PyTorchKR Papers

최신 논문

총 184편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2312.07511공식 코드 · Papers with Code

A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems

Recent advances in computational modelling of atomic systems, spanning molecules, proteins, and materials, represent them as geometric graphs with atoms embedded as nodes in 3D Euclidean space. In these graphs, the geometric attributes transform according to the inherent physical symmetries of 3D atomic systems, including rotations and translations in Euclidean space, as well as node permutations. In recent years, Geometric Graph Neural Networks have emerged as the preferred machine learning architecture powering applications ranging from protein structure prediction to molecular simulations and material generation. Their specificity lies in the inductive biases they leverage - such as physical symmetries and chemical properties - to learn informative representations of these geometric graphs. In this opinionated paper, we provide a comprehensive and self-contained overview of the field of Geometric GNNs for 3D atomic systems. We cover fundamental background material and introduce a pedagogical taxonomy of Geometric GNN architectures: (1) invariant networks, (2) equivariant networks in Cartesian basis, (3) equivariant networks in spherical basis, and (4) unconstrained networks. Additionally, we outline key datasets and application areas and suggest future research directions. The objective of this work is to present a structured perspective on the field, making it accessible to newcomers and aiding practitioners in gaining an intuition for its mathematical abstractions.

arXiv:2312.01186

Linker-Tuning: Optimizing Continuous Prompts for Heterodimeric Protein Prediction

Predicting the structure of interacting chains is crucial for understanding biological systems and developing new drugs. Large-scale pre-trained Protein Language Models (PLMs), such as ESM2, have shown impressive abilities in extracting biologically meaningful representations for protein structure prediction. In this paper, we show that ESMFold, which has been successful in computing accurate atomic structures for single-chain proteins, can be adapted to predict the heterodimer structures in a lightweight manner. We propose Linker-tuning, which learns a continuous prompt to connect the two chains in a dimer before running it as a single sequence in ESMFold. Experiment results show that our method successfully predicts 56.98% of interfaces on the i.i.d. heterodimer test set, with an absolute improvement of +12.79% over the ESMFold-Linker baseline. Furthermore, our model can generalize well to the out-of-distribution (OOD) test set HeteroTest2 and two antibody test sets Fab and Fv while being $9\times$ faster than AF-Multimer.

arXiv:2312.00080공식 코드 · Papers with Code

PDB-Struct: A Comprehensive Benchmark for Structure-based Protein Design

Structure-based protein design has attracted increasing interest, with numerous methods being introduced in recent years. However, a universally accepted method for evaluation has not been established, since the wet-lab validation can be overly time-consuming for the development of new algorithms, and the $\textit{in silico}$ validation with recovery and perplexity metrics is efficient but may not precisely reflect true foldability. To address this gap, we introduce two novel metrics: refoldability-based metric, which leverages high-accuracy protein structure prediction models as a proxy for wet lab experiments, and stability-based metric, which assesses whether models can assign high likelihoods to experimentally stable proteins. We curate datasets from high-quality CATH protein data, high-throughput $\textit{de novo}$ designed proteins, and mega-scale experimental mutagenesis experiments, and in doing so, present the $\textbf{PDB-Struct}$ benchmark that evaluates both recent and previously uncompared protein design methods. Experimental results indicate that ByProt, ProteinMPNN, and ESM-IF perform exceptionally well on our benchmark, while ESM-Design and AF-Design fall short on the refoldability metric. We also show that while some methods exhibit high sequence recovery, they do not perform as well on our new benchmark. Our proposed benchmark paves the way for a fair and comprehensive evaluation of protein design methods in the future. Code is available at https://github.com/WANG-CR/PDB-Struct.

논문 ID: document/1004951

Pareto Dominance Archive and Coordinated Selection Strategy-Based Many-Objective Optimizer for Protein Structure Prediction

Protein structure prediction (PSP) is predicting the three-dimensional of protein from its amino acid sequence only based on the information hidden in the protein sequence. One of the efficient tools to describe this information is protein energy functions. Despite the advancements in biology and computer science, PSP is still a challenging problem due to its large protein conformation space and inaccurate energy functions. In this study, PSP is treated as a many-objective optimization problem and four conflicting energy functions are used as different objectives to be optimized. A novel Pareto-dominance-archive and Coordinated-selection-strategy-based Many-objective-optimizer (PCM) is proposed to perform the conformation search. In it, convergence and diversity-based selection metrics are used to enable PCM to find near-native proteins with well-distributed energy values, while a Pareto-dominance-based archive is proposed to save more potential conformations that can guide the search to more promising conformation areas. The experimental results on thirty-four benchmark proteins demonstrate the significant superiority of PCM in comparison with other single, multiple, and many-objective evolutionary algorithms. Additionally, the inherent characteristics of iterative search of PCM can also give more insights into the dynamic progress of protein folding besides the final predicted static tertiary structure. All these confirm that PCM is a fast, easy-to-use, and fruitful solution generation method for PSP.

arXiv:2311.18219

FoldExplorer: Fast and Accurate Protein Structure Search with Sequence-Enhanced Graph Embedding

The advent of highly accurate protein structure prediction methods has fueled an exponential expansion of the protein structure database. Consequently, there is a rising demand for rapid and precise structural homolog search. Traditional alignment-based methods are dedicated to precise comparisons between pairs, exhibiting high accuracy. However, their sluggish processing speed is no longer adequate for managing the current massive volume of data. In response to this challenge, we propose a novel deep-learning approach FoldExplorer. It harnesses the powerful capabilities of graph attention neural networks and protein large language models for protein structures and sequences data processing to generate embeddings for protein structures. The structural embeddings can be used for fast and accurate protein search. The embeddings also provide insights into the protein space. FoldExplorer demonstrates a substantial performance improvement of 5% to 8% over the current state-of-the-art algorithm on the benchmark datasets. Meanwhile, FoldExplorer does not compromise on search speed and excels particularly in searching on a large-scale dataset.

arXiv:2311.18725

AI in Pharma for Personalized Sequential Decision-Making: Methods, Applications and Opportunities

In the pharmaceutical industry, the use of artificial intelligence (AI) has seen consistent growth over the past decade. This rise is attributed to major advancements in statistical machine learning methodologies, computational capabilities and the increased availability of large datasets. AI techniques are applied throughout different stages of drug development, ranging from drug discovery to post-marketing benefit-risk assessment. Kolluri et al. provided a review of several case studies that span these stages, featuring key applications such as protein structure prediction, success probability estimation, subgroup identification, and AI-assisted clinical trial monitoring. From a regulatory standpoint, there was a notable uptick in submissions incorporating AI components in 2021. The most prevalent therapeutic areas leveraging AI were oncology (27%), psychiatry (15%), gastroenterology (12%), and neurology (11%). The paradigm of personalized or precision medicine has gained significant traction in recent research, partly due to advancements in AI techniques \cite{hamburg2010path}. This shift has had a transformative impact on the pharmaceutical industry. Departing from the traditional "one-size-fits-all" model, personalized medicine incorporates various individual factors, such as environmental conditions, lifestyle choices, and health histories, to formulate customized treatment plans. By utilizing sophisticated machine learning algorithms, clinicians and researchers are better equipped to make informed decisions in areas such as disease prevention, diagnosis, and treatment selection, thereby optimizing health outcomes for each individual.

arXiv:2308.05326공식 코드 · Papers with Code

OpenProteinSet: Training data for structural biology at scale

Multiple sequence alignments (MSAs) of proteins encode rich biological information and have been workhorses in bioinformatic methods for tasks like protein design and protein structure prediction for decades. Recent breakthroughs like AlphaFold2 that use transformers to attend directly over large quantities of raw MSAs have reaffirmed their importance. Generation of MSAs is highly computationally intensive, however, and no datasets comparable to those used to train AlphaFold2 have been made available to the research community, hindering progress in machine learning for proteins. To remedy this problem, we introduce OpenProteinSet, an open-source corpus of more than 16 million MSAs, associated structural homologs from the Protein Data Bank, and AlphaFold2 protein structure predictions. We have previously demonstrated the utility of OpenProteinSet by successfully retraining AlphaFold2 on it. We expect OpenProteinSet to be broadly useful as training and validation data for 1) diverse tasks focused on protein structure, function, and design and 2) large-scale multimodal machine learning research.

arXiv:2311.14003

Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandit

Optimization problems find widespread use in both single-objective and multi-objective scenarios. In practical applications, users aspire for solutions that converge to the region of interest (ROI) along the Pareto front (PF). While the conventional approach involves approximating a fitness function or an objective function to reflect user preferences, this paper explores an alternative avenue. Specifically, we aim to discover a method that sidesteps the need for calculating the fitness function, relying solely on human feedback. Our proposed approach entails conducting direct preference learning facilitated by an active dueling bandit algorithm. The experimental phase is structured into three sessions. Firstly, we assess the performance of our active dueling bandit algorithm. Secondly, we implement our proposed method within the context of Multi-objective Evolutionary Algorithms (MOEAs). Finally, we deploy our method in a practical problem, specifically in protein structure prediction (PSP). This research presents a novel interactive preference-based MOEA framework that not only addresses the limitations of traditional techniques but also unveils new possibilities for optimization problems.

arXiv:2310.19624공식 코드 · Papers with Code

Exploring Post-Training Quantization of Protein Language Models

Recent advancements in unsupervised protein language models (ProteinLMs), like ESM-1b and ESM-2, have shown promise in different protein prediction tasks. However, these models face challenges due to their high computational demands, significant memory needs, and latency, restricting their usage on devices with limited resources. To tackle this, we explore post-training quantization (PTQ) for ProteinLMs, focusing on ESMFold, a simplified version of AlphaFold based on ESM-2 ProteinLM. Our study is the first attempt to quantize all weights and activations of ProteinLMs. We observed that the typical uniform quantization method performs poorly on ESMFold, causing a significant drop in TM-Score when using 8-bit quantization. We conducted extensive quantization experiments, uncovering unique challenges associated with ESMFold, particularly highly asymmetric activation ranges before Layer Normalization, making representation difficult using low-bit fixed-point formats. To address these challenges, we propose a new PTQ method for ProteinLMs, utilizing piecewise linear quantization for asymmetric activation values to ensure accurate approximation. We demonstrated the effectiveness of our method in protein structure prediction tasks, demonstrating that ESMFold can be accurately quantized to low-bit widths without compromising accuracy. Additionally, we applied our method to the contact prediction task, showcasing its versatility. In summary, our study introduces an innovative PTQ method for ProteinLMs, addressing specific quantization challenges and potentially leading to the development of more efficient ProteinLMs with significant implications for various protein-related applications.

arXiv:2310.03899

CrysFormer: Protein Structure Prediction via 3d Patterson Maps and Partial Structure Attention

Determining the structure of a protein has been a decades-long open question. A protein's three-dimensional structure often poses nontrivial computation costs, when classical simulation algorithms are utilized. Advances in the transformer neural network architecture -- such as AlphaFold2 -- achieve significant improvements for this problem, by learning from a large dataset of sequence information and corresponding protein structures. Yet, such methods only focus on sequence information; other available prior knowledge, such as protein crystallography and partial structure of amino acids, could be potentially utilized. To the best of our knowledge, we propose the first transformer-based model that directly utilizes protein crystallography and partial structure information to predict the electron density maps of proteins. Via two new datasets of peptide fragments (2-residue and 15-residue) , we demonstrate our method, dubbed \texttt{CrysFormer}, can achieve accurate predictions, based on a much smaller dataset size and with reduced computation costs.

arXiv:2310.03086

Deep Learning in Computational Biology: Advancements, Challenges, and Future Outlook

Deep learning has become a powerful tool in computational biology, revolutionising the analysis and interpretation of biological data over time. In our article review, we delve into various aspects of deep learning in computational biology. Specifically, we examine its history, advantages, and challenges. Our focus is on two primary applications: DNA sequence classification and prediction, as well as protein structure prediction from sequence data. Additionally, we provide insights into the outlook for this field. To fully harness the potential of deep learning in computational biology, it is crucial to address the challenges that come with it. These challenges include the requirement for large, labelled datasets and the interpretability of deep learning models. The use of deep learning in the analysis of DNA sequences has brought about a significant transformation in the detection of genomic variants and the analysis of gene expression. This has greatly contributed to the advancement of personalised medicine and drug discovery. Convolutional neural networks (CNNs) have been shown to be highly accurate in predicting genetic variations and gene expression levels. Deep learning techniques are used for analysing epigenetic data, including DNA methylation and histone modifications. This provides valuable insights into metabolic conditions and gene regulation. The field of protein structure prediction has been significantly impacted by deep learning, which has enabled accurate determination of the three-dimensional shape of proteins and prediction of their interactions. The future of deep learning in computational biology looks promising. With the development of advanced deep learning models and interpretation techniques, there is potential to overcome current challenges and further our understanding of biological systems.

arXiv:2310.00795

A Comprehensive Review of Generative AI in Healthcare

The advancement of Artificial Intelligence (AI) has catalyzed revolutionary changes across various sectors, notably in healthcare. Among the significant developments in this field are the applications of generative AI models, specifically transformers and diffusion models. These models have played a crucial role in analyzing diverse forms of data, including medical imaging (encompassing image reconstruction, image-to-image translation, image generation, and image classification), protein structure prediction, clinical documentation, diagnostic assistance, radiology interpretation, clinical decision support, medical coding, and billing, as well as drug design and molecular representation. Such applications have enhanced clinical diagnosis, data reconstruction, and drug synthesis. This review paper aims to offer a thorough overview of the generative AI applications in healthcare, focusing on transformers and diffusion models. Additionally, we propose potential directions for future research to tackle the existing limitations and meet the evolving demands of the healthcare sector. Intended to serve as a comprehensive guide for researchers and practitioners interested in the healthcare applications of generative AI, this review provides valuable insights into the current state of the art, challenges faced, and prospective future directions.

arXiv:2309.16519공식 코드 · Papers with Code

AtomSurf : Surface Representation for Learning on Protein Structures

While there has been significant progress in evaluating and comparing different representations for learning on protein data, the role of surface-based learning approaches remains not well-understood. In particular, there is a lack of direct and fair benchmark comparison between the best available surface-based learning methods against alternative representations such as graphs. Moreover, the few existing surface-based approaches either use surface information in isolation or, at best, perform global pooling between surface and graph-based architectures. In this work, we fill this gap by first adapting a state-of-the-art surface encoder for protein learning tasks. We then perform a direct and fair comparison of the resulting method against alternative approaches within the Atom3D benchmark, highlighting the limitations of pure surface-based learning. Finally, we propose an integrated approach, which allows learned feature sharing between graphs and surface representations on the level of nodes and vertices $\textit{across all layers}$. We demonstrate that the resulting architecture achieves state-of-the-art results on all tasks in the Atom3D benchmark, while adhering to the strict benchmark protocol, as well as more broadly on binding site identification and binding pocket classification. Furthermore, we use coarsened surfaces and optimize our approach for efficiency, making our tool competitive in training and inference time with existing techniques. Our code and data can be found online: $\texttt{github.com/Vincentx15/atomsurf}$

arXiv:2308.07954공식 코드 · Papers with Code

APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysics

The prediction of protein 3D structure from amino acid sequence is a computational grand challenge in biophysics, and plays a key role in robust protein structure prediction algorithms, from drug discovery to genome interpretation. The advent of AI models, such as AlphaFold, is revolutionizing applications that depend on robust protein structure prediction algorithms. To maximize the impact, and ease the usability, of these novel AI tools we introduce APACE, AlphaFold2 and advanced computing as a service, a novel computational framework that effectively handles this AI model and its TB-size database to conduct accelerated protein structure prediction analyses in modern supercomputing environments. We deployed APACE in the Delta and Polaris supercomputers, and quantified its performance for accurate protein structure predictions using four exemplar proteins: 6AWO, 6OAN, 7MEZ, and 6D6U. Using up to 300 ensembles, distributed across 200 NVIDIA A100 GPUs, we found that APACE is up to two orders of magnitude faster than off-the-self AlphaFold2 implementations, reducing time-to-solution from weeks to minutes. This computational approach may be readily linked with robotics laboratories to automate and accelerate scientific discovery.

arXiv:2308.03654

FFF: Fragments-Guided Flexible Fitting for Building Complete Protein Structures

Cryo-electron microscopy (cryo-EM) is a technique for reconstructing the 3-dimensional (3D) structure of biomolecules (especially large protein complexes and molecular assemblies). As the resolution increases to the near-atomic scale, building protein structures de novo from cryo-EM maps becomes possible. Recently, recognition-based de novo building methods have shown the potential to streamline this process. However, it cannot build a complete structure due to the low signal-to-noise ratio (SNR) problem. At the same time, AlphaFold has led to a great breakthrough in predicting protein structures. This has inspired us to combine fragment recognition and structure prediction methods to build a complete structure. In this paper, we propose a new method named FFF that bridges protein structure prediction and protein structure recognition with flexible fitting. First, a multi-level recognition network is used to capture various structural features from the input 3D cryo-EM map. Next, protein structural fragments are generated using pseudo peptide vectors and a protein sequence alignment method based on these extracted features. Finally, a complete structural model is constructed using the predicted protein fragments via flexible fitting. Based on our benchmark tests, FFF outperforms the baseline methods for building complete protein structures.

arXiv:2307.14587

Artificial intelligence-aided protein engineering: from topological data analysis to deep protein language models

Protein engineering is an emerging field in biotechnology that has the potential to revolutionize various areas, such as antibody design, drug discovery, food security, ecology, and more. However, the mutational space involved is too vast to be handled through experimental means alone. Leveraging accumulative protein databases, machine learning (ML) models, particularly those based on natural language processing (NLP), have considerably expedited protein engineering. Moreover, advances in topological data analysis (TDA) and artificial intelligence-based protein structure prediction, such as AlphaFold2, have made more powerful structure-based ML-assisted protein engineering strategies possible. This review aims to offer a comprehensive, systematic, and indispensable set of methodological components, including TDA and NLP, for protein engineering and to facilitate their future development.

arXiv:2307.02177

Monte Carlo for Protein Structures

While many good textbooks are available on Protein Structure, Molecular Simulations, Thermodynamics and Bioinformatics methods in general, there is no good introductory level book for the field of Structural Bioinformatics. This book aims to give an introduction into Structural Bioinformatics, which is where the previous topics meet to explore three dimensional protein structures through computational analysis. We provide an overview of existing computational techniques, to validate, simulate, predict and analyse protein structures. More importantly, it will aim to provide practical knowledge about how and when to use such techniques. We will consider proteins from three major vantage points: Protein structure quantification, Protein structure prediction, and Protein simulation & dynamics. In the previous chapter "Molecular Dynamics" we have considered protein simulations from a dynamical point of view, using Newton's laws. In the current Chapter, we first take a step back and return to the bare minimum needed to simulate proteins, and show that proteins may be simulated in a more simple fashion, using the partition function directly. This means we do not have to calculate explicit forces, velocities, moments and do not even consider time explicitly. Instead, we will rely on the fact that for most systems we will want to simulate, the system is in a dynamic equilibrium; and that we want to find the most stable states in such systems by determining the relative stabilities between those states.

arXiv:2307.02176

Molecular Dynamics

While many good textbooks are available on Protein Structure, Molecular Simulations, Thermodynamics and Bioinformatics methods in general, there is no good introductory level book for the field of Structural Bioinformatics. This book aims to give an introduction into Structural Bioinformatics, which is where the previous topics meet to explore three dimensional protein structures through computational analysis. We provide an overview of existing computational techniques, to validate, simulate, predict and analyse protein structures. More importantly, it will aim to provide practical knowledge about how and when to use such techniques. We will consider proteins from three major vantage points: Protein structure quantification, Protein structure prediction, and Protein simulation & dynamics. We know that many proteins have functional motions, and in Chapter "Structure Determination" we already introduced the famous example of the allosteric cooperative binding of oxygen to the haem group in hemoglobin. However, experimentally, such motions are hard to observe. Here, we will introduce MD simulations to investigate the dynamic behaviour of proteins. In a simulation the forces and interactions between particles are used to numerically derive the resulting three-dimensional movement of these particles over a certain time-scale. We will also highlight some applications, and will see how simulation results may be interpreted.

arXiv:2307.02175

Thermodynamics of Protein Folding

While many good textbooks are available on Protein Structure, Molecular Simulations, Thermodynamics and Bioinformatics methods in general, there is no good introductory level book for the field of Structural Bioinformatics. This book aims to give an introduction into Structural Bioinformatics, which is where the previous topics meet to explore three dimensional protein structures through computational analysis. We provide an overview of existing computational techniques, to validate, simulate, predict and analyse protein structures. More importantly, it will aim to provide practical knowledge about how and when to use such techniques. We will consider proteins from three major vantage points: Protein structure quantification, Protein structure prediction, and Protein simulation & dynamics. In the previous chapter, "Introduction to Protein Folding", we introduced the concept of free energy and the protein folding landscape. Here, we provide a deeper, more formal underpinning of free energy in terms of the entropy and enthalpy; to this end, we will first need to better define the meaning of equilibrium, entropy and enthalpy. When we understand these concepts, we will come back for a more quantitative explanation of protein folding and dynamics. We will discuss the influence of temperature on the free energy landscape, and the difference between microstates and macrostates.

arXiv:2307.02174

Introduction to Protein Folding

While many good textbooks are available on Protein Structure, Molecular Simulations, Thermodynamics and Bioinformatics methods in general, there is no good introductory level book for the field of Structural Bioinformatics. This book aims to give an introduction into Structural Bioinformatics, which is where the previous topics meet to explore three dimensional protein structures through computational analysis. We provide an overview of existing computational techniques, to validate, simulate, predict and analyse protein structures. More importantly, it will aim to provide practical knowledge about how and when to use such techniques. We will consider proteins from three major vantage points: Protein structure quantification, Protein structure prediction, and Protein simulation & dynamics. In this chapter we explore basic physical and chemical concepts required to understand protein folding. We introduce major (de)stabilising factors of folded protein structures such as the hydrophobic effect and backbone entropy. In addition, we consider different states along the folding pathway, as well as natively disordered proteins and aggregated protein states. In this chapter, an intuitive understanding is provided about the protein folding process, to prepare for the next chapter on the thermodynamics of protein folding. In particular, it is emphasized that protein folding is a stochastic process and that proteins unfold and refold in a dynamic equilibrium. The effect of temperature on the stability of the folded and unfolded states is also explained.