ChemMORT: an automatic ADMET optimization platform using deep learning and multi-objective particle swarm optimization.

Drug discovery and development constitute a laborious and costly undertaking. The success of a drug hinges not only good efficacy but also acceptable absorption, distribution, metabolism, elimination, and toxicity (ADMET) properties. Overall, up to 50% of drug development failures have been contributed from undesirable ADMET profiles. As a multiple parameter objective, the optimization of the ADMET properties is extremely challenging owing to the vast chemical space and limited human expert knowledge. In this study, a freely available platform called Chemical Molecular Optimization, Representation and Translation (ChemMORT) is developed for the optimization of multiple ADMET endpoints without the loss of potency (https://cadd.nscc-tj.cn/deploy/chemmort/). ChemMORT contains three modules: Simplified Molecular Input Line Entry System (SMILES) Encoder, Descriptor Decoder and Molecular Optimizer. The SMILES Encoder can generate the molecular representation with a 512-dimensional vector, and the Descriptor Decoder is able to translate the above representation to the corresponding molecular structure with high accuracy. Based on reversible molecular representation and particle swarm optimization strategy, the Molecular Optimizer can be used to effectively optimize undesirable ADMET properties without the loss of bioactivity, which essentially accomplishes the design of inverse QSAR. The constrained multi-objective optimization of the poly (ADP-ribose) polymerase-1 inhibitor is provided as the case to explore the utility of ChemMORT.

Reducing false positive rate of docking-based virtual screening by active learning.

Machine learning-based scoring functions (MLSFs) have become a very favorable alternative to classical scoring functions because of their potential superior screening performance. However, the information of negative data used to construct MLSFs was rarely reported in the literature, and meanwhile the putative inactive molecules recorded in existing databases usually have obvious bias from active molecules. Here we proposed an easy-to-use method named AMLSF that combines active learning using negative molecular selection strategies with MLSF, which can iteratively improve the quality of inactive sets and thus reduce the false positive rate of virtual screening. We chose energy auxiliary terms learning as the MLSF and validated our method on eight targets in the diverse subset of DUD-E. For each target, we screened the IterBioScreen database by AMLSF and compared the screening results with those of the four control models. The results illustrate that the number of active molecules in the top 1000 molecules identified by AMLSF was significantly higher than those identified by the control models. In addition, the free energy calculation results for the top 10 molecules screened out by the AMLSF, null model and control models based on DUD-E also proved that more active molecules can be identified, and the false positive rate can be reduced by AMLSF.

Identification and expression analysis of XIP gene family members in rice.

Xylanase inhibitor proteins (XIP) are widely distributed in the plant kingdom, and also exist in rice. However, a systematic bioinformatics analysis of this gene family in rice (OsXIP) has not been conducted to date. In this study, we identified 32 members of the OsXIP gene family and analyzed their physicochemical properties, chromosomal localization, gene structure, protein structure, expression profiles, and interaction networks. Our results indicated that OsXIP genes exhibit an uneven distribution across eight rice chromosomes. These genes generally feature a low number of introns or are intronless, all family members, except for OsXIP20, contain two highly conserved motifs, namely Motif 8 and Motif 9. In addition, it is worth noting that the promoter regions of OsXIP gene family members feature a widespread presence of abscisic acid response elements (ABRE) and gibberellin response elements (GARE-motif and TATC-box). Quantitative Real-time PCR (qRT-PCR) analysis unveiled that the expression of OsXIP genes exhibited higher levels in leaves and roots, with considerable variation in the expression of each gene in these tissues both prior to and following treatments with abscisic acid (ABA) and gibberellin (GA3). Protein interaction studies and microRNA (miRNA) target prediction showed that OsXIP engages with key elements within the hormone-responsive and drought signaling pathways. The qRT-PCR suggested osa-miR2927 as a potential key regulator in the rice responding to drought stress, functioning as tissue-specific and temporally regulation. This study provides a theoretical foundation for further analysis of the functions within the OsXIP gene family.

Design, synthesis and herbicidal activity of novel cyclohexanedione derivations containing pyrazole and pyridine groups as potential HPPD inhibitors.

4-Hydroxyphenylpyruvate dioxygenase (EC 1.13.11.27; HPPD) is one of the important target enzymes in the development of herbicides. To discover novel HPPD inhibitors with unique molecular, 39 cyclohexanedione derivations containing pyrazole and pyridine groups were designed and synthesized. The preliminary herbicidal activity test results showed that some compounds had obvious inhibitory effects on monocotyledon and dicotyledonous weeds. The herbicidal spectrums of the highly active compounds were further determined, and the compound G31 exhibited the best inhibitory rate over 90% against Plantago depressa Willd and Capsella bursa-pastoris at the dosages of 75.0 and 37.5 g ai/ha, which is comparable to the control herbicide mesotrione. Moreover, compound G31 showed excellent crop safety, with less than or equal to 10% injury rates to corn, sorghum, soybean and cotton at a dosage of 225 g ai/ha. Molecular docking and molecular dynamics simulation analysis revealed that the compound G31 could stably bind to Arabidopsis thaliana HPPD (AtHPPD). This study indicated that the compound G31 could be used as a lead molecular structure for the development of novel HPPD inhibitors, which provided an idea for the design of new herbicides with unique molecular scaffold.

Prevalence, predictors, and outcomes of acute respiratory distress syndrome in severe stroke.

OBJECTIVES: Patients with severe stroke are at high risk of developing acute respiratory distress syndrome (ARDS), but this severe complication was often under-diagnosed and rarely explored in stroke patients. We aimed to investigate the prevalence, early predictors, and outcomes of ARDS in severe stroke. METHODS: This prospective study included consecutive patients admitted to neurological intensive care unit (neuro-ICU) with severe stroke, including acute ischemic stroke, intracerebral hemorrhage, and subarachnoid hemorrhage. The incidence of ARDS was examined, and baseline characteristics and severity scores on admission were investigated as potential early predictors for ARDS. The in-hospital mortality, length of neuro-ICU stay, the total cost in neuro-ICU, and neurological functions at 90 days were explored. RESULTS: Of 140 patients included, 35 (25.0%) developed ARDS. Over 90% of ARDS cases occurred within 1 week of admission. Procalcitonin (OR 1.310 95% CI 1.005-1.707, P = 0.046) and PaO2/FiO2 on admission (OR 0.986, 95% CI 0.979-0.993, P < 0.001) were independently associated with ARDS, and high brain natriuretic peptide (OR 0.994, 95% CI 0.989-0.998, P = 0.003) was a red flag biomarker warning that the respiratory symptoms may be caused by cardiac failure rather than ARDS. ARDS patients had longer stays and higher expenses in neuro-ICU. Among patients with ARDS, 25 (62.5%) were moderate or severe ARDS. All the patients with moderate to severe ARDS had an unfavorable outcome at 90 days. CONCLUSIONS: ARDS is common in patients with severe stroke, with most cases occurring in the first week of admission. Procalcitonin and PaO2/FiO2 on admission are early predictors of ARDS. ARDS worsens both short-term and long-term outcomes. The conflict in respiratory support strategies between ARDS and severe stroke needs to be further studied.

Time-Resolved Extensional Rheo-NMR Spectroscopy for Investigating Polymer Nanocomposites under Deformation.

Understanding the microstructure change of polymer nanocomposites (PNCs) under elongation deformation at the molecular level is the key to coupling structure-property relationships of PNCs. In this study, we developed our recently proposed in situ extensional rheology NMR device, Rheo-spin NMR, which can simultaneously obtain both the macroscopic stress-strain curves and the microscopic molecular information with the total sample weight of ∼6 mg. This enables us to conduct a detailed investigation of the evolution of the interfacial layer and polymer matrix in nonlinear elongational strain softening behaviors. A quantitative method is established for in situ analysis of (1) the fraction of the interfacial layer and (2) the network strand orientation distribution of the polymer matrix based on the molecular stress function model under active deformation. The results show that for the current highly filled silicone nanocomposite system, the influence of the interfacial layer fraction on mechanical property change during small amplitude deformation is quite minor, while the main role is reflected in rubber network strand reorientation. The Rheo-spin NMR device and the established analysis method are expected to facilitate the understanding of the reinforcement mechanism of PNC, which can be further applied to understand the deformation mechanism of other systems, i.e., glassy and semicrystalline polymers and the vascular tissues.

Improving structure-based virtual screening performance via learning from scoring function components.

Scoring functions (SFs) based on complex machine learning (ML) algorithms have gradually emerged as a promising alternative to overcome the weaknesses of classical SFs. However, extensive efforts have been devoted to the development of SFs based on new protein-ligand interaction representations and advanced alternative ML algorithms instead of the energy components obtained by the decomposition of existing SFs. Here, we propose a new method named energy auxiliary terms learning (EATL), in which the scoring components are extracted and used as the input for the development of three levels of ML SFs including EATL SFs, docking-EATL SFs and comprehensive SFs with ascending VS performance. The EATL approach not only outperforms classical SFs for the absolute performance (ROC) and initial enrichment (BEDROC) but also yields comparable performance compared with other advanced ML-based methods on the diverse subset of Directory of Useful Decoys: Enhanced (DUD-E). The test on the relatively unbiased actives as decoys (AD) dataset also proved the effectiveness of EATL. Furthermore, the idea of learning from SF components to yield improved screening power can also be extended to other docking programs and SFs available.

BioMedR: an R/CRAN package for integrated data analysis pipeline in biomedical study.

BACKGROUND: With the increasing development of biotechnology and information technology, publicly available data in chemistry and biology are undergoing explosive growth. Such wealthy information in these resources needs to be extracted and then transformed to useful knowledge by various data mining methods. However, a main computational challenge is how to effectively represent or encode molecular objects under investigation such as chemicals, proteins, DNAs and even complicated interactions when data mining methods are employed. To further explore these complicated data, an integrated toolkit to represent different types of molecular objects and support various data mining algorithms is urgently needed. RESULTS: We developed a freely available R/CRAN package, called BioMedR, for molecular representations of chemicals, proteins, DNAs and pairwise samples of their interactions. The current version of BioMedR could calculate 293 molecular descriptors and 13 kinds of molecular fingerprints for small molecules, 9920 protein descriptors based on protein sequences and six types of generalized scale-based descriptors for proteochemometric modeling, more than 6000 DNA descriptors from nucleotide sequences and six types of interaction descriptors using three different combining strategies. Moreover, this package realized five similarity calculation methods and four powerful clustering algorithms as well as several useful auxiliary tools, which aims at building an integrated analysis pipeline for data acquisition, data checking, descriptor calculation and data modeling. CONCLUSION: BioMedR provides a comprehensive and uniform R package to link up different representations of molecular objects with each other and will benefit cheminformatics/bioinformatics and other biomedical users. It is available at: https://CRAN.R-project.org/package=BioMedR and https://github.com/wind22zhu/BioMedR/.

Scopy: an integrated negative design python library for desirable HTS/VS database design.

BACKGROUND: High-throughput screening (HTS) and virtual screening (VS) have been widely used to identify potential hits from large chemical libraries. However, the frequent occurrence of 'noisy compounds' in the screened libraries, such as compounds with poor drug-likeness, poor selectivity or potential toxicity, has greatly weakened the enrichment capability of HTS and VS campaigns. Therefore, the development of comprehensive and credible tools to detect noisy compounds from chemical libraries is urgently needed in early stages of drug discovery. RESULTS: In this study, we developed a freely available integrated python library for negative design, called Scopy, which supports the functions of data preparation, calculation of descriptors, scaffolds and screening filters, and data visualization. The current version of Scopy can calculate 39 basic molecular properties, 3 comprehensive molecular evaluation scores, 2 types of molecular scaffolds, 6 types of substructure descriptors and 2 types of fingerprints. A number of important screening rules are also provided by Scopy, including 15 drug-likeness rules (13 drug-likeness rules and 2 building block rules), 8 frequent hitter rules (four assay interference substructure filters and four promiscuous compound substructure filters), and 11 toxicophore filters (five human-related toxicity substructure filters, three environment-related toxicity substructure filters and three comprehensive toxicity substructure filters). Moreover, this library supports four different visualization functions to help users to gain a better understanding of the screened data, including basic feature radar chart, feature-feature-related scatter diagram, functional group marker gram and cloud gram. CONCLUSION: Scopy provides a comprehensive Python package to filter out compounds with undesirable properties or substructures, which will benefit the design of high-quality chemical libraries for drug design and discovery. It is freely available at https://github.com/kotori-y/Scopy.

Learning to SMILES: BAN-based strategies to improve latent representation learning from molecules.

Computational methods have become indispensable tools to accelerate the drug discovery process and alleviate the excessive dependence on time-consuming and labor-intensive experiments. Traditional feature-engineering approaches heavily rely on expert knowledge to devise useful features, which could be costly and sometimes biased. The emerging deep learning (DL) methods deliver a data-driven method to automatically learn expressive representations from complex raw data. Inspired by this, researchers have attempted to apply various deep neural network models to simplified molecular input line entry specification (SMILES) strings, which contain all the composition and structure information of molecules. However, current models usually suffer from the scarcity of labeled data. This results in a low generalization ability of SMILES-based DL models, which prevents them from competing with the state-of-the-art computational methods. In this study, we utilized the BiLSTM (bidirectional long short term merory) attention network (BAN) in which we employed a novel multi-step attention mechanism to facilitate the extracting of key features from the SMILES strings. Meanwhile, SMILES enumeration was utilized as a data augmentation method in the training phase to substantially increase the number of labeled data and enlarge the probability of mining more patterns from complex SMILES. We again took advantage of SMILES enumeration in the prediction phase to rectify model prediction bias and provide a more accurate prediction. Combined with the BAN model, our strategies can greatly improve the performance of latent features learned from SMILES strings. In 11 canonical absorption, distribution, metabolism, excretion and toxicity-related tasks, our method outperformed the state-of-the-art approaches.

QSAR-assisted-MMPA to expand chemical transformation space for lead optimization.

Matched molecular pairs analysis (MMPA) has become a powerful tool for automatically and systematically identifying medicinal chemistry transformations from compound/property datasets. However, accurate determination of matched molecular pair (MMP) transformations largely depend on the size and quality of existing experimental data. Lack of high-quality experimental data heavily hampers the extraction of more effective medicinal chemistry knowledge. Here, we developed a new strategy called quantitative structure-activity relationship (QSAR)-assisted-MMPA to expand the number of chemical transformations and took the logD7.4 property endpoint as an example to demonstrate the reliability of the new method. A reliable logD7.4 consensus prediction model was firstly established, and its applicability domain was strictly assessed. By applying the reliable logD7.4 prediction model to screen two chemical databases, we obtained more high-quality logD7.4 data by defining a strict applicability domain threshold. Then, MMPA was performed on the predicted data and experimental data to derive more chemical rules. To validate the reliability of the chemical rules, we compared the magnitude and directionality of the property changes of the predicted rules with those of the measured rules. Then, we compared the novel chemical rules generated by our proposed approach with the published chemical rules, and found that the magnitude and directionality of the property changes were consistent, indicating that the proposed QSAR-assisted-MMPA approach has the potential to enrich the collection of rule types or even identify completely novel rules. Finally, we found that the number of the MMP rules derived from the experimental data could be amplified by the predicted data, which is helpful for us to analyze the medicinal chemical rules in local chemical environment. In summary, the proposed QSAR-assisted-MMPA approach could be regarded as a very promising strategy to expand the chemical transformation space for lead optimization, especially when no enough experimental data can support MMPA.

PySmash: Python package and individual executable program for representative substructure generation and application.

BACKGROUND: Substructure screening is widely applied to evaluate the molecular potency and ADMET properties of compounds in drug discovery pipelines, and it can also be used to interpret QSAR models for the design of new compounds with desirable physicochemical and biological properties. With the continuous accumulation of more experimental data, data-driven computational systems which can derive representative substructures from large chemical libraries attract more attention. Therefore, the development of an integrated and convenient tool to generate and implement representative substructures is urgently needed. RESULTS: In this study, PySmash, a user-friendly and powerful tool to generate different types of representative substructures, was developed. The current version of PySmash provides both a Python package and an individual executable program, which achieves ease of operation and pipeline integration. Three types of substructure generation algorithms, including circular, path-based and functional group-based algorithms, are provided. Users can conveniently customize their own requirements for substructure size, accuracy and coverage, statistical significance and parallel computation during execution. Besides, PySmash provides the function for external data screening. CONCLUSION: PySmash, a user-friendly and integrated tool for the automatic generation and implementation of representative substructures, is presented. Three screening examples, including toxicophore derivation, privileged motif detection and the integration of substructures with machine learning (ML) models, are provided to illustrate the utility of PySmash in safety profile evaluation, therapeutic activity exploration and molecular optimization, respectively. Its executable program and Python package are available at https://github.com/kotori-y/pySmash.

ChemFLuo: a web-server for structure analysis and identification of fluorescent compounds.

BACKGROUND: Fluorescent detection methods are indispensable tools for chemical biology. However, the frequent appearance of potential fluorescent compound has greatly interfered with the recognition of compounds with genuine activity. Such fluorescence interference is especially difficult to identify as it is reproducible and possesses concentration-dependent characteristic. Therefore, the development of a credible screening tool to detect fluorescent compounds from chemical libraries is urgently needed in early stages of drug discovery. RESULTS: In this study, we developed a webserver ChemFLuo for fluorescent compound detection, based on two large and high-quality training datasets containing 4906 blue and 8632 green fluorescent compounds. These molecules were used to construct a group of prediction models based on the combination of three machine learning algorithms and seven types of molecular representations. The best blue fluorescence prediction model achieved with balanced accuracy (BA) = 0.858 and area under the receiver operating characteristic curve (AUC) = 0.931 for the validation set, and BA = 0.823 and AUC = 0.903 for the test set. The best green fluorescence prediction model achieved the prediction accuracy with BA = 0.810 and AUC = 0.887 for the validation set, and BA = 0.771 and AUC = 0.852 for the test set. Besides prediction model, 22 blue and 16 green representative fluorescent substructures were summarized for the screening of potential fluorescent compounds. The comparison with other fluorescence detection tools and theapplication to external validation sets and large molecule libraries have demonstrated the reliability of prediction model for fluorescent compound detection. CONCLUSION: ChemFLuo is a public webserver to filter out compounds with undesirable fluorescent properties, which will benefit the design of high-quality chemical libraries for drug discovery. It is freely available at http://admet.scbdd.com/chemfluo/index/.

Systematic comparison of ligand-based and structure-based virtual screening methods on poly (ADP-ribose) polymerase-1 inhibitors.

The poly (ADP-ribose) polymerase-1 (PARP1) has been regarded as a vital target in recent years and PARP1 inhibitors can be used for ovarian and breast cancer therapies. However, it has been realized that most of PARP1 inhibitors have disadvantages of low solubility and permeability. Therefore, by discovering more molecules with novel frameworks, it would have greater opportunities to apply it into broader clinical fields and have a more profound significance. In the present study, multiple virtual screening (VS) methods had been employed to evaluate the screening efficiency of ligand-based, structure-based and data fusion methods on PARP1 target. The VS methods include 2D similarity screening, structure-activity relationship (SAR) models, docking and complex-based pharmacophore screening. Moreover, the sum rank, sum score and reciprocal rank were also adopted for data fusion methods. The evaluation results show that the similarity searching based on Torsion fingerprint, six SAR models, Glide docking and pharmacophore screening using Phase have excellent screening performance. The best data fusion method is the reciprocal rank, but the sum score also performs well in framework enrichment. In general, the ligand-based VS methods show better performance on PARP1 inhibitor screening. These findings confirmed that adding ligand-based methods to the early screening stage will greatly improve the screening efficiency, and be able to enrich more highly active PARP1 inhibitors with diverse structures.

IL-17A-mediated mitochondrial dysfunction induces pyroptosis in colorectal cancer cells and promotes CD8 + T-cell tumour infiltration.

BACKGROUND: Interleukin-17A (IL-17A), a proinflammatory cytokine primarily secreted by Th17 cells, γδT cells and natural killer T (NKT) cells, performs essential roles in the microenvironment of certain inflammation-related tumours by regulating cancer growth and tumour elimination proved in previous literature. In this study, the mechanism of IL-17A that induces mitochondrial dysfunction promoted pyroptosis has been explored in colorectal cancer cells. METHOD: The records of 78 patients diagnosed with CRC were reviewed via the public database to evaluate clinicopathological parameters and prognosis associations of IL-17A expression. The colorectal cancer cells were treated with IL-17A, and the morphological characteristics of those cells were indicated by scanning electron microscope and transmission electron microscope. After IL-17A treatment, mitochondrial dysfunction was tested by mitochondrial membrane potential (MMP) and reactive oxygen species (ROS). The expression of pyroptosis associated proteins including cleaved caspase-4, cleaved gasdermin-D (GSDMD), IL-1ß, receptor activator of nuclear NOD-like receptor family pyrin domain containing 3 (NLRP3), apoptosis-associated speck like protein containing a card (ASC), and factor-kappa B was measured through western blotting. RESULTS: Positive IL-17A protein expression was observed in CRC compared to the non-tumour tissue. IL-17A expression indicates a better differentiation, earlier stage, and better overall survival in CRC. IL-17A treatment could induce mitochondrial dysfunction and stimulate intracellular reactive oxygen species (ROS) production. Furthermore, IL-17A could promote pyroptosis of colorectal cancer cells and significantly increase the secretion of inflammatory factors. Nevertheless, the pyroptosis induced by IL-17A could be inhibited through the pre-treatment with Mito-TEMPO (a mitochondria-targeted superoxide dismutase mimetic with superoxide and alkyl radical scavenging properties) or Z-LEVD-FMK (caspase-4 inhibitor, fluoromethylketone). Additionally, after being treated with IL-17A, an increasing number of CD8 + T cells showed in mouse-derived allograft colon cancer models. CONCLUSION: IL-17A, as a cytokine mainly secreted by γδT cells in the colorectal tumour immune microenvironment, can regulate the tumour microenvironment in multiple ways. IL-17A could induce mitochondrial dysfunction and pyroptosis through the ROS/NLRP3/caspase-4/GSDMD pathway, and promote intracellular ROS accumulation. In addition, IL-17A can promote the secretion of inflammatory factors such as IL-1ß、IL-18 and immune antigens, and recruit CD8 + T cells to infiltrate tumours.

Structural Analysis and Prediction of Hematotoxicity Using Deep Learning Approaches.

Hematotoxicity has been becoming a serious but overlooked toxicity in drug discovery. However, only a few in silico models have been reported for the prediction of hematotoxicity. In this study, we constructed a high-quality dataset comprising 759 hematotoxic compounds and 1623 nonhematotoxic compounds and then established a series of classification models based on a combination of seven machine learning (ML) algorithms and nine molecular representations. The results based on two data partitioning strategies and applicability domain (AD) analysis illustrate that the best prediction model based on Attentive FP yielded a balanced accuracy (BA) of 72.6%, an area under the receiver operating characteristic curve (AUC) value of 76.8% for the validation set, and a BA of 69.2%, an AUC of 75.9% for the test set. In addition, compared with existing filtering rules and models, our model achieved the highest BA value of 67.5% for the external validation set. Additionally, the shapley additive explanation (SHAP) and atom heatmap approaches were utilized to discover the important features and structural fragments related to hematotoxicity, which could offer helpful tips to detect undesired positive substances. Furthermore, matched molecular pair analysis (MMPA) and representative substructure derivation technique were employed to further characterize and investigate the transformation principles and distinctive structural features of hematotoxic chemicals. We believe that the novel graph-based deep learning algorithms and insightful interpretation presented in this study can be used as a trustworthy and effective tool to assess hematotoxicity in the development of new drugs.

Improved GNNs for Log D7.4 Prediction by Transferring Knowledge from Low-Fidelity Data.

The n-octanol/buffer solution distribution coefficient at pH = 7.4 (log D7.4) is an indicator of lipophilicity, and it influences a wide variety of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties and druggability of compounds. In log D7.4 prediction, graph neural networks (GNNs) can uncover subtle structure-property relationships (SPRs) by automatically extracting features from molecular graphs that facilitate the learning of SPRs, but their performances are often limited by the small size of available datasets. Herein, we present a transfer learning strategy called pretraining on computational data and then fine-tuning on experimental data (PCFE) to fully exploit the predictive potential of GNNs. PCFE works by pretraining a GNN model on 1.71 million computational log D data (low-fidelity data) and then fine-tuning it on 19,155 experimental log D7.4 data (high-fidelity data). The experiments for three GNN architectures (graph convolutional network (GCN), graph attention network (GAT), and Attentive FP) demonstrated the effectiveness of PCFE in improving GNNs for log D7.4 predictions. Moreover, the optimal PCFE-trained GNN model (cx-Attentive FP, Rtest2 = 0.909) outperformed four excellent descriptor-based models (random forest (RF), gradient boosting (GB), support vector machine (SVM), and extreme gradient boosting (XGBoost)). The robustness of the cx-Attentive FP model was also confirmed by evaluating the models with different training data sizes and dataset splitting strategies. Therefore, we developed a webserver and defined the applicability domain for this model. The webserver (http://tools.scbdd.com/chemlogd/) provides free log D7.4 prediction services. In addition, the important descriptors for log D7.4 were detected by the Shapley additive explanations (SHAP) method, and the most relevant substructures of log D7.4 were identified by the attention mechanism. Finally, the matched molecular pair analysis (MMPA) was performed to summarize the contributions of common chemical substituents to log D7.4, including a variety of hydrocarbon groups, halogen groups, heteroatoms, and polar groups. In conclusion, we believe that the cx-Attentive FP model can serve as a reliable tool to predict log D7.4 and hope that pretraining on low-fidelity data can help GNNs make accurate predictions of other endpoints in drug discovery.

Prognostic Significance of CD20 Expression in Children with Philadelphia Chromosome-Negative B-Cell Precursor Acute Lymphoblastic Leukemia.

INTRODUCTION: The prognostic significance of CD20 in pediatric B-cell precursor acute lymphoblastic leukemia (BCP-ALL) remains unclear. Therefore, in this study, we evaluated the prognostic value of CD20 expression in leukemia blasts in pediatric BCP-ALL at our institute. METHODS: Between 2005 and 2017, 796 children with newly diagnosed Philadelphia-negative BCP-ALL were enrolled consecutively; clinical characteristics and treatment outcomes were analyzed and compared between CD20-positive and CD20-negative groups. RESULTS: CD20 positivity was observed in 22.7% of enrolled patients. The analysis of overall and event-free survival showed that white blood cell count ≥50 × 109/L, no ETV6-RUNX1, day 33 minimal residual disease (MRD) ≥0.1%, and week 12 MRD ≥0.01% were independent risk factors. Meanwhile, in the CD20-positive group, week 12 MRD ≥0.01% was the only factor associated with long-term survival. Moreover, subgroup analysis revealed that in patients with extramedullary involvement (p = 0.047), MRD ≥0.1% on day 33 (p = 0.032), or MRD ≥0.01% at week 12 (p = 0.004), CD20 expression led to a poorer outcome compared to those without CD20 expression. CONCLUSIONS: Pediatric BCP-ALL with CD20 expression had unique clinicopathological characteristics, and MRD remained the major prognostic factor. CD20 expression had no prognostic value in pediatric BCP-ALL.

[Congenital pulmonary alveolar proteinosis in a neonate]. / æ–°ç”Ÿå„¿å ˆå¤©æ€§è‚ºæ³¡è›‹ç™½æ²‰ç§¯ç—‡1例.

The male patient was referred to the hospital at 44 days old due to dyspnea after birth and inability to wean off oxygen. His brother died three days after birth due to respiratory failure. The main symptoms observed were respiratory failure, dyspnea, and hypoxemia. A chest CT scan revealed characteristic reduced opacity in both lungs with a "crazy-paving" appearance. The bronchoalveolar lavage fluid (BALF) showed periodic acid-Schiff positive proteinaceous deposits. Genetic testing indicated a compound heterozygous mutation in the ABCA3 gene. The diagnosis for the infant was congenital pulmonary alveolar proteinosis (PAP). Congenital PAP is a significant cause of challenging-to-treat respiratory failure in full-term infants. Therefore, congenital PAP should be considered in infants experiencing persistently difficult-to-treat dyspnea shortly after birth. Early utilization of chest CT scans, BALF pathological examination, and genetic testing may aid in early diagnosis.

Low EVI1 expression at diagnosis predicted poor outcomes in pediatric Ph-negative B cell precursor acute lymphoblastic leukemia patients.

Abnormally high ecotropic viral integration site 1 (EVI1) expression has been recognized as a poor prognostic factor in acute myeloid leukemia patients. However, its prognostic impact in B cell precursor acute lymphoblastic leukemia (BCP-ALL) remains unknown. A total of 176 pediatric Ph-negative BCP-ALL patients who received at least 1 course of chemotherapy and received chemotherapy only during follow-up were retrospectively tested for EVI1 transcript levels by real-time quantitative PCR at diagnosis, and survival analysis was performed. Clinical and EVI1 expression data of 129 pediatric BCP-ALL patients were downloaded from therapeutically applicable research to generate effective treatments (TARGET) database for validation. In our cohort, the median EVI1 transcript level was 0.33% (range, 0.0068-136.2%), and 0.10% was determined to be the optimal cutoff value for patient grouping by receiver operating characteristic curve analysis. Low EVI1 expression (<0.10%) was significantly related to lower 5-year relapse-free survival (RFS) and overall survival (OS) rates (P = 0.017 and 0.018, respectively). Multivariate analysis showed that EVI1 expression <0.10% was an independent adverse prognostic factor for RFS and OS. TARGET data showed that low EVI1 expression tended to be related to a lower 5-year OS rate (P = 0.066). In conclusion, low EVI1 expression at diagnosis could predict poor outcomes in pediatric Ph-negative BCP-ALL patients receiving chemotherapy.Supplemental data for this article is available online at https://doi.org/10.1080/08880018.2021.1939818 .