AI

  • |

    Virtual cell

    Byscientist

    Hani Goodrazi – Arc institute has been working on virtual cell. Drugs fail due to overfit experimental models, You need screen drugs with better models of human biology. Geneva is platfrom that brings tumor models into perturbation model – that is a transcriptomics assay that deconvolves into effect. Take multiple cell line and then treat…

  • |

    Open source protein models

    Byscientist

    A company called Profluent (profluent.bio) has been developing protein models that can be used for designing new proteins (https://www.nature.com/articles/s41587-022-01618-2), modeling of new CRISPR-Cas sequences (https://www.nature.com/articles/s41586-025-09298-z) and developing LLM for protein generation (https://www.biorxiv.org/content/10.1101/2025.11.12.688125v1.article-info). What is amazing is that they have open sourced all their models and Profluent-E1 is available in GitHub to download and use. (https://github.com/Profluent-AI/E1)…

  • | | |

    Biotech companies

    Byscientist

    Small Biotechs: Diagonal Tx: Clustering antibodies that mimic the action of the ligand and bypass the need for the ligand and receptor. This mutation that is created makes standard AI models not useful and so need a new method. This restores new ALK1 signaling in Hereditary Hemorrhagic Telangiectasia. It also treates LoF mutations in ALK1…

  • Explainable AI

    Byscientist

    A very traditional problem solving method is the following: given a set of features or variables, can we understand the features to form a conclusion. This could be something like a treatment strategy wherein the strategy is built on a series of data and then ingesting the data helps make a conclusion. However, an equally…

  • LoRa adaptors

    Byscientist

    LoRa in the IOT community are the low power long range wireless standards devices that are utilized to send a signal over large distances. However, in the AI field LoRa implies Low rank adaptation – which is relatively more efficient compute way to fine tune pretrained models (LLM, vision transformers, diffusion models). With a pretrained…

  • |

    Knowledge graphs

    Byscientist

    Knowledge graph is a way of representing information where entities/nodes (people, places, products, concepts) are linked by relationships/edges (works, creates, has ). It is a semantic network that captures facts and context. There is also an ontology that defines different types of node/edges and defines what types exist and how they relate. These are used…

  • |

    Reinforcement learning

    Byscientist

    Reinforcement learning is a method that drives learning and memory in primitive species such as birds, humans and other living species to its use in machine learning. It is used to influence the behavior of us humans on social media to its use to train machines. The essential components were initiated by BF Skinner 20th…