Saturday night BTC universal model long. 2.4R I'm bearish on BTC, so I did not hold this long to a larger target. Taken on my @breakoutprop prop account.

Weekend crypto trade: GxT IRL-ERL Universal Framework SOL short (ETH as correlated pair) 1. M90 2-stage SMT gap fill 2. M30 PSP 3. M15 bearish SS PSP with gap 4. M3 first CSD short entry 2.75R Traded on my crypto-prop funded account Appreciate the excellent mentorship from @GxTradez

Happy Sunday to all! This morning, we are excited to share Chase’s work developing a simple, scalable method to assemble 100s-1000s of custom genes from oligo pools using standard lab tools! (Small 🧵 below)

Published in Nature (2023), Kruse et al. (Tüting lab) demonstrate that adoptively transferred CD4 T cells alone—but not CD8 T cells—can eradicate melanoma tumors completely lacking both MHC class I and II expression. These findings challenge the current paradigm of cancer immunotherapy, which predominantly focuses on CD8 cytotoxic T cells whose effectiveness is limited by MHC loss and immunosuppressive TME. Historically viewed merely as ‘helper’ cells, CD4 T cells instead have a critical yet underappreciated capacity for antitumor immunity independent of CD8 cells. Intriguingly, CD4 T cells do not directly infiltrate tumors in the same way CD8 T cells do. Rather, they profoundly reshape the tumor immune landscape by recruiting and functionally reprogramming myeloid cells. These myeloid cells mature into potent interferon-activated APCs and robust iNOS-expressing tumoricidal effectors. This study uncovers exciting therapeutic opportunities by revealing the potential of CD4 T cells to complement CD8 T cells and NK cells, paving the way for innovative strategies against immune-evasive cancers.

ABCFold: Easier Running and Comparison of AlphaFold 3, Boltz-1, and Chai-1 - Structural biology has seen a revolution with deep learning-based protein structure predictors like AlphaFold 3, Boltz-1, and Chai-1. However, running and comparing these models efficiently remains a challenge. - ABCFold is a new tool that simplifies the process of running and benchmarking AlphaFold 3, Boltz-1, and Chai-1, allowing users to generate structure predictions with a standardized input format. - The tool converts AlphaFold 3 JSON inputs into compatible formats for Boltz-1 and Chai-1, enabling seamless execution of all three models from a single input. - ABCFold provides automated multiple sequence alignment (MSA) handling, supporting both JackHMMER-based searches and the MMseqs2 API. Users can also supply custom MSAs and template structures. - The software includes a unified output visualization framework, allowing side-by-side comparison of model predictions, pLDDT scores, and predicted aligned error (PAE) values. Structural clashes are also highlighted for better assessment. - One of the key benefits of ABCFold is its ability to automate installation and version management of Boltz-1 and Chai-1, reducing setup complexity for researchers. - By providing standardized evaluation metrics and interactive visualization tools, ABCFold enhances reproducibility and helps researchers assess the relative strengths of different structure prediction methods. - This tool is an important step toward better benchmarking of next-generation protein structure predictors, enabling broader adoption and more effective model selection for specific biological applications. 💻Code: github.com/rigdenlab/ABCFold 📜Paper: biorxiv.org/content/10.1101/… #StructuralBiology #AlphaFold #MachineLearning #ProteinFolding #DeepLearning #Bioinformatics #ComputationalBiology

🚀 Introducing TxAgent: a first of its kind AI agent for therapeutic reasoning across a universe of 211 tools, with a comparison against DeepSeek-R1 671B @NVIDIAAI TxAgent is an AI agent that redefines how AI can reason, retrieve, and integrate biomedical knowledge for precision therapeutics, led by stellar @GaoShanghua 🔍 Beyond prediction—reasoning AI for medicine TxAgent is not just another predictive model. It is the first AI system designed to think through therapeutic problems, iteratively query external sources, and generate transparent, step-by-step reasoning traces. By integrating real-time biomedical knowledge, TxAgent's treatment recommendations are accurate and continuously updated 🔗 Benchmarking TxAgent against 671B DeepSeek-R1 We benchmarked TxAgent against DeepSeek-R1 (671B, @NVIDIAAI) and other leading AI models. The results? TxAgent outperformed much larger LLMs in multi-step therapeutic reasoning in drug selection, treatment personalization, and therapeutic reasoning 🏥 What’s Inside the 211 tools in TxAgent’s ToolUniverse? ✅ All FDA-approved drugs since 1939 – Includes drug mechanisms, indications, contraindications, dosing, safety warnings, and pharmacokinetics from FDA drug labels and OpenFDA ✅ Clinical insights from Open Targets – Provides up-to-date drug-disease, phenotype, and molecular target associations used in precision medicine ✅ Pharmacology – Covers drug-drug interactions, metabolic pathways, and contraindications based on comorbidities and concurrent medications ✅ Personalized treatment guidelines – Assesses patient-specific factors such as age, pregnancy, renal function, and genetic variations. Simultaneously assesses molecular, pharmacokinetic, and clinical-level interactions. Evaluates patient factors like genetics, comorbidities, and disease stage ✅ Real-time retrieval – Queries latest treatment indications, regulatory approvals from continuously updated sources 🔥 Key features: ✅ Reasoning over retrieval – Moves beyond RAG-based retrieval to structured, multi-step decision-making ✅ Tool-augmented AI – Interacts with 211 biomedical tools ✅ Real-time knowledge integration and continuous learning – Responses are always grounded in up-to-date clinical knowledge. No outdated medical knowledge by always integrating live sources ✅ Dynamic tool selection – Adapts its reasoning by choosing the most relevant tools in real time ✅ Grounded medical AI – Reduces the risk of hallucinations, verifies every step of the way, and aligns recommendations with clinical guidelines @HarvardDBMI @harvardmed @KempnerInst @harvard_data @MIT @broadinstitute @MIPhilanthropy @cziscience @Harvard Congratulations to a fantastic team Shanghua Gao @GaoShanghua, Richard Zhu @RichardYXZhu, Zhenglun Kong @ZKong50693, Ayush Noori @ayushnoori, Xiaorui Su @xiaorui_su, Curtis Ginder, Theodoros Tsiligkaridis

We introduce 🌿 MINT (Multimer Interaction Transformer) – a Protein Language Model (PLM) trained on 96M protein-protein interactions (PPIs) to predict binding affinity, mutational impacts, & antibody interactions better than existing PLMs. 🔗Code: github.com/VarunUllanat/mint 🧵👇

Proteins power life, but their complexity makes them hard to understand or design. We’re introducing ProtBFN, a 650M parameter Bayesian Flow Networks capable of generating natural, diverse and novel protein sequences. Here's Tom Barrett (@tomdbarrett), Staff Scientist at InstaDeep, to tell you more:

Patent protection for therapeutic monoclonal antibodies requires a fundamental shift in strategy following Amgen v. Sanofi, which invalidated broad functional claims for antibody genera in the USA go.nature.com/4gYpZ5i rdcu.be/ebaZZ

Historic day for builders in bio: We’ve open-sourced @vevo_ai’s #Tahoe100M, largest single-cell atlas ever—by a wide margin—as the inaugural contribution to @arcinstitute’s Virtual Cell Atlas, ready for download today. A leap forward for AI models of cells & drug discovery. 🧵

Structural biology is in an era of dynamics & assemblies but turning raw experimental data into atomic models at scale remains challenging. @mhli41 and I present ROCKET🚀: an AlphaFold augmentation that integrates crystallographic and cryoEM/ET data with room for more! 1/14.

Researchers have developed a deep learning protein language model, ESM3, that enables programmable protein design. Learn more in this week's issue of Science: scim.ag/4b5IlQu

At @ScienceMagazine today, an important new way we can make major headway into immunologic and infectious diseases. Sequencing the lymphocyte B and T cell receptors and A.I. to accurately make the diagnosis! A seminal study @zazius @ScottBoydLab @anshulkundaje and colleagues science.org/doi/10.1126/scie…

Today, the @nvidia healthcare and life sciences team launched Evo 2 -- a powerful foundation model for DNA across all domains of life, developed in collaboration with @arcinstitute and @Stanford. Announced today as the largest publicly available AI model for genomic data, Evo 2 was built using NVIDIA DGX Cloud on @awscloud. More in thread 🧵

AI provides a universal framework that leverages data and compute at scale to uncover higher-order patterns Today, @arcinstitute in collaboration with @nvidia releases Evo 2—a fully open source biological foundation model trained on genomes spanning the entire tree of life 🧵

Excited to share our joint work with @richardwshuai, Full-Atom MPNN (FAMPNN), a protein sequence design method that explicitly models both sequence and side-chain structure! 🧵 1/N

Don’t trust the votes, people don’t know what they’re talking about. Local models are interesting but only so useful. Go for the best open source model possible.

Everyone vote for o3-mini type model to be open-sourced please 🥺🥺🥺 We can distill or quantize a phone sized model dw the open-source community will work its magic!!

.@VertexPharma's opioid-free drug for acute pain wins FDA approval nature.com/articles/s41587-0…

YAbS: The Antibody Society’s Antibody Therapeutics Database 1/ YAbS provides an extensive and dynamic resource tracking over 2,900 antibody therapeutics, including approved, investigational, and in-development antibody candidates, offering a valuable tool for researchers, clinicians, and industry professionals. 2/ The database catalogs detailed information on therapeutic antibodies, such as molecular formats, antigen targets, development status, clinical phase, indications, and company sponsors. It includes over 450 molecules in late-stage clinical development or regulatory review. 3/ YAbS is a comprehensive tool for analyzing trends in antibody therapeutics, offering detailed insights into clinical development timelines, success rates, and emerging trends in antibody formats, including bispecifics and antibody-drug conjugates (ADCs). 4/ Key features of the database include customizable search options, enabling users to filter by clinical development stage, molecular category (e.g., full-length antibodies, fragments, ADCs), therapeutic area, and company sponsor, as well as milestone event dates. 5/ The database is continually updated and provides real-time access to the status of antibody therapeutics, with insightful analysis and reports that inform decisions related to development strategies and industry trends. 6/ YAbS is a crucial resource for tracking antibody therapeutics across all stages, from preclinical to regulatory approval, allowing users to explore development trends, success rates, and therapeutic area coverage, particularly for cancer treatments. 7/ The platform also enables users to assess clinical-stage antibody therapeutics, analyze trends in antibody development, and evaluate milestone events, making it an invaluable resource for understanding the state of the biopharmaceutical industry. @victorgreiff @puneet021192 💻Code: db.antibodysociety.org/ 📜Paper: biorxiv.org/content/10.1101/… #AntibodyTherapeutics #Biopharmaceuticals #DrugDevelopment #Bioinformatics #ClinicalTrials #Immunology #TherapeuticAntibodies #Biotech #AntibodyDrugs #BioinformaticsTools