Congenital dyserythropoietic anemia type II (CDAII) is an autosomal recessive disease resulting from loss-of-function mutations in SEC23 homolog B (SEC23B). We have previously shown that increased expression of SEC23A, a paralogous protein for SEC23B, rescues the CDAII erythroid defect. Here, we generated a human erythroid cell line that expresses enhanced green fluorescent protein (eGFP) from the endogenous SEC23A locus and performed a small-molecule screen to identify compounds that increased SEC23A-eGFP abundance. The top compound passing all filters was an inhibitor of lysine-specific demethylase 1 (LSD1). We found that LSD1 inhibition with RN1 resulted in increased SEC23A expression in erythroid cells derived from human hematopoietic stem and progenitor cells (HSPCs) at doses that did not impair erythroid cell growth or differentiation and rescued the erythroid defect resulting from SEC23B deletion. Genetic down-regulation of LSD1 led to a marked increase in SEC23A mRNA expression in HSPC-derived erythroid cells. Deletion of Lsd1 in mouse erythroid cells resulted in increased Sec23a expression, and RN1 treatment ameliorated the erythroid defect observed in a CDAII mouse model. Mechanistically, we found that LSD1 occupied a sequence in the SEC23A promoter, repressing SEC23A transcription. Deletion of the promotor sequence occupied by LSD1 resulted in increased SEC23A expression and amelioration of CDAII. These findings highlight that LSD1 represses SEC23A transcription and that LSD1 inhibition results in de-repression of SEC23A expression and amelioration of the CDAII erythroid defect, suggesting promising therapeutic strategies for CDAII.

Gene regulatory networks (GRNs) are essential for understanding how genes coordinate cellular processes. Large-scale single-cell perturbation studies now offer powerful opportunities for GRN inference, yet many state-of-the-art (SOTA) methods fail to fully use interventional information. We present PSGRN, a top-performing method in the CausalBench Challenge, which integrates interventional and observational single-cell RNA sequencing data using a self-training framework with synthetic gold standards. Across eight datasets and six evaluation metrics, PSGRN consistently outperformed existing approaches. With interventional data, it achieved up to 43% higher Wasserstein distances and the lowest false omission rate in K562 compared with recent SOTA methods. Using experimentally validated regulatory interactions, PSGRN showed up to 30% gains in precision and over 100% gains in recall. These results highlight PSGRN's versatility and scalability, establishing it as a robust tool for GRN inference and biological discovery from single-cell data.

Decoding visual stimuli from neural signals is an essential step toward understanding how sensory information is represented in the brain. While most existing approaches reconstruct visual stimuli from human functional magnetic resonance imaging (fMRI), utilizing calcium imaging in mice opens the door to single-neuron-level insights into non-primate visual systems with distinct spectral sensitivities. Here, we present Sensorium-Viz, a diffusion-based framework specifically designed for decoding activity in the mouse primary visual cortex. The model is among the first to reliably reconstruct complex, high-resolution images from previously unseen single-neuron responses. At its core, Sensorium-Viz introduces two key advances for neuron-to-image decoding: a synthetic-response augmentation strategy that improves reconstruction performance by more than 30% while enabling cross-mouse generalization through fine-tuning, and an architectural design that integrates a Diffusion Transformer (DiT) with a spatial neuron-embedding module, thereby achieving up to a 10.65% performance gain over leading fMRI-based reconstruction methods across pixel- and content-level benchmarks. Analysis of the neural responses and corresponding reconstructions reveals that neurons sensitive to low-level visual features form the primary basis of V1's representation of external stimuli. These findings establish Sensorium-Viz as a biologically grounded and technically robust tool for vision decoding.

Analysis of Diamond Blackfan anemia syndrome (DBAS) cohorts and animal models have not revealed a potential mechanism for the variable anemia phenotype, a key feature of this disease. Here, we utilized an established Rpl5Skax23-Jus/+ murine DBAS model in order to study this dynamic erythropoiesis deficiency. These haploinsufficient mice exhibit variably penetrant craniofacial and cardiac defects mimicking the phenotypes of DBAS patients bearing RPL5 mutations. We additionally discovered that this specific heterozygous splicing mutation is pathogenic and leads to partial intron retention. By examining the transcriptome of fetal liver erythroid progenitors at E12.5, we demonstrate downregulation of erythroid differentiation pathways consistent with the DBAS phenotype. We also identified dysregulated transcription of lipid metabolism genes with significant reduction in Scd1 expression in the subset of E12.5 mutant embryos at risk for erythroid failure. SCD1, a key enzyme that converts saturated to monounsaturated fatty acids, has not been previously linked to erythropoiesis or DBAS. When anemia was induced in adult Rpl5Skax23-Jus/+ mice, mutant mice exhibited delayed erythroid recovery, whereas pretreatment with an SCD1 inhibitor resulted in improved erythropoiesis in both wildtype and mutant mice. This analysis suggests a potential role of lipid metabolism in the variable anemia penetrance in DBAS and highlights a previously unappreciated pathway that requires further study as a potential target for drug development.

Single-cell sequencing provides detailed insights into individual cell behaviors within complex systems based on the assumption that each cell is uniquely isolated. However, doublets-where two or more cells are sequenced together-disrupt this assumption and can lead to potential data misinterpretations. Traditional doublet detection methods primarily rely on simulated genomic data, which may be less effective in homogeneous cell populations and can introduce biases from experimental processes. Therefore, we introduce ImageDoubler in this study, an innovative image-based model that identifies doublets and missing samples leveraging the Fluidigm single-cell sequencing image data. Our approach showcases a notable doublet detection efficacy, achieving a rate up to 93.87% and registering a minimum improvement of 33.1% in F1 scores compared to existing genomic-based methods. This advancement highlights the potential of using imaging to glean insight into developing doublet detection algorithms and exposes the limitations inherent in current genomic-based techniques.

Analysis of neither Diamond Blackfan anemia syndrome (DBAS) cohorts nor animal models has revealed a potential mechanism for the variable anemia phenotype, a key feature of this disease. Here, we utilized an established Rpl5 Skax23-Jus/+ murine DBAS model in order to study this dynamic erythropoiesis deficiency. These haploinsufficient mice exhibit variably penetrant craniofacial and cardiac defects mimicking the phenotypes of DBAS patients bearing RPL5 mutations. We additionally discovered that this specific heterozygous splicing mutation is pathogenic and leads to partial intron retention. By examining the transcriptome of fetal liver erythroid progenitors at E12.5, we demonstrate that the downregulation of erythroid differentiation pathways is consistent with the DBAS phenotype. We also identified dysregulated transcription of lipid metabolism genes with significant reduction in the abundance of Scd1 in a subset of E12.5 mutant embryos at risk for erythroid failure. SCD1, a key enzyme that converts saturated to monounsaturated fatty acids, has not been previously linked to erythropoiesis or DBAS. When anemia was induced in adult mice, pretreatment with an SCD1 inhibitor resulted in improved erythropoiesis. This analysis suggests a key role of lipid metabolism in the variable anemia penetrance in DBAS and highlights a previously unappreciated pathway that may serve as a potential target for drug development. Key Points:The variable anemia in Rpl5 Skax23-Jus/+ mice is triggered by intrinsic/extrinsic stress Rpl5 haploinsufficient murine and human erythroid progenitors exhibit a lipid metabolism signature with downregulation of Scd1 / SCD .

In drug discovery, mapping interactions between genes within cellular systems is a crucial early step. This helps formulate hypotheses regarding molecular mechanisms that could potentially be targeted by future medicines. The CausalBench Challenge was an initiative to invite the machine learning community to advance the state of the art in constructing gene-gene interaction networks. These networks, derived from large-scale, real-world datasets of single cells under various perturbations, are crucial for understanding the causal mechanisms underlying disease biology. Using the framework provided by the CausalBench benchmark, participants were tasked with enhancing the capacity of the state of the art methods to leverage large-scale genetic perturbation data. This report provides an analysis and summary of the methods submitted during the challenge to give a partial image of the state of the art at the time of the challenge. The winning solutions significantly improved performance compared to previous baselines, establishing a new state of the art for this critical task in biology and medicine.

Diamond Blackfan anemia syndrome (DBAS) is a heterogeneous genetic disorder mainly caused by de novo heterozygous ribosomal protein variants, including RPL5. Analysis of DBAS cohorts and animal models has not revealed a potential mechanism for the variable anemia phenotype, which is a key feature of this disease. Treatment-independence occurs in approximately 20% of individuals who previously required steroids or red blood cell transfusions. The underlying mechanism of this phenomenon remains unknown. We previously characterized Rpl5Skax23-Jus/+mice and demonstrated a severe defect in erythropoiesis at E12.5, which led to early embryonic demise in some mutants while others (within the same litter) survived and had complete resolution of anemia by 3 weeks of age. In order to further explore the mechanism leading to this defect, we performed timed matings (Rpl5Skax23-Jus/+ x wildtype (WT)) to obtain E12.5 fetal liver (FL) cells, which were sorted by flow cytometry to obtain CD71+ Ter119- early erythroid progenitor cells. Total RNA was extracted and we performed bulk RNA-seq analysis. We divided mutants into two groups based on liver cellularity with the hypothesis that mutants with very low cellularity (M-low) were the ones with impending erythroid failure and death, while those with close to normal cellularity (M-high) had a higher chance of spontaneous recovery. Analysis of RNA-seq data demonstrated downregulation of erythroid differentiation pathways consistent with the DBAS phenotype. We also identified dysregulation of lipid metabolism genes with significant downregulation of Scd1 in the subset of E12.5 mutant embryos at risk for complete erythroid failure (M-low). SCD1 is a key enzyme found in the endoplasmic reticulum, which catalyzes the conversion of saturated to monounsaturated fatty acids. The role of SCD1 and lipid metabolism in erythropoiesis and in DBA is currently unknown. To test the effect of Scd1 downregulation on erythropoiesis, we pretreated adult mice with a SCD1 inhibitor (SCD1-i) or DMSO daily for 2 weeks then administered phenylhydrazine following pretreatment in order to induce anemia.Mutant mice treated with DMSO showed a significant anemia compared with WT whereas SCD1-i treated mice had no or less significant differences in red blood cell counts. In order to explore the effect of the drug on erythropoiesis, we analyzed hematopoietic stem and progenitor cells by flow cytometry. Mice treated with SCD1-i showed a significant increase in CFU-E and decrease in pre-CFU-E counts in the bone marrow when compared to mice treated with DMSO indicating that downregulation of Scd1 is a compensatory mechanism to improve erythropoiesis in DBA. We propose modulation of lipid metabolism and/or SCD1 as a possible mechanism for the variable anemia penetrance in DBAS and as a novel treatment strategy that warrants further study.

ABSTRACT:Small molecules that inhibit LSD1 (lysine-specific demethylase 1, KDM1A) have been shown to induce abundant fetal hemoglobin (HbF) levels in red blood cells both in vitro and in vivo, therefore potentially serving as potent and cost-effective therapeutics to treat the β-globinopathies, sickle cell disease (SCD), and β-thalassemia major (TM). However, most LSD1 inhibitors (LSD1is) that induce HbF in vivo are covalent and irreversible, which leads to adverse effects. In this study, we utilized structure-aided drug design to develop potent new reversible LSD1is, leading to robust γ-globin expression in vitro. Moreover, in a mouse model of SCD, oral administration of these novel inhibitors leads to significant HbF elevation and alleviation of multiple features of disease pathology that are the usual consequences of SCD. In addition, we discovered that combined treatment of an LSD1i with a BRD4 degrader (BD-9136) represses the induction of RUNX1 and PU.1, thereby rescuing the erythroid to myeloid lineage conversion that accompanies LSD1is in hematopoiesis. The data indicate that this new generation of LSD1is can effectively induce HbF levels, reduce SCD pathologies, and are well tolerated by oral administration in SCD mice. We anticipate that the combination of these or related binary compounds offer exciting new therapeutic possibilities for treating SCD and TM.

Gene networks (GNs) represent the complex molecular interactions that regulate cellular states. Existing sequence and graph based deep learning approaches have advanced GN inference but remain constrained by their reliance on specialized data. Large language models (LLMs) offer a promising alternative by reframing structured biological problems as natural language inference tasks. However, a major bottleneck lies in prompt design, where fixed prompts or task-specific soft prompts cannot adapt to the heterogeneity of gene-gene relationships. Here we introduce GRASP (Gene-Relation Adaptive Soft Prompt), a framework that performs universal GN inference directly from gene symbols. GRASP generates pair-specific adaptive tokens by encoding gene-level representations and relational contrasts into latent vectors, enabling context-aware inference while preserving parameter efficiency. Across large-scale protein-protein interaction (PPI) benchmarks, GRASP consistently outperforms other baselines, achieving ROC-AUC values up to 0.937. GRASP further demonstrates strong cross-species transferability, robust performance in phosphorylation network inference, and discovery potential by recovering previously mislabeled gene interactions. ### Competing Interest Statement The authors have declared no competing interest.

Artificial intelligence (AI) is driving innovation in clinical pharmacology and translational science with tools to advance drug development, clinical trials, and patient care. This review summarizes the key takeaways from the AI preconference at the American Society for Clinical Pharmacology and Therapeutics (ASCPT) 2024 Annual Meeting in Colorado Springs, where experts from academia, industry, and regulatory bodies discussed how AI is streamlining drug discovery, dosing strategies, outcome assessment, and patient care. The theme of the preconference was centered around how AI can empower clinical pharmacologists and translational researchers to make informed decisions and translate research findings into practice. The preconference also looked at the impact of large language models in biomedical research and how these tools are democratizing data analysis and empowering researchers. The application of explainable AI in predicting drug efficacy and safety, and the ethical considerations that should be applied when integrating AI into clinical and biomedical research were also touched upon. By sharing these diverse perspectives and real-world examples, this review shows how AI can be used in clinical pharmacology and translational science to bring efficiency and accelerate drug discovery and development to address patients' unmet clinical needs.

ABSTRACT:Nuclear receptor TR4 (NR2C2) was previously shown to bind to the -117 position of the γ-globin gene promoters in vitro, which overlaps the more recently described BCL11 transcription factor A (BCL11A) binding site. The role of TR4 in human γ-globin gene repression has not been extensively characterized in vivo, whereas any relationship between TR4 and BCL11A regulation through the γ-globin promoters is unclear at present. We show here that TR4 and BCL11A competitively bind in vitro to distinct, overlapping sequences, including positions overlapping -117 of the γ-globin promoter. We found that TR4 represses γ-globin transcription and fetal hemoglobin accumulation in vivo in a BCL11A-independent manner. Finally, examination of the chromatin occupancy of TR4 within the β-globin locus, compared with BCL11A, shows that both bind avidly to the locus control region and other sites, but only BCL11A binds to the γ-globin promoters at statistically significant frequency. These data resolve an important discrepancy in the literature and, thus, clarify possible approaches to the treatment of sickle cell disease and β-thalassaemia.

Tumours are dynamically evolving populations of cells. Subclonal reconstruction algorithms use bulk DNA sequencing data to quantify parameters of tumour evolution, allowing assessment of how cancers initiate, progress and respond to selective pressures. A plethora of subclonal reconstruction algorithms have been created, but their relative performance across the varying biological and technical features of real-world cancer genomic data is unclear. We therefore launched the ICGC-TCGA DREAM Somatic Mutation Calling -- Tumour Heterogeneity and Evolution Challenge. This seven-year community effort used cloud-computing to benchmark 31 containerized subclonal reconstruction algorithms on 51 simulated tumours. Each algorithm was scored for accuracy on seven independent tasks, leading to 12,061 total runs. Algorithm choice influenced performance significantly more than tumour features, but purity-adjusted read-depth, copy number state and read mappability were associated with performance of most algorithms on most tasks. No single algorithm was a top performer for all seven tasks and existing ensemble strategies were surprisingly unable to outperform the best individual methods, highlighting a key research need. All containerized methods, evaluation code and datasets are available to support further assessment of the determinants of subclonal reconstruction accuracy and development of improved methods to understand tumour evolution.

Recent advancements in digital biomarkers have highlighted the importance of accelerometer and gyroscope data for monitoring activities, identifying motion-related diseases, and assessing disease severity. Prior studies predominantly limit sensor placement to one or two locations. Here, we conducted a trial focusing on the impact of sensor placement in predicting 21 common activities using convolutional neural networks (CNN) and long short-term memory networks (LSTM). Our research found that the optimal locations for activity detection are the right and left upper arms, right wrist, and lower back. These locations yielded an average AUC of 0.76-0.77 using both accelerometer and gyroscope data. Combining data from all locations improved AUC to 0.796 for accelerometer and 0.811 for gyroscope data. We also noted specific activity-body part sensitivity relationships. This study provides a valuable reference for selecting appropriate sensor locations in future digital biomarker studies focused on specific activities.

Abstract Modeling neuron responses to stimuli can shed light on next‐generation technologies such as brain‐chip interfaces. Furthermore, high‐performing models can serve to help formulate hypotheses and reveal the mechanisms underlying neural responses. Here the state‐of‐the‐art computational model is presented for predicting single neuron responses to natural stimuli in the primary visual cortex (V1) of mice. The algorithm incorporates object positions and assembles multiple models with different train‐validation data, resulting in a 15%–30% improvement over the existing models in cross‐subject predictions and ranking first in the SENSORIUM 2022 Challenge, which benchmarks methods for neuron‐specific prediction based on thousands of images. Importantly, The model reveals evidence that the spatial organizations of V1 are conserved across mice. This model will serve as an important noninvasive tool for understanding and utilizing the response patterns of primary visual cortex neurons.

Spinocerebellar ataxia type 3 (SCA3) is the most common dominantly inherited ataxia. Currently, no preventive or disease-modifying treatments exist for this progressive neurodegenerative disorder, although efforts using gene silencing approaches are under clinical trial investigation. The disease is caused by a CAG repeat expansion in the mutant gene, ATXN3, producing an enlarged polyglutamine tract in the mutant protein. Similar to other paradigmatic neurodegenerative diseases, studies evaluating the pathogenic mechanism focus primarily on neuronal implications. Consequently, therapeutic interventions often overlook non-neuronal contributions to disease. Our lab recently reported that oligodendrocytes display some of the earliest and most progressive dysfunction in SCA3 mice. Evidence of disease-associated oligodendrocyte signatures has also been reported in other neurodegenerative diseases, including Alzheimer's disease, amyotrophic lateral sclerosis, Parkinson's disease, and Huntington's disease. Here, we assess the effects of anti-ATXN3 antisense oligonucleotide (ASO) treatment on oligodendrocyte dysfunction in premanifest and symptomatic SCA3 mice. We report a severe, but modifiable, deficit in oligodendrocyte maturation caused by the toxic gain-of-function of mutant ATXN3 early in SCA3 disease that is transcriptionally, biochemically, and functionally rescued with anti-ATXN3 ASO. Our results highlight the promising use of an ASO therapy across neurodegenerative diseases that requires glial targeting in addition to affected neuronal populations.

Drug response prediction is essential for drug development and disease treatment. One key question in predicting drug response is the representation of molecules, which has been greatly advanced by artificial intelligence (AI) techniques in recent years. In this review, we first describe different types of representation methods, pinpointing their key principles and discussing their limitations. Thereafter we discuss potential ways how these methods could be further developed. We expect that this review will provide useful guidance for researchers in the community.

A promising alternative to comprehensively performing genomics experiments is to, instead, perform a subset of experiments and use computational methods to impute the remainder. However, identifying the best imputation methods and what measures meaningfully evaluate performance are open questions. We address these questions by comprehensively analyzing 23 methods from the ENCODE Imputation Challenge. We find that imputation evaluations are challenging and confounded by distributional shifts from differences in data collection and processing over time, the amount of available data, and redundancy among performance measures. Our analyses suggest simple steps for overcoming these issues and promising directions for more robust research.

Alternative splicing (AS) is a key transcriptional regulation pathway. Recent studies have shown that AS events are associated with the occurrence of complex diseases. Various computational approaches have been developed for the detection of disease-associated AS events. In this review, we first describe the metrics used for quantitative characterization of AS events. Second, we review and discuss the three types of methods for detecting disease-associated splicing events, which are differential splicing analysis, aberrant splicing detection and splicing-related network analysis. Third, to further exploit the genetic mechanism of disease-associated AS events, we describe the methods for detecting genetic variants that potentially regulate splicing. For each type of methods, we conducted experimental comparison to illustrate their performance. Finally, we discuss the limitations of these methods and point out potential ways to address them. We anticipate that this review provides a systematic understanding of computational approaches for the analysis of disease-associated splicing.