Pre-trained protein language models have demonstrated significant applicability in different protein engineering task. A general usage of these pre-trained transformer models latent representation is to use a mean pool across residue positions to reduce the feature dimensions to further downstream tasks such as predicting bio-physics properties or other functional behaviours. In this paper we provide a two-fold contribution to machine learning (ML) driven drug design. Firstly, we demonstrate the power of sparsity by promoting penalization of pre-trained transformer models to secure more robust and accurate melting temperature (Tm) prediction of single-chain variable fragments with a mean absolute error of 0.23C. Secondly, we demonstrate the power of framing our prediction problem in a probabilistic framework. Specifically, we advocate for the need of adopting probabilistic frameworks especially in the context of ML driven drug design.

现在，我们目睹了深度学习方法在各种蛋白质（或数据集）中的重大进展。但是，缺乏评估不同方法的性能的标准基准，这阻碍了该领域的深度学习进步。在本文中，我们提出了一种称为PEER的基准，这是一种用于蛋白质序列理解的全面和多任务基准。 PEER提供了一组不同的蛋白质理解任务，包括蛋白质功能预测，蛋白质定位预测，蛋白质结构预测，蛋白质 - 蛋白质相互作用预测和蛋白质 - 配体相互作用预测。我们评估每个任务的不同类型的基于序列的方法，包括传统的特征工程方法，不同的序列编码方法以及大规模的预训练蛋白质语言模型。此外，我们还研究了这些方法在多任务学习设置下的性能。实验结果表明，大规模的预训练蛋白质语言模型可实现大多数单个任务的最佳性能，共同训练多个任务进一步提高了性能。该基准的数据集和源代码均可在https://github.com/deepgraphlearning/peer_benchmark上获得

基于注意的蛋白质序列训练的基于注意力的模型在分类和与人工智能驱动的蛋白质设计相关的分类和生成任务方面取得了令人难以置信的成功。但是，我们对非常大规模的模型和数据在有效的蛋白质模型开发中发挥作用。我们介绍了一套名为progen2的蛋白质语言模型的套件，该模型最高为6.4b参数，并在从基因组，宏基因组和免疫曲目数据库中绘制的不同序列数据集上进行了培训。 GEECEN2模型在捕获观察到的进化序列的分布，生成新型的可行序列并预测蛋白质适应性的情况下显示出最先进的性能，而无需额外的芬特。随着蛋白质序列的大型大小和原始数量继续变得更加广泛，我们的结果表明，越来越多的重点需要放在提供给蛋白质序列模型的数据分布上。我们在https://github.com/salesforce/progen上发布了PECEN2模型和代码。

贝叶斯优化（Bayesopt）是查询有效连续优化的黄金标准。然而，决策变量的离散，高维质阻碍了其对药物设计的采用。我们开发了一种新方法（LAMBO），该方法通过判别性多任务高斯流程主管共同训练Denoising AutoCododer，从而使基于梯度的多目标采集功能优化了自动装编码器的潜在空间。这些采集功能使Lambo能够在多个设计回合上平衡探索探索折衷方案，并通过在Pareto边境上的许多不同地点优化序列来平衡客观权衡。我们在两个小分子设计任务上评估了兰博，并引入了优化\ emph {在硅}和\ emph {Inter {In Betro}特性的新任务。在我们的实验中，兰博的表现优于遗传优化者，并且不需要大量的预处理，表明贝叶诺斯对生物序列设计是实用且有效的。

Deep learning models that leverage large datasets are often the state of the art for modelling molecular properties. When the datasets are smaller (< 2000 molecules), it is not clear that deep learning approaches are the right modelling tool. In this work we perform an extensive study of the calibration and generalizability of probabilistic machine learning models on small chemical datasets. Using different molecular representations and models, we analyse the quality of their predictions and uncertainties in a variety of tasks (binary, regression) and datasets. We also introduce two simulated experiments that evaluate their performance: (1) Bayesian optimization guided molecular design, (2) inference on out-of-distribution data via ablated cluster splits. We offer practical insights into model and feature choice for modelling small chemical datasets, a common scenario in new chemical experiments. We have packaged our analysis into the DIONYSUS repository, which is open sourced to aid in reproducibility and extension to new datasets.

动机：针对感兴趣的蛋白质的新颖化合物的发展是制药行业中最重要的任务之一。深层生成模型已应用于靶向分子设计，并显示出令人鼓舞的结果。最近，靶标特异性分子的产生被视为蛋白质语言与化学语言之间的翻译。但是，这种模型受相互作用蛋白质配对的可用性的限制。另一方面，可以使用大量未标记的蛋白质序列和化学化合物，并已用于训练学习有用表示的语言模型。在这项研究中，我们提出了利用预审核的生化语言模型以初始化（即温暖的开始）目标分子产生模型。我们研究了两种温暖的开始策略：（i）一种一阶段策略，其中初始化模型是针对靶向分子生成（ii）的两阶段策略进行培训的，该策略包含对分子生成的预处理，然后进行目标特定训练。我们还比较了两种生成化合物的解码策略：光束搜索和采样。结果：结果表明，温暖启动的模型的性能优于从头开始训练的基线模型。相对于基准广泛使用的指标，这两种拟议的温暖启动策略相互取得了相似的结果。然而，对许多新蛋白质生成的化合物进行对接评估表明，单阶段策略比两阶段策略更好地概括了。此外，我们观察到，在对接评估和基准指标中，梁搜索的表现优于采样，用于评估复合质量。可用性和实施​​：源代码可在https://github.com/boun-tabi/biochemical-lms-for-drug-design和材料中获得，并在Zenodo归档，网址为https://doi.org/10.5281/zenodo .6832145

学习有效的蛋白质表示在生物学的各种任务中至关重要，例如预测蛋白质功能或结构。现有的方法通常在大量未标记的氨基酸序列上预先蛋白质语言模型，然后在下游任务中使用一些标记的数据来对模型进行修复。尽管基于序列的方法具有有效性，但尚未探索蛋白质性能预测的已知蛋白质结构的预处理功能，尽管蛋白质结构已知是蛋白质功能的决定因素，但尚未探索。在本文中，我们建议根据其3D结构预处理蛋白质。我们首先提出一个简单而有效的编码器，以学习蛋白质的几何特征。我们通过利用多视图对比学习和不同的自我预测任务来预先蛋白质图编码器。对功能预测和折叠分类任务的实验结果表明，我们提出的预处理方法表现优于或与最新的基于最新的序列方法相提并论，同时使用较少的数据。我们的实施可在https://github.com/deepgraphlearning/gearnet上获得。

The prediction of protein structures from sequences is an important task for function prediction, drug design, and related biological processes understanding. Recent advances have proved the power of language models (LMs) in processing the protein sequence databases, which inherit the advantages of attention networks and capture useful information in learning representations for proteins. The past two years have witnessed remarkable success in tertiary protein structure prediction (PSP), including evolution-based and single-sequence-based PSP. It seems that instead of using energy-based models and sampling procedures, protein language model (pLM)-based pipelines have emerged as mainstream paradigms in PSP. Despite the fruitful progress, the PSP community needs a systematic and up-to-date survey to help bridge the gap between LMs in the natural language processing (NLP) and PSP domains and introduce their methodologies, advancements and practical applications. To this end, in this paper, we first introduce the similarities between protein and human languages that allow LMs extended to pLMs, and applied to protein databases. Then, we systematically review recent advances in LMs and pLMs from the perspectives of network architectures, pre-training strategies, applications, and commonly-used protein databases. Next, different types of methods for PSP are discussed, particularly how the pLM-based architectures function in the process of protein folding. Finally, we identify challenges faced by the PSP community and foresee promising research directions along with the advances of pLMs. This survey aims to be a hands-on guide for researchers to understand PSP methods, develop pLMs and tackle challenging problems in this field for practical purposes.

Deep learning has been widely used for protein engineering. However, it is limited by the lack of sufficient experimental data to train an accurate model for predicting the functional fitness of high-order mutants. Here, we develop SESNet, a supervised deep-learning model to predict the fitness for protein mutants by leveraging both sequence and structure information, and exploiting attention mechanism. Our model integrates local evolutionary context from homologous sequences, the global evolutionary context encoding rich semantic from the universal protein sequence space and the structure information accounting for the microenvironment around each residue in a protein. We show that SESNet outperforms state-of-the-art models for predicting the sequence-function relationship on 26 deep mutational scanning datasets. More importantly, we propose a data augmentation strategy by leveraging the data from unsupervised models to pre-train our model. After that, our model can achieve strikingly high accuracy in prediction of the fitness of protein mutants, especially for the higher order variants (> 4 mutation sites), when finetuned by using only a small number of experimental mutation data (<50). The strategy proposed is of great practical value as the required experimental effort, i.e., producing a few tens of experimental mutation data on a given protein, is generally affordable by an ordinary biochemical group and can be applied on almost any protein.

已经开发出各种机器学习模型，包括深神经网络模型，以预测错义（非同义）突变的有害性。尽管如此，使用更复杂的自适应机器学习方法对生物学问题的新审查可能会受益于当前最新水平的潜在改进。自然语言处理领域的最新进展显示了变压器模型 - 一种深神经网络类型，在与上下文依赖性建模序列信息方面特别有力。在这项研究中，我们介绍了Mutformer，这是一种基于变压器的模型，用于预测有害错义突变。 Mutformer使用人类基因组中的参考和突变蛋白序列作为主要特征。它结合了自我发项层和卷积层的结合，以学习蛋白质序列中氨基酸突变之间的远距离依赖性和短期依赖性。我们在参考蛋白序列和突变蛋白序列上预先训练融合剂，该蛋白质序列是由于人类种群中观察到的常见遗传变异而产生的。接下来，我们检查了不同的微调方法，以成功地将模型应用于错义突变的有害性预测。最后，我们在多个测试数据集上评估了杂货商的性能。我们发现，在各种现有工具中，杂种器表现出相似或改进的性能，包括使用常规机器学习方法的工具（例如，支持向量机，卷积神经网络，经常性神经网络）。我们得出的结论是，杂货商成功考虑了以前研究中未探索的序列特征，并且可能会补充现有的计算预测或经验产生的功能分数，以提高我们对疾病变异的理解。

Despite significant progress of generative models in the natural sciences, their controllability remains challenging. One fundamentally missing aspect of molecular or protein generative models is an inductive bias that can reflect continuous properties of interest. To that end, we propose the Regression Transformer (RT), a novel method that abstracts regression as a conditional sequence modeling problem. This introduces a new paradigm of multitask language models which seamlessly bridge sequence regression and conditional sequence generation. We thoroughly demonstrate that, despite using a nominal-scale training objective, the RT matches or surpasses the performance of conventional regression models in property prediction tasks of small molecules, proteins and chemical reactions. Critically, priming the same model with continuous properties yields a highly competitive conditional generative model that outperforms specialized approaches in a substructure-constrained, property-driven molecule generation benchmark. Our dichotomous approach is facilitated by a novel, alternating training scheme that enables the model to decorate seed sequences by desired properties, e.g., to optimize reaction yield. In sum, the RT is the first report of a multitask model that concurrently excels at predictive and generative tasks in biochemistry. This finds particular application in property-driven, local exploration of the chemical or protein space and could pave the road toward foundation models in material design. The code to reproduce all experiments of the paper is available at: https://github.com/IBM/regression-transformer

蛋白质RNA相互作用对各种细胞活性至关重要。已经开发出实验和计算技术来研究相互作用。由于先前数据库的限制，尤其是缺乏蛋白质结构数据，大多数现有的计算方法严重依赖于序列数据，只有一小部分使用结构信息。最近，alphafold彻底改变了整个蛋白质和生物领域。可预应学，在即将到来的年份，也将显着促进蛋白质-RNA相互作用预测。在这项工作中，我们对该字段进行了彻底的审查，调查绑定站点和绑定偏好预测问题，并覆盖常用的数据集，功能和模型。我们还指出了这一领域的潜在挑战和机遇。本调查总结了过去的RBP-RNA互动领域的发展，并预见到了alphafold时代未来的发展。

Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area. However, its efficacy is largely constrained due to the limited quantity of structural data. Meanwhile, protein language models trained on substantial 1D sequences have shown burgeoning capabilities with scale in a broad range of applications. Nevertheless, no preceding studies consider combining these different protein modalities to promote the representation power of geometric neural networks. To address this gap, we make the foremost step to integrate the knowledge learned by well-trained protein language models into several state-of-the-art geometric networks. Experiments are evaluated on a variety of protein representation learning benchmarks, including protein-protein interface prediction, model quality assessment, protein-protein rigid-body docking, and binding affinity prediction, leading to an overall improvement of 20% over baselines and the new state-of-the-art performance. Strong evidence indicates that the incorporation of protein language models' knowledge enhances geometric networks' capacity by a significant margin and can be generalized to complex tasks.

鉴定新型药物靶标相互作用（DTI）是药物发现中的关键和速率限制步骤。虽然已经提出了深入学习模型来加速识别过程，但我们表明最先进的模型无法概括到新颖（即，从未见过的）结构上。我们首先揭示负责此缺点的机制，展示模型如何依赖于利用蛋白质 - 配体二分网络拓扑的捷径，而不是学习节点特征。然后，我们介绍AI-BIND，这是一个与无监督的预训练的基于网络的采样策略相结合的管道，使我们能够限制注释不平衡并改善新型蛋白质和配体的结合预测。我们通过预测具有结合亲和力的药物和天然化合物对SARS-COV-2病毒蛋白和相关的人蛋白质来说明Ai-reat的值。我们还通过自动扩展模拟和与最近的实验证据进行比较来验证这些预测。总体而言，AI-Bind提供了一种强大的高通量方法来识别药物目标组合，具有成为药物发现中强大工具的可能性。

药物目标亲和力（DTA）预测是药物发现和药物研究的重要任务。 DTA的准确预测可以极大地受益于新药的设计。随着湿实验的昂贵且耗时，DTA预测的监督数据非常有限。这严重阻碍了基于深度学习的方法的应用，这些方法需要大量的监督数据。为了应对这一挑战并提高DTA预测准确性，我们在这项工作中提出了一个具有几种简单但有效的策略的框架：（1）多任务培训策略，该策略将DTA预测和蒙版语言建模（MLM）任务采用配对的药品目标数据集； （2）一种半监督的训练方法，通过利用大规模的未配对分子和蛋白质来赋予药物和靶向代表性学习，这与以前仅利用仅利用预训练的预训练和微调方法，这些方法仅利用前培训和微调方法训练; （3）一个交叉意见模块，以增强药物和靶代表性之间的相互作用。在三个现实世界基准数据集上进行了广泛的实验：BindingDB，Davis和Kiba。结果表明，我们的框架大大优于现有方法，并实现最先进的性能，例如，$ 0.712 $ rmse在bindingdb ic $ _ {50} $测量上，比以前的最佳工作要改善了$ 5 \％。此外，关于特定药物目标结合活动，药物特征可视化和现实世界应用的案例研究证明了我们工作的巨大潜力。代码和数据在https://github.com/qizhipei/smt-dta上发布

对于大型小分子的大型库，在考虑一系列疾病模型，测定条件和剂量范围时，详尽的组合化学筛选变得不可行。深度学习模型已实现了硅的最终技术，以预测协同得分。但是，药物组合的数据库对协同剂有偏见，这些结果不一定会概括分布不足。我们采用了使用深度学习模型的顺序模型优化搜索来快速发现与癌细胞系相比的协同药物组合，而与详尽的评估相比，筛查要少得多。在仅3轮ML引导的体外实验（包括校准圆圈）之后，我们发现，对高度协同组合进行了查询的一组药物对。进行了另外两轮ML引导实验，以确保趋势的可重复性。值得注意的是，我们重新发现药物组合后来证实将在临床试验中研究。此外，我们发现仅使用结构信息生成的药物嵌入开始反映作用机理。

Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Various supervised machine learning models have demonstrated promising performance, but the vast chemical space and the limited availability of property labels make supervised learning challenging. Recently, unsupervised transformer-based language models pretrained on a large unlabelled corpus have produced state-of-the-art results in many downstream natural language processing tasks. Inspired by this development, we present molecular embeddings obtained by training an efficient transformer encoder model, MoLFormer, which uses rotary positional embeddings. This model employs a linear attention mechanism, coupled with highly distributed training, on SMILES sequences of 1.1 billion unlabelled molecules from the PubChem and ZINC datasets. We show that the learned molecular representation outperforms existing baselines, including supervised and self-supervised graph neural networks and language models, on several downstream tasks from ten benchmark datasets. They perform competitively on two others. Further analyses, specifically through the lens of attention, demonstrate that MoLFormer trained on chemical SMILES indeed learns the spatial relationships between atoms within a molecule. These results provide encouraging evidence that large-scale molecular language models can capture sufficient chemical and structural information to predict various distinct molecular properties, including quantum-chemical properties.

Artificial intelligence (AI) in the form of deep learning bears promise for drug discovery and chemical biology, $\textit{e.g.}$, to predict protein structure and molecular bioactivity, plan organic synthesis, and design molecules $\textit{de novo}$. While most of the deep learning efforts in drug discovery have focused on ligand-based approaches, structure-based drug discovery has the potential to tackle unsolved challenges, such as affinity prediction for unexplored protein targets, binding-mechanism elucidation, and the rationalization of related chemical kinetic properties. Advances in deep learning methodologies and the availability of accurate predictions for protein tertiary structure advocate for a $\textit{renaissance}$ in structure-based approaches for drug discovery guided by AI. This review summarizes the most prominent algorithmic concepts in structure-based deep learning for drug discovery, and forecasts opportunities, applications, and challenges ahead.

Neural processes (NPs) are models for transfer learning with properties reminiscent of Gaussian Processes (GPs). They are adept at modelling data consisting of few observations of many related functions on the same input space and are trained by minimizing a variational objective, which is computationally much less expensive than the Bayesian updating required by GPs. So far, most studies of NPs have focused on low-dimensional datasets which are not representative of realistic transfer learning tasks. Drug discovery is one application area that is characterized by datasets consisting of many chemical properties or functions which are sparsely observed, yet depend on shared features or representations of the molecular inputs. This paper applies the conditional neural process (CNP) to DOCKSTRING, a dataset of docking scores for benchmarking ML models. CNPs show competitive performance in few-shot learning tasks relative to supervised learning baselines common in chemoinformatics, as well as an alternative model for transfer learning based on pre-training and refining neural network regressors. We present a Bayesian optimization experiment which showcases the probabilistic nature of CNPs and discuss shortcomings of the model in uncertainty quantification.

在三维分子结构上运行的计算方法有可能解决生物学和化学的重要问题。特别地，深度神经网络的重视，但它们在生物分子结构域中的广泛采用受到缺乏系统性能基准或统一工具包的限制，用于与分子数据相互作用。为了解决这个问题，我们呈现Atom3D，这是一个新颖的和现有的基准数据集的集合，跨越几个密钥的生物分子。我们为这些任务中的每一个实施多种三维分子学习方法，并表明它们始终如一地提高了基于单维和二维表示的方法的性能。结构的具体选择对于性能至关重要，具有涉及复杂几何形状的任务的三维卷积网络，在需要详细位置信息的系统中表现出良好的图形网络，以及最近开发的设备越多的网络显示出显着承诺。我们的结果表明，许多分子问题符合三维分子学习的增益，并且有可能改善许多仍然过分曝光的任务。为了降低进入并促进现场进一步发展的障碍，我们还提供了一套全面的DataSet处理，模型培训和在我们的开源ATOM3D Python包中的评估工具套件。所有数据集都可以从https://www.atom3d.ai下载。