Tao Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tao Shen has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Junzhou Huang
The University of Texas at Arlington
2 shared publications - Sheng Wang
King Abdullah University of Science and Technology
2 shared publications - Cheng Zhang
Department of Pharmacology and Chemical Biology, School of Medicine, University of Pittsburgh, Pittsburgh, PA 15213, USA
1 shared publication - Di Liu
Wyss Institute for Biologically Inspired Engineering, Harvard University, Boston, USA
1 shared publication Fei Ye
Tencent AI Lab, 518000, Shenzhen, Guangdong, China
1 shared publicationFelix Wong
Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, USA
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 21 November 2024
- Published by Springer Nature in Nature Methods
- Vol. 21 (12) , 2287-2298
Accurate RNA 3D structure prediction using a language model-based deep learning approach
Accurate prediction of RNA three-dimensional (3D) structures remains an unsolved challenge. Determining RNA 3D structures is crucial for understanding their functions and informing RNA-targeting drug development and synthetic biology design. The structural flexibility of RNA, which leads to the scarcity of experimentally determined data, complicates computational prediction efforts. Here we present RhoFold+, an RNA language model-based deep learning method that accurately predicts 3D structures of single-chain RNAs from sequences. By integrating an RNA language model pretrained on ~23.7 million RNA sequences and leveraging techniques to address data scarcity, RhoFold+ offers a fully automated end-to-end pipeline for RNA 3D structure prediction. Retrospective evaluations on RNA-Puzzles and CASP15 natural RNA targets demonstrate the superiority of RhoFold+ over existing methods, including human expert groups. Its efficacy and generalizability are further validated through cross-family and cross-type assessments, as well as time-censored benchmarks. Additionally, RhoFold+ predicts RNA secondary structures and interhelical angles, providing empirically verifiable features that broaden its applicability to RNA structure and function studies.
- 21 November 2024
- Published by Springer Nature in Nature Methods
- Vol. 21 (12) , 2287-2298
Top Cited PapersOpen AccessAccurate RNA 3D structure prediction using a language model-based deep learning approach
Accurate prediction of RNA three-dimensional (3D) structures remains an unsolved challenge. Determining RNA 3D structures is crucial for understanding their functions and informing RNA-targeting drug development and synthetic biology design. The structural flexibility of RNA, which leads to the scarcity of experimentally determined data, complicates computational prediction efforts. Here we present RhoFold+, an RNA language model-based deep learning method that accurately predicts 3D structures of single-chain RNAs from sequences. By integrating an RNA language model pretrained on ~23.7 million RNA sequences and leveraging techniques to address data scarcity, RhoFold+ offers a fully automated end-to-end pipeline for RNA 3D structure prediction. Retrospective evaluations on RNA-Puzzles and CASP15 natural RNA targets demonstrate the superiority of RhoFold+ over existing methods, including human expert groups. Its efficacy and generalizability are further validated through cross-family and cross-type assessments, as well as time-censored benchmarks. Additionally, RhoFold+ predicts RNA secondary structures and interhelical angles, providing empirically verifiable features that broaden its applicability to RNA structure and function studies.
- Open Access
- 1 October 2022
- Published by Oxford University Press (OUP) in Genomics, Proteomics & Bioinformatics
- Vol. 20 (5) , 989-1001
DeepNoise: Signal and Noise Disentanglement Based on Classifying Fluorescent Microscopy Images via Deep Learning
The high-content image-based assay is commonly leveraged for identifying the phenotypic impact of genetic perturbations in biology field. However, a persistent issue remains unsolved during experiments: the interferential technical noises caused by systematic errors (e.g., temperature, reagent concentration, and well location) are always mixed up with the real biological signals, leading to misinterpretation of any conclusion drawn. Here, we reported a mean teacher-based deep learning model (DeepNoise) that can disentangle biological signals from the experimental noises. Specifically, we aimed to classify the phenotypic impact of 1108 different genetic perturbations screened from 125,510 fluorescent microscopy images, which were totally unrecognizable by the human eye. We validated our model by participating in the Recursion Cellular Image Classification Challenge, and DeepNoise achieved an extremely high classification score (accuracy: 99.596%), ranking the 2nd place among 866 participating groups. This promising result indicates the successful separation of biological and technical factors, which might help decrease the cost of treatment development and expedite the drug discovery process. The source code of DeepNoise is available at https://github.com/Scu-sen/Recursion-Cellular-Image-Classification-Challenge.
- 1 October 2022
- Published by Oxford University Press (OUP) in Genomics, Proteomics & Bioinformatics
- Vol. 20 (5) , 989-1001
Open AccessDeepNoise: Signal and Noise Disentanglement Based on Classifying Fluorescent Microscopy Images via Deep Learning
The high-content image-based assay is commonly leveraged for identifying the phenotypic impact of genetic perturbations in biology field. However, a persistent issue remains unsolved during experiments: the interferential technical noises caused by systematic errors (e.g., temperature, reagent concentration, and well location) are always mixed up with the real biological signals, leading to misinterpretation of any conclusion drawn. Here, we reported a mean teacher-based deep learning model (DeepNoise) that can disentangle biological signals from the experimental noises. Specifically, we aimed to classify the phenotypic impact of 1108 different genetic perturbations screened from 125,510 fluorescent microscopy images, which were totally unrecognizable by the human eye. We validated our model by participating in the Recursion Cellular Image Classification Challenge, and DeepNoise achieved an extremely high classification score (accuracy: 99.596%), ranking the 2nd place among 866 participating groups. This promising result indicates the successful separation of biological and technical factors, which might help decrease the cost of treatment development and expedite the drug discovery process. The source code of DeepNoise is available at https://github.com/Scu-sen/Recursion-Cellular-Image-Classification-Challenge.
- 25 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 739-742
Parameter Analysis of Two-color Laser Sources for Terahertz Wave Radiation from Liquid Water
Liquid water as a source of Terahertz (THz) waves shows better performance than gas medium. In this work, the physical mechanism of THz wave radiation from liquid water excited by two-color laser pulses was investigated by particle-in-cell (PIC) simulation combined with Monte Carlo collision (MCC). The effects of laser parameters including wavelength, relative phase difference and intensity ratio between the fundamental laser and second harmonic on the THz radiation have been analyzed. The flip over of THz field can be obtained by adjusting the relative phase difference. As laser wavelength increases, the intensity of THz radiation keeps increasing. The optimal intensity ratio of fundamental laser and second harmonic for THz generation is approximately 2: 1.
- 25 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 739-742
Parameter Analysis of Two-color Laser Sources for Terahertz Wave Radiation from Liquid Water
Liquid water as a source of Terahertz (THz) waves shows better performance than gas medium. In this work, the physical mechanism of THz wave radiation from liquid water excited by two-color laser pulses was investigated by particle-in-cell (PIC) simulation combined with Monte Carlo collision (MCC). The effects of laser parameters including wavelength, relative phase difference and intensity ratio between the fundamental laser and second harmonic on the THz radiation have been analyzed. The flip over of THz field can be obtained by adjusting the relative phase difference. As laser wavelength increases, the intensity of THz radiation keeps increasing. The optimal intensity ratio of fundamental laser and second harmonic for THz generation is approximately 2: 1.
- Open Access
EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models
Accurate protein structure prediction from amino-acid sequences is critical to better understanding the protein function. Recent advances in this area largely benefit from more precise inter-residue distance and orientation predictions, powered by deep neural networks. However, the structure optimization procedure is still dominated by traditional tools, e.g. Rosetta, where the structure is solved via minimizing a pre-defined statistical energy function (with optional prediction-based restraints). Such energy function may not be optimal in formulating the whole conformation space of proteins. In this paper, we propose a fully-differentiable approach for protein structure optimization, guided by a data-driven generative network. This network is trained in a denoising manner, attempting to predict the correction signal from corrupted distance matrices between Ca atoms. Once the network is well trained, Langevin dynamics based sampling is adopted to gradually optimize structures from random initialization. Extensive experiments demonstrate that our EBM-Fold approach can efficiently produce high-quality decoys, compared against traditional Rosetta-based structure optimization routines.
Open AccessEBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models
Accurate protein structure prediction from amino-acid sequences is critical to better understanding the protein function. Recent advances in this area largely benefit from more precise inter-residue distance and orientation predictions, powered by deep neural networks. However, the structure optimization procedure is still dominated by traditional tools, e.g. Rosetta, where the structure is solved via minimizing a pre-defined statistical energy function (with optional prediction-based restraints). Such energy function may not be optimal in formulating the whole conformation space of proteins. In this paper, we propose a fully-differentiable approach for protein structure optimization, guided by a data-driven generative network. This network is trained in a denoising manner, attempting to predict the correction signal from corrupted distance matrices between Ca atoms. Once the network is well trained, Langevin dynamics based sampling is adopted to gradually optimize structures from random initialization. Extensive experiments demonstrate that our EBM-Fold approach can efficiently produce high-quality decoys, compared against traditional Rosetta-based structure optimization routines.
- Open Access
- 27 October 2020
- Published by Springer Nature in Nature Communications
- Vol. 11 (1) , 1-11
Structure of human steroid 5α-reductase 2 with the anti-androgen drug finasteride
Human steroid 5α-reductase 2 (SRD5A2) is an integral membrane enzyme in steroid metabolism and catalyzes the reduction of testosterone to dihydrotestosterone. Mutations in theSRD5A2gene have been linked to 5α-reductase deficiency and prostate cancer. Finasteride and dutasteride, as SRD5A2 inhibitors, are widely used antiandrogen drugs for benign prostate hyperplasia. The molecular mechanisms underlying enzyme catalysis and inhibition for SRD5A2 and other eukaryotic integral membrane steroid reductases remain elusive due to a lack of structural information. Here, we report a crystal structure of human SRD5A2 at 2.8 Å, revealing a unique 7-TM structural topology and an intermediate adduct of finasteride and NADPH as NADP-dihydrofinasteride in a largely enclosed binding cavity inside the transmembrane domain. Structural analysis together with computational and mutagenesis studies reveal the molecular mechanisms of the catalyzed reaction and of finasteride inhibition involving residues E57 and Y91. Molecular dynamics simulation results indicate high conformational dynamics of the cytosolic region that regulate NADPH/NADP+exchange. Mapping disease-causing mutations of SRD5A2 to our structure suggests molecular mechanisms for their pathological effects. Our results offer critical structural insights into the function of integral membrane steroid reductases and may facilitate drug development.
- 27 October 2020
- Published by Springer Nature in Nature Communications
- Vol. 11 (1) , 1-11
Open AccessStructure of human steroid 5α-reductase 2 with the anti-androgen drug finasteride
Human steroid 5α-reductase 2 (SRD5A2) is an integral membrane enzyme in steroid metabolism and catalyzes the reduction of testosterone to dihydrotestosterone. Mutations in theSRD5A2gene have been linked to 5α-reductase deficiency and prostate cancer. Finasteride and dutasteride, as SRD5A2 inhibitors, are widely used antiandrogen drugs for benign prostate hyperplasia. The molecular mechanisms underlying enzyme catalysis and inhibition for SRD5A2 and other eukaryotic integral membrane steroid reductases remain elusive due to a lack of structural information. Here, we report a crystal structure of human SRD5A2 at 2.8 Å, revealing a unique 7-TM structural topology and an intermediate adduct of finasteride and NADPH as NADP-dihydrofinasteride in a largely enclosed binding cavity inside the transmembrane domain. Structural analysis together with computational and mutagenesis studies reveal the molecular mechanisms of the catalyzed reaction and of finasteride inhibition involving residues E57 and Y91. Molecular dynamics simulation results indicate high conformational dynamics of the cytosolic region that regulate NADPH/NADP+exchange. Mapping disease-causing mutations of SRD5A2 to our structure suggests molecular mechanisms for their pathological effects. Our results offer critical structural insights into the function of integral membrane steroid reductases and may facilitate drug development.