arXiv subjects

Michael J. Keiser

Publications and source records attributed to Michael J. Keiser.

9 recordsLinked to original sources

arXiv2026

Scalable quantum simulation of continuous-time generative models via tensor networks

Continuous-time flow and diffusion models are widely used across many application domains, from large-scale deployment in computer vision and protein folding to emerging adoption for modeling language, time series, and quantum states. After training, inferring statistical properties from continuous-time models is costly. Wavefunction flows target this cost by recasting learned transport as unitary evolution, whose final Born distribution approximates the target distribution. This prepares a coherent amplitude encoding (a qsample) that can be post-processed by quantum algorithms offering a quadratic advantage over Monte Carlo sampling. We present the first numerical study of these flows, in which we represent time-dependent potentials and states as tensor networks. At spatial dimension $d=8$, storage falls by $\sim 10^7\times$ relative to the dense grid of $N^d$ points, and evolution wall-clock time falls by $\gtrsim 10^3\times$ against a baseline extrapolated from the measured $d\le 5$ scaling. We validate our pipeline by reproducing the $O(1/\sqrt{p_{\rm rare}})$ scaling of rare-event sampling.

quant-ph↗

arXiv2026

Equivariant Continuous Normalizing Flows with Offline Sampling for Fermionic Ground State Estimation

We introduce a framework for fermionic variational Monte Carlo (VMC) in which a continuous normalizing flow (CNF) refines a fixed antisymmetric base wavefunction. The flow is implemented as a permutation-equivariant neural ODE, a smooth, topology-preserving map that learns correlations not captured by the base; equivariance preserves the antisymmetry of the base, so the flow can in principle improve any antisymmetric ansatz that can be sampled efficiently. We demonstrate this using Slater and Jastrow-Slater bases, though more expressive choices are admissible. Exact samples from the flow's Born distribution are obtained by pushing pre-cached base samples through the forward ODE, requiring no Markov chain Monte Carlo (MCMC) at training time. The base samples are generated offline and reused across training batches and runs, decoupling sample generation from parameter optimization and enabling embarrassingly parallel training across multiple GPUs. We introduce three novel permutation-equivariant vector field architectures: Pairwise Deep Sets (PDS), FermiNet Vector Fields (FVF), and Pairwise Deep Sets Gradient (PDSG), each offering a different balance of expressivity and computational cost. We further introduce an augmented dynamics formulation for kinetic energy computation that co-evolves the required derivative quantities as ODE state variables, eliminating differentiation through the ODE trajectory and yielding significant reductions in wall-clock time and memory. Training runs on systems of harmonically trapped spinless electrons demonstrate ground-state energies below CISD reference values. Scaling experiments demonstrate near-ideal strong scaling from 1 to 128 NVIDIA A100s using 32 GPU nodes of NERSC's Perlmutter supercomputer for systems of up to $N = 48$ particles in three dimensions.

quant-ph↗

arXiv2025

Leveraging Protein Language Model Embeddings for Catalytic Turnover Prediction of Adenylate Kinase Orthologs in a Low-Data Regime

Accurate prediction of enzymatic activity from amino acid sequences could drastically accelerate enzyme engineering for applications such as bioremediation and therapeutics development. In recent years, Protein Language Model (PLM) embeddings have been increasingly leveraged as the input into sequence-to-function models. Here, we use consistently collected catalytic turnover observations for 175 orthologs of the enzyme Adenylate Kinase (ADK) as a test case to assess the use of PLMs and their embeddings in enzyme kinetic prediction tasks. In this study, we show that nonlinear probing of PLM embeddings outperforms baseline embeddings (one-hot-encoding) and the specialized $k_{cat}$ (catalytic turnover number) prediction models DLKcat and CatPred. We also compared fixed and learnable aggregation of PLM embeddings for $k_{cat}$ prediction and found that transformer-based learnable aggregation of amino-acid PLM embeddings is generally the most performant. Additionally, we found that ESMC 600M embeddings marginally outperform other PLM embeddings for $k_{cat}$ prediction. We explored Low-Rank Adaptation (LoRA) masked language model fine-tuning and direct fine-tuning for sequence-to-$k_{cat}$ mapping, where we found no difference or a drop in performance compared to zero-shot embeddings, respectively. And we investigated the distinct hidden representations in PLM encoders and found that earlier layer embeddings perform comparable to or worse than the final layer. Overall, this study assesses the state of the field for leveraging PLMs for sequence-to-$k_{cat}$ prediction on a set of diverse ADK orthologs.

q-bio.QM↗

arXiv2024

Learning Melanocytic Cell Masks from Adjacent Stained Tissue

Melanoma is one of the most aggressive forms of skin cancer, causing a large proportion of skin cancer deaths. However, melanoma diagnoses by pathologists shows low interrater reliability. As melanoma is a cancer of the melanocyte, there is a clear need to develop a melanocytic cell segmentation tool that is agnostic to pathologist variability and automates pixel-level annotation. Gigapixel-level pathologist labeling, however, is impractical. Herein, we propose a means to train deep neural networks for melanocytic cell segmentation from hematoxylin and eosin (H&E) stained sections and paired immunohistochemistry (IHC) of adjacent tissue sections, achieving a mean IOU of 0.64 despite imperfect ground-truth labels.

q-bio.QM↗

arXiv2023

Autoregressive fragment-based diffusion for pocket-aware ligand design

In this work, we introduce AutoFragDiff, a fragment-based autoregressive diffusion model for generating 3D molecular structures conditioned on target protein structures. We employ geometric vector perceptrons to predict atom types and spatial coordinates of new molecular fragments conditioned on molecular scaffolds and protein pockets. Our approach improves the local geometry of the resulting 3D molecules while maintaining high predicted binding affinity to protein targets. The model can also perform scaffold extension from user-provided starting molecular scaffold.

q-bio.BM↗

arXiv2022

A single-cell gene expression language model

Gene regulation is a dynamic process that connects genotype and phenotype. Given the difficulty of physically mapping mammalian gene circuitry, we require new computational methods to learn regulatory rules. Natural language is a valuable analogy to the communication of regulatory control. Machine learning systems model natural language by explicitly learning context dependencies between words. We propose a similar system applied to single-cell RNA expression profiles to learn context dependencies between genes. Our model, Exceiver, is trained across a diversity of cell types using a self-supervised task formulated for discrete count data, accounting for feature sparsity. We found agreement between the similarity profiles of latent sample representations and learned gene embeddings with respect to biological annotations. We evaluated Exceiver on a new dataset and a downstream prediction task and found that pretraining supports transfer learning. Our work provides a framework to model gene regulation on a single-cell level and transfer knowledge to downstream tasks.

q-bio.QM↗

arXiv2021

Robust Semantic Interpretability: Revisiting Concept Activation Vectors

Interpretability methods for image classification assess model trustworthiness by attempting to expose whether the model is systematically biased or attending to the same cues as a human would. Saliency methods for feature attribution dominate the interpretability literature, but these methods do not address semantic concepts such as the textures, colors, or genders of objects within an image. Our proposed Robust Concept Activation Vectors (RCAV) quantifies the effects of semantic concepts on individual model predictions and on model behavior as a whole. RCAV calculates a concept gradient and takes a gradient ascent step to assess model sensitivity to the given concept. By generalizing previous work on concept activation vectors to account for model non-linearity, and by introducing stricter hypothesis testing, we show that RCAV yields interpretations which are both more accurate at the image level and robust at the dataset level. RCAV, like saliency methods, supports the interpretation of individual predictions. To evaluate the practical use of interpretability methods as debugging tools, and the scientific use of interpretability methods for identifying inductive biases (e.g. texture over shape), we construct two datasets and accompanying metrics for realistic benchmarking of semantic interpretability methods. Our benchmarks expose the importance of counterfactual augmentation and negative controls for quantifying the practical usability of interpretability methods.

stat.ML↗

arXiv2020

Attention-Based Learning on Molecular Ensembles

The three-dimensional shape and conformation of small-molecule ligands are critical for biomolecular recognition, yet encoding 3D geometry has not improved ligand-based virtual screening approaches. We describe an end-to-end deep learning approach that operates directly on small-molecule conformational ensembles and identifies key conformational poses of small-molecules. Our networks leverage two levels of representation learning: 1) individual conformers are first encoded as spatial graphs using a graph neural network, and 2) sampled conformational ensembles are represented as sets using an attention mechanism to aggregate over individual instances. We demonstrate the feasibility of this approach on a simple task based on bidentate coordination of biaryl ligands, and show how attention-based pooling can elucidate key conformational poses in tasks based on molecular geometry. This work illustrates how set-based learning approaches may be further developed for small molecule-based virtual screening.

cs.LG↗

arXiv2019

Global Saliency: Aggregating Saliency Maps to Assess Dataset Artefact Bias

In high-stakes applications of machine learning models, interpretability methods provide guarantees that models are right for the right reasons. In medical imaging, saliency maps have become the standard tool for determining whether a neural model has learned relevant robust features, rather than artefactual noise. However, saliency maps are limited to local model explanation because they interpret predictions on an image-by-image basis. We propose aggregating saliency globally, using semantic segmentation masks, to provide quantitative measures of model bias across a dataset. To evaluate global saliency methods, we propose two metrics for quantifying the validity of saliency explanations. We apply the global saliency method to skin lesion diagnosis to determine the effect of artefacts, such as ink, on model bias.

cs.CV↗