Difference between revisions of "Team:Heidelberg/Software/DeeProtein"

Introduction

While the idea of applying a stack of layers composed of computational nodes to estimate complex functions origins in the 1960s rosenblatt1958perceptron, it was not until the 1990s, when the first convolutional neural networks were introduced LeCun1990Handwritten, that artificial neural networks were successfully applied on real world classification tasks. With the beginning of this decade and the massive increase in broadly available computing power the advent of Deep Learning begun. Groundbreaking work by Krizhevsky in image classification Krizhevsky2012ImageNet paved the way for many applications in image, video, sound and natural language processing. There has also been successful work on biological and medical data alipanahi2015predicting, kadurin2017cornucopia.
Artificial neural networks are powerful function approximators, able to untangle complex relations in the input space cybenko1989approximation. However it were the convolutional neural networks proposed in the early 1990s LeCun1990Handwritten that made deep learning possible. Convolutional neural networks rely on trainable filters or kernels to extract valuable information (features) from the input space. The application of trainable kernels for feature extraction has been demonstrated to be extremely powerful in representation learning oquab2014learning, detection lee2009unsupervised and classification Krizhevsky2012ImageNet tasks. Similar to the visual cortex of mammals, convolutional neural networks comprise different layers of abstraction. While the lower layers detect simple properties like edges and corners, higher layers assemble the features from the lower layers and detect more complex shapes lecun2015deep. With increasing depth the layers have a larger receptive field and are thus able to combine more signals from the layers below lecun2015deep. A convolutional neural network can thus extract the information present in the input space and encode the input in a compressed representation. Handwritten, man-designed feature extraction thus becomes obsolete. Often a convolutional neural network is complemented by a small fully connected (dense) neural network part processing the extracted features to perform the real classification or detection task Krizhevsky2012ImageNet.

Youtube,AMK.

Protein representation learning

The protein space is extremely complex. The amino acid alphabet knows 20 basic letters and an average protein has a length of 500 residues, making the combinatory complexity of the space tremendous. Comparable to images however, functional protein sequences reside on a thin manyfold within the total sequence space. Learning the properties of the protein distribution of a certain functionality would enable not only a decent classification of sequences into functions but also unlimited sampling from this distribution resulting in de novo protein sequence generation. Attempts for protein sequence classification have been made with CNNs szalkai2017near as well as with recurrent neural networks liu2017deep with good success, however without the possibility for generative modelling.
Also handwritten feature extractors exist for protein sequences bandyopadhyay2005efficientsaeys2007review. Along with support vector machines they were applied in protein-protein interaction prediciton hamp2015evolutionary as well as in protein family classification cai2003svmleslie2002spectrum. However they are outperformed by trainable approaches applying CNNs szalkai2017near or word2vec models leslie2002spectrum. To find the optimal feature representation of proteins we applied a word2vec embedding as well as convolutional neural network.

Convolutional Approach

To harness the strenghts of convolutional networks in representation learning and feature extraction we implemented a fully convolutional architecture to classify protein sequences to functions. Function labels were thereby defined by the gene ontology (GO) annotation gene2004gene. The gene ontology annotation is hierarchical and best described as a directed acyclic graph (DAG). It contains labels providing information on the cellular location, pathway and molecular function of a particular protein. As we were interested solely in protein function classification, we considered on GO-labels in the molecular function sub-DAG. The molecular function sub-DAG has up to 12 levels and 11135 GO-terms, YYY of the leaf nodes. As the population between terms varies greatly and strongly depends on the terms level in the DAG, with terms towards the roots being stringer populated than leaf terms. We thresholded the considered labels based on their minimum population, ending with a set of 1509 GO terms with a minimum population of 50 samples when considering the manually annotated SwissProt database apweiler2004uniprot. As the hierachy from leaf node towards the root is fully inferable we further excluded all non-leaf nodes from the 1509-nodes sub-DAG, ending up with 886 GO-terms.

Data preprocessing

In order to convert the protein sequences into a machine readable format we preprocessed the whole UniProt database (release 08/17) as well as the SwissProt database (release 08/17) apweiler2004uniprot. For the classification task of 886 GO-labels we genererated a dataset containing 180774 sequences for SwissProt and ~7 million sequences for Uniprot respectively. The dataset was then split into training and validation set, where the validation set was composed of at least 5 distinct sequences per GO-term and the training set the remaining sequences.
Subsequently all sequences were one-hot encoded and clipped or zero padded to a window of 1000 residues. The labels were also one-hot encoded, where the average sequence had 1.3 labels assigned.

Results

The performance of the network was asserted on an exclusive validation set of 4425 sequences. For each GO-label the validation set contained at least 5 distinct samples. Our model achieved an area under the curve (AUC) for the reciever operating characteristic (ROC) of 99.8% with an average F1 score of 78% (Figure 1).

Wet Lab Validation

To assert the value of DeeProtein in sequence activtiy evaluation context, we validated the correlation between the DeeProtein classification score and enzyme activity in the wetlab. First we predicted a set of 25 single and double mutant beta-Lactamase variants with both higher and lower scores as the wildtype and subsequently asserted the activity in the wetlab.
In order to derive a measure for enzyme activity we investigated the minimum inhibitory concentration (MIC) of Carbenicillin for all predicted mutants. The MIC was asserted by OD600-measurement in Carbenicillin containing media. As the OD was measuren in a 96-well plate the values are not absolute. From the measurements the MIC-score was calculated as the first Carbenicillin concentration where the OD fell below a threshold of 0.08. Next the classification scores were averaged for each MIC-score and then plotted against the Carbenicilline concentration (Figure 2).

Protein Sequence Embedding

A protein representation first described by Asgari et al is prot2vec asgari2015continuous. The technique originates in the natural language processing and is based on the word2vec model mikolov2013efficient originally deriving vectorized word representations. Applied to proteins a word is defined as a k-mer of 3 amino acid residues. A protein sequence can thus be respresented as the sum over all internal k-mers. Interesting properties have been described in the resulting vectorspace, for example clustering of hydrophobic and hydrophilic k-mers and sequences asgari2015continuous. However there are limitations to the prot2vec model, the most important being the information loss on the sequence order. This has been addressed by application of the continuous bag of words model, with a paragraph embedding kimothi2016distributed. However training is here extremely slow as a proteinsequence itself is embedded in the paragraph context, where a paragraph is a greater set of protein sequences (e.g. SwissProt-DB). Further new protein sequences can not be added to the embedding as the paragraph context may not change.
Thus we intended to find a optimized word2vec approach for fast, reproducible and simple protein sequence embedding. Therefore we applied a word2vec model mikolov2013efficient on kmers of length 3 with a total dimension size of 100. As the quality of the representation estimate scales with the number of training samples we trained our model on the whole UniProt database (Release 8/2017, apweiler2004uniprot), composed of over 87 million sequences, exceeding the training base of 324,018 sequences derived by asgari2015continuous.

Results

We visualized our 100 dimensional embedding through PCA dimensionality reduction as shown in fig 3. Highlighted in sequence are all kmers containing a certain amino acid. Clear clusters can be observed for the aminoacids Cysteine (top right corner), Lysine (top left corner), Tryptophane (center right), Glutamate (center left), Proline (bottom) and Arginine (center) even after dimensionality reduction. In contrast, for aminoacids like Glycine, Serine and Valine are distributed over the whole kmer space.

Application

Our kmer embedding provides a great base to explore the protein space for future research. The embedding may be applied in classification as demonstrated by asgari2015continuous but also in alternation of existing sequences. By exploiting the intrinsic properties of the vector space, a sequence defined as the path through that vector space (namely by its start and ending point) may be altered by exchanging vector components along that path to similar ones. For instance if the kmer 'AAG' and 'GAG' cluster closely in figure 3 and the distance between their embedding vectors is close, out hypothesis is they're exchangeable, without huge perturbations to the sequence because the two kmers are likely in the same sequence context.