Related papers: Polyformer: a generative framework for thermodynam…
The prediction of the biologically active native conformation of a protein is one of the fundamental challenges of structural biology. This problem remains yet unsolved mainly due to three factors: the partial knowledge of the effective…
Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery. A plethora of generative models is available, building molecules either atom-by-atom and bond-by-bond or fragment-by-fragment.…
Globular proteins are expected to assume folds with fixed secondary structures, alpha-helices and beta-sheets. Fold-switching proteins challenge this expectation by remodeling their secondary and/or tertiary structures in response to…
Protein sequences are believed to have been selected to provide the stability of, and reliable renaturation to, an encoded unique spatial fold. In recently proposed theoretical schemes, this selection is modeled as ``minimal frustration,''…
Structure-based drug design (SBDD) aims to efficiently discover high-affinity ligands within vast chemical spaces. However, current generative models struggle with objective misalignment and rigid sampling budgets. We present MolFORM, a…
Epigenetic Tracking is a mathematical model of biological cells, originally conceived to study embryonic development. Computer simulations proved the capacity of the model to generate complex 3-dimensional cellular structures, and the…
Computation biology helps to understand all processes in organisms from interaction of molecules to complex functions of whole organs. Therefore, there is a need for mathematical methods and models that deliver logical explanations in a…
Given (small amounts of) time-series' data from a high-dimensional, fine-grained, multiscale dynamical system, we propose a generative framework for learning an effective, lower-dimensional, coarse-grained dynamical model that is predictive…
The dynamics of biological polymers, including proteins, RNA, and DNA, occur in very high-dimensional spaces. Many naturally-occurring polymers can navigate a vast phase space and rapidly find their lowest free energy (folded) state. Thus,…
We consider the statistical mechanics of a full set of two-dimensional protein-like heteropolymers, whose thermodynamics is characterized by the coil-to-globular ($T_\theta$) and the folding ($T_f$) transition temperatures. For our model,…
Recent advances in artificial intelligence have propelled the development of innovative computational materials modeling and design techniques. Generative deep learning models have been used for molecular representation, discovery, and…
Modeling boiling (an inherently chaotic, multiphase process central to energy and thermal systems) remains a significant challenge for neural PDE surrogates. Existing models require future input (e.g., bubble positions) during inference…
The remarkable success of AlphaFold2 in providing accurate atomic-level prediction of protein structures from their amino acid sequence has transformed approaches to the protein folding problem. However, its core paradigm of mapping one…
Proteins are the basic building blocks of life. They usually perform functions by folding to a particular structure. Understanding the folding process could help the researchers to understand the functions of proteins and could also help to…
Proteins fold to a specific functional conformation with a densely packed hydrophobic core that controls their stability. We develop a geometric, yet all-atom model for proteins that explains the universal core packing fraction of…
The self-assembly of polyhedral shells, each constructed from 60 trapezoidal particles, is simulated using molecular dynamics. The spatial organization of the component particles in this shell is similar to the capsomer proteins forming the…
Accurate protein structures are essential for understanding biological function, yet incorporating experimental data into protein generative models remains a major challenge. Most predictors of experimental observables are…
Diffusion models have emerged as a leading framework in generative modeling, poised to transform the traditionally slow and costly process of drug discovery. This review provides a systematic comparison of their application in designing two…
A small model polypeptide represented in atomic detail is folded using Monte Carlo dynamics. The polypeptide is designed to have a native conformation similar to the central part of the helix-turn-helix protein ROP. Starting from a…
Understanding how human health changes over time, and why responses to interventions vary between individuals, remains a central challenge in medicine. Here we present HealthFormer, a decoder-only transformer that models the human…