MOTIVATION: Predicting synergistic cancer drug combinations through computational methods offers a scalable approach to creating therapies that are more effective and less toxic. However, most algorithms focus solely on synergy without considering toxicity when selecting optimal drug combinations. In the absence of combinatorial toxicity assays, a few models use toxicity penalties to balance high synergy with lower toxicity. Still, these penalties have not been explicitly validated against known drug-drug interactions. RESULTS: In this study, we examine whether synergy scores and toxicity metrics correlate with known adverse drug interactions. While some metrics show trends with toxicity levels, our results reveal significant limitations in using them as penalties. These findings highlight the challenges of incorporating toxicity into synergy prediction frameworks and suggest that advancing the field requires more comprehensive combination toxicity data. AVAILABILITY AND IMPLEMENTATION: The code written for this project is available at https://github.com/amw14/toxicity-cancer-drug-combination.

Protein language models (PLMs) pretrained via a masked language modeling objective have proven effective across a range of structure-related tasks, including high-resolution structure prediction. However, it remains unclear to what extent these models factorize protein structural categories among their learned parameters. In this work, we introduce trainable subnetworks, which mask out the PLM weights responsible for language modeling performance on a structural category of proteins. We systematically trained 39 PLM subnetworks targeting both sequence- and residue-level features at varying degrees of resolution using annotations defined by the CATH taxonomy and secondary structure elements. Using these PLM subnetworks, we assessed how structural factorization in PLMs influences downstream structure prediction. Our results show that PLMs are highly sensitive to sequence-level features and can predominantly disentangle extremely coarse or fine-grained information. Furthermore, we observe that structure prediction is highly responsive to factorized PLM representations and that small changes in language modeling performance can significantly impair PLM-based structure prediction capabilities. Our work presents a framework for studying feature entanglement within pretrained PLMs and can be leveraged to improve the alignment of learned PLM representations with known biological concepts.

In this paper, we aim to build a platform that will help bridge the gap between high-dimensional computation and wet-lab experimentation by allowing users to interrogate genomic signatures at multiple molecular levels and identify best next actionable steps for downstream decision making. We introduce Multioviz: a publicly accessible R package and web application platform to easily perform in silico hypothesis testing of generated gene regulatory networks. We demonstrate the utility of Multioviz by conducting an end-to-end analysis in a statistical genetics application focused on measuring the effect of in silico perturbations of complex trait architecture. By using a real dataset from the Wellcome Trust Centre for Human Genetics, we both recapitulate previous findings and propose hypotheses about the genes involved in the percentage of immune CD8+ cells found in heterogeneous stocks of mice. Source code for the Multioviz R package is available at https://github.com/lcrawlab/multio-viz and an interactive version of the platform is available at https://multioviz.ccv.brown.edu/ .

Significant variations have been observed in viral copies generated during SARS-CoV-2 infections. However, the factors that impact viral copies and infection dynamics are not fully understood, and may be inherently dependent upon different viral and host factors. Here, we conducted virus whole genome sequencing and measured viral copies using RT-qPCR from 9,902 SARS-CoV-2 infections over a 2-year period to examine the impact of virus genetic variation on changes in viral copies adjusted for host age and vaccination status. Using a genome-wide association study (GWAS) approach, we identified multiple single-nucleotide polymorphisms (SNPs) corresponding to amino acid changes in the SARS-CoV-2 genome associated with variations in viral copies. We further applied a marginal epistasis test to detect interactions among SNPs and identified multiple pairs of substitutions located in the spike gene that have non-linear effects on viral copies. We also analyzed the temporal patterns and found that SNPs associated with increased viral copies were predominantly observed in Delta and Omicron BA.2/BA.4/BA.5/XBB infections, whereas those associated with decreased viral copies were only observed in infections with Omicron BA.1 variants. Our work showcases how GWAS can be a useful tool for probing phenotypes related to SNPs in viral genomes that are worth further exploration. We argue that this approach can be used more broadly across pathogens to characterize emerging variants and monitor therapeutic interventions.

Randomized experiments often need to be stopped prematurely due to the treatment having an unintended harmful effect. Existing methods that determine when to stop an experiment early are typically applied to the data in aggregate and do not account for treatment effect heterogeneity. In this paper, we study the early stopping of experiments for harm on heterogeneous populations. We first establish that current methods often fail to stop experiments when the treatment harms a minority group of participants. We then use causal machine learning to develop CLASH, the first broadly-applicable method for heterogeneous early stopping. We demonstrate CLASH's performance on simulated and real data and show that it yields effective early stopping for both clinical trials and A/B tests.

Natural products are chemical compounds that form the basis of many therapeutics used in the pharmaceutical industry. In microbes, natural products are synthesized by groups of colocalized genes called biosynthetic gene clusters (BGCs). With advances in high-throughput sequencing, there has been an increase of complete microbial isolate genomes and metagenomes, from which a vast number of BGCs are undiscovered. Here, we introduce a self-supervised learning approach designed to identify and characterize BGCs from such data. To do this, we represent BGCs as chains of functional protein domains and train a masked language model on these domains. We assess the ability of our approach to detect BGCs and characterize BGC properties in bacterial genomes. We also demonstrate that our model can learn meaningful representations of BGCs and their constituent domains, detect BGCs in microbial genomes, and predict BGC product classes. These results highlight self-supervised neural networks as a promising framework for improving BGC prediction and classification.

Identifying structural differences among proteins can be a non-trivial task. When contrasting ensembles of protein structures obtained from molecular dynamics simulations, biologically-relevant features can be easily overshadowed by spurious fluctuations. Here, we present SINATRA Pro, a computational pipeline designed to robustly identify topological differences between two sets of protein structures. Algorithmically, SINATRA Pro works by first taking in the 3D atomic coordinates for each protein snapshot and summarizing them according to their underlying topology. Statistically significant topological features are then projected back onto a user-selected representative protein structure, thus facilitating the visual identification of biophysical signatures of different protein ensembles. We assess the ability of SINATRA Pro to detect minute conformational changes in five independent protein systems of varying complexities. In all test cases, SINATRA Pro identifies known structural features that have been validated by previous experimental and computational studies, as well as novel features that are also likely to be biologically-relevant according to the literature. These results highlight SINATRA Pro as a promising method for facilitating the non-trivial task of pattern recognition in trajectories resulting from molecular dynamics simulations, with substantially increased resolution.