Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models taken from NLP. These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids. The LMs were trained on the Summit supercomputer using 5616 GPUs and TPU Pod up-to 1024 cores. Dimensionality reduction revealed that the raw protein LM-embeddings from unlabeled data captured some biophysical features of protein sequences. We validated the advantage of using the embeddings as exclusive input for several subsequent tasks. The first was a per-residue prediction of protein secondary structure (3-state accuracy Q3=81%-87%); the second were per-protein predictions of protein sub-cellular localization (ten-state accuracy: Q10=81%) and membrane vs. water-soluble (2-state accuracy Q2=91%). For the per-residue predictions the transfer of the most informative embeddings (ProtT5) for the first time outperformed the state-of-the-art without using evolutionary information thereby bypassing expensive database searches. Taken together, the results implied that protein LMs learned some of the grammar of the language of life. To facilitate future work, we released our models at https://github.com/agemagician/ProtTrans.

Motivation: Natural Language Processing (NLP) continues improving substantially through auto-regressive (AR) and auto-encoding (AE) Language Models (LMs). These LMs require expensive computing resources for self-supervised or un-supervised learning from huge unlabelled text corpora. The information learned is transferred through so-called embeddings to downstream prediction tasks. Computational biology and bioinformatics provide vast gold-mines of structured and sequentially ordered text data leading to extraordinarily successful protein sequence LMs that promise new frontiers for generative and predictive tasks at low inference cost. As recent NLP advances link corpus size to model size and accuracy, we addressed two questions: (1) To which extent can High-Performance Computing (HPC) up-scale protein LMs to larger databases and larger models? (2) To which extent can LMs extract features from single proteins to get closer to the performance of methods using evolutionary information? Methodology: Here, we trained two auto-regressive language models (Transformer-XL and XLNet) and two auto-encoder models (BERT and Albert) on 80 billion amino acids from 200 million protein sequences (UniRef100) and one language model (Transformer-XL) on 393 billion amino acids from 2.1 billion protein sequences taken from the Big Fat Database (BFD), today's largest set of protein sequences (corresponding to 22- and 112-times, respectively of the entire English Wikipedia). The LMs were trained on the Summit supercomputer, using 936 nodes with 6 GPUs each (in total 5616 GPUs) and one TPU Pod, using V3-512 cores. Results: We validated the feasibility of training big LMs on proteins and the advantage of up-scaling LMs to larger models supported by more data. The latter was assessed by predicting secondary structure in three- and eight-states (Q3=75-83, Q8=63-72), localization for 10 cellular compartments (Q10=74) and whether a protein is membrane-bound or water-soluble (Q2=89). Dimensionality reduction revealed that the LM-embeddings from unlabelled data (only protein sequences) captured important biophysical properties of the protein alphabet, namely the amino acids, and their well orchestrated interplay in governing the shape of proteins. In the analogy of NLP, this implied having learned some of the grammar of the language of life realized in protein sequences. The successful up-scaling of protein LMs through HPC slightly reduced the gap between models trained on evolutionary information and LMs. Additionally, our results highlighted the importance of bi-directionality when processing proteins as the uni-directional TransformerXL was outperformed by its bi-directional counterparts. Availability ProtTrans: <a href="https://github.com/agemagician/ProtTrans">https://github.com/agemagician/ProtTrans</a>

BackgroundPredicting protein function and structure from sequence is one important challenge for computational biology. For 26 years, most state-of-the-art approaches combined machine learning and evolutionary information. However, for some applications retrieving related proteins is becoming too time-consuming. Additionally, evolutionary information is less powerful for small families, e.g. for proteins from the Dark Proteome. Both these problems are addressed by the new methodology introduced here.ResultsWe introduced a novel way to represent protein sequences as continuous vectors (embeddings) by using the language model ELMo taken from natural language processing. By modeling protein sequences, ELMo effectively captured the biophysical properties of the language of life from unlabeled big data (UniRef50). We refer to these new embeddings as SeqVec (Sequence-to-Vector) and demonstrate their effectiveness by training simple neural networks for two different tasks. At the per-residue level, secondary structure (Q3 = 79% ± 1, Q8 = 68% ± 1) and regions with intrinsic disorder (MCC = 0.59 ± 0.03) were predicted significantly better than through one-hot encoding or through Word2vec-like approaches. At the per-protein level, subcellular localization was predicted in ten classes (Q10 = 68% ± 1) and membrane-bound were distinguished from water-soluble proteins (Q2 = 87% ± 1). Although SeqVec embeddings generated the best predictions from single sequences, no solution improved over the best existing method using evolutionary information. Nevertheless, our approach improved over some popular methods using evolutionary information and for some proteins even did beat the best. Thus, they prove to condense the underlying principles of protein sequences. Overall, the important novelty is speed: where the lightning-fast HHblits needed on average about two minutes to generate the evolutionary information for a target protein, SeqVec created embeddings on average in 0.03 s. As this speed-up is independent of the size of growing sequence databases, SeqVec provides a highly scalable approach for the analysis of big data in proteomics, i.e. microbiome or metaproteome analysis.ConclusionTransfer-learning succeeded to extract information from unlabeled sequence databases relevant for various protein prediction tasks. SeqVec modeled the language of life, namely the principles underlying protein sequences better than any features suggested by textbooks and prediction methods. The exception is evolutionary information, however, that information is not available on the level of a single sequence.

Pathway Commons (https://www.pathwaycommons.org) is an integrated resource of publicly available information about biological pathways including biochemical reactions, assembly of biomolecular complexes, transport and catalysis events and physical interactions involving proteins, DNA, RNA, and small molecules (e.g. metabolites and drug compounds). Data is collected from multiple providers in standard formats, including the Biological Pathway Exchange (BioPAX) language and the Proteomics Standards Initiative Molecular Interactions format, and then integrated. Pathway Commons provides biologists with (i) tools to search this comprehensive resource, (ii) a download site offering integrated bulk sets of pathway data (e.g. tables of interactions and gene sets), (iii) reusable software libraries for working with pathway information in several programming languages (Java, R, Python and Javascript) and (iv) a web service for programmatically querying the entire dataset. Visualization of pathways is supported using the Systems Biological Graphical Notation (SBGN). Pathway Commons currently contains data from 22 databases with 4794 detailed human biochemical processes (i.e. pathways) and ∼2.3 million interactions. To enhance the usability of this large resource for end-users, we develop and maintain interactive web applications and training materials that enable pathway exploration and advanced analysis.