Analyzing Molecular Dynamics Trajectories Thermodynamically through Artificial Intelligence

Abstract

Molecular dynamics simulations produce trajectories that correspond to vast amounts of structure when exploring biochemical processes. Extracting valuable information, e.g., important intermediate states and collective variables (CVs) that describe the major movement modes, from molecular trajectories to understand the underlying mechanisms of biological processes presents a significant challenge. To achieve this goal, we introduce a deep learning approach, coined DIKI (deep identification of key intermediates), to determine low-dimensional CVs distinguishing key intermediate conformations without a-priori assumptions. DIKI dynamically plans the distribution of latent space and groups together similar conformations within the same cluster. Moreover, by incorporating two user-defined parameters, namely, coarse focus knob and fine focus knob, to help identify conformations with low free energy and differentiate the subtle distinctions among these conformations, resolution-tunable clustering was achieved. Furthermore, the integration of DIKI with a path-finding algorithm contributes to the identification of crucial intermediates along the lowest freeenergy pathway. We postulate that DIKI is a robust and flexible tool that can find widespread applications in the analysis of complex biochemical processes.

Collective Variable-Based Enhanced Sampling: From Human Learning to Machine Learning

“…To guarantee that the mCVs accurately represent the transition states, principles from transition path theory (TPT) and committor analysis , have been incorporated into deep-learning algorithms, which further improves the reliability of mCVs. ,, Beyond techniques that calculate the time autocorrelation function, methods that feature automated clustering of samples can also eliminate the need for labeling. Information distillation of metastability (IDM) and deep identification of key intermediates (DIKI) are representative of such methods. Typically, these methods are applied in the postanalysis of molecular simulation trajectories, not in enhanced sampling simulations, due to their insufficient focus on slow degrees of freedom.…”

AttenGpKa: A Universal Predictor of Solvation Acidity Using Graph Neural Network and Molecular Topology

“…Therefore, there is an urgent need for more efficient and accurate methods for predicting p K a . In recent years, the application of machine learning methods in the field of chemistry has made significant advancements, − providing a new paradigm for p K a prediction.…”