A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
DeepNovoV2 improves de novo peptide sequencing from mass spectrometry data.
New method designs antimicrobial peptides with high potency and low toxicity.
Given the emerging global threat of antimicrobial resistance, new methods for next-generation antimicrobial design are urgently needed. We report a peptide generation framework PepCVAE, based on a semi-supervised variational autoencoder (VAE) model, for designing novel antimicrobial peptide (AMP) sequences. Our model l…
AMP0 predicts antimicrobial peptides targeting specific microbes.
Study improves peptide design efficiency using active and meta-learning.
We propose a molecular generative model based on the conditional variational autoencoder for de novo molecular design. It is specialized to control multiple molecular properties simultaneously by imposing them on a latent space. As a proof of concept, we demonstrate that it can be used to generate drug-like molecules w…
Bayesian network models are finding success in characterizing enzyme-catalyzed reactions, slow conformational changes, predicting enzyme inhibition, and genomics. In this work, we apply them to statistical modeling of peptides by simultaneously identifying amino acid sequence motifs and using a motif-based model to cla…
Chemical autoencoders are attractive models as they combine chemical space navigation with possibilities for de-novo molecule generation in areas of interest. This enables them to produce focused chemical libraries around a single lead compound for employment early in a drug discovery project. Here it is shown that the…
A major challenge in computational chemistry is the generation of novel molecular structures with desirable pharmacological and physiochemical properties. In this work, we investigate the potential use of autoencoder, a deep learning methodology, for de novo molecular design. Various generative autoencoders were used t…
We propose a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). Based on deep and reinforcement learning approaches, ReLeaSE integrates two deep neural networks - generative and predictive - that are trained separately b…
Non-autoregressive method speeds up protein folding prediction 23 times.
Recent advances in high-throughput cDNA sequencing (RNA-Seq) technology have revolutionized transcriptome studies. A major motivation for RNA-Seq is to map the structure of expressed transcripts at nucleotide resolution. With accurate computational tools for transcript reconstruction, this technology may also become us…
Major histocompatibility complex class two (MHC-II) molecules are trans-membrane proteins and key components of the cellular immune system. Upon recognition of foreign peptides expressed on the MHC-II binding groove, helper T cells mount an immune response against invading pathogens. Therefore, mechanistic identificati…
Recently exciting progress has been made on protein contact prediction, but the predicted contacts for proteins without many sequence homologs is still of low quality and not very useful for de novo structure prediction. This paper presents a new deep learning method that predicts contacts by integrating both evolution…
We propose a specialized string kernel for small bio-molecules, peptides and pseudo-sequences of binding interfaces. The kernel incorporates physico-chemical properties of amino acids and elegantly generalize eight kernels, such as the Oligo, the Weighted Degree, the Blended Spectrum, and the Radial Basis Function. We …
In de novo drug design, computational strategies are used to generate novel molecules with good affinity to the desired biological target. In this work, we show that recurrent neural networks can be trained as generative models for molecular structures, similar to statistical language models in natural language process…
This work improves molecular design by efficiently selecting diverse candidate molecules.
GEGL uses genetic experts to improve deep learning for molecular design.
Learning policies on data synthesized by models can in principle quench the thirst of reinforcement learning algorithms for large amounts of real experience, which is often costly to acquire. However, simulating plausible experience de novo is a hard problem for many complex environments, often resulting in biases for …
New method infers centromere locations in yeast using Hi-C data.
Benchmark proposes to assess molecule docking efficiency.
As in many other scientific domains, we face a fundamental problem when using machine learning to identify proteins from mass spectrometry data: large ground truth datasets mapping inputs to correct outputs are extremely difficult to obtain. Instead, we have access to imperfect hand-coded models crafted by domain exper…
Machine learning predicts signaling peptides from protein star graphs.
Semi-supervised deep learning detects problematic reads for genome assembly.
Liquid chromatography coupled with tandem mass spectrometry, also known as shotgun proteomics, is a widely-used high-throughput technology for identifying proteins in complex biological samples. Analysis of the tens of thousands of fragmentation spectra produced by a typical shotgun proteomics experiment begins by assi…
Few-step protein backbone generators reduce sampling time by over 20x.
Motivation: Post-database searching is a key procedure in peptide dentification with tandem mass spectrometry (MS/MS) strategies for refining peptide-spectrum matches (PSMs) generated by database search engines. Although many statistical and machine learning-based methods have been developed to improve the accuracy of …
We attempt to set a mathematical foundation of immunology and amino acid chains. To measure the similarities of these chains, a kernel on strings is defined using only the sequence of the chains and a good amino acid substitution matrix (e.g. BLOSUM62). The kernel is used in learning machines to predict binding affinit…
Advanced GNNs improve molecular generation models.
Next-generation sequencing technologies provide a revolutionary tool for generating gene expression data. Starting with a fixed RNA sample, they construct a library of millions of differentially abundant short sequence tags or "reads", which constitute a fundamentally discrete measure of the level of gene expression. A…
This paper presents regression models obtained from a process of blind prediction of peptide binding affinity from provided descriptors for several distinct datasets as part of the 2006 Comparative Evaluation of Prediction Algorithms (COEPRA) contest. This paper finds that kernel partial least squares, a nonlinear part…
This paper uses bandit theory and Thompson Sampling to optimize protein sequences.
Study of de Rham cohomology on non-Hausdorff manifolds.
BoGA combines evolutionary search with Bayesian optimization for efficient protein design.
Deep neural networks improve free energy calculations for peptide conformations.
Proves Mayer-Vietoris sequence for diffeological spaces using generating families.
Two de Rham complexes in diffeology are compared using a factor map.
The paper explores the Rumin complex and spectral sequence on Carnot groups.
Generative model gradients enhance MS/MS peptide identification.
EHVI outperforms scalarized EI in MOBO for molecule design.
Spectral sequence analysis for Sobolev mappings in Carnot groups.
Let be a closed oriented surface of genus at least . Using the parameterisation of the deformation space of globally hyperbolic maximal anti-de Sitter structures on by the cotangent bundle over the Teichmüller space of , we study the behaviour of these geometric structures along pinching…
"Deep Archetypal Analysis" generates latent representations of high-dimensional datasets in terms of fractions of intuitively understandable basic entities called archetypes. The proposed method is an extension of linear "Archetypal Analysis" (AA), an unsupervised method to represent multivariate data points as sparse …
New projection operators for multipatch spaces with stable properties.
Develops a spectral sequence for Lie group actions on manifolds.
Novel RL approach for molecular design using quantum mechanics.
Novel model predicts anticancer compound sensitivity with high accuracy and interpretability.
New construction of Riemannian deformation sequence using differential operators.