arXiv subjects

Anthony Gitter

Publications and source records attributed to Anthony Gitter.

At least 19 recordsLinked to original sources

arXiv2025

Assay2Mol: large language model-based drug design using BioAssay context

Scientific databases aggregate vast amounts of quantitative data alongside descriptive text. In biochemistry, molecule screening assays evaluate candidate molecules' functional responses against disease targets. Unstructured text that describes the biological mechanisms through which these targets operate, experimental screening protocols, and other attributes of assays offer rich information for drug discovery campaigns but has been untapped because of that unstructured format. We present Assay2Mol, a large language model-based workflow that can capitalize on the vast existing biochemical screening assays for early-stage drug discovery. Assay2Mol retrieves existing assay records involving targets similar to the new target and generates candidate molecules using in-context learning with the retrieved assay screening data. Assay2Mol outperforms recent machine learning approaches that generate candidate ligand molecules for target protein structures, while also promoting more synthesizable molecule generation.

cs.LG↗

arXiv2025

Benchmarking and Evaluation of AI Models in Biology: Outcomes and Recommendations from the CZI Virtual Cells Workshop

Artificial intelligence holds immense promise for transforming biology, yet a lack of standardized, cross domain, benchmarks undermines our ability to build robust, trustworthy models. Here, we present insights from a recent workshop that convened machine learning and computational biology experts across imaging, transcriptomics, proteomics, and genomics to tackle this gap. We identify major technical and systemic bottlenecks such as data heterogeneity and noise, reproducibility challenges, biases, and the fragmented ecosystem of publicly available resources and propose a set of recommendations for building benchmarking frameworks that can efficiently compare ML models of biological systems across tasks and data modalities. By promoting high quality data curation, standardized tooling, comprehensive evaluation metrics, and open, collaborative platforms, we aim to accelerate the development of robust benchmarks for AI driven Virtual Cells. These benchmarks are crucial for ensuring rigor, reproducibility, and biological relevance, and will ultimately advance the field toward integrated models that drive new discoveries, therapeutic insights, and a deeper understanding of cellular systems.

cs.LG↗

arXiv2025

Exploring zero-shot structure-based protein fitness prediction

The ability to make zero-shot predictions about the fitness consequences of protein sequence changes with pre-trained machine learning models enables many practical applications. Such models can be applied for downstream tasks like genetic variant interpretation and protein engineering without additional labeled data. The advent of capable protein structure prediction tools has led to the availability of orders of magnitude more precomputed predicted structures, giving rise to powerful structure-based fitness prediction models. Through our experiments, we assess several modeling choices for structure-based models and their effects on downstream fitness prediction. Zero-shot fitness prediction models can struggle to assess the fitness landscape within disordered regions of proteins, those that lack a fixed 3D structure. We confirm the importance of matching protein structures to fitness assays and find that predicted structures for disordered regions can be misleading and affect predictive performance. Lastly, we evaluate an additional structure-based model on the ProteinGym substitution benchmark and show that simple multi-modal ensembles are strong baselines.

q-bio.QM↗

arXiv2024

Chemical Language Model Linker: blending text and molecules with modular adapters

The development of large language models and multi-modal models has enabled the appealing idea of generating novel molecules from text descriptions. Generative modeling would shift the paradigm from relying on large-scale chemical screening to find molecules with desired properties to directly generating those molecules. However, multi-modal models combining text and molecules are often trained from scratch, without leveraging existing high-quality pretrained models. Training from scratch consumes more computational resources and prohibits model scaling. In contrast, we propose a lightweight adapter-based strategy named Chemical Language Model Linker (ChemLML). ChemLML blends the two single domain models and obtains conditional molecular generation from text descriptions while still operating in the specialized embedding spaces of the molecular domain. ChemLML can tailor diverse pretrained text models for molecule generation by training relatively few adapter parameters. We find that the choice of molecular representation used within ChemLML, SMILES versus SELFIES, has a strong influence on conditional molecular generation performance. SMILES is often preferable despite not guaranteeing valid molecules. We raise issues in using the entire PubChem dataset of molecules and their associated descriptions for evaluating molecule generation and provide a filtered version of the dataset as a generation test set. To demonstrate how ChemLML could be used in practice, we generate candidate protein inhibitors and use docking to assess their quality and also generate candidate membrane permeable molecules.

cs.LG↗

arXiv2024

Product Manifold Representations for Learning on Biological Pathways

Machine learning models that embed graphs in non-Euclidean spaces have shown substantial benefits in a variety of contexts, but their application has not been studied extensively in the biological domain, particularly with respect to biological pathway graphs. Such graphs exhibit a variety of complex network structures, presenting challenges to existing embedding approaches. Learning high-quality embeddings for biological pathway graphs is important for researchers looking to understand the underpinnings of disease and train high-quality predictive models on these networks. In this work, we investigate the effects of embedding pathway graphs in non-Euclidean mixed-curvature spaces and compare against traditional Euclidean graph representation learning models. We then train a supervised model using the learned node embeddings to predict missing protein-protein interactions in pathway graphs. We find large reductions in distortion and boosts on in-distribution edge prediction performance as a result of using mixed-curvature embeddings and their corresponding graph neural network models. However, we find that mixed-curvature representations underperform existing baselines on out-of-distribution edge prediction performance suggesting that these representations may overfit to the training graph topology. We provide our Mixed-Curvature Product Graph Convolutional Network code at https://github.com/mcneela/Mixed-Curvature-GCN and our pathway analysis code at https://github.com/mcneela/Mixed-Curvature-Pathways.

q-bio.QM↗

arXiv2023

Current and future directions in network biology

Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These challenges stem from various factors, notably the growing complexity and volume of data together with the increased diversity of data types describing different tiers of biological organization. We discuss prevailing research directions in network biology and highlight areas of inference and comparison of biological networks, multimodal data integration and heterogeneous networks, higher-order network analysis, machine learning on networks, and network-based personalized medicine. Following the overview of recent breakthroughs across these five areas, we offer a perspective on the future directions of network biology. Additionally, we offer insights into scientific communities, educational initiatives, and the importance of fostering diversity within the field. This paper establishes a roadmap for an immediate and long-term vision for network biology.

q-bio.MN↗

arXiv2023

A Text-guided Protein Design Framework

Current AI-assisted protein design mainly utilizes protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in the text format describing proteins' high-level functionalities. Yet, whether the incorporation of such text data can help protein design tasks has not been explored. To bridge this gap, we propose ProteinDT, a multi-modal framework that leverages textual descriptions for protein design. ProteinDT consists of three subsequent steps: ProteinCLAP which aligns the representation of two modalities, a facilitator that generates the protein representation from the text modality, and a decoder that creates the protein sequences from the representation. To train ProteinDT, we construct a large dataset, SwissProtCLAP, with 441K text and protein pairs. We quantitatively verify the effectiveness of ProteinDT on three challenging tasks: (1) over 90% accuracy for text-guided protein generation; (2) best hit ratio on 12 zero-shot text-guided protein editing tasks; (3) superior performance on four out of six protein property prediction benchmarks.

cs.LG↗

arXiv2022

Graph algorithms for predicting subcellular localization at the pathway level

Protein subcellular localization is an important factor in normal cellular processes and disease. While many protein localization resources treat it as static, protein localization is dynamic and heavily influenced by biological context. Biological pathways are graphs that represent a specific biological context and can be inferred from large-scale data. We develop graph algorithms to predict the localization of all interactions in a biological pathway as an edge-labeling task. We compare a variety of models including graph neural networks, probabilistic graphical models, and discriminative classifiers for predicting localization annotations from curated pathway databases. We also perform a case study where we construct biological pathways and predict localizations of human fibroblasts undergoing viral infection. Pathway localization prediction is a promising approach for integrating publicly available localization data into the analysis of large-scale biological data.

q-bio.MN↗

arXiv2022

The Coming of Age of Nucleic Acid Vaccines during COVID-19

In the 21st century, several emergent viruses have posed a global threat. Each pathogen has emphasized the value of rapid and scalable vaccine development programs. The ongoing SARS-CoV-2 pandemic has made the importance of such efforts especially clear. New biotechnological advances in vaccinology allow for recent advances that provide only the nucleic acid building blocks of an antigen, eliminating many safety concerns. During the COVID-19 pandemic, these DNA and RNA vaccines have facilitated the development and deployment of vaccines at an unprecedented pace. This success was attributable at least in part to broader shifts in scientific research relative to prior epidemics; the genome of SARS-CoV-2 was available as early as January 2020, facilitating global efforts in the development of DNA and RNA vaccines within two weeks of the international community becoming aware of the new viral threat. Additionally, these technologies that were previously only theoretical are not only safe but also highly efficacious. Although historically a slow process, the rapid development of vaccines during the COVID-19 crisis reveals a major shift in vaccine technologies. Here, we provide historical context for the emergence of these paradigm-shifting vaccines. We describe several DNA and RNA vaccines and in terms of their efficacy, safety, and approval status. We also discuss patterns in worldwide distribution. The advances made since early 2020 provide an exceptional illustration of how rapidly vaccine development technology has advanced in the last two decades in particular and suggest a new era in vaccines against emerging pathogens.

q-bio.BM↗

arXiv2022

Application of Traditional Vaccine Development Strategies to SARS-CoV-2

Over the past 150 years, vaccines have revolutionized the relationship between people and disease. During the COVID-19 pandemic, technologies such as mRNA vaccines have received attention due to their novelty and successes. However, more traditional vaccine development platforms have also yielded important tools in the worldwide fight against the SARS-CoV-2 virus. A variety of approaches have been used to develop COVID-19 vaccines that are now authorized for use in countries around the world. In this review, we highlight strategies that focus on the viral capsid and outwards, rather than on the nucleic acids inside. These approaches fall into two broad categories: whole-virus vaccines and subunit vaccines. Whole-virus vaccines use the virus itself, either in an inactivated or attenuated state. Subunit vaccines contain instead an isolated, immunogenic component of the virus. Here, we highlight vaccine candidates that apply these approaches against SARS-CoV-2 in different ways. In a companion manuscript, we review the more recent and novel development of nucleic-acid based vaccine technologies. We further consider the role that these COVID-19 vaccine development programs have played in prophylaxis at the global scale. Well-established vaccine technologies have proved especially important to making vaccines accessible in low- and middle-income countries. Vaccine development programs that use established platforms have been undertaken in a much wider range of countries than those using nucleic-acid-based technologies, which have been led by wealthy Western countries. Therefore, these vaccine platforms, though less novel from a biotechnological standpoint, have proven to be extremely important to the management of SARS-CoV-2.

q-bio.OT↗

arXiv2022

Molecular and Serologic Diagnostic Technologies for SARS-CoV-2

The COVID-19 pandemic has presented many challenges that have spurred biotechnological research to address specific problems. Diagnostics is one area where biotechnology has been critical. Diagnostic tests play a vital role in managing a viral threat by facilitating the detection of infected and/or recovered individuals. From the perspective of what information is provided, these tests fall into two major categories, molecular and serological. Molecular diagnostic techniques assay whether a virus is present in a biological sample, thus making it possible to identify individuals who are currently infected. Additionally, when the immune system is exposed to a virus, it responds by producing antibodies specific to the virus. Serological tests make it possible to identify individuals who have mounted an immune response to a virus of interest and therefore facilitate the identification of individuals who have previously encountered the virus. These two categories of tests provide different perspectives valuable to understanding the spread of SARS-CoV-2. Within these categories, different biotechnological approaches offer specific advantages and disadvantages. Here we review the categories of tests developed for the detection of the SARS-CoV-2 virus or antibodies against SARS-CoV-2 and discuss the role of diagnostics in the COVID-19 pandemic.

q-bio.BM↗

arXiv2021

An Open-Publishing Response to the COVID-19 Infodemic

The COVID-19 pandemic catalyzed the rapid dissemination of papers and preprints investigating the disease and its associated virus, SARS-CoV-2. The multifaceted nature of COVID-19 demands a multidisciplinary approach, but the urgency of the crisis combined with the need for social distancing measures present unique challenges to collaborative science. We applied a massive online open publishing approach to this problem using Manubot. Through GitHub, collaborators summarized and critiqued COVID-19 literature, creating a review manuscript. Manubot automatically compiled citation information for referenced preprints, journal publications, websites, and clinical trials. Continuous integration workflows retrieved up-to-date data from online sources nightly, regenerating some of the manuscript's figures and statistics. Manubot rendered the manuscript into PDF, HTML, LaTeX, and DOCX outputs, immediately updating the version available online upon the integration of new content. Through this effort, we organized over 50 scientists from a range of backgrounds who evaluated over 1,500 sources and developed seven literature reviews. While many efforts from the computational community have focused on mining COVID-19 literature, our project illustrates the power of open publishing to organize both technical and non-technical scientists to aggregate and disseminate information in response to an evolving crisis.

cs.DL↗

arXiv2021

Ten Quick Tips for Deep Learning in Biology

Machine learning is a modern approach to problem-solving and task automation. In particular, machine learning is concerned with the development and applications of algorithms that can recognize patterns in data and use them for predictive modeling. Artificial neural networks are a particular class of machine learning algorithms and models that evolved into what is now described as deep learning. Given the computational advances made in the last decade, deep learning can now be applied to massive data sets and in innumerable contexts. Therefore, deep learning has become its own subfield of machine learning. In the context of biological research, it has been increasingly used to derive novel insights from high-dimensional biological data. To make the biological applications of deep learning more accessible to scientists who have some experience with machine learning, we solicited input from a community of researchers with varied biological and deep learning interests. These individuals collaboratively contributed to this manuscript's writing using the GitHub version control platform and the Manubot manuscript generation toolset. The goal was to articulate a practical, accessible, and concise set of guidelines and suggestions to follow when using deep learning. In the course of our discussions, several themes became clear: the importance of understanding and applying machine learning fundamentals as a baseline for utilizing deep learning, the necessity for extensive model comparisons with careful evaluation, and the need for critical thought in interpreting results generated by deep learning, among others.

q-bio.OT↗

arXiv2021

Identification and Development of Therapeutics for COVID-19

After emerging in China in late 2019, the novel Severe acute respiratory syndrome-like coronavirus 2 (SARS-CoV-2) spread worldwide and as of early 2021, continues to significantly impact most countries. Only a small number of coronaviruses are known to infect humans, and only two are associated with the severe outcomes associated with SARS-CoV-2: Severe acute respiratory syndrome-related coronavirus, a closely related species of SARS-CoV-2 that emerged in 2002, and Middle East respiratory syndrome-related coronavirus, which emerged in 2012. Both of these previous epidemics were controlled fairly rapidly through public health measures, and no vaccines or robust therapeutic interventions were identified. However, previous insights into the immune response to coronaviruses gained during the outbreaks of severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS) have proved beneficial to identifying approaches to the treatment and prophylaxis of novel coronavirus disease 2019 (COVID-19). A number of potential therapeutics against SARS-CoV-2 and the resultant COVID-19 illness were rapidly identified, leading to a large number of clinical trials investigating a variety of possible therapeutic approaches being initiated early on in the pandemic. As a result, a small number of therapeutics have already been authorized by regulatory agencies such as the Food and Drug Administration (FDA) in the United States, and many other therapeutics remain under investigation. Here, we describe a range of approaches for the treatment of COVID-19, along with their proposed mechanisms of action and the current status of clinical investigation into each candidate. The status of these investigations will continue to evolve, and this review will be updated as progress is made.

q-bio.QM↗

arXiv2021

Pathogenesis, Symptomatology, and Transmission of SARS-CoV-2 through Analysis of Viral Genomics and Structure

The novel coronavirus SARS-CoV-2, which emerged in late 2019, has since spread around the world and infected hundreds of millions of people with coronavirus disease 2019 (COVID-19). While this viral species was unknown prior to January 2020, its similarity to other coronaviruses that infect humans has allowed for rapid insight into the mechanisms that it uses to infect human hosts, as well as the ways in which the human immune system can respond. Here, we contextualize SARS-CoV-2 among other coronaviruses and identify what is known and what can be inferred about its behavior once inside a human host. Because the genomic content of coronaviruses, which specifies the virus's structure, is highly conserved, early genomic analysis provided a significant head start in predicting viral pathogenesis and in understanding potential differences among variants. The pathogenesis of the virus offers insights into symptomatology, transmission, and individual susceptibility. Additionally, prior research into interactions between the human immune system and coronaviruses has identified how these viruses can evade the immune system's protective mechanisms. We also explore systems-level research into the regulatory and proteomic effects of SARS-CoV-2 infection and the immune response. Understanding the structure and behavior of the virus serves to contextualize the many facets of the COVID-19 pandemic and can influence efforts to control the virus and treat the disease.

q-bio.QM↗

arXiv2020

Bayes Optimal Informer Sets for Early-Stage Drug Discovery

An important experimental design problem in early-stage drug discovery is how to prioritize available compounds for testing when very little is known about the target protein. Informer based ranking (IBR) methods address the prioritization problem when the compounds have provided bioactivity data on other potentially relevant targets. An IBR method selects an informer set of compounds, and then prioritizes the remaining compounds on the basis of new bioactivity experiments performed with the informer set on the target. We formalize the problem as a two-stage decision problem and introduce the Bayes Optimal Informer SEt (BOISE) method for its solution. BOISE leverages a flexible model of the initial bioactivity data, a relevant loss function, and effective computational schemes to resolve the two-step design problem. We evaluate BOISE and compare it to other IBR strategies in two retrospective studies, one on protein-kinase inhibition and the other on anti-cancer drug sensitivity. In both empirical settings BOISE exhibits better predictive performance than available methods. It also behaves well with missing data, where methods that use matrix completion show worse predictive performance. We provide an R implementation of BOISE at https://github.com/wiscstatman/esdd/BOISE

stat.ME↗

arXiv2020

Inferring Signaling Pathways with Probabilistic Programming

Cells regulate themselves via dizzyingly complex biochemical processes called signaling pathways. These are usually depicted as a network, where nodes represent proteins and edges indicate their influence on each other. In order to understand diseases and therapies at the cellular level, it is crucial to have an accurate understanding of the signaling pathways at work. Since signaling pathways can be modified by disease, the ability to infer signaling pathways from condition- or patient-specific data is highly valuable. A variety of techniques exist for inferring signaling pathways. We build on past works that formulate signaling pathway inference as a Dynamic Bayesian Network structure estimation problem on phosphoproteomic time course data. We take a Bayesian approach, using Markov Chain Monte Carlo to estimate a posterior distribution over possible Dynamic Bayesian Network structures. Our primary contributions are (i) a novel proposal distribution that efficiently samples sparse graphs and (ii) the relaxation of common restrictive modeling assumptions. We implement our method, named Sparse Signaling Pathway Sampling, in Julia using the Gen probabilistic programming language. Probabilistic programming is a powerful methodology for building statistical models. The resulting code is modular, extensible, and legible. The Gen language, in particular, allows us to customize our inference procedure for biological graphs and ensure efficient sampling. We evaluate our algorithm on simulated data and the HPN-DREAM pathway reconstruction challenge, comparing our performance against a variety of baseline methods. Our results demonstrate the vast potential for probabilistic programming, and Gen specifically, for biological network inference. Find the full codebase at https://github.com/gitter-lab/ssps

q-bio.MN↗

arXiv2016

Unsupervised learning of transcriptional regulatory networks via latent tree graphical models

Gene expression is a readily-observed quantification of transcriptional activity and cellular state that enables the recovery of the relationships between regulators and their target genes. Reconstructing transcriptional regulatory networks from gene expression data is a problem that has attracted much attention, but previous work often makes the simplifying (but unrealistic) assumption that regulator activity is represented by mRNA levels. We use a latent tree graphical model to analyze gene expression without relying on transcription factor expression as a proxy for regulator activity. The latent tree model is a type of Markov random field that includes both observed gene variables and latent (hidden) variables, which factorize on a Markov tree. Through efficient unsupervised learning approaches, we determine which groups of genes are co-regulated by hidden regulators and the activity levels of those regulators. Post-processing annotates many of these discovered latent variables as specific transcription factors or groups of transcription factors. Other latent variables do not necessarily represent physical regulators but instead reveal hidden structure in the gene expression such as shared biological function. We apply the latent tree graphical model to a yeast stress response dataset. In addition to novel predictions, such as condition-specific binding of the transcription factor Msn4, our model recovers many known aspects of the yeast regulatory network. These include groups of co-regulated genes, condition-specific regulator activity, and combinatorial regulation among transcription factors. The latent tree graphical model is a general approach for analyzing gene expression data that requires no prior knowledge of which possible regulators exist, regulator activity, or where transcription factors physically bind.

q-bio.MN↗