Traditional Screening Research Articles

Comparison of a dual antibody and antigen HCV immunoassay to standard of care algorithmic testing.

The Centers for Disease Control and Prevention (CDC) guidelines for hepatitis C virus (HCV) testing, although effective, may miss crucial diagnostic opportunities. The goal of this study was to assess the utility of an antibody (Ab) and antigen (Ag) combination immunoassay as an alternative to traditional HCV screening. Remnant specimens from 1,341 patients with concurrent third-generation serologic (Roche anti-HCV-II) and nucleic acid amplification testing (NAAT) were assessed using the HCV Duo Ab/Ag immunoassay (Roche). Patient demographics, risk factors, and standard of care (SOC) laboratory results from the medical records were recorded. Overall, 99.0% (197/199) of the HCV Duo Ab+/Ag+specimens accurately identified active infections as confirmed by NAAT, and 99.9% (670/671) Ab-/Ag- samples corresponded to those without HCV infections. Individually, the HCV Duo Ab component demonstrated a 95.6% positive percent agreement (PPA) (95% CI = 93.8-96.9) and 99.1% negative percent agreement (NPA) (98.8-99.6) compared with SOC anti-HCV II Ab assay. The HCV Duo Ag had a 73.5% PPA (67.9-78.4) and 99.8% NPA (99.3-100) with NAAT. Among RNA+ specimens, 73.4% (197/267) were HCV Duo Ag+, and 265/267 (99.3%) were successfully detected on the HCV Duo Ab component. Notably, 5/7 (71.4%) Ab-/RNA +specimens were detected by HCV Duo, which would have been missed by traditional algorithmic testing. Fourth generation HCV Duo Ab/Ag assay demonstrated comparable performance to SOC testing and shortens the diagnostic window but does not eliminate the need for NAAT in all patients. Ab/Ag testing identified several Ab-/RNA+ cases, a subgroup often undiagnosed by current algorithmic testing, demonstrating promise for improved diagnostic efficiency and accuracy in HCV detection.IMPORTANCEThis study highlights the potential of a combined hepatitis C virus (HCV) Duo antibody (Ab) and antigen (Ag) immunoassay to improve early detection of HCV infections. Traditional Ab-only screening methods recommended by the Centers for Disease Control and Prevention may miss early-stage infections. The HCV Duo assay showed high accuracy, detecting nearly all active infections confirmed by nucleic acid amplification testing. Dual detection of HCV Ab and Ag shortens the diagnostic window, enabling intervention and treatment in a single visit, which is crucial for improving patient outcomes and reducing HCV transmission, especially in areas with limited access to confirmatory molecular testing.

Multifocal, multiphenotypic tumours arising from an MTOR mutation acquired in early embryogenesis.

Embryogenesis is a vulnerable time. Mutations in developmental cells can result in the wide dissemination of cells predisposed to disease within mature organs. We characterised the evolutionary history of four synchronous renal tumours from a 14-year-old girl using whole genome sequencing alongside single cell and bulk transcriptomic sequencing. Phylogenetic reconstruction timed the origin of all tumours to a multipotent embryonic cell committed to the right kidney, around 4 weeks post-conception. Biochemical and structural analysis of their shared MTOR mutation, absent from normal tissues, demonstrates enhanced protein flexibility, enabling a FAT domain hinge to dramatically increase activity of mTORC1 and mTORC2. Developmental mutations, not usually detected in traditional genetic screening, have vital clinical importance in guiding prognosis, targeted treatment, and family screening decisions for paediatric tumours.

Screening of oxytetracycline-degrading strains in the intestine of the black soldier fly larvae and their degradation characteristics

The presence of excessive antibiotic residues poses a significant threat to human health and the environment. This study was designed to identify an effective oxytetracycline (OTC)-degrading strain through the screening of the intestine of black soldier fly larvae (BSFL). A strain designated “B2” was selected using a series of traditional microbial screening methods. It could be identified as Enterococcus faecalis by Gram staining and 16S rDNA sequencing, with a similarity of 99.93%. Its ability to degrade OTC was then assessed using high-performance liquid chromatography (HPLC). The degradation of the strain was characterized using a one-way test to assess the effects of the substrate concentration, inoculum amount, and initial pH on the degrading bacteria. The results indicate that strain B2 exhibited optimal OTC-degrading performance at a substrate concentration of 50 mg/L, with an inoculum amount of 6% and a pH value of 5.0. Specifically, strain B2 achieved degradation rates of 71.11%, 56.14%, and 45.03%. These findings demonstrate the effectiveness of strain B2 in degrading OTC, indicating its potential for use in environmental remediation efforts.

A New Method for Scoliosis Screening Incorporating Deep Learning With Back Images.

Retrospective observational study. Scoliosis is commonly observed in adolescents, with a world0wide prevalence of 0.5%. It is prone to be overlooked by parents during its early stages, as it often lacks overt characteristics. As a result, many individuals are not aware that they may have scoliosis until the symptoms become quite severe, significantly affecting the physical and mental well-being of patients. Traditional screening methods for scoliosis demand significant physician effort and require unnecessary radiography exposure; thus, implementing large-scale screening is challenging. The application of deep learning algorithms has the potential to reduce unnecessary radiation risks as well as the costs of scoliosis screening. The data of 247 scoliosis patients observed between 2008 and 2021 were used for training. The dataset included frontal, lateral, and back upright images as well as X-ray images obtained during the same period. We proposed and validated deep learning algorithms for automated scoliosis screening using upright back images. The overall process involved the localization of the back region of interest (ROI), spinal region segmentation, and Cobb angle measurements. The results indicated that the accuracy of the Cobb angle measurement was superior to that of the traditional human visual recognition method, providing a concise and convenient scoliosis screening capability without causing any harm to the human body. The method was automated, accurate, concise, and convenient. It is potentially applicable to a wide range of screening methods for the detection of early scoliosis.

Design and optimization of refractive index biosensor for MDA-MB-231 and MCF-7 breast cancer biomarker detection

Breast cancer is the leading malignancy in women and the 2nd widespread cancer globally. Earlier identification of breast cancer can improve treatment outcomes and prevent metastasis beyond the breast. Traditional screening tests are not sensitive enough for early diagnosis and have extended detection periods. Recent studies have explored diversified Breast cancer biosensor techniques, including optical, electrical, electrochemical, and mechanical biosensors. This paper nominates a circlet with a large plus sign refraction indices biosensor for the evaluation of two distinct breast cancer cells namely, MDA-MB-231 and MCF-7. The supreme sensitivity has been viewed as 1714.28 nm/RIU for the MDA-MB-231 and 1714.28 nm/RIU for the MCF-7. The supreme quality factor (QF) value for UC1(usual cell of MDA-MB-231) is 10.52, for CC1(cancer cell of MDA-MB-231) is 11.94, for UC2 (usual cell of MCF-7) is 10.64, and for CC2 (cancer cell of MCF-7) is 12.09. The minimal detection value (DL) for UC1 is 0.1573, CC1 is 0.1360, UC2 is 0.1554, and CC2 is 0.1341. This nominated sensor has the potential to sense breast tumor biomarkers.

Harnessing artificial intelligence for efficient systematic reviews: A case study in ecosystem condition indicators

Effective evidence synthesis is important for the integration of scientific research into decision-making. However, fully depicting the vast mosaic of concepts and applications in environmental sciences and ecology often entails a substantial workload. New Artificial Intelligence (AI) tools present an attractive option for addressing this challenge but require sufficient validation to match the vigorous standards of a systematic review. This article demonstrates the use of generative AI in the selection of relevant literature as part of a systematic review on indicators of ecosystem condition. We highlight, through the development of an optimal prompt to communicate inclusion and exclusion criteria, the need to describe ecosystem condition as a multidimensional concept whilst also maintaining clarity on what does not meet the criteria of comprehensiveness. We show that, although not completely infallible, the GPT-3.5 model significantly outperforms traditional literature screening processes in terms of speed and efficiency whilst correctly selecting 83 % of relevant literature for review. Our study highlights the importance of precision in prompt design and the setting of query parameters for the AI model and opens the perspective for future work using language models to contextualize complex concepts in the environmental sciences. Future development of this methodology in tandem with the continued evolution of the accessibility and capacity of AI tools presents a great potential to improve evidence synthesis through gains in efficiency and possible scope.

Multiobjective Optimization Strategy for Enhancing the Efficiency and Quality of Organic Thin-Film Manufacturing with Electrohydrodynamic Atomization Coating.

Electrohydrodynamic atomization coating technology is well-suited for micro-/nanoscale thin-film additive manufacturing. However, there are still some challenges in quality control and parameter adjustment during the coating process. Especially when coating on nonconductive and nonhydrophilic substrates, film quality and thickness uniformity are difficult to control. This paper proposes an optimization strategy for enhancing the efficiency and quality of thin-film manufacturing on nonconductive, nonhydrophilic glass substrates. In this paper, a visual inspection system was developed for in situ inspection and identification of droplet deposition states in the substrate surface. Then, the statistical relationship between the operating parameters and the quality of the deposition state was analyzed by response surface methodology. On this basis, machine learning models and intelligent recommendation frameworks for small data sets were developed to rapidly optimize operating parameters and improve the quality of thin-film coating. Optimization strategy developed by applying the principles of statistical modeling, analysis of variance, and global optimization are more efficient and less costly than traditional parameter screening methods. The experimental results show that optimum deposition quality can be obtained with the recommended operating parameters. And, validation results show a 12.8% improvement in film thickness uniformity. At the same time, no mura defects appeared on the thin-film surface. The proposed optimization strategy can improve the efficiency and quality of additive manufacturing of micro and nano thin films and is beneficial for advancing industrial applications of the electrohydrodynamic atomization coating.

Comparing psychometric characteristics of a computerized cognitive test (BrainCheck Assess) against the Montreal cognitive assessment.

Previous validation studies demonstrated that BrainCheck Assess (BC-Assess), a computerized cognitive test battery, can reliably and sensitively distinguish individuals with different levels of cognitive impairment (i.e., normal cognition (NC), mild cognitive impairment (MCI), and dementia). Compared with other traditional paper-based cognitive screening instruments commonly used in clinical practice, the Montreal Cognitive Assessment (MoCA) is generally accepted to be among the most comprehensive and robust screening tools, with high sensitivity/specificity in distinguishing MCI from NC and dementia. In this study, we examined: (1) the linear relationship between BC-Assess and MoCA and their equivalent cut-off scores, and (2) the extent to which they agree on their impressions of an individual's cognitive status. A subset of participants (N = 55; age range 54-94, mean/SD = 80/9.5) from two previous studies who took both the MoCA and BC-Assess were included in this analysis. Linear regression was used to calculate equivalent cut-off scores for BC-Assess based on those originally recommended for the MoCA to differentiate MCI from NC (cut-off = 26), and dementia from MCI (cut-off = 19). Impression agreement between the two instruments were measured through overall agreement (OA), positive percent agreement (PPA), and negative percent agreement (NPA). A high Pearson correlation coefficient of 0.77 (CI = 0.63-0.86) was observed between the two scores. According to this relationship, MoCA cutoffs of 26 and 19 correspond to BC-Assess scores of 89.6 and 68.5, respectively. These scores are highly consistent with the currently recommended BC-Assess cutoffs (i.e., 85 and 70). The two instruments also show a high degree of agreement in their impressions based on their recommended cut-offs: (i) OA = 70.9%, PPA = 70.4%, NPA = 71.4% for differentiating dementia from MCI/NC; (ii) OA = 83.6%, PPA = 84.1%, NPA = 81.8% for differentiating dementia/MCI from NC. This study provides further validation of BC-Assess in a sample of older adults by showing its high correlation and agreement in impression with the widely used MoCA.

Diagnostic Accuracy of Artificial Intelligence-Based Systems for Detecting Diabetic Retinopathy: A Systematic Review

Diabetic retinopathy (DR) represents a leading cause of blindness worldwide, early detection is critical to prevent vision loss. However, traditional screening methods, which rely on human experts, prove to be costly and time-consuming. The systematic review aims to assess the validity of artificial intelligence (AI) as a screening tool for detecting DR among diabetic patients. A systematic literature search was performed of the following databases: PubMed, Scopus, CINAHL, and Web of Science. The last date of our search was January 31, 2024. We included all observational studies, including cohort, case–control and cross-sectional studies and evaluated their quality using the Joanna Briggs Institute tool. We included diagnostic test accuracy studies evaluating the use of AI algorithms for DR screening in patients with diabetes. Studies were excluded if they exclusively assessed diagnostic accuracy for DR that did not use AI algorithms as a diagnostic tool and studies with incomplete or inaccessible data. Thirteen studies with sample sizes ranging from 69 to 1378 participants, reported good sensitivity of AI for detecting visually threatening DR (VTDR). The lowest sensitivity was 89.2%, and the highest was 100%. In terms of specificity, Any DR exhibited higher specificity compared to RDR and VTDR, ranging from 80.2% to 100%. The sensitivity and specificity of the Artificial Intelligence (AI)-based tools available for DR screening was considered acceptable, especially in detecting VTDR and Any DR, was regarded as good. These results implied the potential usefulness of these tools for DR screening in settings with limited resources. However, further high-quality comparative studies were deemed necessary to evaluate their effectiveness in real-world clinical settings.

In Situ Raman Hyperspectral Analysis of Microbial Colonies for Secondary Metabolites Screening.

Since the discovery of penicillin, a vast array of microbial antibiotics has been identified and applied in the medical field. Globally, the search for drug candidates via microbial screening is ongoing. Traditional screening methods, however, are time-consuming and require labor-intensive sample processing, significantly reducing throughput. This research introduces a Raman spectroscopy-based screening system tailored to the in situ analysis of microbial colonies on solid culture media. Employing multivariate curve resolution-alternating least-squares (MCR-ALS) for spectral decomposition, our approach reveals the production of secondary metabolites at the single colony level. We enhanced the microbial culture method, enabling direct, high signal-to-noise (S/N) ratio Raman spectroscopic measurements of colonies of Escherichia coli and actinomycetes species. Through semisupervised MCR analysis using the known spectra of actinorhodin and undecylprodigiosin as references, we accurately assessed the production of these compounds by Streptomyces coelicolor A3(2). Furthermore, we herein successfully detected the production of amphotericin B by Streptomyces nodosus, even in the absence of prior spectral information. This demonstrates the potential of our technique in the discovery of secondary metabolites. In addition to enabling the detection of the above-mentioned compounds, this analysis revealed the heterogeneity of the spatial distribution of their production in each colony. Our technique makes a significant contribution to the advancement of microbial screening, offering a rapid, efficient alternative to conventional methods and opening avenues for secondary metabolites discovery.

Genome-Wide Screening Approaches for Biochemical Reactions Independent of Cell Growth.

Genome-wide screening is a potent approach for comprehensively understanding the molecular mechanisms of biological phenomena. However, despite its widespread use in the past decades across various biological targets, its application to biochemical reactions with temporal and reversible biological outputs remains a formidable challenge. To uncover the molecular machinery underlying various biochemical reactions, we have recently developed the revival screening method, which combines flow cytometry-based cell sorting with library reconstruction from collected cells. Our refinements to the traditional genome-wide screening technique have proven successful in revealing the molecular machinery of biochemical reactions of interest. In this article, we elucidate the technical basis of revival screening, focusing on its application to CRISPR-Cas9 single guide RNA (sgRNA) library and complementary DNA (cDNA) library screening. Finally, we also discuss the future of genome-wide screening while describing recent achievements from in vitro and in vivo screening.

Molecular identification of lactic acid bacteria from traditional fermented foods and screening exopolysaccharide production by using food wastes.

In this study, lactic acid bacteria (LAB) isolation from fermented foods and molecular identification using magnetic bead technology were performed. And then exopolysaccharide (EPS) production possibility was tested in agar medium, and the positive ones were selected for the next step. The bacteria that could produce higher carbohydrate level were grown in MRS medium fortified with whey and pumpkin waste. In our study, 19 different LAB species were identified from fermented products collected from different places in Hatay(Türkiye) province. In molecular identification, universal primer pairs, p806R/p8FPL, and PEU7/DG74 were used for PCR amplification. After that, PCR products purified using paramagnetic bead technology were sequenced by the Sanger sequencing method. The dominant species, 23.8% of the isolates, were identified as Lactiplantibacillus plantarum. As a technological property of LAB, exopolysaccharide production capability of forty-two LAB isolate was tested in agar medium, and after eleven isolates were selected as positive. Two LAB (Latilactobacillus curvatus SHA2-3B and Loigolactobacillus coryniformis SHA6-3B) had higher EPS production capability when they were grown in MRS broth fortified with pumpkin waste and whey. The highest EPS content (1750mg/L glucose equivalent) was determined in Loigolactobacillus coryniformis SHA6-3B grown in MRS broth fortified with 10% pumpkin waste. Besides the produced EPS samples were validated with FTIR and SEM methods.

Genomic insights and biocontrol potential of ten bacterial strains from the tomato core microbiome.

Despite their adverse environmental effects, modern agriculture relies heavily on agrochemicals to manage diseases and pests and enhance plant growth and productivity. Some of these functions could instead be fulfilled by endophytes from the plant microbiota, which have diverse activities beneficial for plant growth and health. We therefore used a microbiome-guided top-down approach to select ten bacterial strains from different taxa in the core microbiome of tomato plants in the production chain for evaluation as potential bioinoculants. High-quality genomes for each strain were obtained using Oxford Nanopore long-read and Illumina short-read sequencing, enabling the dissection of their genetic makeup to identify phyto-beneficial traits. Bacterial strains included both taxa commonly used as biofertilizers and biocontrol agents (i.e. Pseudomonas and Bacillus) as well as the less studied genera Leclercia, Chryseobacterium, Glutamicibacter, and Paenarthorbacter. When inoculated in the tomato rhizosphere, these strains promoted plant growth and reduced the severity of Fusarium Crown and Root Rot and Bacterial Spot infections. Genome analysis yielded a comprehensive inventory of genes from each strain related to processes including colonization, biofertilization, phytohormones, and plant signaling. Traits directly relevant to fertilization including phosphate solubilization and acquisition of nitrogen and iron were also identified. Moreover, the strains carried several functional genes putatively involved in abiotic stress alleviation and biotic stress management, traits that indirectly foster plant health and growth. This study employs a top-down approach to identify new plant growth-promoting rhizobacteria (PGPRs), offering an alternative to the conventional bottom-up strategy. This method goes beyond the traditional screening of the strains and thus can expand the range of potential bioinoculants available for market application, paving the way to the use of new still underexplored genera.

Performance of machine learning-based models to screen obstructive sleep apnea in pregnancy

The purpose of this study is to improve the performance of existing OSA screening tools for pregnant women with machine learning algorithms. A total of 296 pregnant women who complained of snoring OSA were recruited to complete four traditional OSA screening questionnaires: Berlin, STOP, STOP-Bang questionnaires, and Epworth Sleepiness Scale. OSA status was confirmed using an overnight type III home sleep test. 76 of the participants repeated the procedure at different trimesters, generating a total of 402 records. The participants were randomly split into a training set (n = 207) and a test set (n = 89) in a 7:3 ratio. We applied a logistic regression model to build Mixture of Models for OSA screen (MoMOSA) based on demographic data and selected questions from all the questionnaires. Finally, we transformed the MoMOSA into a new questionnaire with a nomogram. MoMOSA, with 13 features, achieved the highest performance among the traditional questionnaires and built models.

Targeting STING oligomerization with licochalcone D ameliorates STING-driven inflammatory diseases.

The development of STING inhibitors for the treatment of STING-related inflammatory diseases continues to encounter significant challenges. The activation of STING is a multi-step process that includes binding with cGAMP, self-oligomerization, and translocation from the endoplasmic reticulum to the Golgi apparatus, ultimately inducing the expression of IRF3 and NF-κB-mediated interferons and inflammatory cytokines. It has been demonstrated that disruption of any of these steps can effectively inhibit STING activation. Traditional structure-based drug screening methodologies generally focus on specific binding sites. In this study, a TransformerCPI model based on protein primary sequences and independent of binding sites is employed to identify compounds capable of binding to the STING protein. The natural product Licochalcone D (LicoD) is identified as a potent and selective STING inhibitor. LicoD does not bind to the classical ligand-binding pocket; instead, it covalently modifies the Cys148 residue of STING. This modification inhibits STING oligomerization, consequently suppressing the recruitment of TBK1 and the nuclear translocation of IRF3 and NF-κB. LicoD treatment ameliorates the inflammatory phenotype in Trex1-1- mice and inhibits the progression of DSS-induced colitis and AOM/DSS-induced colitis-associated colon cancer (CAC). In summary, this study reveals the potential of LicoD in treating STING-driven inflammatory diseases. It also demonstrates the utility of the TransformerCPI model in discovering allosteric compounds beyond the conventional binding pockets.

Evaluating the effectiveness of large language models in abstract screening: a comparative analysis

ObjectiveThis study aimed to evaluate the performance of large language models (LLMs) in the task of abstract screening in systematic review and meta-analysis studies, exploring their effectiveness, efficiency, and potential integration into existing human expert-based workflows.MethodsWe developed automation scripts in Python to interact with the APIs of several LLM tools, including ChatGPT v4.0, ChatGPT v3.5, Google PaLM 2, and Meta Llama 2, and latest tools including ChatGPT v4.0 turbo, ChatGPT v3.5 turbo, Google Gemini 1.0 pro, Meta Llama 3, and Claude 3. This study focused on three databases of abstracts and used them as benchmarks to evaluate the performance of these LLM tools in terms of sensitivity, specificity, and overall accuracy. The results of the LLM tools were compared to human-curated inclusion decisions, gold standard for systematic review and meta-analysis studies.ResultsDifferent LLM tools had varying abilities in abstract screening. Chat GPT v4.0 demonstrated remarkable performance, with balanced sensitivity and specificity, and overall accuracy consistently reaching or exceeding 90%, indicating a high potential for LLMs in abstract screening tasks. The study found that LLMs could provide reliable results with minimal human effort and thus serve as a cost-effective and efficient alternative to traditional abstract screening methods.ConclusionWhile LLM tools are not yet ready to completely replace human experts in abstract screening, they show great promise in revolutionizing the process. They can serve as autonomous AI reviewers, contribute to collaborative workflows with human experts, and integrate with hybrid approaches to develop custom tools for increased efficiency. As technology continues to advance, LLMs are poised to play an increasingly important role in abstract screening, reshaping the workflow of systematic review and meta-analysis studies.

Screening for abdominal aortic aneurysm in the world and in Russia

Despite the global trend towards a decrease in the prevalence of abdominal aortic aneurysm (AAA), this disease remains one of the sudden death causes in the elderly. This necessitates the need to conduct screening studies, the effectiveness and feasibility of which has been proven in large studies, including population-based ones, and meta-analyses. The traditional and most optimal screening method is ultrasound examination. According to the guidelines of different countries, the indications for abdominal aorta ultrasound vary. Today in Russia there is no accurate data on the prevalence of AAA, while the target group for screening has not been defined, and therefore the country needs to conduct large population studies to study its prevalence and risk factors, as well as to calculate indicators of the clinical and economic effectiveness of implementation AAA screening programs.

Voice-based depression assessment in patients with gynecological cancer.

161 Background: Although depression in patients with cancer can lead to a deterioration of treatment adherence and quality of life (QOL), diagnosis of depression in patients with cancer is difficult due to symptoms overlapping with side effects of cancer treatment such as fatigue. Traditional screening tools like the PHQ-9 questionnaire are underutilized in clinical practice. Recently, interest has grown in utilizing patients' voices to assess their mental well-being. This study aims to evaluate depression in patients with gynecological cancer and explore the usefulness of voice analysis as a depression detection tool. Methods: PHQ-9 scores were collected from 197 patients with gynecological cancer, with 28 cases undergoing longitudinal assessments at diagnosis, postoperatively, and during chemotherapy. Voice recordings were obtained from 70 patients at diagnosis, alongside serum samples from 22 patients. The PHQ-9 scores were compared across different treatment periods, with a specific focus on patients exhibiting a PHQ score of ≧10, who can be diagnosed with Major Depressive Disorder (MDD). The provision of supportive care for MDD patients was also verified. A random forest model was developed from voice features obtained from 70 patients, with hyperparameter tuning and cross-validation to predict mild depression. Serum metabolites were comprehensively analyzed between depression prediction group and normal prediction group by the depression prediction model. Results: Mean PHQ-9 scores decreased over time since diagnosis; initially 6.50 ± 4.99 (mean ±SD), post-operatively 6.18 ± 4.25, and during chemotherapy 4.88 ± 4.29. The frequencies of MDD also decreased over the clinical course; at diagnosis 24.3%, post-operatively 15.5%, and during chemotherapy 15.4%. Out of 17 cases of MDD during chemotherapy, only one (6.25%) received psychiatric intervention. All MDD cases during chemotherapy had PHQ-9 scores of 5 or higher, representing mild depression at diagnosis. Mild depression at diagnosis could be predicted with an AUC of 0.89 using voice features. Metabolites identified by the voice-based depression prediction model were associated with depression, such as xanthine, methionine, and taurocholic acid. Conclusions: Depression during chemotherapy is often not intervened. Patients with mild depression at diagnosis tend to develop MDD during chemotherapy. Voice-based mental health assessment at diagnosis is possibly a promising screening tool for depression during subsequent cancer treatment. Clinical trial information: UMIN000044266 .

(Invited) First Principles Treatments of Heterogeneous Electrocatalysis – Reactivity Trends and Electrocatalyst Structure

Advances in the theoretical understanding of electrochemical systems have, over the past decade, led to growing use of periodic Density Functional Theory studies to treat a surprisingly large ensemble of electrocatalytic reactions, ranging from carbon dioxide electroreduction to oxygen evolution. Many such studies have employed simplified models of the electrochemical environment to determine reactivity trends across a broad space of catalytic materials, while other efforts have focused on developing detailed descriptions of electrochemical phenomena, such as the structure of electrochemical double layers, on model catalyst structures. An emerging challenge is to combine these approaches to ultimately enable theoretical design of electrocatalysts for reactions of significantly expanded chemical and materials complexity.In this talk, I will begin by discussing how we have applied strategies from computational heterogeneous catalysis to design enhanced electrocatalysts for the classic oxygen reduction reaction. In such treatments, we have effected highly detailed analyses of the catalyst surface structure and have employed machine learning-based methods to describe interactions between the various ORR reaction intermediates that are present at significant surface coverages. I will then explore challenges in obtaining more detailed descriptions of the electrocatalytic reaction environment, including the structure of catalysts with solid/solid interfaces, the distribution of charges in electrochemical double layers, and the structure and entropy of solvents near the electrocatalyst surface. I will conclude with some perspectives on how these complexities may be incorporated into traditional computational catalyst screening approaches to identify improved materials for more complex electrocatalytic systems.

Identification of Active Molecules against Thrombocytopenia through Machine Learning.

Thrombocytopenia, which is associated with thrombopoietin (TPO) deficiency, presents very limited treatment options and can lead to life-threatening complications. Discovering new therapeutic agents against thrombocytopenia has proven to be a challenging task using traditional screening approaches. Fortunately, machine learning (ML) techniques offer a rapid avenue for exploring chemical space, thereby increasing the likelihood of uncovering new drug candidates. In this study, we focused on computational modeling for drug-induced megakaryocyte differentiation and platelet production using ML methods, aiming to gain insights into the structural characteristics of hematopoietic activity. We developed 112 different classifiers by combining eight ML algorithms with 14 molecule features. The top-performing model achieved good results on both 5-fold cross-validation (with an accuracy of 81.6% and MCC value of 0.589) and external validation (with an accuracy of 83.1% and MCC value of 0.642). Additionally, by leveraging the Shapley additive explanations method, the best model provided quantitative assessments of molecular properties and structures that significantly contributed to the predictions. Furthermore, we employed an ensemble strategy to integrate predictions from multiple models and performed in silico predictions for new molecules with potential activity against thrombocytopenia, sourced from traditional Chinese medicine and the Drug Repurposing Hub. The findings of this study could offer valuable insights into the structural characteristics and computational prediction of thrombopoiesis inducers.