Rayees Rahman

We are thrilled to announce our $8M seed financing lead by @iendeavors along with @fiftyyears @ycombinator Boom Capital and @caffeinatedcap! We are also excited to announce that @jdudley will be joining our Board of Directors! prnewswire.com/news-releases/…

@NYCMayor What did we just learn about child care across the country? It’s a great way to create fraud and launder money. Caution here…

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 🧵

A Chemical Language Model for Molecular Taste Prediction 1. Introducing FART (Flavor Analysis and Recognition Transformer), a chemical language model trained on the largest molecular taste dataset (15,025 compounds), capable of predicting four taste categories (sweet, bitter, sour, umami) simultaneously with over 91% accuracy. 2. FART outperforms previous binary classifiers, delivering state-of-the-art results across individual taste classes, even when benchmarked on larger and more diverse test sets. 3. A key feature is its interpretability: gradient-based visualization highlights molecular substructures driving taste predictions, offering insights into the chemical basis of taste. 4. SMILES augmentation enhances FART’s robustness, ensuring consistency across diverse molecular representations and enabling a confidence metric that boosts prediction reliability to 94%. 5. FART’s architecture, built on ChemBERTa and fine-tuned on taste data, captures nuanced patterns in molecular taste prediction while handling undefined classes, such as tasteless compounds or out-of-distribution molecules. 6. Practical applications include food science, drug formulation, and natural product analysis, providing a tool for rapid, interpretable predictions to accelerate tastant discovery and systematic flavor exploration. 7. By making FART and its dataset publicly available, this study paves the way for further advancements in molecular taste prediction and its integration into broader chemical discovery workflows. 💻Code: github.com/fart-lab/fart.… 📜Paper: doi.org/10.26434/chemr… #ChemicalLanguageModel #TastePrediction #MachineLearning #FoodScience #ChemBERTa #AI

Amazing. Train a network to classify papers (accept/reject). Then run the network on the paper describing the network, and it classifies the paper as a strong reject. This is why we can't have nice paper classifiers. (h/t @hardmaru) arxiv.org/abs/1812.08775

Can we train LLMs on the language of chemistry? What about build a DALL-E for new medicines? We're throwing an event on gen AI and Drug Discovery with @Techweek_, @kaleidoscopebio, @BioLabsNY, @awscloud, @a16z for #NYTechWeek . Register👉lu.ma/tx1tr61x

Webpage's live: ml4lms.bio Update's there to follow!