Yaoqi Zhou

On the completeness of existing RNA fragment structures

The paper assesses the completeness of RNA fragment structural space and finds it incomplete, especially at higher oligomer levels, with fewer backbone fragments compared to proteins.

ESM-LoRA-Gly: Improved prediction of N- and O-linked glycosylation sites by tuning protein language models with low-rank adaptation (LoRA)

ESM-LoRA-Gly improves prediction of N- and O-linked glycosylation sites by fine-tuning ESM2-3B with LoRA, achieving better accuracy and efficiency.

RESM: Capturing sequence and structure encoding of RNAs by mapped transfer learning from ESM (evolutionary scale modeling) protein language model

RESM improves RNA sequence-structure-function prediction by transferring knowledge from protein language models, outperforming existing models in multiple tasks.

Designing a broad-spectrum four-helix bundle targeting different strains of SARS-CoV-2 Spike Receptor Binding Domains with ACE2-like binding interface

The paper designs a protein that binds to multiple SARS-CoV-2 RBD variants with high affinity, demonstrating a strategy for broad-spectrum antiviral inhibitors.

RPcontact: Improved prediction of RNA-protein contacts using RNA and protein language models

RPcontact predicts RNA-protein contacts using RNA and protein language models, outperforming existing methods on contact prediction.

Ultra-fast and highly sensitive protein structure alignment with segment-level representations and block-sparse optimization

SPfast improves protein structure alignment speed and sensitivity, enabling large-scale comparisons and uncovering new biological insights.

RNA-MobiSeq: Deep mutational scanning and mobility-based selection for RNA structure inference

The paper introduces MobiSeq, a method combining deep mutational scanning and mobility-based selection to predict RNA tertiary structures by analyzing covariational signals and improving energy-based predictions.

SPIN-CGNN: Improved fixed backbone protein design with contact map-based graph construction and contact graph neural network

This paper introduces SPIN-CGNN, a protein design method using contact maps and graph neural networks, showing improved sequence recovery and structural accuracy compared to existing methods.

Effective High-Accuracy Prediction of Protein Structures from Easily Obtainable Artificial Homologous Sequences by Structure-Stability-Based Selection

The paper shows that using artificially generated, structure-stability-selected homologous sequences improves AlphaFold2's accuracy for protein structure prediction, achieving better than 2 Å RMSD for most tested proteins.

Multiple sequence-alignment-based RNA language model and its application to structural inference

This paper introduces an RNA language model based on multiple sequence alignment, showing it can accurately predict RNA structure from sequence data.

Deep learning models of RNA base-pairing structures generalize to unseen folds and make accurate zero-shot predictions of base-base interactions of RNA complexes

This study evaluates deep learning models for RNA base-pairing prediction, showing that SPOT-RNA can accurately predict RNA-RNA interactions in unseen structures and without monomeric structures.

RNA tertiary structure modeling with BRiQ potential in CASP15

The paper describes an RNA tertiary structure modeling method used in CASP15, combining secondary structure information, motif prediction, and the BRiQ potential for energy optimization.

The Master Database of All Possible RNA Sequences and Its Integration with RNAcmap for RNA Homology Search

The paper builds a large RNA sequence database (MARS) and integrates it with RNAcmap to improve homology search and RNA structure/function inference.

Improved RNA homology detection and alignment by automatic iterative search in an expanded database

The paper improves RNA homology detection and alignment using an automated iterative search with an expanded database, achieving performance comparable to Rfam.

SPOT-Contact-Single: Improving Single-Sequence-Based Prediction of Protein Contact Map using a Transformer Language Model

The paper introduces SPOT-Contact-Single, a method that improves single-sequence-based protein contact map prediction using a transformer language model, achieving better performance than existing methods on proteins without homologs.

DeepANIS: Predicting antibody paratope from concatenated CDR sequences by integrating bidirectional long-short-term memory and transformer neural networks

DeepANIS predicts antibody paratopes by integrating BiLSTM and transformer networks on concatenated CDR sequences, outperforming existing methods.

SPOT-1D-LM: Reaching Alignment-profile-based Accuracy in Predicting Protein Secondary and Tertiary Structural Properties without Alignment.

The paper introduces SPOT-1D-LM, a model that achieves alignment-profile-based accuracy in predicting protein structural properties without using multiple sequence alignments.

RNAcmap: A Fully Automatic Method for Predicting Contact Maps of RNAs by Evolutionary Coupling Analysis

RNAcmap automatically predicts RNA contact maps using evolutionary coupling analysis, outperforming manual methods and showing consistency across RNA sequences.

Critical Assessment of Protein Intrinsic Disorder Prediction

The paper evaluates 43 methods for predicting intrinsically disordered regions and binding regions in proteins, finding that deep learning methods outperform older physicochemical approaches but binding prediction remains challenging.

Resurrecting self-cleaving mini-ribozymes from 40-million-year-old LINE-1 elements in human genome

The paper identifies a self-cleaving ribozyme in ancient LINE-1 elements, showing its emergence 40 million years ago and extinction 30 million years ago.

Accurate inference of the full base-pairing structure of RNA by deep mutational scanning and covariation-induced deviation of activity

The paper uses deep mutational scanning to accurately infer the full base-pairing structure of RNA with high precision.

Predicting functional long non-coding RNAs validated by low throughput experiments

The paper develops a method to distinguish experimentally validated lncRNAs from high-throughput lncRNAs and mRNAs using Support Vector Machines, achieving high accuracy in human and mouse data.

RegSNPs-Intron: A Computational Framework For Prioritizing Intronic Single Nucleotide Variants in Human Genetic Disease

The paper develops regSNPs-intron, a random forest classifier to prioritize intronic SNVs for disease, validated using ASSET-seq functional assays.