Scholars@Duke
Rohit Singh

Scholarly Works - Journal articles

Miniaturizing and modifying natural proteins with Raygun.

Journal article Nature · July 29, 2026 Proteins have evolved over billions of years through coordinated substitutions, insertions and deletions, yet computational protein design cannot fully replicate nature's ability to engineer new proteins from existing templates. Protein language models1-3 ... Full text Link to item Cite

Foundation model reveals the shared organization of transcription and topologically associating domains.

Journal article Cell Syst · July 17, 2026 The three-dimensional organization of chromatin into topologically associating domains (TADs) may impact gene regulation by bringing distant genes into contact. However, studies of TADs' function and their influence on transcription have been constrained b ... Full text Link to item Cite

Democratizing protein language model training, sharing and collaboration.

Journal article Nat Biotechnol · October 24, 2025 Training and deploying large-scale protein language models typically requires deep machine learning expertise-a barrier for researchers outside this field. SaprotHub overcomes this challenge by offering an intuitive platform that facilitates training and p ... Full text Link to item Cite

Unveiling causal regulatory mechanisms through cell-state parallax.

Journal article Nat Commun · August 29, 2025 Genome-wide association studies (GWAS) identify numerous disease-linked genetic variants at noncoding genomic loci, yet therapeutic progress is hampered by the challenge of deciphering the regulatory roles of these loci in tissue-specific contexts. Single- ... Full text Link to item Cite

The basic helix-loop-helix transcription factor TCF4 recruits the Mediator Complex to activate gonadal genes and drive ovarian development.

Journal article bioRxiv · July 11, 2025 The bipotential gonad is the precursor organ to both the ovary and testis and develops as part of the embryonic urogenital system. In mice, gonadogenesis initiates around embryonic day 9.5 (E9.5), when coelomic epithelial (CE) cells overlaying the mesoneph ... Full text Link to item Cite

Comparative analysis of the syncytiotrophoblast in placenta tissue and trophoblast organoids using snRNA sequencing

Journal article eLife · May 27, 2025 The syncytiotrophoblast (STB) is a multinucleated cell layer that forms the outer surface of human chorionic villi. Its unusual structure, with billions of nuclei in a single cell, makes it difficult to resolve using conventional single-cell method ... Full text Cite

Topology-driven discovery of transmembrane protein S-palmitoylation.

Journal article J Biol Chem · March 2025 Protein S-palmitoylation is a reversible lipophilic posttranslational modification regulating diverse signaling pathways. Within transmembrane proteins (TMPs), S-palmitoylation is implicated in conditions from inflammatory disorders to respiratory viral in ... Full text Link to item Cite

Comparative analysis of the syncytiotrophoblast in placenta tissue and trophoblast organoids using snRNA sequencing.

Journal article bioRxiv · February 19, 2025 The outer surface of chorionic villi in the human placenta consists of a single multinucleated cell called the syncytiotrophoblast (STB). The unique cellular ultrastructure of the STB presents challenges in deciphering its gene expression signature at the ... Full text Link to item Cite

Learning the language of antibody hypervariability.

Journal article Proc Natl Acad Sci U S A · January 7, 2025 Protein language models (PLMs) have demonstrated impressive success in modeling proteins. However, general-purpose "foundational" PLMs have limited performance in modeling antibodies due to the latter's hypervariable regions, which do not conform to the ev ... Full text Link to item Cite

Aggregating residue-level protein language model embeddings with optimal transport.

Journal article Bioinform Adv · 2025 MOTIVATION: Protein language models (PLMs) have emerged as powerful approaches for mapping protein sequences into embeddings suitable for various applications. As protein representation schemes, PLMs generate per-token (i.e. per-residue) representations, r ... Full text Open Access Link to item Cite

Causal gene regulatory analysis with RNA velocity reveals an interplay between slow and fast transcription factors.

Journal article Cell Syst · May 15, 2024 Single-cell expression dynamics, from differentiation trajectories or RNA velocity, have the potential to reveal causal links between transcription factors (TFs) and their target genes in gene regulatory networks (GRNs). However, existing methods either ov ... Full text Link to item Cite

TT3D: Leveraging precomputed protein 3D sequence models to predict protein-protein interactions.

Journal article Bioinformatics · November 1, 2023 MOTIVATION: High-quality computational structural models are now precomputed and available for nearly every protein in UniProt. However, the best way to leverage these models to predict which pairs of proteins interact in a high-throughput manner is not im ... Full text Link to item Cite

Contrastive learning in protein language space predicts interactions between drugs and protein targets.

Journal article Proc Natl Acad Sci U S A · June 13, 2023 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 ... Full text Link to item Cite

split-intein Gal4 provides intersectional genetic labeling that is repressible by Gal80.

Journal article Proc Natl Acad Sci U S A · June 13, 2023 The split-Gal4 system allows for intersectional genetic labeling of highly specific cell types and tissues in Drosophila. However, the existing split-Gal4 system, unlike the standard Gal4 system, cannot be repressed by Gal80, and therefore cannot be contro ... Full text Link to item Cite

Transfer of knowledge from model organisms to evolutionarily distant non-model organisms: The coral Pocillopora damicornis membrane signaling receptome.

Journal article PLoS One · 2023 With the ease of gene sequencing and the technology available to study and manipulate non-model organisms, the extension of the methodological toolbox required to translate our understanding of model organisms to non-model organisms has become an urgent pr ... Full text Link to item Cite

Causally-guided Regularization of Graph Attention Improves Generalizability

Journal article Transactions on Machine Learning Research · January 1, 2023 Graph attention networks estimate the relational importance of node neighbors to aggregate relevant information over local neighborhoods for a prediction task. However, the inferred attentions are vulnerable to spurious correlations and connectivity in the ... Cite

Topsy-Turvy: integrating a global view into sequence-based PPI prediction.

Journal article Bioinformatics · June 24, 2022 SUMMARY: Computational methods to predict protein-protein interaction (PPI) typically segregate into sequence-based 'bottom-up' methods that infer properties from the characteristics of the individual protein sequences, or global 'top-down' methods that in ... Full text Link to item Cite

D-SCRIPT translates genome to phenome with sequence-based, structure-aware, genome-scale predictions of protein-protein interactions.

Journal article Cell Syst · October 20, 2021 We combine advances in neural language modeling and structurally motivated design to develop D-SCRIPT, an interpretable and generalizable deep-learning model, which predicts interaction between two proteins using only their sequence and maintains high accu ... Full text Link to item Cite

Schema: metric learning enables interpretable synthesis of heterogeneous single-cell modalities.

Journal article Genome Biol · May 3, 2021 A complete understanding of biological processes requires synthesizing information across heterogeneous modalities, such as age, disease status, or gene expression. Technological advances in single-cell profiling have enabled researchers to assay multiple ... Full text Link to item Cite

Proteomic and functional genomic landscape of receptor tyrosine kinase and ras to extracellular signal-regulated kinase signaling.

Journal article Sci Signal · October 25, 2011 Characterizing the extent and logic of signaling networks is essential to understanding specificity in such physiological and pathophysiological contexts as cell fate decisions and mechanisms of oncogenesis and resistance to chemotherapy. Cell-based RNA in ... Full text Link to item Cite

Sparse estimation for structural variability.

Journal article Algorithms Mol Biol · April 19, 2011 BACKGROUND: Proteins are dynamic molecules that exhibit a wide range of motions; often these conformational changes are important for protein function. Determining biologically relevant conformational changes, or true variability, efficiently is challengin ... Full text Link to item Cite

IsoBase: a database of functionally related proteins across PPI networks.

Journal article Nucleic Acids Res · January 2011 We describe IsoBase, a database identifying functionally related proteins, across five major eukaryotic model organisms: Saccharomyces cerevisiae, Drosophila melanogaster, Caenorhabditis elegans, Mus musculus and Homo Sapiens. Nearly all existing algorithm ... Full text Link to item Cite

Struct2Net: a web service to predict protein-protein interactions using a structure-based approach.

Journal article Nucleic Acids Res · July 2010 Struct2Net is a web server for predicting interactions between arbitrary protein pairs using a structure-based approach. Prediction of protein-protein interactions (PPIs) is a central area of interest and successful prediction would provide leads for exper ... Full text Link to item Cite

Global alignment of multiple protein interaction networks with application to functional orthology detection.

Journal article Proc Natl Acad Sci U S A · September 2, 2008 Protein-protein interactions (PPIs) and their networks play a central role in all biological processes. Akin to the complete sequencing of genomes and their comparative analysis, complete descriptions of interactomes and their comparative analysis is funda ... Full text Link to item Cite

Predicting and annotating catalytic residues: an information theoretic approach.

Journal article J Comput Biol · October 2007 We introduce a computational method to predict and annotate the catalytic residues of a protein using only its sequence information, so that we describe both the residues' sequence locations (prediction) and their specific biochemical roles in the catalyze ... Full text Link to item Cite

Identifying structural motifs in proteins.

Journal article Pac Symp Biocomput · 2003 In biological macromolecules, structural patterns (motifs) are often repeated across different molecules. Detection of these common motifs in a new molecule can provide useful clues to the functional properties of such a molecule. We formulate the problem ... Link to item Cite