🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We are looking for talented postdocs to develop computational models for bladder cancer immunotherapy or microinvasions in breast cancer in close collaboration with biologists. More info: rejniak.net/RejniakLab/Rej… Please RT

Check out our latest publication in Frontiers - Immunology using a novel multiplex image-based spatial analysis of the #tumormicroenvironment in #HCC applied to #Cabozantinib and #Nivolumab treatments doi.org/10.3389/fimmu.…

Excited to share newly published book Vasculome edited by Dr. Zorina Galis Elsevier, covering a wide range of topics in #vascularbiology! We're (Yu Zhang, Dr. Chen Zhao) excited to contribute a chapter on #systemsbiology modeling of #Angiogenesis elsevier.com/books/the-vasc…

Now Online Signalling mechanisms and cellular functions of SUMO dlvr.it/SSmns3

Review: Computational systems biology in disease modeling and control, review and perspectives - npj Systems Biology and Applications buff.ly/3fJljXj

Explaining your PhD project to your family x.com/buitengebieden…

Now in #ACSPharmacologyandTranslationalScience: Check our latest systems biology model of endothelial signaling in angiogenesis-driven tumor growth: doi.org/10.1021/acspts…

I am looking forward to sharing my work on Sunday, 12/3 at 1:45pm. Stop by P1656 if you are interested in cell shape changes, apical constriction, and actin dynamics.

Watch a simulation of a macrophage engulfing an old, rigid red blood cell that needs to be recycled. The simulation was produced as part of a modeling study on macrophage dynamics that could help develop therapies for sickle cell disease. In PNAS Nexus: ow.ly/Om8r50QuQOu

ADMET-AI is now published in Bioinformatics! ADMET-AI provides free, fast, & accurate prediction of absorption, distribution, metabolism, excretion, & toxicity properties of molecules at admet.ai.greenstonebio.com Blog: portal.valencelabs.com/blogs/post/adm… Paper: academic.oup.com/bioinformatics…

How to design State Space Models (SSM) from principles? We propose to view SSM's recurrence as the per-step closed-form solution to an online learning problem. To this end, we present Longhorn, a novel SSM that achieves 1.8x better sampling efficiency against Mamba.

In this nature article, read about the 5 ways scientists are tackling the antibiotic resistance crisis, including how #PhareBio is using #generativeAI to design novel antibiotics against the deadliest bacteria: bit.ly/4cGsx6h #AIForGood #AMR #superbugs

Oh, hey! My talk video is online if you'd like a tutorial on AI in preclinical drug discovery: "Phenomics in Drug Discovery: Microscopy and Machine Learning" from the 2024 Machine Learning for Drug Discovery Summer School hosted by Mila/Valence Labs youtube.com/watch?v=mc3vVx…

Prediction of Protein Half-lives from Amino Acid Sequences by Protein Language Models 1. This paper presents PLTNUM, a protein half-life prediction model that leverages protein language models (PLMs) using amino acid sequences as input, achieving an impressive accuracy of 71% on

ChemFlow will appear in NeurIPS 2024! See you in Vancouver this December! #NeurIPS2024

Recent advances in interpretable machine learning using structure-based protein representations 1. This paper explores how interpretable machine learning (ML) is transforming protein science, specifically focusing on structure-based protein representations. A key point is the

Generative Modeling of Molecular Dynamics Trajectories MIT CSAIL 1. MDGEN introduces a revolutionary approach to surrogate molecular dynamics (MD) modeling by directly generating molecular trajectories rather than individual frames. This paradigm enables faster simulations of

Generative AI for Drug Discovery: A GPT-2 and LSTM Based Models for Designing EGFR Inhibitors • This study explores the use of GPT-2 and LSTM architectures to generate novel inhibitors targeting the Epidermal Growth Factor Receptor (EGFR), a key therapeutic target in cancer.

Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation 1. This paper introduces E3WAE, a novel E(3)-equivariant Wasserstein autoencoder designed for explicit control in 3D molecule generation. It factors the latent space into two

EFFICIENT FINE-TUNING OF SINGLE-CELL FOUNDATION MODELS ENABLES ZERO-SHOT MOLECULAR PERTURBATION PREDICTION Genentech 1. A breakthrough for drug discovery: the study introduces scDCA, a novel drug-conditional adapter, enabling single-cell foundation models (FMs) to predict