Daily biotech intelligence: FDA actions, drug recalls, and recent research.
Unknown — Approved Sponsor: EXTROVIS · Application type: ORIG · Date: 20260417 · Priority: STANDARD
COSENTYX (SECUKINUMAB) — Approved Sponsor: NOVARTIS PHARMS CORP · Application type: SUPPL · Date: 20200129 · Priority: STANDARD
Unknown — Approved Sponsor: AUROBINDO PHARMA LTD · Application type: ORIG · Date: 20260420 · Priority: STANDARD
COSENTYX (SECUKINUMAB) — Approved Sponsor: NOVARTIS PHARMS CORP · Application type: SUPPL · Date: 20250312 · Priority: STANDARD
VALPROIC ACID — Approved Sponsor: QUAGEN · Application type: SUPPL · Date: 20260417 · Priority: STANDARD
DALFAMPRIDINE — Approved Sponsor: ACCORD HLTHCARE · Application type: ORIG · Date: 20180711 · Priority: STANDARD
Fagron Compounding Services [Class II] — 20260415 Product: Vancomycin HCI, 1.5 grams added to 250 mL, 0.9% Sodium Chloride Injection USP, Fagron Sterile Servic Reason: Lack of Assurance of Sterility; blue Break-Off-Part could detach from the administration port
Fresenius Kabi USA, LLC [Class II] — 20260415 Product: 0.9% Sodium Chloride Injection, USP, (2,250 mg per 250 mL) (9 mg per mL) 250 mL in a 250 mL freeflex Reason: Lack of Assurance of Sterility
Fresenius Kabi USA, LLC [Class II] — 20260415 Product: 0.45% Sodium Chloride Injection, USP, 1.125 grams per 250 mL (4.5 mg per mL), 250 mL in a 250 mL fre Reason: Lack of Assurance of Sterility
Teva Pharmaceuticals USA, Inc [Class II] — 20260415 Product: Clonidine Transdermal System, USP, 0.2 mg/day, supplied in cartons of 4 Systems and 4 Adhesive Cover Reason: CGMP Deviations: use of an unapproved raw material
Fresenius Kabi USA, LLC [Class II] — 20260415 Product: 0.9% Sodium Chloride Injection, USP 900 mg per 100 mL (9 mg per mL) 500 mL in a Single Dose freeflex Reason: Lack of Assurance of Sterility
Sina Gholami, Abdulmoneam Ali, Tania Haghighi · 2026-04-22 · cs.LG · cs.AI
Federated learning (FL) enables collaborative model training without sharing raw data; however, the presence of noisy labels across distributed clients can severely degrade the learning performance. In this paper, we propose FedSIR, a multi-stage framework for robust FL under noisy labels. Different from existing approaches that mainly rely on desi
Ana Sanchez-Fernandez, Thomas Pinetz, Werner Zellinger · 2026-04-22 · cs.LG · q-bio.QM
The central problem in biomedical imaging are batch effects: systematic technical variations unrelated to the biological signal of interest. These batch effects critically undermine experimental reproducibility and are the primary cause of failure of deep learning systems on new experimental batches, preventing their practical use in the real world
Thorsten Hoeser, Felix Bachofer, Claudia Kuenzer · 2026-04-22 · cs.CV · cs.LG
The offshore wind energy sector is expanding rapidly, increasing the need for independent, high-temporal-resolution monitoring of infrastructure deployment and operation at global scale. While Earth Observation based offshore wind infrastructure mapping has matured for spatial localization, existing open datasets lack temporally dense and semantica
Yiming Bian, Joshua M. Akey · 2026-04-22 · cs.LG · cs.DC
The scalability of long-context large language models is fundamentally limited by the quadratic memory cost of exact self-attention, which often leads to out-of-memory (OOM) failures on modern hardware. Existing methods improve memory efficiency to near-linear complexity, while assuming that the full query, key, and value tensors fit in device memo
Deqing Fu, Tianyi Zhou, Mikhail Belkin · 2026-04-22 · cs.CL · cs.AI
Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this paper, we identify a two-tiered hierarchy of these features: while Transformers, Linear RNNs, LSTMs, and classical word embeddings trained in different ways all learn features that have period-$T$ spikes in the F
Shelly Golan, Michael Finkelson, Ariel Bereslavsky · 2026-04-22 · cs.LG · cs.CV
Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a single scalar reward. When multiple criteria matter, the prevailing practice of ``early scalarization'' collapses rewards into a fixed weighted sum. This commits the model to a single trade-off point at
Dimitrije Antić, Alvaro Budria, George Paschalidis · 2026-04-22 · cs.CV · cs.LG
Reconstructing 3D Human-Object Interaction from an RGB image is essential for perceptive systems. Yet, this remains challenging as it requires capturing the subtle physical coupling between the body and objects. While current methods rely on sparse, binary contact cues, these fail to model the continuous proximity and dense spatial relationships th
Ali Rayat, Yaohang Li, Gia-Wei Chern · 2026-04-22 · cond-mat.str-el · cs.LG
Local gauge symmetry underlies fundamental interactions and strongly correlated quantum matter, yet existing machine-learning approaches lack a general, principled framework for learning under site-dependent symmetries, particularly for intrinsically nonlocal observables. Here we introduce a gauge-equivariant graph neural network that embeds non-Ab
STAT+: Can Erasca be biotech’s next big thing? We’ll see (STAT News) Can Erasca be biotech's next big thing?
Opinion: Kennedy’s new silence on vaccines is political — and it won’t last (STAT News) Kennedy’s public messaging on vaccines has shifted ahead of the midterms. It won’t last.
STAT+: Will bargain-basement telehealth visits help pharma drive drug scripts? (STAT News) As links between pharmaceutical companies and telehealth providers grow, health policy experts and legislators have sounded alarms.
STAT+: Publicly, Kennedy embraces a more moderate MAHA (STAT News) Kennedy continues to make waves across health care, but he's pulled back on a number of core MAHA issues.
STAT+: Federal test of AI prior authorization is delaying care for seniors, report says (STAT News) A new Medicare prior authorization test is delaying care at Washington state hospitals – and should be scrapped, senator says.
Former tobacco executive joins CDC senior leadership, raising concerns over industry influence (STAT News) Naming a former Imperial Brands executive for a CDC job is the latest example, advocates say, of tobacco industry influence in Trump administration.
STAT+: At AACR, talk of Chinese biotech, oncology’s comms issue, and more (STAT News) At AACR, there was talk of Chinese biotech's place in cancer research, oncology’s comms issue, and more.
Video: Robert F. Kennedy Jr. testifies before Senate HELP committee (STAT News) Watch RFK Jr. testify before the Senate's health care panel.
Increased calls to 988 hotline associated with a drop in suicides among young people, study finds (STAT News) Suicide rates among young people dropped 11% after the U.S. launched the 988 national suicide and crisis hotline, a new study shows
STAT+: Gene therapy trial for deafness adds evidence to drug’s efficacy (STAT News) After gene therapy for a rare form of deafness, 90% of participants in a clinical trial in China had significant improvement in hearing.
Revolution drug shows promise in early pancreatic cancer (BioPharma Dive) The findings build on data suggesting Revolution’s therapy could upend treatment for a notoriously tough-to-treat tumor and generate billions in sales.
Moderna, after losing US funding, rebounds to start mRNA bird flu vaccine trial (BioPharma Dive) A program that got caught up in HHS’ decision to abandon mRNA research was revived by a public-private coalition and is now beginning a large, late-stage test that could support a future approval.
This briefing is compiled automatically from FDA public APIs (openFDA), arXiv, and industry RSS feeds (STAT News, Fierce Biotech, BioPharma Dive, Nature, Science News). Not investment advice. Verify all data before making any decisions.