in forage legumes (such as alfalfa and trefoils) and in leafy vegetables (like lettuce and spinach) to positively impact economically valuable crop species.

Quantified treatment effect at the individual level is more indicative for personalized radical prostatectomy recommendation: implications for prostate cancer treatment using deep learning.

BACKGROUND: There are potential uncertainties and overtreatment existing in radical prostatectomy (RP) for prostate cancer (PCa) patients, thus identifying optimal candidates is quite important. PURPOSE: This study aims to establish a novel causal inference deep learning (DL) model to discern whether a patient can benefit more from RP and to identify heterogeneity in treatment responses among PCa patients. METHODS: We introduce the Self-Normalizing Balanced individual treatment effect for survival data (SNB). Six models were trained to make individualized treatment recommendations for PCa patients. Inverse probability treatment weighting (IPTW) was used to avoid treatment selection bias. RESULTS: 35,236 patients were included. Patients whose actual treatment was consistent with SNB recommendations had better survival outcomes than those who were inconsistent (multivariate hazard ratio (HR): 0.76, 95% confidence interval (CI), 0.64-0.92; IPTW-adjusted HR: 0.77, 95% CI, 0.61-0.95; risk difference (RD): 3.80, 95% CI, 2.48-5.11; IPTW-adjusted RD: 2.17, 95% CI, 0.92-3.35; the difference in restricted mean survival time (dRMST): 3.81, 95% CI, 2.66-4.85; IPTW-adjusted dRMST: 3.23, 95% CI, 2.06-4.45). Keeping other covariates unchanged, patients with 1 ng/mL increase in PSA levels received RP caused 1.77 months increase in the time to 90% mortality, and the similar results could be found in age, Gleason score, tumor size, TNM stages, and metastasis status. CONCLUSIONS: Our highly interpretable and reliable DL model (SNB) may identify patients with PCa who could benefit from RP, outperforming other models and clinical guidelines. Additionally, the DL-based treatment guidelines obtained can provide priori evidence for subsequent studies.

Individualized survival prediction and surgery recommendation for patients with glioblastoma.

Background: There is a lack of individualized evidence on surgical choices for glioblastoma (GBM) patients. Aim: This study aimed to make individualized treatment recommendations for patients with GBM and to determine the importance of demographic and tumor characteristic variables in the selection of extent of resection. Methods: We proposed Balanced Decision Ensembles (BDE) to make survival predictions and individualized treatment recommendations. We developed several DL models to counterfactually predict the individual treatment effect (ITE) of patients with GBM. We divided the patients into the recommended (Rec.) and anti-recommended groups based on whether their actual treatment was consistent with the model recommendation. Results: The BDE achieved the best recommendation effects (difference in restricted mean survival time (dRMST): 5.90; 95% confidence interval (CI), 4.40-7.39; hazard ratio (HR): 0.71; 95% CI, 0.65-0.77), followed by BITES and DeepSurv. Inverse probability treatment weighting (IPTW)-adjusted HR, IPTW-adjusted OR, natural direct effect, and control direct effect demonstrated better survival outcomes of the Rec. group. Conclusion: The ITE calculation method is crucial, as it may result in better or worse recommendations. Furthermore, the significant protective effects of machine recommendations on survival time and mortality indicate the superiority of the model for application in patients with GBM. Overall, the model identifies patients with tumors located in the right and left frontal and middle temporal lobes, as well as those with larger tumor sizes, as optimal candidates for SpTR.

Personalized surgical recommendations and quantitative therapeutic insights for patients with metastatic breast cancer: Insights from deep learning.

Background: The role of surgery in metastatic breast cancer (MBC) is currently controversial. Several novel statistical and deep learning (DL) methods promise to infer the suitability of surgery at the individual level. Objective: The objective of this study was to identify the most applicable DL model for determining patients with MBC who could benefit from surgery and the type of surgery required. Methods: We introduced the deep survival regression with mixture effects (DSME), a semi-parametric DL model integrating three causal inference methods. Six models were trained to make individualized treatment recommendations. Patients who received treatments in line with the DL models' recommendations were compared with those who underwent treatments divergent from the recommendations. Inverse probability weighting (IPW) was used to minimize bias. The effects of various features on surgery selection were visualized and quantified using multivariate linear regression and causal inference. Results: In total, 5269 female patients with MBC were included. DSME was an independent protective factor, outperforming other models in recommending surgery (IPW-adjusted hazard ratio [HR] = 0.39, 95% confidence interval [CI]: 0.19-0.78) and type of surgery (IPW-adjusted HR = 0.66, 95% CI: 0.48-0.93). DSME was superior to other models and traditional guidelines, suggesting a higher proportion of patients benefiting from surgery, especially breast-conserving surgery. The debiased effect of patient characteristics, including age, tumor size, metastatic sites, lymph node status, and breast cancer subtypes, on surgery decision was also quantified. Conclusions: Our findings suggested that DSME could effectively identify patients with MBC likely to benefit from surgery and the specific type of surgery needed. This method can facilitate the development of efficient, reliable treatment recommendation systems and provide quantifiable evidence for decision-making.

IiAGL6 participates in the regulation of stamen development and pollen formation in Isatis indigotica.

The AGL6 (AGMOUSE LIKE 6) gene is a member of the SEP subfamily and functions as an E-class floral homeotic gene in the development of floral organs. In this study, we cloned IiAGL6, the orthologous gene of AGL6 in Isatis indigotica. The constitutive expression of IiAGL6 in Arabidopsis thaliana resulted in a late-flowering phenotype and the development of curly leaves during the vegetative growth period. Abnormal changes in floral organ development were observed during the reproductive stage. In woad plants, suppression of IiAGL6 using TRV-VIGS (tobacco rattle virus-mediated virus-induced gene silencing) decreased the number of stamens and led to the formation of aberrant anthers. Similar changes in stamen development were also observed in miRNA-AGL6 transgenic Arabidopsis plants. Yeast two-hybrid and BiFC tests showed that IiAGL6 can interact with other MADS-box proteins in woad; thus, playing a key role in defining the identities of floral organs, particularly during stamen formation. These findings might provide novel insights and help investigate the biological roles of MADS transcription factors in I. indigotica.

Deep sequencing of Lotus corniculatus L. reveals key enzymes and potential transcription factors related to the flavonoid biosynthesis pathway.

Lotus corniculatus L. is used worldwide as a forage crop due to its abundance of secondary metabolites and its ability to grow in severe environments. Although the entire genome of L. corniculatus var. japonicus R. is being sequenced, the differences in morphology and production of secondary metabolites between these two related species have led us to investigate this variability at the genetic level, in particular the differences in flavonoid biosynthesis. Our goal is to use the resulting information to develop more valuable forage crops and medicinal materials. Here, we conducted Illumina/Solexa sequencing to profile the transcriptome of L. corniculatus. We produced 26,492,952 short reads that corresponded to 2.38 gigabytes of total nucleotides. These reads were then assembled into 45,698 unigenes, of which a large number associated with secondary metabolism were annotated. In addition, we identified 2,998 unigenes based on homology with L. japonicus transcription factors (TFs) and grouped them into 55 families. Meanwhile, a comparison of four tag-based digital gene expression libraries, built from the flowers, pods, leaves, and roots, revealed distinct patterns of spatial expression of candidate unigenes in flavonoid biosynthesis. Based on these results, we identified many key enzymes from L. corniculatus which were different from reference genes of L. japonicus, and five TFs that are potential enhancers in flavonoid biosynthesis. Our results provide initial genetics resources that will be valuable in efforts to manipulate the flavonoid metabolic pathway in plants.

Enhanced resistance to stripe rust disease in transgenic wheat expressing the rice chitinase gene RC24.

Stripe rust is a devastating fungal disease of wheat worldwide which is primarily caused by Puccinia striiformis f. sp tritici. Transgenic wheat (Triticum aestivum L.) expressing rice class chitinase gene RC24 were developed by particle bombardment of immature embryos and tested for resistance to Puccinia striiformis f.sp tritici. under greenhouse and field conditions. Putative transformants were selected on kanamycin-containing media. Polymease chain reaction indicated that RC24 was transferred into 17 transformants obtained from bombardment of 1,684 immature embryos. Integration of RC24 was confirmed by Southern blot with a RC24-labeled probe and expression of RC24 was verified by RT-PCR. Nine transgenic T1 lines exhibited enhanced resistance to stripe rust infection with lines XN8 and BF4 showing the highest level of resistance. Southern blot hybridization confirmed the stable inheritance of RC24 in transgenic T1 plants. Resistance to stripe rust in transgenic T2 and T3 XN8 and BF4 plants was confirmed over two consecutive years in the field. Increased yield (27-36 %) was recorded for transgenic T2 and T3 XN8 and BF4 plants compared to controls. These results suggest that rice class I chitinase RC24 can be used to engineer stripe rust resistance in wheat.

Analyzing and predicting the risk of death in stroke patients using machine learning.

Background: Stroke is an acute disorder and dysfunction of the focal neurological system that has long been recognized as one of the leading causes of death and severe disability in most regions globally. This study aimed to supplement and exploit multiple comorbidities, laboratory tests and demographic factors to more accurately predict death related to stroke, and furthermore, to make inferences about the heterogeneity of treatment in stroke patients to guide better treatment planning. Methods: We extracted data from the Medical Information Mart from the Intensive Care (MIMIC)-IV database. We compared the distribution of the demographic factors between the control and death groups. Subsequently, we also developed machine learning (ML) models to predict mortality among stroke patients. Furthermore, we used meta-learner to recognize the heterogeneity effects of warfarin and human albumin. We comprehensively evaluated and interpreted these models using Shapley Additive Explanation (SHAP) analysis. Results: We included 7,483 patients with MIMIC-IV in this study. Of these, 1,414 (18.9%) patients died during hospitalization or 30 days after discharge. We found that the distributions of age, marital status, insurance type, and BMI differed between the two groups. Our machine learning model achieved the highest level of accuracy to date in predicting mortality in stroke patients. We also observed that patients who were consistent with the model determination had significantly better survival outcomes than the inconsistent population and were better than the overall treatment group. Conclusion: We used several highly interpretive machine learning models to predict stroke prognosis with the highest accuracy to date and to identify heterogeneous treatment effects of warfarin and human albumin in stroke patients. Our interpretation of the model yielded a number of findings that are consistent with clinical knowledge and warrant further study and verification.