Jannis Born

Last Name

Born

First Name

Jannis

ORCID

0000-0001-8307-5670

Show all metadata

Search Results

Publications 1 - 10 of 22

Active Site Sequence Representations of Human Kinases Outperform Full Sequence Representations for Affinity Prediction and Inhibitor Generation: 3D Effects in a 1D Model
Born, Jannis; Huynh, Tien; Stroobants, Astrid; et al. (2022)
Journal of Chemical Information and Modeling
Recent advances in deep learning have enabled the development of large-scale multimodal models for virtual screening and de novo molecular design. The human kinome with its abundant sequence and inhibitor data presents an attractive opportunity to develop proteochemometric models that exploit the size and internal diversity of this family of targets. Here, we challenge a standard practice in sequence-based affinity prediction models: instead of leveraging the full primary structure of proteins, each target is represented by a sequence of 29 discontiguous residues defining the ATP binding site. In kinase–ligand binding affinity prediction, our results show that the reduced active site sequence representation is not only computationally more efficient but consistently yields significantly higher performance than the full primary structure. This trend persists across different models, data sets, and performance metrics and holds true when predicting pIC50 for both unseen ligands and kinases. Our interpretability analysis reveals a potential explanation for the superiority of the active site models: whereas only mild statistical effects about the extraction of three-dimensional (3D) interaction sites take place in the full sequence models, the active site models are equipped with an implicit but strong inductive bias about the 3D structure stemming from the discontiguity of the active sites. Moreover, in direct comparisons, our models perform similarly or better than previous state-of-the-art approaches in affinity prediction. We then investigate a de novo molecular design task and find that the active site provides benefits in the computational efficiency, but otherwise, both kinase representations yield similar optimized affinities (for both SMILES- and SELFIES-based molecular generators). Our work challenges the assumption that the full primary structure is indispensable for modeling human kinases.
Unifying Molecular and Textual Representations via Multi-task Language Modelling
Christofidellis, Dimitrios; Giannone, Giorgio; Born, Jannis; et al. (2023)
Proceedings of Machine Learning Research ~ Proceedings of the 40th International Conference on Machine Learning
The recent advances in neural language models have also been successfully applied to the field of chemistry, offering generative solutions for classical problems in molecular design and synthesis planning. These new methods have the potential to fuel a new era of data-driven automation in scientific discovery. However, specialized models are still typically required for each task, leading to the need for problem-specific fine-tuning and neglecting task interrelations. The main obstacle in this field is the lack of a unified representation between natural language and chemical representations, complicating and limiting human-machine interaction. Here, we propose the first multidomain, multi-task language model that can solve a wide range of tasks in both the chemical and natural language domains. Our model can handle chemical and natural language concurrently, without requiring expensive pre-training on single domains or task-specific models. Interestingly, sharing weights across domains remarkably improves our model when benchmarked against state-of-the-art baselines on single-domain and cross-domain tasks. In particular, sharing information across domains and tasks gives rise to large improvements in cross-domain tasks, the magnitude of which increase with scale, as measured by more than a dozen of relevant metrics. Our work suggests that such models can robustly and efficiently accelerate discovery in physical sciences by superseding problem-specific fine-tuning and enhancing human-model interactions.
A computational investigation of inventive spelling and the “Lesen durch Schreiben” method
Born, Jannis; Nikolov, Nikola I.; Rosenkranz, Anna; et al. (2022)
Computers and Education: Artificial Intelligence
In primary schools, Lesen durch Schreiben (LdS; “reading through writing”, known internationally as inventive spelling) is a prevalent didactic method of reading and spelling instruction. In LdS, pupils learn writing through prolonged inventive spelling, meaning that only phonological but not orthographic spelling errors are corrected. Rigorous studies of the effectiveness of LdS are scarce and have delivered inconsistent results, casting doubt on the suitability of LdS for primary school instruction. Empirical investigations of writing acquisition methods are time-consuming, costly, and are plagued by methodological evaluation difficulties, such as separating method effects from other instruction-related variables. In this work, we developed a computational framework (based on recurrent neural networks) for reading and writing acquisition. This framework enables us to extract and systematically investigate some core principles of writing acquisition methods. Focusing on two German corpora, we compared the behavior of learning agents trained using the LdS regime against agents trained using a classical, primer-based regime. Experimental results revealed that our LdS agents performed significantly worse than our primer agents in writing tasks and, to a lesser extent, in reading tasks. Our results show that the stereotypical spelling mistakes of children exposed to LdS can be replicated with neural network models. These mistakes arise naturally during writing acquisition for all learning agents but are either suppressed or reinforced depending on the learning regime. We examined the learned, internal representations of both agents and found deviations in the LdS agent that may have induced the amplified confusion of similar phonemes. While we focused on two German corpora, similar results can be expected for alphabetic languages with similar graphene-phoneme regularities. In sum, LdS does not exhibit benefits over standard instruction in our simulations. However, we urge caution in drawing immediate conclusions for human learners. Instead, our work presents a modest step towards the construction of a computational framework for writing and reading instructional methods that may inspire future research.
Chemical representation learning for toxicity prediction
Born, Jannis; Markert, Greta; Janakarajan, Nikita; et al. (2023)
Digital Discovery
Undesired toxicity is a major hindrance to drug discovery and largely responsible for high attrition rates in early stages. This calls for new, reliable, and interpretable molecular property prediction models that help prioritize compounds and thus reduce the high costs for development and the risk to humans, animals, and the environment. Here, we propose an interpretable chemical language model that combines attention with multiscale convolutions and relies on data augmentation. We first benchmark various molecular representations (e.g., fingerprints, different flavors of SMILES and SELFIES, as well as graph and graph kernel methods) revealing that SMILES coupled with augmentation overall yields the best performance. Despite its simplicity, our model is then shown to outperform existing approaches across a wide range of molecular property prediction tasks, including but not limited to toxicity. Moreover, the attention weights of the model allow for easy interpretation and show enrichment of known toxicophores even without explicit supervision. To introduce a notion of model reliability, we propose and combine two simple methods for uncertainty estimation (Monte-Carlo dropout and test-time-augmentation). These methods not only identify samples with high prediction uncertainty, but also allow formation of implicit model ensembles that improve accuracy. Last, we validate our model on a large-scale proprietary toxicity dataset and find that it outperforms previous work while giving similar insights into revealing cytotoxic substructures.
PaccMann: a web service for interpretable anticancer compound sensitivity prediction
Cadow, Joris; Born, Jannis; Manica, Matteo; et al. (2020)
Nucleic Acids Research
The identification of new targeted and personalized therapies for cancer requires the fast and accurate assessment of the drug efficacy of potential compounds against a particular biomolecular sample. It has been suggested that the integration of complementary sources of information might strengthen the accuracy of a drug efficacy prediction model. Here, we present a web-based platform for the Prediction of AntiCancer Compound sensitivity with Multimodal Attention-based Neural Networks (PaccMann). PaccMann is trained on public transcriptomic cell line profiles, compound structure information and drug sensitivity screenings, and outperforms state-of-the-art methods on anticancer drug sensitivity prediction. On the open-access web service (https://ibm.biz/paccmann-aas), users can select a known drug compound or design their own compound structure in an interactive editor, perform in-silico drug testing and investigate compound efficacy on publicly available or user-provided transcriptomic profiles. PaccMann leverages methods for model interpretability and outputs confidence scores as well as attention heatmaps that highlight the genes and chemical sub-structures that were more important to make a prediction, hence facilitating the understanding of the model’s decision making and the involved biochemical processes. We hope to serve the community with a toolbox for fast and efficient validation in drug repositioning or lead compound identification regimes.
On the Choice of Active Site Sequences for Kinase-Ligand Affinity Prediction
Born, Jannis; Shoshan, Yoel; Huynh, Tien; et al. (2022)
Journal of Chemical Information and Modeling
Recent work showed that active site rather than full-protein-sequence information improves predictive performance in kinase-ligand binding affinity prediction. To refine the notion of an "active site", we here propose and compare multiple definitions. We report significant evidence that our novel definition is superior to previous definitions and better models of ATP-noncompetitive inhibitors. Moreover, we leverage the discontiguity of the active site sequence to motivate novel protein-sequence augmentation strategies and find that combining them further improves performance.
PaccMannRL: De novo generation of hit-like anticancer molecules from transcriptomic data via reinforcement learning
Born, Jannis; Manica, Matteo; Oskooei, Ali; et al. (2021)
iScience
With the advent of deep generative models in computational chemistry, in-silico drug design is undergoing an unprecedented transformation. Although deep learning approaches have shown potential in generating compounds with desired chemical properties, they disregard the cellular environment of target diseases. Bridging systems biology and drug design, we present a reinforcement learning method for de novo molecular design from gene expression profiles. We construct a hybrid Variational Autoencoder that tailors molecules to target-specific transcriptomic profiles, using an anticancer drug sensitivity prediction model (PaccMann) as reward function. Without incorporating information about anticancer drugs, the molecule generation is biased toward compounds with high predicted efficacy against cell lines or cancer types. The generation can be further refined by subsidiary constraints such as toxicity. Our cancer-type-specific candidate drugs are similar to cancer drugs in drug-likeness, synthesizability, and solubility and frequently exhibit the highest structural similarity to compounds with known efficacy against these cancer types.
On the role of artificial intelligence in medical imaging of COVID-19
Born, Jannis; Beymer, David; Rajan, Deepta; et al. (2021)
Patterns
Although a plethora of research articles on AI methods on COVID-19 medical imaging are published, their clinical value remains unclear. We conducted the largest systematic review of the literature addressing the utility of AI in imaging for COVID-19 patient care. By keyword searches on PubMed and preprint servers throughout 2020, we identified 463 manuscripts and performed a systematic meta-analysis to assess their technical merit and clinical relevance. Our analysis evidences a significant disparity between clinical and AI communities, in the focus on both imaging modalities (AI experts neglected CT and ultrasound, favoring X-ray) and performed tasks (71.9% of AI papers centered on diagnosis). The vast majority of manuscripts were found to be deficient regarding potential use in clinical practice, but 2.7% (n = 12) publications were assigned a high maturity level and are summarized in greater detail. We provide an itemized discussion of the challenges in developing clinically relevant AI solutions with recommendations and remedies.
COVID-19 Control by Computer Vision Approaches: A Survey
Ulhaq, Anwaar; Born, Jannis; Khan, Asim; et al. (2020)
IEEE Access
The COVID-19 pandemic has triggered an urgent call to contribute to the fight against an immense threat to the human population. Computer Vision, as a subfield of artificial intelligence, has enjoyed recent success in solving various complex problems in health care and has the potential to contribute to the fight of controlling COVID-19. In response to this call, computer vision researchers are putting their knowledge base at test to devise effective ways to counter COVID-19 challenge and serve the global community. New contributions are being shared with every passing day. It motivated us to review the recent work, collect information about available research resources, and an indication of future research directions. We want to make it possible for computer vision researchers to find existing and future research directions. This survey article presents a preliminary review of the literature on research community efforts against COVID-19 pandemic.
Language Models in Molecular Discovery
Janakarajan, Nikita; Erdmann, Tim; Swaminathan, Sarath; et al. (2024)
Drug Development Supported by Informatics
The success of language models, especially transformer-based architectures, has trickled into other scientific domains, giving rise to the concept of “scientific language models” that operate on small molecules, proteins, or polymers. In chemistry, language models contribute to accelerating the molecule discovery cycle as evidenced by promising recent findings in early-stage drug discovery. In this chapter, we review the role of language models in molecular discovery, underlining their strengths and examining their weaknesses in de novo drug design, property prediction, and reaction chemistry. We highlight valuable open-source software assets to lower the entry barrier to the field of scientific language modeling. Furthermore, as a solution to some of the weaknesses we identify, we outline a vision for future molecular design that integrates a chatbot interface with available computational chemistry tools through techniques such as retrieval-augmented generation (RAG). Our contribution serves as a valuable resource for researchers, chemists, and AI enthusiasts interested in understanding how language models can and will be used to accelerate chemical discovery.

Publications 1 - 10 of 22

Jannis Born

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results