[{"content":"","permalink":"https://amyx.lu/talks/2025-insilico/","summary":"","title":"[In silico #002](https://luma.com/txswapqo), IDEALondon"},{"content":"","permalink":"https://amyx.lu/news/2025-10-01/","summary":"","title":"Invited talk at IDEALondon."},{"content":"","permalink":"https://amyx.lu/news/2025-07-07/","summary":"","title":"I've joined [Isomorphic Labs](https://www.isomorphiclabs.com/) as a Research Scientist 🥳!"},{"content":"","permalink":"https://amyx.lu/news/2025-04-28/","summary":"","title":"[PhD Dissertation Talk](https://events.berkeley.edu/eecs/event/298296-dissertation-talk-generative-models-for-real-world) at the BAIR seminar series 👩‍🎓."},{"content":"","permalink":"https://amyx.lu/talks/2025-dissertation/","summary":"","title":"BAIR Seminar / [UC Berkeley EECS PhD Dissertation Talk](https://events.berkeley.edu/eecs/event/298296-dissertation-talk-generative-models-for-real-world)"},{"content":"","permalink":"https://amyx.lu/news/2025-04-23/","summary":"","title":"Excited to be in Singapore for [ICLR 2025](https://iclr.cc/) to present our work on protein language model likelihoods."},{"content":"","permalink":"https://amyx.lu/news/2025-04-08/","summary":"","title":"New post on the [BAIR blog](https://bair.berkeley.edu/blog/2025/04/08/plaid/) on our work with CHEAP and PLAID."},{"content":"","permalink":"https://amyx.lu/news/2025-03-20/","summary":"","title":"The [Exploration in AI Today (EXAIT)](https://exait-workshop.github.io/) workshop is accepted at ICML 2025."},{"content":"","permalink":"https://amyx.lu/news/2025-03-19/","summary":"","title":"New post on [Nathan's substack](https://ncfrey.substack.com/p/hit-the-vintage-store-and-get-yourself) on CHEAP and PLAID."},{"content":"","permalink":"https://amyx.lu/talks/2025-bakerlab/","summary":"","title":"[Baker Lab](https://www.bakerlab.org/) Journal Club, UW Institute for Protein Design"},{"content":"","permalink":"https://amyx.lu/talks/2025-latent-labs/","summary":"","title":"[Latent Labs](https://www.latentlabs.com/) Journal Club"},{"content":"","permalink":"https://amyx.lu/talks/2025-nvidia/","summary":"","title":"[NVIDIA Fundamental Generative AI Research](https://research.nvidia.com/labs/genair/)"},{"content":"","permalink":"https://amyx.lu/talks/2025-xaira/","summary":"","title":"[Xaira Therapeutics](https://www.xaira.com/)"},{"content":"","permalink":"https://amyx.lu/publications/2025-evo2/","summary":"Evo 2 is a 40B parameter genomic foundation model capable of predicting functional impacts of genetic variations, autonomously learning biological features, and generating novel genomic sequences across all domains of life.","title":"Genome modeling and design across all domains of life with Evo 2"},{"content":"","permalink":"https://amyx.lu/talks/2025-ginkgo/","summary":"","title":"[Ginkgo Bioworks](https://www.ginkgo.bio/) Journal Club"},{"content":"","permalink":"https://amyx.lu/talks/2025-isomorphic-labs/","summary":"","title":"[Isomorphic Labs](https://www.isomorphiclabs.com/)"},{"content":"","permalink":"https://amyx.lu/talks/2025-lila-sciences/","summary":"","title":"[Lila Sciences](https://www.lila.ai/)"},{"content":"","permalink":"https://amyx.lu/talks/2025-genesis-therapeutics/","summary":"","title":"[Genesis Therapeutics](https://genesistherapeutics.ai/)"},{"content":"","permalink":"https://amyx.lu/talks/2025-profluent/","summary":"","title":"[Profluent Bio](https://www.profluent.bio/)"},{"content":"","permalink":"https://amyx.lu/talks/2025-msr-ai-science/","summary":"","title":"[Microsoft Research AI for Science](https://www.microsoft.com/en-us/research/lab/microsoft-research-ai-for-science/)"},{"content":"","permalink":"https://amyx.lu/talks/2025-evolutionaryscale/","summary":"","title":"[EvolutionaryScale](https://www.evolutionaryscale.ai/)"},{"content":"","permalink":"https://amyx.lu/news/2025-01-21/","summary":"","title":"Remote talk at [EvolutionaryScale](https://www.evolutionaryscale.ai/) on our work with CHEAP and PLAID."},{"content":"","permalink":"https://amyx.lu/talks/2025-marks-lab/","summary":"","title":"[Debora Marks Lab](https://www.deboramarkslab.com/) Journal Club, Harvard Medical School"},{"content":"","permalink":"https://amyx.lu/news/2025-01-17/","summary":"","title":"I'll be giving a remote talk at the [Marks Lab](https://www.deboramarkslab.com/) at Harvard Medical School."},{"content":"","permalink":"https://amyx.lu/talks/2024-mlsb/","summary":"","title":"[Machine Learning for Structural Biology](https://www.mlsb.io/) (MLSB) 2024 workshop"},{"content":"","permalink":"https://amyx.lu/news/2024-12-09/","summary":"","title":"I'll be in Vancouver for [NeurIPS 2024](https://neurips.cc/Conferences/2024). Come say hi!"},{"content":"","permalink":"https://amyx.lu/news/2024-12-06/","summary":"","title":"Our [preprint](https://www.biorxiv.org/content/10.1101/2024.12.02.626353v1) and [code](https://github.com/amyxlu/plaid) on all-atom co-generation with latent diffusion is released!"},{"content":"","permalink":"https://amyx.lu/publications/2024-plaid/","summary":"PLAID is a multimodal protein generation model that generates all-atom protein structures from function and organism prompts, but requires only sequence training data.","title":"All-Atom Protein Generation with Latent Diffusion"},{"content":"","permalink":"https://amyx.lu/news/2024-10-22/","summary":"","title":"Excited to give an invited talk at the [Stanford AI + Biomedicine series](https://snap.stanford.edu/ai-bio-seminar/)."},{"content":"","permalink":"https://amyx.lu/talks/2024-stanford/","summary":"","title":"[Stanford AI + Biomedicine Seminar](https://snap.stanford.edu/ai-bio-seminar/)"},{"content":"","permalink":"https://amyx.lu/talks/2024-mlproteins/","summary":"","title":"[ML Protein Engineering Seminar Series](https://www.ml4proteinengineering.com/)"},{"content":"","permalink":"https://amyx.lu/news/2024-10-11/","summary":"","title":"[Model weights](https://huggingface.co/amyxlu/cheap-proteins) for CHEAP are now released."},{"content":"","permalink":"https://amyx.lu/news/2024-10-08/","summary":"","title":"Very excited to have two papers accepted as an oral presentation at [MLSB 2024](https://www.mlsb.io/)!"},{"content":"","permalink":"https://amyx.lu/news/2024-10-03/","summary":"","title":"Checkout our [preprint](https://www.biorxiv.org/content/10.1101/2024.10.03.616542v1) on understanding how training data affects protein language model likelihoods!"},{"content":"","permalink":"https://amyx.lu/publications/2024-preference/","summary":"Enabled by a one-pass pseudolikelihood algorithm, we find that pLMs capture artifacts of training data selection rather than true fitness landscape via influence functions.","title":"Protein Language Model Fitness Is a Matter of Preference"},{"content":"","permalink":"https://amyx.lu/news/2024-10-01/","summary":"","title":"Excited to return to the [ML Protein Engineering Seminar Series](https://www.ml4proteinengineering.com/) for an invited talk."},{"content":"","permalink":"https://amyx.lu/talks/2024-spc/","summary":"","title":"[South Park Commons](https://www.southparkcommons.com/) Demo Night on Interpretability and Steerability"},{"content":"","permalink":"https://amyx.lu/news/2024-09-05/","summary":"","title":"Lightning talk at [South Park Commons](https://www.southparkcommons.com/) for the interpretability and steerability series."},{"content":"","permalink":"https://amyx.lu/talks/2024-logg/","summary":"","title":"[Learning on Graphs and Geometry (LoGG) Seminar Series](https://portal.valencelabs.com/events/post/tokenized-and-continuous-embedding-compressions-of-protein-sequence-and-Uq8Nm5HEcHopMrX)"},{"content":"","permalink":"https://amyx.lu/news/2024-08-08/","summary":"","title":"New [preprint](https://www.biorxiv.org/content/10.1101/2024.08.06.606920v2) on the unreasonable compressibility of protein folding model latent spaces."},{"content":"","permalink":"https://amyx.lu/publications/2024-cheap/","summary":"CHEAP is a joint embedding of protein sequence and structure that can be obtained from sequence alone, and unveil insights into the compressibilitiy, tokenizability, and mechanistic interpretability of protein folding models.","title":"Tokenized and Continuous Embedding Compressions of Protein Sequence and Structure"},{"content":"","permalink":"https://amyx.lu/news/2024-07-27/","summary":"","title":"Will be in Vienna to share two ICML workshop papers at [AccMLBio](https://accml.bio/) and [ML4LMS](https://ml4lms.bio/)."},{"content":"","permalink":"https://amyx.lu/talks/2024-af2/","summary":"","title":"BIOE 145/245 Guest Lecture on AlphaFold2"},{"content":"","permalink":"https://amyx.lu/publications/2023-toph/","summary":"We present a protein semantic similarity search method for RNA-Guided endonuclease discovery, inspired by dense retrieval methods in open-domain question answering, and introduce a new dataset of CRISPR-Cas and evolutionary-related nucleases.","title":"TOPH: Adapting A Contrastive Question-Answering Framework for Protein Search"},{"content":"","permalink":"https://amyx.lu/publications/2023-promoter/","summary":"Pretraining and transfer learning strategies for improving model-based design of promoters for cell type-specific expression.","title":"Pretraining strategies for effective promoter-driven gene expression prediction"},{"content":"","permalink":"https://amyx.lu/publications/2022-mldd/","summary":"Strategies for data curation, model-training, optimization, and evaluation heuristics for data-driven proposals of novel de novo proteins.","title":"Data-Driven Optimization for Protein Design: Workflows, Algorithms and Metrics"},{"content":"","permalink":"https://amyx.lu/publications/2022-reverse-homology/","summary":"Reverse Homology is a self-supervised method which captures evolutionary information by contrastive learning to discover molecular features of intrinsically disordered regions.","title":"Discovering molecular features of intrinsically disordered regions by using evolution for contrastive learning"},{"content":"","permalink":"https://amyx.lu/publications/2021-bioembeddings/","summary":"","title":"Learned embeddings from deep learning to visualize and predict protein sets"},{"content":"","permalink":"https://amyx.lu/publications/2020-eiayn/","summary":"We outline how viewing evolution as natural sequence augmentation for contrastive learning recapitulates comparative genomics, and maximizes the mutual information between sequence and function.","title":"Evolution Is All You Need: Phylogenetic Augmentation for Contrastive Learning"},{"content":"","permalink":"https://amyx.lu/publications/2020-cpcprot/","summary":"CPCProt uses contrastive learning to learn a parameter-efficient way of embedding proteins, and performs competitively with large language models.","title":"Self-Supervised Contrastive Learning of Protein Representations by Mutual Information Maximization"},{"content":"","permalink":"https://amyx.lu/publications/2020-hurtful-words/","summary":"We apply fairness definitions to quantify the cross-group bias in BERT embeddings pretrained on medical notes, and find statistically significant differences in classifier performance.","title":"Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings"},{"content":"","permalink":"https://amyx.lu/publications/2019-coos/","summary":"Introduces the COOS-7 dataset to benchmark and evaluate the capacity of feature learning methods to generalize to natural distribution shifts in microscopy images.","title":"The Cells Out of Sample (COOS) dataset and benchmarks for measuring out-of-sample generalization of image classifiers"}]