Traditional Screening Approaches Research Articles

CSKINet: A multimodal network model integrating conceptual semantic knowledge injection for relation extraction of Chinese corporate reports

Recognizing the associations among entities in corporate reports accurately is crucial for market regulation and policy development. Nevertheless, confronted with massive corporate information, the traditional manual screening approach is cumbersome, struggling to match the demand. Consequently, we propose a multimodal network model incorporating conceptual semantic knowledge injection, CSKINet, for accurately extracting relations from Chinese corporate reports. The essential highlights in the design of the CSKINet model are the following: (1) Integrate the conceptual descriptions of corporations from external resources to construct the semantic knowledge repository of corporate concepts, which provides a solid semantic foundation for the model. (2) Multimodal features are extracted from the documents by various means and corporate conceptual knowledge is integrated into the model representation to enhance the representation capability of the model. (3) The multimodal self-attention mechanism that captures cross-modal associations and the biaffine classifier with Taylor polynomial loss function that optimizes training iterations further improve the learning efficiency and prediction accuracy. The results on the real corporate report dataset show that our proposed model can more accurately extract the relations from Chinese corporate reports compared to other baseline models, where the F1 score reaches 85.76%.

Advancing Rare-Earth (4f) and Actinide (5f) Separation through Machine Learning and Automated High-Throughput Experiments.

Identifying improved and sustainable alternatives to "classic" separation techniques is an active research field due to its potential widespread impact in fundamental and applied chemistry. As basic purification methodologies, like liquid-liquid extraction, undergo continuous refinement by chemists and engineers, identifying new conditions that outperform existing techniques can be difficult. A major contributor to this challenging problem is the need to explore a vast experimental space to identify the precise conditions that optimize the separation procedure. The advent of artificial intelligence and the advancement of robotic technologies offer the potential to shift the traditional design paradigm. Toward that end, we applied a combination of Bayesian Optimization and high-throughput robotic experiments on the liquid-liquid extraction of thorium (Th4+) and demonstrated that this approach speeds up discovery and significantly accelerates the optimization process. By using Bayesian Optimization as a guide, our automated instrument carried out a total of 339 distribution ratio measurements, corresponding to 113 unique conditions, identifying the optimal experimental conditions with reduced experimental efforts by an estimated 74% compared to a traditional full screening approach. This time and cost saving is particularly significant for radioactive materials, as it not only is more economical and sustainable but also minimizes human exposure to radioactivity.

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.

LigandDiff: de Novo Ligand Design for 3D Transition Metal Complexes with Diffusion Models.

Transition metal complexes are a class of compounds with varied and versatile properties, making them of great technological importance. Their applications cover a wide range of fields, either as metallodrugs in medicine or as materials, catalysts, batteries, solar cells, etc. The demand for the novel design of transition metal complexes with new properties remains of great interest. However, the traditional high-throughput screening approach is inherently expensive and laborious since it depends on human expertise. Here, we present LigandDiff, a generative model for the de novo design of novel transition metal complexes. Unlike the existing methods that simply extract and combine ligands with the metal to get new complexes, LigandDiff aims at designing configurationally novel ligands from scratch, which opens new pathways for the discovery of organometallic complexes. Moreover, it overcomes the limitations of current methods, where the diversity of new complexes highly relies on the diversity of available ligands, while LigandDiff can design numerous novel ligands without human intervention. Our results indicate that LigandDiff designs unique and novel ligands under different contexts, and these generated ligands are synthetically accessible. Moreover, LigandDiff shows good transferability by generating successful ligands for any transition metal complex.

Abstract 3097: CETSA HT: Employing rapid high-throughput target engagement technology in primary screening of P53

Abstract The confirmation of target engagement for candidate drugs is a fundamental requisite in drug discovery. A significant portion of projects fail to reach the clinic due to lack of efficacy or failure to show lead candidates interacting with the intended target in a more complex environment. The utility of using the CETSA® (CEllular Thermal Shift Assay) technology to measure target engagement in intact cells is increasingly exploited in high throughput screening, where examples demonstrate low false positive rates in screens of up to 500K compounds. The p53 tumor suppressor protein, a crucial guardian against cancer, functions as a transcription factor that mediates cancer suppression by regulating genes involved in a wide range of cellular processes such as DNA repair, cell cycle and apoptosis. Unfortunately, frequent mutations in the TP53 gene hinder p53's tumor suppressor role in human cancers, thus designating it as a promising target for anticancer therapy. However, attempts to restore p53 function for therapeutic purposes have not yet advanced to clinical approval, highlighting the complexities in leveraging p53 for cancer treatment. Its undruggable nature, attributed to the absence of accessible deep pockets, lack of enzymatic activity, and its intracellular location, further complicates targeted interventions with both low and high molecular weight drugs. Here, we demonstrate the analysis of a high-throughput plate based CETSA® HT screen on the challenging target p53, performed using AlphaLISA® SureFire® Ultra™ technology and our newly developed high-throughput screening platform. Hits identified from this screen are privileged from the onset by binding to the target in a physiologically relevant cellular matrix and in a binding-mode agnostic way. This is in contrast to traditional screening methods targeting activity or in vitro interaction where cellular activity is addressed in later stages. This assay cascade highlights a rapid target-to-hit lead generation strategy placing the emphasis on finding chemical matter that interacts with endogenous target in living cells first, followed by analysis of hit material activity. The ‘shortcut’ to chemical matter active in living cells represents significant potential cost savings in comparison to assay development time on recombinantly produced proteins and/or modified cell lines for traditional HTS screening approaches that still rely on target engagement assessment downstream. Citation Format: Merve Kacal, Tomas Friman, Laurence Arnold, Victoria Brehmer, Daniel Martinez Molina, Stina Lundgren. CETSA HT: Employing rapid high-throughput target engagement technology in primary screening of P53 [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3097.

Current controversies in prenatal diagnosis: Noninvasive prenatal testing should replace other screening strategies for fetal trisomies 13, 18, 21.

This is a written summary of the oral debate presented at the International Society for Prenatal Diagnosis annual conference in Edinburgh in 2023. The topic under debate is whether noninvasive prenatal testing (NIPT) using cell-free fetal DNA should replace other screening strategies for the detection of fetal trisomies 13, 18, 21. There is no disagreement that NIPT is far more sensitive and has better positive predictive values for identifying trisomies 13, 18, and 21 than traditional screening approaches using biochemical markers and measurement of nuchal translucency. The major issue lies in the potential adverse consequences associated with abandoning traditional screening methods. The source of disagreement stems primarily from whether you consider the role of ultrasound in the context of screening to be strictly for nuchal translucency measurement or whether it should be combined with a fetal anatomy scan. The debate featured two experts who presented evidence in favor of each argument.

A dual sgRNA library design to probe genetic modifiers using genome-wide CRISPRi screens

Mapping genetic interactions is essential for determining gene function and defining novel biological pathways. We report a simple to use CRISPR interference (CRISPRi) based platform, compatible with Fluorescence Activated Cell Sorting (FACS)-based reporter screens, to query epistatic relationships at scale. This is enabled by a flexible dual-sgRNA library design that allows for the simultaneous delivery and selection of a fixed sgRNA and a second randomized guide, comprised of a genome-wide library, with a single transduction. We use this approach to identify epistatic relationships for a defined biological pathway, showing both increased sensitivity and specificity than traditional growth screening approaches.

MPFFPSDC: A multi-pooling feature fusion model for predicting synergistic drug combinations.

Drug combination therapies are common practice in the treatment of cancer, but not all combinations result in synergy. As traditional screening approaches are restricted in their ability to uncover synergistic drug combinations, computer-aided medicine is becoming a increasingly prevalent in this field. In this work, a predictive model of potential interactions between drugs named MPFFPSDC is presented, which can maintain the symmetry of drug inputs and eliminate inconsistencies in predictive results caused by different drug inputting sequences or positions. The experimental results show that MPFFPSDC outperforms comparative models in major performance indicators and exhibits better generalization for independent data. Furthermore, the case study demonstrates that our model can capture molecular substructures that contribute to the synergistic effect of two drugs. These results indicate that MPFFPSDC not only offers strong predictive performance, but also has good model interpretability that may provide new insights for the study of drug interaction mechanisms and the development of new drugs.

MSR61 AI Support Reduced Screening Burden in a Systematic Review with Costs and Cost-Effectiveness Outcomes (SR-CCEO) for Cost-Effectiveness Modeling

SR-CCEO should follow the same structured approach as SRs of effectiveness. Screening is one of the most resource-intensive stages and typically requires two independent reviewers to avoid errors. ISPOR Good Practices for Critical Appraisal of SR-CCEO lists two screening approaches to accelerate the process: single reviewer screening and text mining. However, their effectiveness is still debated. We explored whether an AI-assisted, semi-automated three-stage screening approach (AI-assisted single screening – AISS) improves efficiency in identifying the relevant studies for SR of economic evaluations and if it is a safe alternative to the traditional two-reviewers screening approach.

Genome Mining and Screening for Secondary Metabolite Production in the Endophytic Fungus Dactylonectria alcacerensis CT-6.

Endophytic fungi are a treasure trove of natural products with great chemical diversity that is largely unexploited. As an alternative to the traditional bioactivity-guided screening approach, the genome-mining-based approach provides a new methodology for obtaining novel natural products from endophytes. In our study, the whole genome of an endophyte, Dactylonectria alcacerensis CT-6, was obtained for the first time. Genomic analysis indicated that D. alcacerensis CT-6 has one 61.8 Mb genome with a G+C content of 49.86%. Gene annotation was extensively carried out using various BLAST databases. Genome collinearity analysis revealed that D. alcacerensis CT-6 has high homology with three other strains of the Dactylonectria genus. AntiSMASH analysis displayed 45 secondary metabolite biosynthetic gene clusters (BGCs) in D. alcacerensis CT-6, and most of them were unknown and yet to be unveiled. Furthermore, only six known substances had been isolated from the fermented products of D. alcacerensis CT-6, suggesting that a great number of cryptic BGCs in D. alcacerensis CT-6 are silent and/or expressed at low levels under conventional conditions. Therefore, our study provides an important basis for further chemical study of D. alcacerensis CT-6 using the gene-mining strategy to awaken these cryptic BGCs for the production of bioactive secondary metabolites.

Direct Selection of DNA-Encoded Libraries for Biased Agonists of GPCRs on Live Cells.

G protein-coupled receptors (GPCRs) are the largest superfamily of human membrane target proteins for approved drugs. GPCR ligands can have a complex array of pharmacological activities. Among these activities, biased agonists have potential to serve as both chemical probes to understand specific aspects of receptor signaling and therapeutic leads with more specific, desired activity. Challenges exist, however, in the development of new biased activators due, in part, to the low throughput of traditional screening approaches. DNA-encoded chemical libraries (DELs) dramatically improve the throughput of drug discovery by allowing a collective selection, rather than discrete screening, of large compound libraries. The use of DELs has been largely limited to affinity-based selections against purified protein targets, which identify binders only. Herein, we report a split protein complementation approach that allows direct identification of DNA-linked molecules that induce the dimerization of two proteins. We used this selection with a DEL against opioid receptor GPCRs on living cells for the identification of small molecules that possess the specific function of activation of either β-arrestin or G protein signaling pathways. This approach was applied to δ-, μ-, and κ-opioid receptors and enabled the discovery of compound [66,66], a selective, G-protein-biased agonist of the κ-opioid receptor (EC50 = 100 nM, E max = 82%, Gi bias factor = 6.6). This approach should be generally applicable for the direct selection of chemical inducers of dimerization from DELs and expand the utility of DELs to enrich molecules with a specific and desired biochemical function.

Potential roles of extracellular vesicles as a noninvasive tool for prenatal genetic diagnosis

The rate of infertility is increasing owing to genetic and environmental factors. Consequently, assisted reproductive technology has been introduced as an alternative. Bearing in mind the global trend toward the transfer of only one embryo, there is an increasing trend for assessing embryo quality before transfer through prenatal genetic diagnosis (PGD) tests. This ensures that the best-quality embryos are implanted into the uterus. In the invitro fertilization cycle, PGD is not only used for diseases or quality checks before embryo freezing but also for evaluating unfortunate risks, such as aneuploidy, signs of early abortions, and preterm birth. However, traditional preimplantation genetic testing and screening approaches are invasive and harm the health of both the mother and embryo, raising the risk of miscarriage. In the last decade, embryonic extracellular vesicles (EVs) have been investigated and have emerged as a promising diagnostic tool. In this mini-review, we address the use of EVs as a noninvasive biomarker in PGD to test for biological hazards within the embryo without invading its cells. We summarize the state-of-the-art in the use of the embryo's EV content, genomic DNA, messenger RNA, and microRNA in the spent culture medium and their relationship with embryo quality, successful implantation, and pregnancy.

Identification of a novel P2X7 antagonist using structure-based virtual screening.

P2X4 and P2X7 receptors are ATP-gated ion channels, which play important roles in neuropathic and inflammatory pain, and as such they are important drug targets in diseases of inflammatory origin. While several compounds targeting P2X4 and P2X7 receptors have been developed using traditional high-throughput screening approaches, relatively few compounds have been developed using structure-based design. We initially set out to develop compounds targeting human P2X4, by performing virtual screening on the orthosteric (ATP-binding) pocket of a molecular model of human P2X4 based on the crystal structure of the Danio rerio receptor. The screening of a library of approximately 300,000 commercially available drug-like compounds led to the initial selection of 17 compounds; however, none of these compounds displayed a significant antagonist effect at P2X4 in a Fluo-4 ATP-induced calcium influx assay. When the same set of compounds was tested against human P2X7 in an ATP-stimulated Yo-Pro1 dye uptake assay, one compound (an indeno(1,2-b)pyridine derivative; GP-25) reduced the response by greater than 50% when applied at a concentration of 30µM. GP-25 displayed an IC50 value of 8.7μM at human P2X7 and 24.4μM at rat P2X7, and was confirmed to be active using whole-cell patch clamp electrophysiology and not cytotoxic. Schild analysis suggested that mode of action of GP-25 was orthosteric. Screening of a further 16 commercially available analogues of GP-25 led to the discovery of five additional compounds with antagonist activity at human P2X7, enabling us to investigate the structure-activity relationship. Finally, docking of the R- and S-enantiomers of GP-25 into the orthosteric pocket of molecular models of human P2X4 and human P2X7 revealed that, while both enantiomers were able to make multiple interactions between their carboxyl moieties and conserved positively charged amino-acids in human P2X7, only the S-enantiomer of GP-25 was able to do this in human P2X4, potentially explaining the lack of activity of GP-25 at this receptor.

Optimized Screening for At-Risk Students in Mathematics: A Machine Learning Approach

Traditional screening approaches identify students who might be at risk for academic problems based on how they perform on a single screening measure. However, using multiple screening measures may improve accuracy when identifying at-risk students. The advent of machine learning algorithms has allowed researchers to consider using advanced predictive models to identify at-risk students. The purpose of this study is to investigate if machine learning algorithms can strengthen the accuracy of predictions made from progress monitoring data to classify students as at risk for low mathematics performance. This study used a sample of first-grade students who completed a series of computerized formative assessments (Star Math, Star Reading, and Star Early Literacy) during the 2016–2017 (n = 45,478) and 2017–2018 (n = 45,501) school years. Predictive models using two machine learning algorithms (i.e., Random Forest and LogitBoost) were constructed to identify students at risk for low mathematics performance. The classification results were evaluated using evaluation metrics of accuracy, sensitivity, specificity, F1, and Matthews correlation coefficient. Across the five metrics, a multi-measure screening procedure involving mathematics, reading, and early literacy scores generally outperformed single-measure approaches relying solely on mathematics scores. These findings suggest that educators may be able to use a cluster of measures administered once at the beginning of the school year to screen their first grade for at-risk math performance.

Using Alzheimer's disease blood tests to accelerate clinical trial enrollment.

Screening potential participants in Alzheimer's disease (AD) clinical trials with amyloid positron emission tomography (PET) is often time consuming and expensive. A web-based application was developed to model the time and financial cost of screening for AD clinical trials. Four screening approaches were compared; three approaches included an AD blood test at different stages of the screening process. The traditional screening approach using only amyloid PET was the most time consuming and expensive. Incorporating an AD blood test at any point in the screening process decreased both the time and financial cost of trial enrollment. Improvements in AD blood test accuracy over currently available tests only marginally increased savings. Use of a high specificity cut-off may improve the feasibility of screening with only an AD blood test. Incorporating AD blood tests into screening for AD clinical trials may reduce the time and financial cost of enrollment. The time and cost of enrolling participants in Alzheimer's disease (AD) clinical trials were modeled. A web-based application was developed to enable evaluation of key parameters. AD blood tests may decrease the time and financial cost of clinical trial enrollment. Improvements in AD blood test accuracy only marginally increased savings. Use of a high specificity cut-off may enable screening with only an AD blood test.

Trans-channel fluorescence learning improves high-content screening for Alzheimer's disease therapeutics.

In microscopy-based drug screens, fluorescent markers carry critical information on how compounds affect different biological processes. However, practical considerations, such as the labor and preparation formats needed to produce different image channels, hinders the use of certain fluorescent markers. Consequently, completed screens may lack biologically informative but experimentally impractical markers. Here, we present a deep learning method for overcoming these limitations. We accurately generated predicted fluorescent signals from other related markers and validated this new machine learning (ML) method on two biologically distinct datasets. We used the ML method to improve the selection of biologically active compounds for Alzheimer's disease (AD) from a completed high-content high-throughput screen (HCS) that had only contained the original markers. The ML method identified novel compounds that effectively blocked tau aggregation, which had been missed by traditional screening approaches unguided by ML. The method improved triaging efficiency of compound rankings over conventional rankings by raw image channels. We reproduced this ML pipeline on a biologically independent cancer-based dataset, demonstrating its generalizability. The approach is disease-agnostic and applicable across diverse fluorescence microscopy datasets.

Identifying and managing psoriasis-associated comorbidities: the IMPACT research programme

BackgroundPsoriasis is a common, lifelong inflammatory skin disease, the severity of which can range from limited disease involving a small body surface area to extensive skin involvement. It is associated with high levels of physical and psychosocial disability and a range of comorbidities, including cardiovascular disease, and it is currently incurable.ObjectivesTo (1) confirm which patients with psoriasis are at highest risk of developing additional long-term conditions and identify service use and costs to patient, (2) apply knowledge about risk of comorbid disease to the development of targeted screening services to reduce risk of further disease, (3) learn how patients with psoriasis cope with their condition and about their views of service provision, (4) identify the barriers to provision of best care for patients with psoriasis and (5) develop patient self-management resources and staff training packages to improve the lives of people with psoriasis.DesignMixed methods including two systematic reviews, one population cohort study, one primary care screening study, one discrete choice study, four qualitative studies and three mixed-methodology studies.SettingPrimary care, secondary care and online surveys.ParticipantsPeople with psoriasis and health-care professionals who manage patients with psoriasis.ResultsPrevalence rates for psoriasis vary by geographical location. Incidence in the UK was estimated to be between 1.30% and 2.60%. Knowledge about the cost-effectiveness of therapies is limited because high-quality clinical comparisons of interventions have not been done or involve short-term follow-up. After adjusting for known cardiovascular risk factors, psoriasis (including severe forms) was not found to be an independent risk factor for major cardiovascular events; however, co-occurrence of inflammatory arthritis was a risk factor. Traditional risk factors were high in patients with psoriasis. Large numbers of patients with suboptimal management of known risk factors were found by screening patients in primary care. Risk information was seldom discussed with patients as part of screening consultations, meaning that a traditional screening approach may not be effective in reducing comorbidities associated with psoriasis. Gaps in training of health-care practitioners to manage psoriasis effectively were identified, including knowledge about risk factors for comorbidities and methods of facilitating behavioural change. Theory-based, high-design-quality patient materials broadened patient understanding of psoriasis and self-management. A 1-day training course based on motivational interviewing principles was effective in increasing practitioner knowledge and changing consultation styles. The primary economic analysis indicated a high level of uncertainty. Sensitivity analysis indicated some situations when the interventions may be cost-effective. The interventions need to be assessed for long-term (cost-)effectiveness.LimitationsThe duration of patient follow-up in the study of cardiovascular disease was relatively short; as a result, future studies with longer follow-up are recommended.ConclusionsRecognition of the nature of the psoriasis and its impact, knowledge of best practice and guideline use are all limited in those most likely to provide care for the majority of patients. Patients and practitioners are likely to benefit from the provision of appropriate support and/or training that broadens understanding of psoriasis as a complex condition and incorporates support for appropriate health behaviour change. Both interventions were feasible and acceptable to patients and practitioners. Cost-effectiveness remains to be explored.Future workPatient support materials have been created for patients and NHS providers. A 1-day training programme with training materials for dermatologists, specialist nurses and primary care practitioners has been designed. Spin-off research projects include a national study of responses to psoriasis therapy and a global study of the prevalence and incidence of psoriasis. A new clinical service is being developed locally based on the key findings of the Identification and Management of Psoriasis Associated ComorbidiTy (IMPACT) programme.FundingThis project was funded by the National Institute for Health Research (NIHR) Programme Grants for Applied Research programme and will be published in full inProgramme Grants for Applied Research; Vol. 10, No. 3. See the NIHR Journals Library website for further project information.

Automated Generation of Novel Fragments Using Screening Data, a Dual SMILES Autoencoder, Transfer Learning and Syntax Correction

Fragment-based hit identification (FBHI) allows proportionately greater coverage of chemical space using fewer molecules than traditional high-throughput screening approaches. However, effectively exploiting this advantage is highly dependent on the library design. Solubility, stability, chemical complexity, chemical/shape diversity, and synthetic tractability for fragment elaboration are all critical aspects, and molecule design remains a time-consuming task for computational and medicinal chemists. Artificial neural networks have attracted considerable attention in automated de novo design applications and could also prove useful for fragment library design. Chemical autoencoders are neural networks consisting of encoder and decoder parts, which respectively compress and decompress molecular representations. The decoder is applied to samples drawn from the space of compressed representations to generate novel molecules that can be scored for properties of interest. Here, we report an autoencoder model using a recurrent neural network architecture, which was trained using 486,565 fragments curated from commercial sources, to simultaneously reconstruct both SMILES and chemical fingerprints. To explore its utility in fragment design, we applied transfer learning to the fingerprint decoder layers to train a classifier using 66 frequent hitter fragments identified from our screening campaigns. Using a particle swarm optimization sampling approach, we compare the performance of this "dual" model to an architecture encoding SMILES only. The dual model produced valid SMILES with improved features, considering a range of properties including aromatic ring counts, heavy atom count, synthetic accessibility, and a new fragment complexity score we term Feature Complexity (FeCo). Additionally, we demonstrate that generative performance is further enhanced by use of a simple syntax-correction procedure during training, in which invalid and undesirable SMILES are spiked into the training set. Finally, we used the syntax-corrected model to generate a library of novel candidate privileged fragments.

Safely Increasing Connection to Community-Based Services: A Study of Multidisciplinary Team Decision Making for Child Welfare Referrals.

Initial child welfare screening decisions, traditionally made by an individual worker, determine if a family will receive further intervention by child protective services. A multi-disciplinary team (MDT) decision-making approach for child welfare referrals aims to provide a more thorough assessment of needs and strengths and to connect families to appropriate community-based providers. This study examined 159 child welfare referrals handled by MDTs compared to 331 referrals handled via the traditional screening approach. The study used a pseudo randomization procedure to assign referrals to the study conditions: Referrals logged on 2.5 days of the week were assigned to the treatment group; all others were assigned to the comparison group. Referrals handled by an MDT were more than four times as likely as those not handled by an MDT to be referred to community-based organizations (OR = 4.32, p < .001). There were no statistically significant differences in families' engagement with community-based organizations or child welfare outcomes. MDTs are a promising step in the initial process of connecting families to services, although they did not affect this study's longer-term outcomes.

Trans-Channel Fluorescence Learning Improves High-Content Screening for Alzheimer's Disease Therapeutics

In microscopy-based drug screens, fluorescent markers carry critical information on how compounds affect different biological processes. However, practical considerations may hinder the use of certain fluorescent markers. Here, we present a deep learning method for overcoming this limitation. We accurately generated predicted fluorescent signals from other related markers, and validated this new machine learning (ML) method on two biologically distinct datasets. We used the ML method to improve the selection of potentially efficacious therapeutic compounds for Alzheimer’s disease (AD) from high-content high-throughput screening (HCS). The ML method identified compounds that effectively blocked tau aggregation, which would have been missed by traditional screening approaches unguided by ML. The ML method also improved triaging efficiency of compound rankings over a current in-house screening approach. We reproduced this ML method on a biologically independent cancer-based dataset, demonstrating its generalizability. The approach is disease-agnostic, and applicable across fluorescence microscopy datasets.