Related papers: ESM All-Atom: Multi-scale Protein Language Model f…

While deep generative models show promise for learning inverse protein folding directly from data, the lack of publicly available structure-sequence pairings limits their generalization. Previous improvements and data augmentation efforts…

Antibodies play a central role in the immune response by specifically recognizing and neutralizing antigens, and therapeutic antibodies have become major drugs for cancer and autoimmune diseases. However, their discovery still relies on…

We describe a combination of all-atom simulations with CABS, a well-established coarse-grained protein modeling tool, into a single multiscale protocol. The simulation method has been tested on the C-terminal beta hairpin of protein G, a…

Multimodal approaches that integrate protein structure and sequence have achieved remarkable success in protein-protein interface prediction. However, extending these methods to protein-peptide interactions remains challenging due to the…

Traditional AI methods often rely on task-specific model designs and training, which constrain both the scalability of model size and generalization across different tasks. Here, we introduce ChemFM, a large foundation model specifically…

We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair…

Despite their ability to understand chemical knowledge, large language models (LLMs) remain limited in their capacity to propose novel molecules with desired functions (e.g., drug-like properties). In addition, the molecules that LLMs…

We developed a multiscale approach (MultiSCAAL) that integrates the potential of mean force (PMF) obtained from all-atomistic molecular dynamics simulations with a knowledge-based energy function for coarse-grained molecular simulations in…

Protein language models are trained primarily with masked language modeling (MLM), which predicts amino-acid identities at masked positions. We ask whether latent-space prediction can complement these token-level objectives under matched…

Understanding protein solubility is essential for their functional applications. Computational methods for predicting protein solubility are crucial for reducing experimental costs and enhancing the efficiency and success rates of protein…

Large language models (LLMs) have become increasingly popular in medical domains to assist physicians with a variety of clinical and operational tasks. Given the fast-paced and high-stakes environment of emergency departments (EDs), small…

In the real world, a molecule is a 3D geometric structure. Compared to 1D SMILES sequences and 2D molecular graphs, 3D molecules represent the most informative molecular modality. Despite the rapid progress of autoregressive-based language…

In the molecular domain, numerous studies have explored the use of multimodal large language models (LLMs) to construct a general-purpose, multi-task molecular model. However, these efforts are still far from achieving a truly universal…

Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language, symbolic notations, with emerging extensions to incorporate multi-modal…

Most current molecular language models transfer the masked language model or image-text generation model from natural language processing to molecular field. However, molecules are not solely characterized by atom/bond symbols; they…

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an input text with…

Identification of protein-protein interactions (PPIs) helps derive cellular mechanistic understanding, particularly in the context of complex conditions such as neurodegenerative disorders, metabolic syndromes, and cancer. Large Language…

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

A class of analog computers built from large numbers of microscopic probabilistic machines is discussed. It is postulated that such computers are implemented in biological systems as ensembles of protein molecules. The formalism is based on…

Is there a foreign language describing protein sequences and structures simultaneously? Protein structures, represented by continuous 3D points, have long posed a challenge due to the contrasting modeling paradigms of discrete sequences. To…