Tool For Identification Research Articles

Transfer learning enables identification of multiple types of RNA modifications using nanopore direct RNA sequencing

Nanopore direct RNA sequencing (DRS) has emerged as a powerful tool for RNA modification identification. However, concurrently detecting multiple types of modifications in a single DRS sample remains a challenge. Here, we develop TandemMod, a transferable deep learning framework capable of detecting multiple types of RNA modifications in single DRS data. To train high-performance TandemMod models, we generate in vitro epitranscriptome datasets from cDNA libraries, containing thousands of transcripts labeled with various types of RNA modifications. We validate the performance of TandemMod on both in vitro transcripts and in vivo human cell lines, confirming its high accuracy for profiling m6A and m5C modification sites. Furthermore, we perform transfer learning for identifying other modifications such as m7G, Ψ, and inosine, significantly reducing training data size and running time without compromising performance. Finally, we apply TandemMod to identify 3 types of RNA modifications in rice grown in different environments, demonstrating its applicability across species and conditions. In summary, we provide a resource with ground-truth labels that can serve as benchmark datasets for nanopore-based modification identification methods, and TandemMod for identifying diverse RNA modifications using a single DRS sample.

Multiplexing the Identification of Microorganisms via Tandem Mass Tag Labeling Augmented by Interference Removal through a Novel Modification of the Expectation Maximization Algorithm.

Having fast, accurate, and broad spectrum methods for the identification of microorganisms is of paramount importance to public health, research, and safety. Bottom-up mass spectrometer-based proteomics has emerged as an effective tool for the accurate identification of microorganisms from microbial isolates. However, one major hurdle that limits the deployment of this tool for routine clinical diagnosis, and other areas of research such as culturomics, is the instrument time required for the mass spectrometer to analyze a single sample, which can take ∼1 h per sample, when using mass spectrometers that are presently used in most institutes. To address this issue, in this study, we employed, for the first time, tandem mass tags (TMTs) in multiplex identifications of microorganisms from multiple TMT-labeled samples in one MS/MS experiment. A difficulty encountered when using TMT labeling is the presence of interference in the measured intensities of TMT reporter ions. To correct for interference, we employed in the proposed method a modified version of the expectation maximization (EM) algorithm that redistributes the signal from ion interference back to the correct TMT-labeled samples. We have evaluated the sensitivity and specificity of the proposed method using 94 MS/MS experiments (covering a broad range of protein concentration ratios across TMT-labeled channels and experimental parameters), containing a total of 1931 true positive TMT-labeled channels and 317 true negative TMT-labeled channels. The results of the evaluation show that the proposed method has an identification sensitivity of 93-97% and a specificity of 100% at the species level. Furthermore, as a proof of concept, using an in-house-generated data set composed of some of the most common urinary tract pathogens, we demonstrated that by using the proposed method the mass spectrometer time required per sample, using a 1 h LC-MS/MS run, can be reduced to 10 and 6 min when samples are labeled with TMT-6 and TMT-10, respectively. The proposed method can also be used along with Orbitrap mass spectrometers that have faster MS/MS acquisition rates, like the recently released Orbitrap Astral mass spectrometer, to further reduce the mass spectrometer time required per sample.

Mannheimia indoligenes sp. nov., proposed for clade V organisms of Mannheimia.

A set of 25 strains belonging to clade V of Mannheimia mainly isolated from cattle was investigated and is proposed to represent Mannheimia indoligenes sp. nov. The species can be separated from the other validly published species of the genus by pheno- and genotype. Only indole separates M. indoligenes and Mannheimia varigena while two to seven characters separate M. indoligenes from other species of Mannheimia. Thirteen strains belonging to biogroups 6, 7, 8C, 9, 10, 12 and UG5 formed a monophyletic group based on 16S rRNA gene sequence comparisons with 98-100 % similarity. Eight of these strains were further included in the whole genome comparison. Digital DNA-DNA hybridization showed that the similarities between the suggested type strain M14.4T and the other strains of M. indoligenes were 62.9 % or higher. The average nucleotide identity was 95.5 % or higher between M14.4T and the other strains of the species. The rpoB gene sequence similarity was 95-100 % within M. indoligenes. MALDI-TOF allowed a clear separation from other Mannheimia species further supporting classification as a novel species and making it the diagnostic identification tool of choice for M. indoligenes. The type strain is M14.4T (=CCUG 77347T=DSM 116804T) isolated from a cattle tongue in Scotland.

A DNA barcode reference library of Croatian mosquitoes (Diptera: Culicidae): implications for identification and delimitation of species, with notes on the distribution of potential vector species

BackgroundMosquitoes pose a risk to human health worldwide, and correct species identification and detection of cryptic species are the most important keys for surveillance and control of mosquito vectors. In addition to traditional identification based on morphology, DNA barcoding has recently been widely used as a complementary tool for reliable identification of mosquito species. The main objective of this study was to create a reference DNA barcode library for the Croatian mosquito fauna, which should contribute to more accurate and faster identification of species, including cryptic species, and recognition of relevant vector species.MethodsSampling was carried out in three biogeographical regions of Croatia over six years (2017–2022). The mosquitoes were morphologically identified; molecular identification was based on the standard barcoding region of the mitochondrial COI gene and the nuclear ITS2 region, the latter to identify species within the Anopheles maculipennis complex. The BIN-RESL algorithm assigned the COI sequences to the corresponding BINs (Barcode Index Number clusters) in BOLD, i.e. to putative MOTUs (Molecular Operational Taxonomic Units). The bPTP and ASAP species delimitation methods were applied to the genus datasets in order to verify/confirm the assignment of specimens to specific MOTUs.ResultsA total of 405 mosquito specimens belonging to six genera and 30 morphospecies were collected and processed. Species delimitation methods assigned the samples to 31 (BIN-RESL), 30 (bPTP) and 28 (ASAP) MOTUs, with most delimited MOTUs matching the morphological identification. Some species of the genera Culex, Aedes and Anopheles were assigned to the same MOTUs, especially species that are difficult to distinguish morphologically and/or represent species complexes. In total, COI barcode sequences for 34 mosquito species and ITS2 sequences for three species of the genus Anopheles were added to the mosquito sequence database for Croatia, including one individual from the Intrudens Group, which represents a new record for the Croatian mosquito fauna.ConclusionWe present the results of the first comprehensive study combining morphological and molecular identification of most mosquito species present in Croatia, including several invasive and vector species. With the exception of some closely related species, this study confirmed that DNA barcoding based on COI provides a reliable basis for the identification of mosquito species in Croatia.Graphical

Missing persons and infrastructures of search and identification

People go missing all over the world, but the reasons for disappearances are enormously diverse. Some people are intentionally disappeared by the state: totalitarian and military governments as well as various paramilitary and criminal organizations have used enforced disappearances as a tactic to control the population and create submissive citizens or subjects though fear and insecurity. Both civilians and soldiers disappear invariably in the chaotic circumstances of war and armed conflict. Some people disappear in natural catastrophes or fatal accidents; some disappear of their own free will. Whatever the reason for disappearance, it disturbs the everyday flow of life in families and communities, and in many places, it creates anomalies for modern state bureaucracies. Unaccounted-for absences give rise to search practices, but the circumstances of search are radically different in different places and different contexts of disappearance. One way to approach these differences is to analyse the infrastructures of search in each site. I am especially interested in the entanglement of the local with the global, and of the spatial reach of search infrastructures . Moreover, I consider the significance of the material affordances of some infrastructural forms, especially of the DNA as the key tool for identification. I make some observations on how the entanglements of local and transnational investment and the material affordances of the techniques allow some of the disappeared to be found and identified, while others stay more ‘disappearable’ (Laakkonen 2022).

Biomarkers of mussel exposure to Vibrionaceae: A review

AbstractFor more than a century, bacterial infections caused by Vibrio spp. have affected various species of mussels around the world, with limited insights into the responses implemented by mussels against these infections. A combination of chemical analyses and carefully selected biological endpoints from haemolymph and tissues can be used to identify the welfare status of mussels and potentially protect aquatic ecosystems from catastrophic health threats. Recent developments in biomarker identification tools, such as omics and bioinformatics, have been successfully applied to evaluate the effect of environmental pollutants and other chemicals on mussels. However, the application of biomarkers to assess mussel health is limited. This review describes the available scientific literature on biomarker research for Vibrio-mussel interactions, and those aspects related to mussel health and disease assessment, grouped as biomarkers of exposure, effects, and susceptibility. From the review, it is clear that when integrated biomarkers are used, they can provide a deeper understanding of the relative health and potential susceptibility of mussels for better management practices. Furthermore, health biomarker data can be used to build resilience in mussels against climate change conditions, strengthen biosecurity management programs, improve farming and processing efficiency, and add value in terms of market-desirable traits. These data hold promise for advancing sustainability efforts within the aquaculture industry. Graphical abstract

Analysis and Prevention of AI-Based Phishing Email Attacks

Phishing email attacks are among the most common and most harmful cybersecurity attacks. With the emergence of generative AI, phishing attacks can be based on emails generated automatically, making it more difficult to detect them. That is, instead of a single email format sent to a large number of recipients, generative AI can be used to send each potential victim a different email, making it more difficult for cybersecurity systems to identify the scam email before it reaches the recipient. Here, we describe a corpus of AI-generated phishing emails. We also use different machine learning tools to test the ability of automatic text analysis to identify AI-generated phishing emails. The results are encouraging, and show that machine learning tools can identify an AI-generated phishing email with high accuracy compared to regular emails or human-generated scam emails. By applying descriptive analytics, the specific differences between AI-generated emails and manually crafted scam emails are profiled and show that AI-generated emails are different in their style from human-generated phishing email scams. Therefore, automatic identification tools can be used as a warning for the user. The paper also describes the corpus of AI-generated phishing emails that are made open to the public and can be used for consequent studies. While the ability of machine learning to detect AI-generated phishing emails is encouraging, AI-generated phishing emails are different from regular phishing emails, and therefore, it is important to train machine learning systems also with AI-generated emails in order to repel future phishing attacks that are powered by generative AI.

Study regarding the influence of a student’s personality and an LMS usage profile on learning performance using machine learning techniques

AbstractAcademic performance (AP) is crucial for lifelong success. Unfortunately, many students fail to meet expected academic benchmarks, leading to altered career paths or university dropouts. This issue is particularly pronounced in the early stages of higher education, highlighting the need for the instructors of these foundational courses to have access to simple yet effective tools for the early identification of students at high risk of academic failure. In this study, we propose a streamlined conceptual model inspired by the Model of Human Behavior (MHB) to which we have incorporated two dimensions: capacity and willingness. These dimensions are assessed through the definition of three variables: Prior Academic Performance (PAP), Personality and Academic Engagement, whose measurements can easily be obtained by the instructors. Furthermore, we outline a Machine Learning (ML) process that higher education instructors can use to create their own tailored models in order to predict AP and identify risk groups with high levels of transparency and interpretability. The application of our approach to a sample of 322 Spanish undergraduates studying two mathematical subjects at a Spanish university demonstrates its potential to detect failure early in the semester with a precision that is comparable with that of more complex models found in literature. Our tailored model identified that capacity was the primary predictor of AP, with a gain-to-baseline improvement of 21%, and the willingness variables increasing this to 27%. This approach is consistent over time. Implications for instructors are discussed and an open prediction and analysis tool is developed.

A Combined Interventional Approach to Train Interview Skills in Autistic Transition-Age Youth.

The job interview can be challenging for autistic adolescents considering the required social communication skills. Further, having decreased awareness of personal strengths may make it difficult to advocate for oneself to a future employer. The purpose of the current pilot randomized controlled trial (RCT) is to examine the preliminary efficacy and feasibility of a combined interventional approach using: the Virtual Interview Tool for Autistic Transition-Age Youth (VIT-TAY) and Kessler Foundation Strength Identification and Expression (KF-STRIDE). Twenty autistic transition-age youth (TAY) were randomly assigned to two groups: an intervention group (n = 10) that received 9h of VIT-TAY (interviewing practice with a virtual human), and three lessons of KF-STRIDE (positive psychology intervention to learn and discuss one's personal character strengths) and a services-as-usual (SAU) group (n = 10). The primary outcome was measured using a video-recorded mock job interview performed at pre- and post-test, which was rated by blinded assessors. Secondary outcomes included self-reports of job interview skill, interview anxiety, work readiness and recent job search behavior. Paired samples t-tests revealed significant differences between pre- and post-test in the intervention group (but not the control group) on the mock interview total score (p = 0.02, d = 0.76) and self-reported job interview skills total score (p = 0.02, d = 0.75). The intervention group (but not the control group) had improvements in work-readiness (p = 0.06, d = 0.53) and job search behavior (p = 0.07, d = 0.52) that were characterized by medium effect sizes. This pilot study suggests that combining VIT-TAY with KF-STRIDE leads to improvements in performance-based and self-reported job interview skills.

Perfusion index: could it be a new tool for early identification of pulmonary embolism severity?

Perfusion index (PI) is a promising indicator for monitoring peripheral perfusion. The present study aimed to compare the efficiency of PI and PESI score in estimating the 30-day mortality and treatment needs of patients diagnosed with pulmonary embolism in the emergency department. This study was prospective and observational. The demographic features of the patients, comorbidities, vital signs, PESI score, PI, treatment applied to the patient and airway management, right ventricular diameter/left ventricular diameter ratio, length of hospital stay, outcome, and 30-day mortality were recorded. A total of 94 patients were included. All patients' vital signs and PI values were recorded on admission. The mean pulse rate (p = 0.001) and shock index (p = 0.017) values of deceased patients were statistically significantly higher, while the mean PI (p = 0.034) was statistically significantly lower. PESI score and PI were statistically significant to predict the need for mechanical ventilation (PI, p = 0.004; PESI score, p < 0.001), inotropic treatment (PI, p = 0.047; PESI score p = 0.005), and thrombolytic therapy (PI, p = 0.035; PESI score p = 0.003). According to the ROC curve, the mortality prediction power of both PESI (AUC: 0.787, 95% CI 0.688-0.886, cutoff: 109.5, p < 0.001) and PI index (AUC: 0.668, 95% CI 0.543-0.793, cutoff: 1, p = 0.011) were determined as statistically significant. PI might be helpful in clinical practice as a tool that can be applied to predict mortality and treatment needs in PE.

First Report of Wilt Caused by Fusarium nanum (FIESC 25) on Mungbean (Vigna radiata) in Pakistan.

Mungbean, Vigna radia (L.) R. Wilczek, is ranked 2nd next to chickpea (Cicer arietinum) in total cultivation and production in Pakistan. In August of 2022 and 2023, mungbean plants (cv. PRI Mung-2018) were found wilting in a field at the Ayub Agricultural Research Institute, Faisalabad, Pakistan. Wilted leaves turned yellow, died, but remained attached to the stem. Vascular tissue at the base of the stem showed light to dark brown discoloration. Roots were stunted with purplish brown to black discoloration. Symptomatic mungbean plants were collected from fields at five different locations (20 samples/location). Disease incidence was similar among the five fields, ranging from 5 to 10% at each location depending upon type of germplasm and date of sowing. For fungal isolation and morphological identification, symptomatic stem and root tissues were cut into ~5 mm2 pieces with a sterilized blade. Tissues were surface-sterilized for one min in a 0.5% sodium hypochlorite solution, rinsed twice in sterilized water, air dried on sterilized filter paper, and aseptically placed on potato dextrose agar (PDA) containing 0.5 g/L-1 streptomycin sulphate. Plates were incubated for 3-4 days at 25 ± 2°C with a 12-h photoperiod. Single-spore cultures were used for morphological and molecular analyses. Isolates on PDA grew rapidly and produced abundant white aerial mycelium that turned off-white to beige with age. Macroconidia were hyaline, falcate, typically 3-to-6 septate with a pointed apical cell and a foot-shaped basal cell, measuring 24.5-49.5 x 2.7-4.7 μm (n = 40). Globose to obovate chlamydospores measuring 5.8 ± 0.5 μm (n = 40) were produced singly or in chains and were intercalary or terminal and possessed roughened walls. The morphological data indicated the isolates were members of the genus Fusarium (Leslie and Summerell 2006). To obtain a species-level identification, a portion of translation elongation factor 1-α (TEF1), the largest subunit of RNA polymerase (RPB1), and the second largest subunit of RNA polymerase (RPB2) region were PCR amplified and sequenced using EF1/EF2 (O'Donnell et al. 1998), Fa/G2R (Hofstetter et al. 2007), and 5f2/7cr (Liu et al. 1999) primers, respectively. DNA sequences of these genes were deposited in GenBank under accession numbers MW059021, MW059017 and MW059019, respectively. The partial TEF1, RPB1 and RPB2 sequences were queried against the Fusarium MLST database (https://fusarium.mycobank.org/page/Fusarium_identification), using the polyphasic identification tool. The BLASTn search revealed 99.9% identity of the isolate to F. nanum (Xia et al. 2019), formerly FIESC 25 of the F. incarnatum-equiseti species complex (MRC 2610, NRRL 54143; O'Donnell et al. 2018). To confirm pathogenicity, roots of 3-5 leaf stage mungbean seedlings were soaked in a 106 spores ml-1 conidial suspension of the fungus for 15 min and then planted in 10 cm pots containing sterilized soil. Mock-inoculated plants with sterile water served as a negative control. Twenty pots that were used for each inoculated and control treatment were maintained at 25 ± 2°C, 14:8 h photoperiod, and 80% relative humidity in a growth chamber. After 15 days, leaf yellowing, internal browning from the base of stems and root discoloration was observed in all the inoculated plants. The uninoculated negative control plants remained asymptomatic. Fusarium nanum was re-isolated from artificially inoculated plants and identified by colony growth, conidial characteristics on PDA and molecular analyses (TEF1). To our knowledge, this is the first report of wilt caused by F.nanum on mungbean in Pakistan. In Pakistan, mungbean cultivation in irrigated areas has increased in recent years. It has been introduced frequently in citrus orchards, crop rotation of maize and sesame, intercropping with sugarcane and as green manure. However, citrus, maize, sesame and sugarcane are also hosts of Fusarium spp. Therefore, this information warrants sustainable crop protection and may have an impact on further interaction of F. nanum with other wilt pathogens.

Digital health interventions for remote follow-up after mild traumatic brain injury

Background After a mild traumatic brain injury (mild TBI,) a significant number of patients may experience persistent symptoms and disabilities for months to years. Early identification and timely management of persistent symptoms may help to reduce the long-term impacts of mild TBIs. There is currently no formalised method for identifying patients with persistent symptoms after mild TBI once they are discharged from emergency department. Objective Assess the feasibility of a remote monitoring tool for early identification of persistent symptoms after mild TBI in the outpatient setting using digital tools. Methods Electronic surveys were sent to patients with mild TBI who presented to the emergency department at a Major Trauma Centre in England. The surveys were completed at three different timepoints (within days of injury (S1), 1 month (S2), and 3 months (S3) after injury). The indicators used to assess feasibility were engagement, number of eligible patients for follow-up evidence of need for the intervention, and consistency with the literature. Feedback was sought from participants. Results Of the 200 people invited to participate, 134 (67.0%) completed S1, 115 (57.5%) completed S2, and 95 (47.5%) completed S3. The rates of persistent symptoms ranged from 17.9%–62.6% depending on the criteria used, and we found a significant proportion of the participants experienced morbidity 1 and 3 months after injury. The electronic follow-up tool was deemed an acceptable and user-friendly method for service delivery by participants. Conclusion Using digital tools to monitor and screen mild TBI patients for persistent symptoms is feasible. This could be a scalable, cost-effective, and convenient solution which could improve access to healthcare and reduce healthcare inequalities. This could enable early identification of patients with further medical needs and facilitate timely intervention to improve the clinical workflows, patient satisfaction, and health outcomes for people with persistent morbidities after mild TBIs.

Network pharmacology speaking to ethnopharmacology: new data on an ancient remedy

Network pharmacology as a “green approach”, predicting metabolite behaviours chemically and biologically and guid¬ing biological experimental design, is a new strategy aiming to uncover the mechanism of action of natural products as drug candidates. It provides a powerful way to identify novel mechanisms of natural products with potential thera¬peutic effects. This approach has emerged as a powerful tool to overcome the limitations of traditional methods, such as the ability to predict the adverse effects of a drug and the likelihood of failure during clinical trials, by applying systems biology principles to the field of pharmacology. This method combines the multi-omics dataset, computer modeling, and chemical biology so as to reveal pharmaceutical actions and guide drug discovery. Therefore, computer-aided drug design combined with network pharmacology can be viewed as a novel in silico screening ap¬proach to drug discovery, by utilising chemoinformatics, bioinformatics, structure biology, and chemical biology. This strategy includes target-based virtual screening - molecular docking, ligand similarity-based virtual screening, and inverse screening (Inver-dock), providing a powerful tool for target identification of drug candidates, multitarget dis¬covery, and natural bioactive product profiling. It can also be used for selectivity profiling of drugs, drug repositioning, safety profiling, and metabolism profiling prediction (ADMET).

Criminal Investigation Tracker with Suspect Prediction

This initiative seeks to craft an inclusive and intuitive web-based platform tailored for criminal identification via image and video surveillance, leveraging cutting-edge facial recognition technology. The system integrates a registration portal for inputting data and images of known criminals, utilizing OpenCV and advanced facial recognition algorithms to securely analyze and store their facial attributes. In addition to allowing users to upload images for analysis, the system offers immediate feedback on potential matches with registered criminals. Moreover, the video surveillance module extends this capability to short videos, employing video analytics to identify faces within the footage. The platform ensures real-time feedback for successful identifications and provides an advanced feature enabling users to download details of identified criminals in an Excel format. By amalgamating state-of-the-art technology with an intuitive interface, this project endeavors to bolster law enforcement endeavors by furnishing an efficient and precise tool for criminal identification and tracking. Its objectives encompass developing a robust system for identifying and tracking criminals through advanced facial recognition algorithms and OpenCV technology, designing a user-friendly web interface for seamless navigation across various modules, and establishing a secure and efficient registration section for compiling comprehensive databases of facial features.

Acceptability and feasibility of screening with a pediatric care provider-led social determinants of health identification tool

BackgroundComplex social determinants of health may not be easily recognized by health care providers and pose a unique challenge in the vulnerable pediatric population where patients may not be able to advocate for themselves. The goal of this study was to examine the acceptability and feasibility of health care providers using an integrated brief pediatric screening tool in primary care and hospital settings.MethodsThe framework of the Child and Adolescent Needs and Strengths (CANS) and Pediatric Intermed tools was used to inform the selection of items for the 9-item Child and Adolescent Needs and Strengths-Pediatric Complexity Indicator (CANS-PCI). The tool consisted of three domains: biological, psychological, and social. Semi-structured interviews were conducted with health care providers in pediatric medical facilities in Ottawa, Canada. A low inference and iterative thematic synthesis approach was used to analyze the qualitative interview data specific to acceptability and feasibility.ResultsThirteen health care providers participated in interviews. Six overarching themes were identified: acceptability, logistics, feasibility, pros/cons, risk, and privacy. Overall, participants agreed that a routine, trained provider-led pediatric tool for the screening of social determinants of health is important (n = 10, 76.9%), acceptable (n = 11; 84.6%), and feasible (n = 7, 53.8%).InterpretationThough the importance of social determinants of health are widely recognized, there are limited systematic methods of assessing, describing, and communicating amongst health care providers about the biomedical and psychosocial complexities of pediatric patients. Based on this study’s findings, implementation of a brief provider-led screening tool into pediatric care practices may contribute to this gap.

Harnessing Consumer Wearable Digital Biomarkers for Individualized Recognition of Postpartum Depression Using the All of Us Research Program Data Set: Cross-Sectional Study.

Postpartum depression (PPD) poses a significant maternal health challenge. The current approach to detecting PPD relies on in-person postpartum visits, which contributes to underdiagnosis. Furthermore, recognizing PPD symptoms can be challenging. Therefore, we explored the potential of using digital biomarkers from consumer wearables for PPD recognition. The main goal of this study was to showcase the viability of using machine learning (ML) and digital biomarkers related to heart rate, physical activity, and energy expenditure derived from consumer-grade wearables for the recognition of PPD. Using the All of Us Research Program Registered Tier v6 data set, we performed computational phenotyping of women with and without PPD following childbirth. Intraindividual ML models were developed using digital biomarkers from Fitbit to discern between prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods. Models were built using generalized linear models, random forest, support vector machine, and k-nearest neighbor algorithms and evaluated using the κ statistic and multiclass area under the receiver operating characteristic curve (mAUC) to determine the algorithm with the best performance. The specificity of our individualized ML approach was confirmed in a cohort of women who gave birth and did not experience PPD. Moreover, we assessed the impact of a previous history of depression on model performance. We determined the variable importance for predicting the PPD period using Shapley additive explanations and confirmed the results using a permutation approach. Finally, we compared our individualized ML methodology against a traditional cohort-based ML model for PPD recognition and compared model performance using sensitivity, specificity, precision, recall, and F1-score. Patient cohorts of women with valid Fitbit data who gave birth included <20 with PPD and 39 without PPD. Our results demonstrated that intraindividual models using digital biomarkers discerned among prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods, with random forest (mAUC=0.85; κ=0.80) models outperforming generalized linear models (mAUC=0.82; κ=0.74), support vector machine (mAUC=0.75; κ=0.72), and k-nearest neighbor (mAUC=0.74; κ=0.62). Model performance decreased in women without PPD, illustrating the method's specificity. Previous depression history did not impact the efficacy of the model for PPD recognition. Moreover, we found that the most predictive biomarker of PPD was calories burned during the basal metabolic rate. Finally, individualized models surpassed the performance of a conventional cohort-based model for PPD detection. This research establishes consumer wearables as a promising tool for PPD identification and highlights personalized ML approaches, which could transform early disease detection strategies.

A new bacterial consortia for management of Fusarium head blight in wheat

Fusarium head blight (FHB) is a significantly important disease in cereals primarily caused by Fusarium species. FHB control is largely executed through chemical strategies, which are costlier to sustainable wheat production, resulting in leaning towards sustainable sources such as resistance breeding and biological control methods for FHB. The present investigation was aimed at evaluating newly identified bacterial consortium (BCM) as biocontrol agents for FHB and understanding the morpho-physiological traits associated with the disease resistance of spring wheat. Preliminary evaluation through antagonistic plate assay and in vivo assessment indicated that BCM effectively inhibited Fusarium growth in spring wheat, reducing area under disease progress curve (AUDPC) and deoxynivalenol (DON), potentially causing type II and V resistance, and improving single spike yield (SSPY). Endurance to FHB infection with the application of BCM is associated with better sustenance of spike photosynthetic performance by improving the light energy harvesting and its utilization. Correlation and path-coefficient analysis indicated that maximum quantum yield (QY_max) is directly influencing the improvement of SSPY and reduction of grain DON accumulation, which is corroborated by principal component analysis. The chlorophyll fluorescence traits identified in the present investigation might be applied as a phenotyping tool for the large-scale identification of wheat sensitivity to FHB.

Abstract PO2-11-10: Can chemotherapy-induced peripheral neuropathy be predicted? Implications for future prevention and treatment of this side-effect

Abstract Background: The pain and sensory abnormalities associated with chemotherapy-induced peripheral neuropathy (CIPN) may persist for months or even years after chemotherapy. CIPN has a negative impact on routine activities, functions, and behaviors in the domestic, work, and social lives of cancer patients, adversely affecting the quality of their survivorship. CIPN is a major adverse effect of taxanes and other agents, possibly requiring dose-reduction or early termination of treatment. Taxane-based regimens are first-line treatment in both early-stage and metastatic breast cancer and therefore place numerous women at risk for developing CIPN. Regrettably, taxane-induced neurotoxicity can be arduous to predict, and there are no preventive or curative treatments currently available. Our work aims to assess a predictive tool for identification of patients at high risk of developing neuropathy and the progression of symptoms towards chronic CIPN. We hypothesized that oxidative stress might be a triggering event for the development of CIPN and that changes in glutathione recycling can identify patients at high risk for developing prolonged and severe CIPN. This hypothesis is based on reports in the literature proposing that CIPN is triggered by damage to the myelin sheath, which protects nerves from damage, by drug-induced free radicals in and around the nerves. Damage to myelin, a lipid- and protein rich sheath, by lipid peroxidation can result in loss of signal transmission, false signaling, or signal overload. Prolonged exposure to elevated levels of free radicals might result in structural changes to the nerves. Methods: Cancer patients seeking treatment at the Lankenau Medical Center Cancer center were asked to participate in our Institutional Review Board approved study of adverse effects. In this on-going study, the cohort (Ntotal =352) includes 104 breast cancer patients that are predominantly Caucasian with 14.9% African American. The median age is 56 (range 26 – 82) and 60.9% were treated with a taxane-based regimen. Nearly half the breast cancer group were diagnosed with Stage I disease. All consented patients donated a tube of blood prior to each treatment and filled out the Rotterdam Symptom Checklist (RSCL). Blood samples were analyzed for glutathione recycling using the ChemoTox assay (MNT™ Test, MYNARI Biomedical) and lipid peroxidation using a thiobarbituric acid reactive substances (TBARS) test (Cayman Chemical). All samples were analyzed in duplicate, and results analyzed using GraphPad Prism 8.4.3. Results: Preliminary results from the first 83 breast cancer patients showed African American patients reported a higher rate of NCCN grade 2 and 3 CIPN while Caucasians reported a higher rate of severe, long-lasting CIPN. Our results showed that patients who reported CIPN at later cycles had diminished glutathione recycling capacity already after the first treatment. Drop in recycling capacity had an inverse relationship with lipid peroxidation and grade of CIPN. Both decreased recycling capacity and increase in lipid oxidation were apparent already after the first treatment in patients that reported CIPN after cycle 6-8 or after completion of treatment Discussion: There are many proposed mechanisms for the development of CIPN. One mechanism that is shared by both most agents is damage induced by free radicals released following chemotherapy. We show that patients with reduced ability to neutralize free radicals have elevated and prolonged lipid peroxidation. Both processes precede the development of CIPN by several treatment cycles. Therefore, this test could identify patients that might benefit from other regimens rather than a taxane-based therapy. The test could also aid in the identification of patients for preventive therapy once such agents become available. Citation Format: Alisha Maity, Nolan Metz, Kathryn Fleck, Zonera Ali, Aarthi Shevade, Arezoo Ghaneie, Margaretha Wallon. Can chemotherapy-induced peripheral neuropathy be predicted? Implications for future prevention and treatment of this side-effect [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-11-10.

An updated list of eumycetoma causative agents and their differences in grain formation and treatment response.

SUMMARYIn 2023, the World Health Organization designated eumycetoma causative agents as high-priority pathogens on its list of fungal priority pathogens. Despite this recognition, a comprehensive understanding of these causative agents is lacking, and potential variations in clinical manifestations or therapeutic responses remain unclear. In this review, 12,379 eumycetoma cases were reviewed. In total, 69 different fungal species were identified as causative agents. However, some were only identified once, and there was no supporting evidence that they were indeed present in the grain. Madurella mycetomatis was by far the most commonly reported fungal causative agent. In most studies, identification of the fungus at the species level was based on culture or histology, which was prone to misidentifications. The newly used molecular identification tools identified new causative agents. Clinically, no differences were reported in the appearance of the lesion, but variations in mycetoma grain formation and antifungal susceptibility were observed. Although attempts were made to explore the differences in clinical outcomes based on antifungal susceptibility, the lack of large clinical trials and the inclusion of surgery as standard treatment posed challenges in drawing definitive conclusions. Limited case series suggested that eumycetoma cases caused by Fusarium species were less responsive to treatment than those caused by Madurella mycetomatis. However, further research is imperative for a comprehensive understanding.

Enhancing rational approximation of wideband resonant MIMO systems with frequency-domain data

Vector Fitting (VF) is a successful methodology for both time and frequency domain estimation of dynamic systems. These algorithms have gained popularity as a system identification tool due to their ability to provide a practical procedure for accurately approximating the measured frequency response behavior of complex and highly resonant dynamic systems using rational models. Instrumental Variable (IV) techniques can also be added to the VF algorithm to enhance the optimality of the solutions in the presence of measurement noise. In this context, this paper presents a multiple-input multiple-output (MIMO) generalization of instrumental variable (IV-)VF. The proposed algorithm can be applied to accurately estimating models formed by either continuous- or discrete-time rational basis functions (RBFs). We show that such a generalization preserves the main implementation features observed in Standard VF, but with improved optimality property for its solutions. Additionally, in order to alleviate convergence problems that may arise from the fixed high-frequency normalization, we also present in this paper how to incorporate in the proposed IV-VF method the relaxed formulation found in standard VF for both the continuous and discrete-time cases. The resulting MIMO IV-VF algorithm can be easily understood by VF users, and its applicability is discussed by using an estimation case study with two power system pieces of equipment (an 88 kV Transformer and a 550 kV Instrument Transformer) for which actual frequency domain measurements were collected in the field. It is shown that the proposed algorithm significantly improves the modeling accuracy when compared to standard VF algorithms.