1
|
Temizer AB, Uludoğan G, Özçelik R, Koulani T, Ozkirimli E, Ulgen KO, Karali N, Özgür A. Exploring data-driven chemical SMILES tokenization approaches to identify key protein-ligand binding moieties. Mol Inform 2024; 43:e202300249. [PMID: 38196065 DOI: 10.1002/minf.202300249] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Revised: 11/13/2023] [Accepted: 01/06/2024] [Indexed: 01/11/2024]
Abstract
Machine learning models have found numerous successful applications in computational drug discovery. A large body of these models represents molecules as sequences since molecular sequences are easily available, simple, and informative. The sequence-based models often segment molecular sequences into pieces called chemical words, analogous to the words that make up sentences in human languages, and then apply advanced natural language processing techniques for tasks such as de novo drug design, property prediction, and binding affinity prediction. However, the chemical characteristics and significance of these building blocks, chemical words, remain unexplored. To address this gap, we employ data-driven SMILES tokenization techniques such as Byte Pair Encoding, WordPiece, and Unigram to identify chemical words and compare the resulting vocabularies. To understand the chemical significance of these words, we build a language-inspired pipeline that treats high affinity ligands of protein targets as documents and selects key chemical words making up those ligands based on tf-idf weighting. The experiments on multiple protein-ligand affinity datasets show that despite differences in words, lengths, and validity among the vocabularies generated by different subword tokenization algorithms, the identified key chemical words exhibit similarity. Further, we conduct case studies on a number of target to analyze the impact of key chemical words on binding. We find that these key chemical words are specific to protein targets and correspond to known pharmacophores and functional groups. Our approach elucidates chemical properties of the words identified by machine learning models and can be used in drug discovery studies to determine significant chemical moieties.
Collapse
Affiliation(s)
- Asu Busra Temizer
- Department of Pharmaceutical Chemistry, Faculty of Pharmacy, İstanbul University, İstanbul, Turkey
- Department of Pharmaceutical Chemistry, Institute of Health Sciences, İstanbul University, İstanbul, Turkey
| | - Gökçe Uludoğan
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Rıza Özçelik
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Taha Koulani
- Department of Pharmaceutical Chemistry, Faculty of Pharmacy, İstanbul University, İstanbul, Turkey
- Department of Pharmaceutical Chemistry, Institute of Health Sciences, İstanbul University, İstanbul, Turkey
| | - Elif Ozkirimli
- Science and Research Informatics, F. Hoffmann-La Roche Ltd, Basel, Switzerland
| | - Kutlu O Ulgen
- Department of Chemical Engineering, Boğaziçi University, İstanbul, Turkey
| | - Nilgun Karali
- Department of Pharmaceutical Chemistry, Faculty of Pharmacy, İstanbul University, İstanbul, Turkey
| | - Arzucan Özgür
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| |
Collapse
|
2
|
Barsbey M, ÖZçelİk R, Bağ A, Atil B, ÖZgür A, Ozkirimli E. A Computational Software for Training Robust Drug-Target Affinity Prediction Models: pydebiaseddta. J Comput Biol 2023; 30:1240-1245. [PMID: 37988394 DOI: 10.1089/cmb.2023.0194] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2023] Open
Abstract
Robust generalization of drug-target affinity (DTA) prediction models is a notoriously difficult problem in computational drug discovery. In this article, we present pydebiaseddta: a computational software for improving the generalizability of DTA prediction models to novel ligands and/or proteins. pydebiaseddta serves as the practical implementation of the DebiasedDTA training framework, which advocates modifying the training distribution to mitigate the effect of spurious correlations in the training data set that leads to substantially degraded performance for novel ligands and proteins. Written in Python programming language, pydebiaseddta combines a user-friendly streamlined interface with a feature-rich and highly modifiable architecture. With this article we introduce our software, showcase its main functionalities, and describe practical ways for new users to engage with it.
Collapse
Affiliation(s)
- Melİh Barsbey
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Riza ÖZçelİk
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Alperen Bağ
- Technical University of Munich, Munich, Germany
| | - Berk Atil
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Arzucan ÖZgür
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Elif Ozkirimli
- Roche Informatics, F. Hoffmann-La Roche AG, Basel, Switzerland
| |
Collapse
|
3
|
ÖZçelİk R, Bağ A, Atil B, Barsbey M, ÖZgür A, Ozkirimli E. A Framework for Improving the Generalizability of Drug-Target Affinity Prediction Models. J Comput Biol 2023; 30:1226-1239. [PMID: 37988395 DOI: 10.1089/cmb.2023.0208] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2023] Open
Abstract
Statistical models that accurately predict the binding affinity of an input ligand-protein pair can greatly accelerate drug discovery. Such models are trained on available ligand-protein interaction data sets, which may contain biases that lead the predictor models to learn data set-specific, spurious patterns instead of generalizable relationships. This leads the prediction performances of these models to drop dramatically for previously unseen biomolecules. Various approaches that aim to improve model generalizability either have limited applicability or introduce the risk of degrading overall prediction performance. In this article, we present DebiasedDTA, a novel training framework for drug-target affinity (DTA) prediction models that addresses data set biases to improve the generalizability of such models. DebiasedDTA relies on reweighting the training samples to achieve robust generalization, and is thus applicable to most DTA prediction models. Extensive experiments with different biomolecule representations, model architectures, and data sets demonstrate that DebiasedDTA achieves improved generalizability in predicting drug-target affinities.
Collapse
Affiliation(s)
- Riza ÖZçelİk
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Alperen Bağ
- Technical University of Munich, Munich, Germany
| | - Berk Atil
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Melİh Barsbey
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Arzucan ÖZgür
- Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
| | - Elif Ozkirimli
- Roche Informatics, F. Hoffmann-La Roche AG, Basel, Switzerland
| |
Collapse
|
4
|
Uludoğan G, Ozkirimli E, Ulgen KO, Karalı N, Özgür A. Exploiting pretrained biochemical language models for targeted drug design. Bioinformatics 2022; 38:ii155-ii161. [PMID: 36124801 DOI: 10.1093/bioinformatics/btac482] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/25/2022] Open
Abstract
MOTIVATION The development of novel compounds targeting proteins of interest is one of the most important tasks in the pharmaceutical industry. Deep generative models have been applied to targeted molecular design and have shown promising results. Recently, target-specific molecule generation has been viewed as a translation between the protein language and the chemical language. However, such a model is limited by the availability of interacting protein-ligand pairs. On the other hand, large amounts of unlabelled protein sequences and chemical compounds are available and have been used to train language models that learn useful representations. In this study, we propose exploiting pretrained biochemical language models to initialize (i.e. warm start) targeted molecule generation models. We investigate two warm start strategies: (i) a one-stage strategy where the initialized model is trained on targeted molecule generation and (ii) a two-stage strategy containing a pre-finetuning on molecular generation followed by target-specific training. We also compare two decoding strategies to generate compounds: beam search and sampling. RESULTS The results show that the warm-started models perform better than a baseline model trained from scratch. The two proposed warm-start strategies achieve similar results to each other with respect to widely used metrics from benchmarks. However, docking evaluation of the generated compounds for a number of novel proteins suggests that the one-stage strategy generalizes better than the two-stage strategy. Additionally, we observe that beam search outperforms sampling in both docking evaluation and benchmark metrics for assessing compound quality. AVAILABILITY AND IMPLEMENTATION The source code is available at https://github.com/boun-tabi/biochemical-lms-for-drug-design and the materials (i.e., data, models, and outputs) are archived in Zenodo at https://doi.org/10.5281/zenodo.6832145. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Gökçe Uludoğan
- Department of Computer Engineering, Boğaziçi University, İstanbul 34342, Turkey
| | - Elif Ozkirimli
- Data and Analytics Chapter, Pharma International Informatics, F. Hoffmann-La Roche AG 4303, Switzerland
| | - Kutlu O Ulgen
- Department of Chemical Engineering, Boğaziçi University, İstanbul 34342, Turkey
| | - Nilgün Karalı
- Faculty of Pharmacy, Department of Pharmaceutical Chemistry, İstanbul University, İstanbul 34116, Turkey
| | - Arzucan Özgür
- Department of Computer Engineering, Boğaziçi University, İstanbul 34342, Turkey
| |
Collapse
|
5
|
Zeng Y, Chen X, Peng D, Zhang L, Huang H. Multi-scaled self-attention for drug-target interaction prediction based on multi-granularity representation. BMC Bioinformatics 2022; 23:314. [PMID: 35922768 PMCID: PMC9347097 DOI: 10.1186/s12859-022-04857-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Accepted: 07/22/2022] [Indexed: 11/21/2022] Open
Abstract
Background Drug–target interaction (DTI) prediction plays a crucial role in drug discovery. Although the advanced deep learning has shown promising results in predicting DTIs, it still needs improvements in two aspects: (1) encoding method, in which the existing encoding method, character encoding, overlooks chemical textual information of atoms with multiple characters and chemical functional groups; as well as (2) the architecture of deep model, which should focus on multiple chemical patterns in drug and target representations. Results In this paper, we propose a multi-granularity multi-scaled self-attention (SAN) model by alleviating the above problems. Specifically, in process of encoding, we investigate a segmentation method for drug and protein sequences and then label the segmented groups as the multi-granularity representations. Moreover, in order to enhance the various local patterns in these multi-granularity representations, a multi-scaled SAN is built and exploited to generate deep representations of drugs and targets. Finally, our proposed model predicts DTIs based on the fusion of these deep representations. Our proposed model is evaluated on two benchmark datasets, KIBA and Davis. The experimental results reveal that our proposed model yields better prediction accuracy than strong baseline models. Conclusion Our proposed multi-granularity encoding method and multi-scaled SAN model improve DTI prediction by encoding the chemical textual information of drugs and targets and extracting their various local patterns, respectively.
Collapse
Affiliation(s)
- Yuni Zeng
- School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China
| | - Xiangru Chen
- College of Computer Science, Sichuan University, Chengdu, China
| | - Dezhong Peng
- College of Computer Science, Sichuan University, Chengdu, China.,Shenzhen Peng Cheng Laboratory, Shenzhen, China.,Chengdu Sobey Digital Technology Co., Ltd, Chengdu, China
| | - Lijun Zhang
- Sichuan Zhiqian Technology Co., Ltd, Chengdu, China.,Chengdu Ruibei Yingte Information Technology Co., Ltd, Chengdu, China
| | - Haixiao Huang
- Sichuan Provincial Commission of Politics and Law, Chengdu, China.
| |
Collapse
|
6
|
Sabando MV, Ponzoni I, Milios EE, Soto AJ. Using molecular embeddings in QSAR modeling: does it make a difference? Brief Bioinform 2021; 23:6366344. [PMID: 34498670 DOI: 10.1093/bib/bbab365] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2021] [Revised: 07/29/2021] [Accepted: 08/18/2021] [Indexed: 11/13/2022] Open
Abstract
With the consolidation of deep learning in drug discovery, several novel algorithms for learning molecular representations have been proposed. Despite the interest of the community in developing new methods for learning molecular embeddings and their theoretical benefits, comparing molecular embeddings with each other and with traditional representations is not straightforward, which in turn hinders the process of choosing a suitable representation for Quantitative Structure-Activity Relationship (QSAR) modeling. A reason behind this issue is the difficulty of conducting a fair and thorough comparison of the different existing embedding approaches, which requires numerous experiments on various datasets and training scenarios. To close this gap, we reviewed the literature on methods for molecular embeddings and reproduced three unsupervised and two supervised molecular embedding techniques recently proposed in the literature. We compared these five methods concerning their performance in QSAR scenarios using different classification and regression datasets. We also compared these representations to traditional molecular representations, namely molecular descriptors and fingerprints. As opposed to the expected outcome, our experimental setup consisting of over $25 000$ trained models and statistical tests revealed that the predictive performance using molecular embeddings did not significantly surpass that of traditional representations. Although supervised embeddings yielded competitive results compared with those using traditional molecular representations, unsupervised embeddings tended to perform worse than traditional representations. Our results highlight the need for conducting a careful comparison and analysis of the different embedding techniques prior to using them in drug design tasks and motivate a discussion about the potential of molecular embeddings in computer-aided drug design.
Collapse
Affiliation(s)
| | - Ignacio Ponzoni
- Institute for Computer Science and Engineering, UNS-CONICET, Bahía Blanca, Argentina.,Department of Computer Science and Engineering, Universidad Nacional del Sur, Bahía Blanca, Argentina
| | | | - Axel J Soto
- Institute for Computer Science and Engineering, UNS-CONICET, Bahía Blanca, Argentina.,Department of Computer Science and Engineering, Universidad Nacional del Sur, Bahía Blanca, Argentina
| |
Collapse
|
7
|
Gupta R, Srivastava D, Sahu M, Tiwari S, Ambasta RK, Kumar P. Artificial intelligence to deep learning: machine intelligence approach for drug discovery. Mol Divers 2021; 25:1315-1360. [PMID: 33844136 PMCID: PMC8040371 DOI: 10.1007/s11030-021-10217-3] [Citation(s) in RCA: 264] [Impact Index Per Article: 88.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2021] [Accepted: 03/22/2021] [Indexed: 02/06/2023]
Abstract
Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists. However, low efficacy, off-target delivery, time consumption, and high cost impose a hurdle and challenges that impact drug design and discovery. Further, complex and big data from genomics, proteomics, microarray data, and clinical trials also impose an obstacle in the drug discovery pipeline. Artificial intelligence and machine learning technology play a crucial role in drug discovery and development. In other words, artificial neural networks and deep learning algorithms have modernized the area. Machine learning and deep learning algorithms have been implemented in several drug discovery processes such as peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modeling, quantitative structure-activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Evidence from the past strengthens the implementation of artificial intelligence and deep learning in this field. Moreover, novel data mining, curation, and management techniques provided critical support to recently developed modeling algorithms. In summary, artificial intelligence and deep learning advancements provide an excellent opportunity for rational drug design and discovery process, which will eventually impact mankind. The primary concern associated with drug design and development is time consumption and production cost. Further, inefficiency, inaccurate target delivery, and inappropriate dosage are other hurdles that inhibit the process of drug delivery and development. With advancements in technology, computer-aided drug design integrating artificial intelligence algorithms can eliminate the challenges and hurdles of traditional drug design and development. Artificial intelligence is referred to as superset comprising machine learning, whereas machine learning comprises supervised learning, unsupervised learning, and reinforcement learning. Further, deep learning, a subset of machine learning, has been extensively implemented in drug design and development. The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms applied to the drug design and discovery process. Artificial intelligence has been applied to different areas of drug design and development process, such as from peptide synthesis to molecule design, virtual screening to molecular docking, quantitative structure-activity relationship to drug repositioning, protein misfolding to protein-protein interactions, and molecular pathway identification to polypharmacology. Artificial intelligence principles have been applied to the classification of active and inactive, monitoring drug release, pre-clinical and clinical development, primary and secondary drug screening, biomarker development, pharmaceutical manufacturing, bioactivity identification and physiochemical properties, prediction of toxicity, and identification of mode of action.
Collapse
Affiliation(s)
- Rohan Gupta
- Molecular Neuroscience and Functional Genomics Laboratory, Department of Biotechnology, Delhi Technological University (Formerly DCE), Shahbad Daulatpur, Bawana Road, Delhi, 110042, India
| | - Devesh Srivastava
- Molecular Neuroscience and Functional Genomics Laboratory, Department of Biotechnology, Delhi Technological University (Formerly DCE), Shahbad Daulatpur, Bawana Road, Delhi, 110042, India
| | - Mehar Sahu
- Molecular Neuroscience and Functional Genomics Laboratory, Department of Biotechnology, Delhi Technological University (Formerly DCE), Shahbad Daulatpur, Bawana Road, Delhi, 110042, India
| | - Swati Tiwari
- Molecular Neuroscience and Functional Genomics Laboratory, Department of Biotechnology, Delhi Technological University (Formerly DCE), Shahbad Daulatpur, Bawana Road, Delhi, 110042, India
| | - Rashmi K Ambasta
- Molecular Neuroscience and Functional Genomics Laboratory, Department of Biotechnology, Delhi Technological University (Formerly DCE), Shahbad Daulatpur, Bawana Road, Delhi, 110042, India
| | - Pravir Kumar
- Molecular Neuroscience and Functional Genomics Laboratory, Department of Biotechnology, Delhi Technological University (Formerly DCE), Shahbad Daulatpur, Bawana Road, Delhi, 110042, India.
| |
Collapse
|