Biology subjects

Sledzieski, S.

Publications and source records attributed to Sledzieski, S..

11 recordsLinked to original sources

bioRxiv2025

RocketSHP: Ultra-fast Proteome-scale Prediction of Protein Dynamics

Proteins are dynamic molecules that depend on conformational flexibility to carry out functions in the cell, yet despite significant advances in the modeling of static protein structure, prediction of these dynamics remains challenging. We introduce PLANET-MD, a machine learning model that predicts dynamic protein properties from sequence or static structure with unprecedented speed and accuracy. Trained on thousands of molecular dynamics trajectories spanning diverse protein families, PLANET-MD simultaneously models multiple dynamics features: root-mean-square fluctuations (RMSF), generalized correlation coefficients (GCC-LMI), and a novel structural heterogeneity profile (SHP) based on recent structure quantization methods. PLANET-MD significantly outperforms existing methods in predicting simulation-derived dynamics. We reduce RMSF prediction error by 57% compared to BioEmu and calibrated Dyna-1 predictions, including an up to 73% error reduction for long proteins. We validate these predictions with experimental hetNOE data, and we demonstrate the ability to adapt predictions to different physical temperatures. We highlight PLANET-MDs utility in constructing allosteric networks in the oncogene KRAS and identify structural sub-modules with correlated motions, and we validate PLANET-MD by showing that changes in node centrality within predicted KRAS allosteric networks correlate with changes of folding free energy in experimental DMS data. Our approach makes predictions in seconds rather than hours or days, enabling us to perform the first comprehensive dynamics analysis of the entire human proteome. PLANET-MD bridges the gap between static structural biology and dynamic functional understanding, enabling dynamics-aware structural analysis and variant effect prediction at scales previously unavailable. PLANET-MD is available as free and open-source software at https://github.com/flatironinstitute/PLANET-MD.

bioinformatics↗

bioRxiv2025

Learning the language of protein-protein interactions

Protein Language Models (PLMs) trained on large databases of protein sequences have proven effective in modeling protein biology across a wide range of applications. However, while PLMs excel at capturing individual protein properties, they face challenges in natively representing protein-protein interactions (PPIs), which are crucial to understanding cellular processes and disease mechanisms. Here, we introduce MINT, a PLM specifically designed to model sets of interacting proteins in a contextual and scalable manner. Using unsupervised training on a large curated PPI dataset derived from the STRING database, MINT outperforms existing PLMs in diverse tasks relating to protein-protein interactions, including binding affinity prediction and estimation of mutational effects. Beyond these core capabilities, it excels at modeling interactions in complex protein assemblies and surpasses specialized models in antibody-antigen modeling and T cell receptor-epitope binding prediction. MINTs predictions of mutational impacts on oncogenic PPIs align with experimental studies, and it provides reliable estimates for the potential for cross-neutralization of antibodies against SARS-CoV-2 variants of concern. These findings position MINT as a powerful tool for elucidating complex protein interactions, with significant implications for biomedical research and therapeutic discovery.

bioinformatics↗

bioRxiv2024

Decoding the Functional Interactome of Non-Model Organisms with PHILHARMONIC

Despite the widespread availability of genome sequencing pipelines, many genes remain part of the genome's "dark matter," where existing inference tools cannot even begin to guess the biological function of their proteins from sequence alone. This challenge is especially pronounced in organisms that are highly evolutionarily distant from well-studied models, where homology-based methods break down. Here, we describe PHILHARMONIC, a computational method that combines deep learning-based de novo protein interaction network inference with robust unsupervised spectral clustering and remote homology to illuminate functional organization in any non-model organism. From only a sequenced proteome, we show PHILHARMONIC generates meaningful functional hypothesis for protein functions, functional communities, and higher-order network structure. We validate its performance using experimental gene expression and pathway data in D. melanogaster, and we demonstrate its broad utility by analyzing temperature sensing and stress response pathways in the reef-building coral P. damicornis and its algal symbiont C. goreaui. PHILHARMONIC provides a general-purpose engine for functional discovery and biological hypothesis generation in non-model organisms, enabling systems-level insights across the full diversity of life.

bioinformatics↗

bioRxiv2023

Democratizing Protein Language Models with Parameter-Efficient Fine-Tuning

Proteomics has been revolutionized by large pre-trained protein language models, which learn unsupervised representations from large corpora of sequences. The parameters of these models are then fine-tuned in a supervised setting to tailor the model to a specific downstream task. However, as model size increases, the computational and memory footprint of fine-tuning becomes a barrier for many research groups. In the field of natural language processing, which has seen a similar explosion in the size of models, these challenges have been addressed by methods for parameter-efficient fine-tuning (PEFT). In this work, we newly bring parameter-efficient fine-tuning methods to proteomics. Using the parameter-efficient method LoRA, we train new models for two important proteomic tasks: predicting protein-protein interactions (PPI) and predicting the symmetry of homooligomers. We show that for homooligomer symmetry prediction, these approaches achieve performance competitive with traditional fine-tuning while requiring reduced memory and using three orders of magnitude fewer parameters. On the PPI prediction task, we surprisingly find that PEFT models actually outperform traditional fine-tuning while using two orders of magnitude fewer parameters. Here, we go even further to show that freezing the parameters of the language model and training only a classification head also outperforms fine-tuning, using five orders of magnitude fewer parameters, and that both of these models outperform state-of-the-art PPI prediction methods with substantially reduced compute. We also demonstrate that PEFT is robust to variations in training hyper-parameters, and elucidate where best practices for PEFT in proteomics differ from in natural language processing. Thus, we provide a blueprint to democratize the power of protein language model tuning to groups which have limited computational resources.

bioinformatics↗

bioRxiv2022

Learning the Drug-Target Interaction Lexicon

Sequence-based prediction of drug-target interactions has the potential to accelerate drug discovery by complementing experimental screens. Such computational prediction needs to be generalizable and scalable while remaining sensitive to subtle variations in the inputs. However, current computational techniques fail to simultaneously meet these goals, often sacrificing performance on one to achieve the others. We develop a deep learning model, ConPLex, successfully leveraging the advances in pre-trained protein language models ("PLex") and employing a novel protein-anchored contrastive co-embedding ("Con") to outperform state-of-the-art approaches. ConPLex achieves high accuracy, broad adaptivity to unseen data, and specificity against decoy compounds. It makes predictions of binding based on the distance between learned representations, enabling predictions at the scale of massive compound libraries and the human proteome. Furthermore, ConPLex is interpretable, which enables us to visualize the drug-target lexicon and use embeddings to characterize the function of human cell-surface proteins. We anticipate ConPLex will facilitate novel drug discovery by making highly sensitive and interpretable in-silico drug screening feasible at genome scale. Con-PLex is available open-source at https://github.com/samsledje/ConPLex. Significance StatementIn time and money, one of the most expensive steps of the drug discovery pipeline is the experimental screening of small molecules to see which will bind to a protein target of interest. Therefore, accurate high-throughput computational prediction of drug-target interactions would unlock significant value, guiding and prioritizing promising candidates for experimental screening. We introduce ConPLex, a machine learning method for predicting drug-target binding which achieves state-of-the-art accuracy on many types of targets by using a pre-trained protein language model. The approach co-locates the proteins and the potential drug molecules in a shared feature space while learning to contrast true drugs from similar non-binding "decoy" molecules. ConPLex is extremely fast, which allows it to rapidly shortlist candidates for deeper investigation.

bioinformatics↗

bioRxiv2022

Adapting protein language models for rapid DTI prediction

We consider the problem of sequence-based drug-target interaction (DTI) prediction, showing that a straightforward deep learning architecture that leverages pre-trained protein language models (PLMs) for protein embedding outperforms state of the art approaches, achieving higher accuracy, expanded generalizability, and an order of magnitude faster training. PLM embeddings are found to contain general information that is especially useful in few-shot (small training data set) and zero-shot instances (unseen proteins or drugs). Additionally, the PLM embeddings can be augmented with features tuned by task-specific pre-training, and we find that these task-specific features are more informative than baseline PLM features. We anticipate such transfer learning approaches will facilitate rapid prototyping of DTI models, especially in low-N scenarios.

bioinformatics↗

bioRxiv2022

Contrasting drugs from decoys

Protein language models (PLMs) have recently been proposed to advance drugtarget interaction (DTI) prediction, and have shown state-of-the-art performance on several standard benchmarks. However, a remaining challenge for all DTI prediction models (including PLM-based ones) is distinguishing true drugs from highly-similar decoys. Leveraging techniques from self-supervised contrastive learning, we introduce a second-generation PLM-based DTI model trained on triplets of proteins, drugs, and decoys (small drug-like molecules that do not bind to the protein). We show that our approach, CON-Plex, improves specificity while maintaining high prediction accuracy and generalizability to new drug classes. CON-Plex maps proteins and drugs to a shared latent space which can be interpreted to identify mutually-compatible classes of proteins and drugs. Data and code are available at https://zenodo.org/record/7127229.

bioinformatics↗

bioRxiv2022

Single-cell mosaicism analysis reveals cell-type-specific somatic mutational burden in Alzheimer's Dementia

Despite significant advances in identifying genetic drivers of neurodegenerative disorders, the majority of affected individuals lack molecular genetic diagnosis, with somatic mutations proposed as one potential contributor to increased risk. Here, we report the first cell-type-specific map of somatic mosaicism in Alzheimers Dementia (AlzD), using 4,014 cells from prefrontal cortex samples of 19 AlzD and 17 non-AlzD individuals. We integrate full-transcript single-nucleus RNA-seq (SMART-Seq) with matched individual-level whole-genome sequencing to jointly infer mutational events and the cell-type in which they occurred. AlzD individuals show increased mutational burden, localized in excitatory neurons, oligodendrocytes, astrocytes and disease-associated "senescent" cells. High-mutational-burden cells showed mutational enrichment and similar single-cell expression profiles in AlzD cases versus non-AlzD individuals, indicating cellular-level genotype-to-phenotype correlation. Somatic mutations are specifically enriched for known AlzD genes, and implicate biologically meaningful cell-type specific processes, including: neuronal energy regulation, endocytic trafficking (NEFM), lipid metabolism (CNP, CRYAB), proteostasis (USP34), cytoskeleton, and microtubule dynamics (MACF1).

neuroscience↗

bioRxiv2021

Phylogenetic reconciliation reveals extensive ancestral recombination in Sarbecoviruses and the SARS-CoV-2 lineage

An accurate understanding of the evolutionary history of rapidly-evolving viruses like SARS-CoV-2, responsible for the COVID-19 pandemic, is crucial to tracking and preventing the spread of emerging pathogens. However, viruses undergo frequent recombination, which makes it difficult to trace their evolutionary history using traditional phylogenetic methods. Here, we present a phylogenetic workflow, virDTL, for analyzing viral evolution in the presence of recombination. Our approach leverages reconciliation methods developed for inferring horizontal gene transfer in prokaryotes, and, compared to existing tools, is uniquely able to identify ancestral recombinations while accounting for several sources of inference uncertainty, including in the construction of a strain tree, estimation and rooting of gene family trees, and reconciliation itself. We apply this workflow to the Sarbecovirus subgenus and demonstrate how a principled analysis of predicted recombination gives insight into the evolution of SARS-CoV-2. In addition to providing confirming evidence for the horseshoe bat as its zoonotic origin, we identify several ancestral recombination events that merit further study.

evolutionary biology↗

bioRxiv2021

Sequence-based prediction of protein-protein interactions: a structure-aware interpretable deep learning model

Protein-protein interaction (PPI) networks have proven to be a valuable tool in systems biology to facilitate the discovery and understanding of protein function. Unfortunately, experimental PPI data remains sparse in most model organisms and even more so in other species. Existing methods for computational prediction of PPIs seek to address this limitation, and while they perform well when sufficient within-species training data is available, they generalize poorly to new species or often require specific types and sizes of training data that may not be available in the species of interest. We therefore present D-SCRIPT, a deep learning method for predicting a physical interaction between two proteins given just their sequences. Compared to existing methods, D-SCRIPT generalizes better to new species and is robust to limitations in training data size. Our approach encodes the intuition that for two proteins to physically interact, a subset of amino acids from each protein should be in contact with the other. The intermediate stages of D-SCRIPT directly implement this intuition; the penultimate stage in D-SCRIPT is a rough estimate of the inter-protein contact map of the protein dimer. This structurally-motivated design enables interpretability of our model and, since structure is more conserved evolutionarily than sequence, improves generalizability across species. We show that a D-SCRIPT model trained on 38,345 human PPIs enables significantly improved functional characterization of fly proteins compared to the state-of-the-art approach. Evaluating the same D-SCRIPT model on protein complexes with known 3-D structure, we find that the inter-protein contact map output by D-SCRIPT has significant overlap with the ground truth. Our work suggests that recent advances in deep learning language modeling of protein structure can be leveraged for protein interaction prediction from sequence. D-SCRIPT is available at http://dscript.csail.mit.edu.

bioinformatics↗

bioRxiv2019

TreeFix-TP: Phylogenetic Error-Correction for Infectious Disease Transmission Network Inference

BackgroundMany existing methods for estimation of infectious disease transmission networks use a phylogeny of the infecting strains as the basis for transmission network inference, and accurate network inference relies on accuracy of this underlying evolutionary history. However, phylogenetic reconstruction can be highly error prone and more sophisticated methods can fail to scale to larger outbreaks, negatively impacting downstream transmission network inference. Additionally, there are no currently available methods which are able to use within-host diversity to improve phylogenetic reconstruction.\n\nResultsWe introduce a new method, TreeFix-TP, for accurate and scalable reconstruction of transmission phylogenies based on an error-correction framework. Our method uses intra-host strain diversity and host information to balance a parsimonious evaluation of the implied transmission network with statistical hypothesis testing on sequence data likelihood. The reconstructed tree minimizes the number of required disease transmissions while being as well supported by sequence data as the maximum likelihood phylogeny. We use a simulation framework for viral transmission and evolution to demonstrate that TreeFix-TP improves phylogenetic accuracy and downstream transmission network accuracy. We also use real data from ten HCV outbreaks and demonstrate how error-correction improves source detection.\n\nConclusionsOur results show that using TreeFix-TP can lead to significant improvement in transmission phylogeny inference and that its performance is robust to variations in transmission and evolutionary parameters. Our experiments also demonstrate the importance of sampling multiple strain sequences from each infected host for accurate transmission network inference. TreeFix-TP is freely available open-source from https://compbio.engr.uconn.edu/software/treefix-tp/.

bioinformatics↗