James Kozloski

Hongyang Li, Sanjoy Dey, Bum Chul Kwon et al.

Large language models (LLMs) trained on text demonstrated remarkable results on natural language processing (NLP) tasks. These models have been adapted to decipher the language of DNA, where sequences of nucleotides act as "words" that encode genomic functions. However, the genome differs fundamentally from natural language, as it lacks clearly defined words or a consistent grammar. Although DNA language models (DNALMs) such as DNABERT, GENA-LM have achieved high level of performance on genome-related biological tasks, these models do not encode biological functions in the presence of sequence variations. To address this problem, we pre-train foundation models that effectively integrate sequence variations, in particular Single Nucleotide Polymorphisms (SNPs), as they underlie important biological functions. Specifically, we use ModernBERT to pre-train two different Biomedical Foundation Models (BMFM), namely, BMFM-DNA-REF in which the model is trained with sequences of varying lengths along with their reverse complements derived from the reference genome and BMFM-DNA-SNP in which the model is trained with sequences created using a novel representation scheme that encodes sequence variations. Our findings indicate that integrating sequence variations into DNALMs helps capture the biological functions as seen in improvements on all fine-tuning tasks. To explore the model's practical utility, we experimented with various strategies for SNP imputation on promoter detection task introduced in DNABERT-2. However, we acknowledge that the current benchmarks are limited in their ability to fully evaluate these models. To enable more comprehensive assessment in the future and encourage community contributions, we release our models through HuggingFace and the code to reproduce the results at https://github.com/BiomedSciAI/biomed-multi-omic

Takuya Ito, Soham Dan, Mattia Rigotti et al.

The advent of the Transformer has led to the development of large language models (LLM), which appear to demonstrate human-like capabilities. To assess the generality of this class of models and a variety of other base neural network architectures to multimodal domains, we evaluated and compared their capacity for multimodal generalization. We introduce a multimodal question-answer benchmark to evaluate three specific types of out-of-distribution (OOD) generalization performance: distractor generalization (generalization in the presence of distractors), systematic compositional generalization (generalization to new task permutations), and productive compositional generalization (generalization to more complex tasks structures). We found that across model architectures (e.g., RNNs, Transformers, Perceivers, etc.), models with multiple attention layers, or models that leveraged cross-attention mechanisms between input domains, fared better. Our positive results demonstrate that for multimodal distractor and systematic generalization, either cross-modal attention or models with deeper attention layers are key architectural features required to integrate multimodal inputs. On the other hand, neither of these architectural features led to productive generalization, suggesting fundamental limitations of existing architectures for specific types of multimodal generalization. These results demonstrate the strengths and limitations of specific architectural components underlying modern neural models for multimodal reasoning. Finally, we provide Generic COG (gCOG), a configurable benchmark with several multimodal generalization splits, for future studies to explore.

Timothy Rumbell, Jaimit Parikh, James Kozloski et al.

Predictions for physical systems often rely upon knowledge acquired from ensembles of entities, e.g., ensembles of cells in biological sciences. For qualitative and quantitative analysis, these ensembles are simulated with parametric families of mechanistic models (MM). Two classes of methodologies, based on Bayesian inference and Population of Models, currently prevail in parameter estimation for physical systems. However, in Bayesian analysis, uninformative priors for MM parameters introduce undesirable bias. Here, we propose how to infer parameters within the framework of stochastic inverse problems (SIP), also termed data-consistent inversion, wherein the prior targets only uncertainties that arise due to MM non-invertibility. To demonstrate, we introduce new methods to solve SIP based on rejection sampling, Markov chain Monte Carlo, and generative adversarial networks (GANs). In addition, to overcome limitations of SIP, we reformulate SIP based on constrained optimization and present a novel GAN to solve the constrained optimization problem.

German Abrevaya, Irina Rish, Aleksandr Y. Aravkin et al.

Many real-world data sets, especially in biology, are produced by complex nonlinear dynamical systems. In this paper, we focus on brain calcium imaging (CaI) of different organisms (zebrafish and rat), aiming to build a model of joint activation dynamics in large neuronal populations, including the whole brain of zebrafish. We propose a new approach for capturing dynamics of temporal SVD components that uses the coupled (multivariate) van der Pol (VDP) oscillator, a nonlinear ordinary differential equation (ODE) model describing neural activity, with a new parameter estimation technique that combines variable projection optimization and stochastic search. We show that the approach successfully handles nonlinearities and hidden state variables in the coupled VDP. The approach is accurate, achieving 0.82 to 0.94 correlation between the actual and model-generated components, and interpretable, as VDP's coupling matrix reveals anatomically meaningful positive (excitatory) and negative (inhibitory) interactions across different brain subsystems corresponding to spatial SVD components. Moreover, VDP is comparable to (or sometimes better than) recurrent neural networks (LSTM) for (short-term) prediction of future brain activity; VDP needs less parameters to train, which was a plus on our small training data. Finally, the overall best predictive method, greatly outperforming both VDP and LSTM in short- and long-term predictive settings on both datasets, was the new hybrid VDP-LSTM approach that used VDP to simulate large domain-specific dataset for LSTM pretraining; note that simple LSTM data-augmentation via noisy versions of training data was much less effective.