诸如GPT-3之类的大型审慎模型通过利用自学学习的学习来学习明显的表现，从而对现代自然语言处理产生了巨大影响，这些表现可以轻易地对各种下游任务进行挑剔。我们通过使用微笑语言构建化学基础模型Chemberta-2来研究将这种进步转移到分子机器学习中的可能性。虽然标记的分子预测任务数据通常很少，但微笑字符串的库很容易获得。在这项工作中，我们通过优化预处理过程来建立Chemberta。我们比较了通过不同的超参数和预处理数据集尺寸的多任务和自我监督预训练的预测，来自PubChem最多77m化合物。据我们所知，77m集合构成了迄今为止用于分子预处理的最大数据集之一。我们发现，通过这些预处理的改进，我们与Moleculenet基准套件上现有的最先进的体系结构具有竞争力。我们分析了预读的改进的程度，转化为下游任务的改进。

Models that accurately predict properties based on chemical structure are valuable tools in drug discovery. However, for many properties, public and private training sets are typically small, and it is difficult for the models to generalize well outside of the training data. Recently, large language models have addressed this problem by using self-supervised pretraining on large unlabeled datasets, followed by fine-tuning on smaller, labeled datasets. In this paper, we report MolE, a molecular foundation model that adapts the DeBERTa architecture to be used on molecular graphs together with a two-step pretraining strategy. The first step of pretraining is a self-supervised approach focused on learning chemical structures, and the second step is a massive multi-task approach to learn biological information. We show that fine-tuning pretrained MolE achieves state-of-the-art results on 9 of the 22 ADMET tasks included in the Therapeutic Data Commons.

We discover a robust self-supervised strategy tailored towards molecular representations for generative masked language models through a series of tailored, in-depth ablations. Using this pre-training strategy, we train BARTSmiles, a BART-like model with an order of magnitude more compute than previous self-supervised molecular representations. In-depth evaluations show that BARTSmiles consistently outperforms other self-supervised representations across classification, regression, and generation tasks setting a new state-of-the-art on 11 tasks. We then quantitatively show that when applied to the molecular domain, the BART objective learns representations that implicitly encode our downstream tasks of interest. For example, by selecting seven neurons from a frozen BARTSmiles, we can obtain a model having performance within two percentage points of the full fine-tuned model on task Clintox. Lastly, we show that standard attribution interpretability methods, when applied to BARTSmiles, highlight certain substructures that chemists use to explain specific properties of molecules. The code and the pretrained model are publicly available.

分子性质预测在化学中至关重要，特别是对于药物发现应用。但是，可用的分子属性数据通常受到限制，鼓励信息从相关数据传输。转移学习对计算机视觉和自然语言处理信号等领域产生了巨大影响，以实现其在分子财产预测中的潜力。我们提出了使用反应数据进行分子表示学习的预训练程序，并将其用于预训练微笑变压器。我们对从物理化学，生物物理学和生理学中的分子的12个分子性质预测任务进行微调和评估预先训练的模型，并与非预先训练的基线模型相比，对12个任务中的5个任务显示出统计学上的显着积极作用。

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.

对聚合物性质的准确预测在聚合物的开发和设计中具有重要意义。通常，需要进行昂贵且耗时的实验或模拟来评估聚合物的功能。最近，配备了注意力机制的变压器模型在各种自然语言处理任务中表现出卓越的性能。但是，这种方法尚未在聚合物科学中进行研究。在此，我们报告了TransPolymer，这是一种基于变压器的语言模型，用于聚合物属性预测。由于我们提出的具有化学意识的聚合物令牌，转染剂可以直接从聚合物序列中学习表示。该模型通过在大型未标记数据集上进行预处理，从而学习表达性表示，然后在下游数据集上进行有关各种聚合物属性的模型。转聚合物在所有八个数据集中都能达到卓越的性能，并且在大多数下游任务上都显着超过其他基线。此外，预处理的转聚合物对监督转聚合物和其他语言模型的改善增强了对代表学习中大型未标记数据预处理的显着好处。实验结果进一步证明了注意机制在理解聚合物序列中的重要作用。我们强调该模型是一种有前途的计算工具，用于促进数据科学视图中的结构 - 质谱关系。

使用图神经网络（GNN）提取分子的信息表示，对于AI驱动的药物发现至关重要。最近，图形研究界一直在试图复制自然语言处理预处理的成功，并获得了一些成功。但是，我们发现在许多情况下，自我监督预审计对分子数据的益处可以忽略不计。我们对GNN预处理的关键组成部分进行了彻底的消融研究，包括预处理目标，数据拆分方法，输入特征，预处理数据集量表和GNN体系结构，以决定下游任务的准确性。我们的第一个重要发现是，在许多情况下，自我监督的图表预处理没有统计学上的显着优势。其次，尽管可以通过额外的监督预处理可以观察到改进，但通过更丰富或更平衡的数据拆分，改进可能会减少。第三，实验性超参数对下游任务的准确性具有更大的影响，而不是训练训练的任务。我们假设对分子进行预训练的复杂性不足，从而导致下游任务的可转移知识较低。

Recently, deep learning approaches have been extensively studied for various problems in chemistry, such as property prediction, virtual screening, de novo molecule design, etc. Despite the impressive successes, separately designed networks for specific tasks are usually required for end-to-end training, so it is often difficult to acquire a unified principle to synergistically combine existing models and training datasets for novel tasks. To address this, here we present a novel multimodal chemical foundation model that can be used for various downstream tasks that require a simultaneous understanding of structure and property. Specifically, inspired by recent advances in pre-trained multi-modal foundation models such as Vision-Language Pretrained models (VLP), we proposed a novel structure-property multi-modal (SPMM) foundation model using the dual-stream transformer with X-shape attention, so that it can align the molecule structure and the chemical properties in a common embedding space. Thanks to the outstanding structure-property unimodal representation, experimental results confirm that SPMM can simultaneously perform molecule generation, property prediction, classification, reaction prediction, etc., which was previously not possible with a single architecture.

对表格数据的深度学习的最新工作表明了深层表格模型的强劲表现，通常会弥合梯度增强的决策树和神经网络之间的差距。除了准确性之外，神经模型的主要优点是它们学习可重复使用的功能，并且在新域中很容易进行微调。该属性通常在计算机视觉和自然语言应用中被利用，在特定于任务的培训数据稀缺时，转移学习是必不可少的。在这项工作中，我们证明上游数据使表格神经网络比广泛使用的GBDT模型具有决定性的优势。我们为表格转移学习提出了一个现实的医学诊断基准，并提出了使用上游数据来通过各种表格神经网络体系结构来提高性能的方法指南。最后，我们为上游和下游特征集不同的情况提出了一种伪特征方法，在现实世界中，特定于表格的问题广泛。我们的代码可在https://github.com/levinroman/tabular-transfer-learning上找到。

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a;Radford et al., 2018), BERT is designed to pretrain deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be finetuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial taskspecific architecture modifications.BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

Molecular representation learning is crucial for the problem of molecular property prediction, where graph neural networks (GNNs) serve as an effective solution due to their structure modeling capabilities. Since labeled data is often scarce and expensive to obtain, it is a great challenge for GNNs to generalize in the extensive molecular space. Recently, the training paradigm of "pre-train, fine-tune" has been leveraged to improve the generalization capabilities of GNNs. It uses self-supervised information to pre-train the GNN, and then performs fine-tuning to optimize the downstream task with just a few labels. However, pre-training does not always yield statistically significant improvement, especially for self-supervised learning with random structural masking. In fact, the molecular structure is characterized by motif subgraphs, which are frequently occurring and influence molecular properties. To leverage the task-related motifs, we propose a novel paradigm of "pre-train, prompt, fine-tune" for molecular representation learning, named molecule continuous prompt tuning (MolCPT). MolCPT defines a motif prompting function that uses the pre-trained model to project the standalone input into an expressive prompt. The prompt effectively augments the molecular graph with meaningful motifs in the continuous representation space; this provides more structural patterns to aid the downstream classifier in identifying molecular properties. Extensive experiments on several benchmark datasets show that MolCPT efficiently generalizes pre-trained GNNs for molecular property prediction, with or without a few fine-tuning steps.

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer training times. To address these problems, we present two parameterreduction techniques to lower memory consumption and increase the training speed of BERT (Devlin et al., 2019). Comprehensive empirical evidence shows that our proposed methods lead to models that scale much better compared to the original BERT. We also use a self-supervised loss that focuses on modeling inter-sentence coherence, and show it consistently helps downstream tasks with multi-sentence inputs. As a result, our best model establishes new state-of-the-art results on the GLUE, RACE, and SQuAD benchmarks while having fewer parameters compared to BERT-large. The code and the pretrained models are available at https://github.com/google-research/ALBERT. * Work done as an intern at Google Research, driving data processing and downstream task evaluations.

Many applications of machine learning require a model to make accurate predictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training. An effective approach to this challenge is to pre-train a model on related tasks where data is abundant, and then fine-tune it on a downstream task of interest. While pre-training has been effective in many language and vision domains, it remains an open question how to effectively use pre-training on graph datasets. In this paper, we develop a new strategy and self-supervised methods for pre-training Graph Neural Networks (GNNs). The key to the success of our strategy is to pre-train an expressive GNN at the level of individual nodes as well as entire graphs so that the GNN can learn useful local and global representations simultaneously. We systematically study pre-training on multiple graph classification datasets. We find that naïve strategies, which pre-train GNNs at the level of either entire graphs or individual nodes, give limited improvement and can even lead to negative transfer on many downstream tasks. In contrast, our strategy avoids negative transfer and improves generalization significantly across downstream tasks, leading up to 9.4% absolute improvements in ROC-AUC over non-pre-trained models and achieving state-of-the-art performance for molecular property prediction and protein function prediction.However, pre-training on graph datasets remains a hard challenge. Several key studies (

Recent trends in language modeling have focused on increasing performance through scaling, and have resulted in an environment where training language models is out of reach for most researchers and practitioners. While most in the community are asking how to push the limits of extreme computation, we ask the opposite question: How far can we get with a single GPU in just one day? We investigate the downstream performance achievable with a transformer-based language model trained completely from scratch with masked language modeling for a single day on a single consumer GPU. Aside from re-analyzing nearly all components of the pretraining pipeline for this scenario and providing a modified pipeline with performance close to BERT, we investigate why scaling down is hard, and which modifications actually improve performance in this scenario. We provide evidence that even in this constrained setting, performance closely follows scaling laws observed in large-compute settings. Through the lens of scaling laws, we categorize a range of recent improvements to training and architecture and discuss their merit and practical applicability (or lack thereof) for the limited compute setting.

最先进的愿景和愿景和语言模型依靠大规模的Visio-linguisting预借鉴，以获得各种下游任务的良好性能。通常，这种模型通常是跨模态（对比）或多模态（具有早期融合）但不是两者;它们通常只针对特定的方式或任务。有希望的方向将是使用单一整体普遍模型，作为“基础”，目标是一次性的所有方式 - 真正的视觉和语言基础模型应该擅长视力任务，语言任务和交叉和多数模态视觉和语言任务。我们将Flava介绍在这样的模型中，并在跨越这些目标模式的广泛的35个任务上展示令人印象深刻的性能。

Although substantial efforts have been made using graph neural networks (GNNs) for AI-driven drug discovery (AIDD), effective molecular representation learning remains an open challenge, especially in the case of insufficient labeled molecules. Recent studies suggest that big GNN models pre-trained by self-supervised learning on unlabeled datasets enable better transfer performance in downstream molecular property prediction tasks. However, they often require large-scale datasets and considerable computational resources, which is time-consuming, computationally expensive, and environmentally unfriendly. To alleviate these limitations, we propose a novel pre-training model for molecular representation learning, Bi-branch Masked Graph Transformer Autoencoder (BatmanNet). BatmanNet features two tailored and complementary graph autoencoders to reconstruct the missing nodes and edges from a masked molecular graph. To our surprise, BatmanNet discovered that the highly masked proportion (60%) of the atoms and bonds achieved the best performance. We further propose an asymmetric graph-based encoder-decoder architecture for either nodes and edges, where a transformer-based encoder only takes the visible subset of nodes or edges, and a lightweight decoder reconstructs the original molecule from the latent representation and mask tokens. With this simple yet effective asymmetrical design, our BatmanNet can learn efficiently even from a much smaller-scale unlabeled molecular dataset to capture the underlying structural and semantic information, overcoming a major limitation of current deep neural networks for molecular representation learning. For instance, using only 250K unlabelled molecules as pre-training data, our BatmanNet with 2.575M parameters achieves a 0.5% improvement on the average AUC compared with the current state-of-the-art method with 100M parameters pre-trained on 11M molecules.

Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to downstream NLP tasks, they generally require large amounts of compute to be effective. As an alternative, we propose a more sample-efficient pre-training task called replaced token detection. Instead of masking the input, our approach corrupts it by replacing some tokens with plausible alternatives sampled from a small generator network. Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not. Thorough experiments demonstrate this new pre-training task is more efficient than MLM because the task is defined over all input tokens rather than just the small subset that was masked out. As a result, the contextual representations learned by our approach substantially outperform the ones learned by BERT given the same model size, data, and compute. The gains are particularly strong for small models; for example, we train a model on one GPU for 4 days that outperforms GPT (trained using 30x more compute) on the GLUE natural language understanding benchmark. Our approach also works well at scale, where it performs comparably to RoBERTa and XLNet while using less than 1/4 of their compute and outperforms them when using the same amount of compute.

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。

变压器负责自然语言处理的绝大多数近期进步。这些模型的大多数实际的自然语言处理应用程序通常通过转移学习启用。本文研究了用于微调用于微调的特异性标记提高了模型的结果。通过一系列实验，我们证明这种令牌化与词汇令牌的初始化和微调策略相结合，加速了转移并提高了微调模型的性能。我们称之为转让促进词汇转移的这个方面。

我们可以将袖珍配体的相互作用知识注入预训练的模型并共同学习其化学空间吗？近年来，预处理的分子和蛋白质引起了很大的关注，而这些方法中的大多数都集中在学习一个化学空间，并且缺乏注射生物学知识。我们提出一个共同监督预告片（COSP）的框架，以同时学习3D口袋和配体表示。我们使用封闭式的几何消息传递层来对3D口袋和配体进行建模，其中每个节点的化学特征，几何位置和方向都被考虑。为了学习生物学有意义的嵌入，我们通过对比度损失将袖珍配体相互作用知识注入预处理模型。考虑到分子的特异性，我们进一步提出了化学相似性增强的负抽样策略，以提高对比度学习绩效。通过广泛的实验，我们得出的结论是，COSP可以在口袋匹配，分子属性预测和虚拟筛选中获得竞争成果。