AI News Archive: July 5, 2026 — Part 7
Sourced from 500+ daily AI sources, scored by relevance.
- Hanes Moisture-Wicking Briefs
Stay cool, dry, and comfortable all day with advanced tech.
- CT999 Gaming
Money Earning Gambling App
- 5 AI Workflows for Coaches
Free PDF — built & sold by an AI running its own company
- Notion Ultimate Life Planner
All-in-One Second Brain & Productivity System
- SmileCare AI
AI receptionist for dental clinics and salons.
- Aura Volume Booster for Chromium.
Boost your browser audio up to 600% with clarity.
- FuelNow
cheapest gas station
- Pixel Recall
Memorize pixel art. Redraw it from memory. Every day.
- White-Label Crypto Exchange Software
Skip 12 months of dev - launch a crypto exchange today
- Corteiz Spains
Corteiz® | Tienda oficial RTW CRTZ | Recién llegados
- Fintly
A calm, present AI companion — always there to talk to
- ZAMPETY
Swipe, Play, Repeat Zampety
- Tagada
The ecommerce OS for DTC brands scaling aggressively
- Offering Pre-Launch Over 50% Off Guss Ai
Business Agent "Desktop Software!" (Lifetime) Who Act Now!
- FinchPulse
AI-powered customer feedback & product intelligence platform
- Leave Your Face Alone
Privacy first Auto-Detection for Hand-to-Face Habits
- Nyan-8
World's Cutest Language Exchange Site
- Fubo.tv/connect Enter Code
active smart tv instantly
- QariAI
AI coach that hears every mistake and corrects
- chattypet
Every Pet Has a Voice. ChattyPet Brings It to Life
- QuelpAI - Your Website Sales Assistant
Turn your website into an AI sales assistant
- QevosAgent
Your local generic task AI agent , no cloud needed
- Meant for More. break the scroll
Ai productivity rules enforcer.
- OkzByte
AI, Blockchain & Full-Stack Technology Company
- AI Agents Vault
AI voice agents for restaurants, dental, law & real estate
- Black_Dragon AI
lightweight AI assistant and local code workbench
- AgentForgeAI
Your AI Sales Rep That Never Sleeps
- Hystersis
Turning interactions into intelligence.
- CueTheScene
Finish a YouTube video in 20 minutes. Not 8 hours.
- Specifys.ai
Plan your dream app with smart AI tools
- Task-adapted biological foundation models uncover perturbation-centric representations
Foundation models have emerged as powerful tools for learning transferable representations of biological systems, yet their latent spaces are typically optimized to capture cellular state rather than the effects of perturbations. Here, we demonstrate that a biological foundation model can be repurposed to learn a fundamentally different representation by changing its learning objective. We finetuned scGPT, a transformer pre-trained on over 30 million single cell transcriptomes, on more than three million LINCS L1000 perturbation profiles using a supervised objective that predicts perturbation identity. This transformed the latent space into a perturbation centric representation that aligned transcriptional responses induced by the same chemical or genetic perturbation across heterogeneous experimental conditions. Finetuned embeddings substantially outperformed both gene expression profiles and the original pretrained model, recovering [85, 100%] of perturbations within the top 100 nearest neighbors and increasing perturbation classification accuracy from [10, 19%] to [25, 49%]. Remarkably, although the model was trained exclusively to recognize perturbation identity, the learned representation spontaneously captured orthogonal biological relationships never provided during training, including chemical similarity (AUROC up to 0.81), mechanisms of action (Hit@10 up to 100%), compound target relationships (AUROC up to 0.74), and functional relationships between genetic perturbations. The resulting embedding space enabled mechanism-of-action annotation of nearly 12,000 previously uncharacterized compounds, prioritization of target related chemical genetic associations, and contextualization of unseen perturbations and external transcriptomic datasets. Together, our results establish objective-driven adaptation as a general strategy for repurposing biological foundation models to learn reusable representations of complex biological phenomena.
- Improving Generalizability in Whole-Cell Antibiotic Discovery Through Active Learning
Machine learning (ML) has accelerated molecular discovery, yet training models to generalize to out-of-distribution (OOD) chemical spaces remains fundamentally constrained by the high cost of experimental validation. In antibiotic discovery, where whole-cell phenotypic high throughput screening (HTS) is resource-intensive, iterative ML-guided compound selection, or Active Learning (AL), offers a pathway to efficiently navigate available chemical spaces. However, the algorithmic tradeoffs between prioritizing compound novelty (exploration), predicted bioactivity (exploitation), and their impact on OOD generalizability remain unresolved for noisy, whole-cell biological systems. In this work, we systematically evaluate three AL strategies for whole-cell bacterial bioactivity and benchmark their effects on model accuracy, hit rate, and OOD performance. Using retrospective simulations on Mycobacterium tuberculosis HTS data, we identify an optimal AL strategy that balances predicted hit/non-hit novelty with overall hit rate. We then integrate the strategy in a closed-loop Borrelia burgdorferi antibiotic discovery HTS campaign. The AL-guided approach successfully increased the experimental screening hit rate five-fold (from a 0.2% rate within investigator-selected plates to 1.0%). Further, when the trained model was applied in prospective in silico selection of highly diverse compounds across multiple bacterial species, the AL-trained whole-cell inhibition predictor demonstrates 53-fold enrichment over investigator-directed screening (11.0% experimental validation of predicted hits). Of these, 100% demonstrated the intended narrow spectrum activity for Borrelia burgdorferi. These results demonstrate that calibrated AL strategies can overcome data acquisition bottlenecks and train generalizable property predictors able to extrapolate to OOD molecules.