Storylines
Storylines connect related signals across days and weeks so you can follow a narrative over time.
How to use: Scan → open one item → check evidence.
- FDA press release on higher dose Wegovy approvalfda.gov · fda.gov
- FDA approves higher Wegovy dose via 4th priority voucherpharmaphorum.com · pharmaphorum
- Still basking in the afterglow of its Wegovy pill launch earlier this year, Novo has achieved another victory as it strives to make the most out of its block...fiercepharma.com · Fierce Pharma (All)
Sorted by momentum. Use the chevron to expand a card. Use the action button for the full drawer.
No investment advice. Research signals and sources only. EarlyNarratives provides informational signals derived from public sources. It does not provide financial, legal, or tax advice.
Editorial picks from the weekly briefing.
BioNTech founders to leave and launch new next-generation mRNA company
BioNTech CEO Uğur Şahin and CMO/co-founder Özlem Türeci plan to depart the company by the end of the year to start a new venture focused on next-generation mRNA innovations.
Details
- The departure is planned by the end of the current year, marking an imminent transition.
- Next-generation mRNA innovations are a critical focus area for biotech advancement.
- Industry watchers are closely monitoring BioNTech's post-founder strategic direction.
- Leadership changes at BioNTech could impact the future of mRNA drug development.
- The founders' new venture may drive innovation in next-generation mRNA technologies.
- BioNTech's ability to sustain growth without its founders is uncertain.
EMA publishes multiple new paediatric investigation plans
The European Medicines Agency (EMA) has released several new paediatric investigation plans (PIPs), including EMA/PE/0000224883, EMA/PE/0000224955, EMA/PE/0000225023, EMA/PE/0000225241, EMA/PE/0000226088, and EMA/PE/0000226246.
Details
- EMA’s recent release reflects ongoing regulatory focus on paediatric drug development.
- New PIPs provide updated frameworks for upcoming clinical trials involving children.
- Timely publication aids pharmaceutical companies in aligning with EMA requirements early in development.
- Paediatric investigation plans ensure medicines are appropriately tested for children’s safety and efficacy.
- EMA’s publication supports regulatory compliance and guides clinical trial design for paediatric populations.
- These plans help address the specific medical needs of children in drug development.
FDA approves leucovorin for rare cerebral folate deficiency but not for autism
The FDA has approved Wellcovorin (leucovorin calcium) tablets for treating cerebral folate deficiency in patients with a confirmed folate receptor 1 gene variant (CFD-FOLR1).
Details
- FDA's recent decision addresses urgent unmet needs in rare genetic diseases.
- Walkback on autism claims corrects earlier public confusion about leucovorin's uses.
- Approval expands treatment options for patients with confirmed CFD-FOLR1 variants.
- Provides the first FDA-approved treatment for ultra-rare cerebral folate deficiency.
- Demonstrates regulatory flexibility by approving a drug without a clinical trial for a rare genetic disorder.
- Clarifies that leucovorin is not approved for autism, preventing off-label use.
Advances in antimicrobial resistance prediction using genomic and phenotypic data with novel AI models
Recent research presents innovative computational frameworks to tackle antimicrobial resistance (AMR) by integrating genomic and phenotypic data.
Details
- Rising AMR prevalence demands accelerated development of predictive and diagnostic tools.
- Recent advances in neural networks and foundation models allow improved integration of complex biological data.
- Experimental validation of AI-predicted drug synergies confirms practical utility for combating resistant infections.
- AMR is a critical global health threat needing rapid, interpretable diagnostics and new therapies.
- AI models integrating genomic and phenotypic data can identify resistance mechanisms and drug synergies efficiently.
- Cross-species prediction models enable broader applicability across diverse bacterial pathogens.
Latest storylines from the latest runs. Sorted by momentum.
DeSCENT: Deconvolutional Single-Cell RNA-seq Enhances Transcriptome-based Cancer Survival Analysis
Motivation: Accurate cancer survival prediction requires modeling tumor heterogeneity across both population and cell levels. Most cancer survival analyses use tumor transcriptomes only, since cohorts are usually measured with bulk RNA-seq but are rarely recorded with single-cell RNA-seq. This prevents the direct use of cell-level transcriptomes in cancer survival analysis. Results: To bridge this
Details
The bone marrow microenvironment of RAS pathway mutant B-ALL is enriched for immunosuppressive regulatory T cells
Somatic mutations in the RAS pathway are highly prevalent in B Cell Acute Lymphoblastic Leukemia (B ALL), yet their impact on the bone marrow immune microenvironment and response to immunotherapy remains poorly defined. In this study, we integrated bulk RNA sequencing, single cell RNA sequencing (scRNAseq), and spectral flow cytometry to characterize the immune landscape of RAS mutant B ALL. We id
Details
SpotGraphs: Graph-based analysis of spatially resolved transcriptional data in R
Common spatial transcriptomic analysis pipelines in R focus on pre-processing and visualization, while providing limited and indirect methods to leverage true spatially resolved quantification of transcripts. Often, x,y-coordinates in spatial transcriptomics (ST) data are integrated into analysis via spatially aware normalization (Salim et al., 2024), clustering methods (Zhao et al., 2021), or the
Details
Decoding conformational heterogeneity across disordered proteomes
Intrinsically disordered proteins (IDPs) comprise nearly one-third of the human proteome and play key roles in regulation, signaling, and disease, yet their dynamic nature has resisted accurate structural prediction. Here we introduce AI-IDP, a deep-learning framework that transforms sequence information into experiment-consistent conformational ensembles of disordered proteins. By combining deep-
Details
FDA approves higher Wegovy dose via 4th priority voucher
FDA approves higher Wegovy dose via 4th priority voucher Jonah.Comstock Thu, 19/03/2026 - 18:59
Details
SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction
arXiv:2603.17380v2 Announce Type: replace-cross Abstract: Virtual cell models aim to enable in silico experimentation by predicting how cells respond to genetic, chemical, or cytokine perturbations from single-cell measurements. In practice, however, large-scale perturbation prediction remains constrained by three coupled bottlenecks: inefficient training and inference pipelines, unstable modeling
Details
Dual targeting of PDPK1 and BRAF V600E is synthetically lethal
PDPK1 functions downstream of PI3K and is essential for activating AKT and other AGC kinases. Although PDPK1 has a central role in the PI3K/AKT/mTOR signaling pathway, there has been limited evaluation of it as a target for cancer therapy. Anaplastic thyroid cancer (ATC) has one of the highest mortality rates of all human malignancies. Although combined BRAF and MEK inhibition in BRAF V600E mutant
Details
HARVEST: Unlocking the Dark Bioactivity Data of Pharmaceutical Patents via Agentic AI
Pharmaceutical patents contain vast Structure-Activity Relationship tables documenting protein-ligand binding data that are technically public yet computationally inaccessible, rendering this wealth of data effectively dark - trapped in unstructured archives no existing database has systematically captured. We present HARVEST, a multi-agent large language model pipeline that autonomously extracts
Details
Structure’s GLP-1 pill shows ‘best-in-class’ potential in obesity trial
Testing revealed weight loss effects some Wall Street analysts believe compare favorably to Lilly’s orforglipron, which regulators could approve within weeks.
Details
RNASTOP: A Deep Learning Framework for mRNA Chemical Stability Prediction and Optimization
Messenger RNA (mRNA) vaccines offer promising therapeutics for combating various diseases, yet their inherent chemical instability hampers their long-term efficacy. Although several methods have been developed to predict mRNA degradation, they exhibit limited accuracy and lack the capability for rational sequence optimization. Here, we propose RNASTOP, a novel framework integrating deep learning w
Details
Pfizer’s Ibrance successor moves forward with new study data
The drug, which one analyst described as a “critical” part of Pfizer’s oncology strategy, represents a possible improvement upon Ibrance and other, similar breast cancer medicines from Eli Lilly and Novartis.
Details
Glydentify: An explainable deep learning platform for glycosyltransferase donor substrate prediction
Glycosyltransferases (GTs) are a large family of enzymes that catalyze the formation of glycosidic linkages between chemically diverse donor and acceptor molecules to regulate diverse cellular processes across all domains of life. Despite their importance, the activated sugar donors (donor substrates) used by most GTs remain unidentified, limiting our understanding of GT functions. To address this
Details
Rhythm obesity drug wins broader use from FDA
Imcivree’s clearance in a type of obesity driven by brain injury could unlock an opportunity Wall Street analysts believe to be worth more than $1 billion.
Details
US judge rules Kennedy's vaccine changes 'unlawful'
US judge rules Kennedy's vaccine changes 'unlawful' Phil.Taylor Tue, 17/03/2026 - 08:03
Details
Bacteriophage host prediction using a genome language model
Computational bacteriophage host prediction from genomic sequences remains challenging because host range depends on diverse, rapidly evolving genomic determinants--from receptor-binding proteins to anti-defense systems and downstream infection compatibility--and because the signals available to predictors, including sequence homology, CRISPR spacer matches, nucleotide composition, and mobile gene
Details
STiLE: Automated Tissue Microarray Dearraying for Spatial Transcriptomics
Tissue microarrays (TMAs) enable high-throughput spatial transcriptomic profiling of dozens of tissue cores on a single slide. However, existing dearraying methods operate on histological images and do not support the coordinate-based outputs of spatial transcriptomics platforms. Therefore, task of assigning cells to their respective cores (dearraying) remains a manual bottleneck. We present STiLE
Details
Novartis snaps up PI3Kα breast cancer drug in $3bn deal
Novartis snaps up PI3Kα breast cancer drug in $3bn deal Phil.Taylor Fri, 20/03/2026 - 11:21
Details
Neuronal overexpression of Nrf2 reduces dystrophic neurites in 5XFAD Alzheimer's disease model mice
Background: The hallmark lesions of the Alzheimer's disease (AD) brain are amyloid plaques consisting of the beta-amyloid protein and neurofibrillary tangles comprised of hyperphosphorylated, aggregated tau protein, which both cause neuronal dysfunction and loss. One goal of neuroprotective therapies is to maintain normal neuronal function and survival in the presence of toxic pathologies such as
Details
Unlock source trails, evidence timestamps, archive access, and workflow tools.